2023年第6期共收录43篇

1. Optimization of Crop Patterns Inversion and Collaborative Analysis with Soil Salinity Spatial Distribution in Large Irrigation District

Accession number: 20233014437850

Title of translation:

Authors: Zhang, Jingxiao (1, 2); Cai, Jiabing (1); Xu, Di (1); Chang, Hongfang (1); Xiao, Chun¡¯An (1)

Author affiliation: (1) State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing; 100038, China; (2) Department of Hydraulic Engineering, Hehei University of Water Resources and Electric Engineering, Cangzhou; 061001, China

Corresponding author: Cai, Jiabing(caijb@iwhr.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 373-385

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Linkage of crop patterns with soil salinity will be of great significance for the assessment and management of ecological environment in large irrigation district, as well as be helpful for the protection of cultivated land and food security. To explore the synergic relationship between them, the coupling coordination degree was collaboratively analyzed based on accurate extraction of crop planting information and spatial analysis of soil salinity. Yongji Sub-irrigation Area in Hetao Irrigation District of Inner Mongolia, which had complex crop patterns and severe soil salinization, was selected as the study area. With remote sensing data of Landsat 8 OLI and ground observing data of crop planting survey during the growth period from 2021 to 2022, three classification models were constructed to inverse the crop planting information, which namely were the decision tree (DT), support vector machine (SVM), and random forest ( RF), respectively. By comparing the accuracy of the models, an optimal model would be given accompanied by the best result of crop patterns. Combined with the spatial heterogeneity of soil salinity measured from field sampling sites, the synergic relationship between them was further explored quantitatively. Results showed that the classification accuracy of the three models performed as RF > DT > SVM. The overall accuracy and Kappa coefficient of RF model were 92. 81%, 0. 91 in 2021, and 91. 64%, 0. 89 in 2022, respectively, which was the biggest among the three models. Therefore, the RF model was ultimately employed as the optimal one to inverse crop patterns in this area. Moreover, soil salinity presented more severe in the northern part than that in the middle and southern parts. The semi-variance function of soil salinity was best fitted by the Gaussian model, and the spatial autocorrelation of soil salinity fluctuated from medium- to strong- level, which indicated that both structural factors and random factors influenced the spatial variation of soil salinity. Crop pattern, as an important factor of random factors, was essential to be further analyzed with soil salinity collaboratively. Two aspects of the collaborative relationship were mainly revealed. On one hand, the spatial heterogeneity of soil salinity determined the spatial characteristics of crop patterns, specifically that sunflower was mainly cultivated in the northern part, while maize, wheat, interplanting, and other crops ( e. g. water melon, pepper, tomato, etc. ) were mainly distributed in the middle and southern parts. On the other hand, the crops performed different adaptabilities and tolerance to soil salinity, with the average values of soil salt content from big to small as follows; sunflower (0. 377% in 2021, and 0. 328% in 2022), maize (0. 358% in 2021, and 0.319% in 2022), interplanting (0.246% in 2021 and 2022), and wheat (0.259% in 2021, and 0. 248% in 2022). As a result, crop patterns interacted with soil salinity in space, jointly determining the sustainable development of agriculture in the irrigation area. In 2021 and 2022, the coupling coordination degree between them was 0. 784 and 0. 787 in the study area, respectively, which reached a high level. It could be concluded that the development between crop patterns and soil salinity was balanced and coordinated with each other during the observation period. The results would provide some references for optimizing crop planting patterns and improving soil environment in large irrigation district to some extent. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 47

Main heading: Crops

Controlled terms: Classification (of information)? - ?Couplings? - ?Decision trees? - ?Food supply? - ?Forestry? - ?Irrigation? - ?Remote sensing? - ?Soils? - ?Support vector machines

Uncontrolled terms: Collaborative analysis? - ?Coordination degree? - ?Coupling coordination degree? - ?Crop pattern? - ?Irrigation area? - ?Irrigation districts? - ?Plantings? - ?Random forests? - ?Remote-sensing? - ?Soil salinity

Classification code: 483.1 Soils and Soil Mechanics? - ?716.1 Information Theory and Signal Processing? - ?723 Computer Software, Data Handling and Applications? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.3 Agricultural Methods? - ?821.4 Agricultural Products? - ?822.3 Food Products? - ?903.1 Information Sources and Analysis? - ?921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory? - ?961 Systems Science

Numerical data indexing: Percentage 3.58E 02%, Percentage 3.77E 02%, Percentage 6.40E 01%, Percentage 8.10E 01%, Size 1.99898E 01m, Size 2.2606E 00m, Size 2.3114E 00m, Percentage 2.46E-01%, Percentage 2.48E 02%, Percentage 2.59E-01%, Percentage 3.19E-01%, Percentage 3.28E 02%

DOI: 10.6041/j.issn.1000-1298.2023.06.038

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

2. Method of Maturity Detection for Papaya Fruits in Natural Environment Based on YOLO v5-Lite

Accession number: 20233014437809

Title of translation: YOLO v5-Lite

Authors: Xiong, Juntao (1); Han, Yonglin (1); Wang, Xiao (1); Li, Zexing (1); Chen, Haoran (1); Huang, Qiyin (1)

Author affiliation: (1) College of Mathematics and Informatics, South China Agricultural University, Guangzhou; 510642, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 243-252

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Using visual detection technologies based on deep learning to identify the maturity of papaya fruits on tree in natural environment and monitor the growing periods of papaya is of great significance to the intelligent management of papaya orchard. At present, there are relatively few studies on the identification of papaya maturity. The maturity of papaya is mainly judged manually, which have urgent needs to be replaced by some alternative fast and accurate automatic detection methods. Based on the lightweight YOLO v5 - Lite model, a method of papaya maturity detection in natural environment was studied. The detection algorithm was improved based on the YOLO v5 network. In order to alleviate frequent slicing operations, a faster convolution operation was used to replace the Focus layer of the original network, which reduced the amount of computation and released the memory usage and accelerated the inference speed. To reduce the amount of calculation, the ShuffleNetv2 was used in the model to change the 1¡Á1 group convolution in the middle to ordinary convolution by reducing the use of group convolution. At the same time, the ordinary convolution on the branch was changed to a depth-wise separable convolution, which greatly reduced the amount of calculation and improved the calculation efficiency. The number of C3 Layers especially the ones in deep neural blocks was reduced, so as to reduce the cache space occupation and speed up the operations. The channel number in FPN and PAN was set identical to speed the memory accessment. Totally 1 386 papaya images were selected to create a dataset in PASCAL VOC format. Under the Ubuntu 16.04 environment, the training parameters of network were set as the epoch number of 300, the batchsize of 128, the total number of iterations of 300, and the initial learning rate of 0. 001. During training, the loss value of the model tended to stabilize at the 200th iteration, indicating that the network was converged and the training performance was good. The evaluation indicators for papaya maturity identification of the experiments were the accuracy rate, recall rate, overall average accuracy, detection speed and model size. The experimental results showed that the mAP of the papaya maturity detection model was 92. 4%, which outperformed the mainstream lightweight object detection algorithms namely the YOLO v5s and the YOLO v4 - tiny and the classic two-stage algorithm Faster R - CNN by 1. 1 percentage points, 5. 1 percentage points and 4.7 percentage points, on mAP, respectively. In addition, under the condition of relatively accurate detection, the detection time was up to 7 ms, and the model size was only 11. 3 MB. At the same time, the model can accurately identify the fruits under different shooting distances, occlusion conditions and lighting conditions, showing the performance of fast and effective identification and good robustness under complex backgrounds. The proposed method provided technical support for yield estimation of papaya orchards and the positioning detection of picking robots, which can also provide reference for researches on the maturity detection of other fruits. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 31

Main heading: Convolution

Controlled terms: Computer vision? - ?Convolutional neural networks? - ?Deep neural networks? - ?Fruits? - ?Iterative methods? - ?Learning systems? - ?Multilayer neural networks? - ?Object detection? - ?Signal detection

Uncontrolled terms: Convolutional neural network? - ?Deep convolutional neural network? - ?Deep learning? - ?Fruit maturation? - ?Fruit maturation detection? - ?Machine-vision? - ?Natural environments? - ?Papaya? - ?Percentage points? - ?Performance

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?716.1 Information Theory and Signal Processing? - ?723.2 Data Processing and Image Processing? - ?723.5 Computer Applications? - ?741.2 Vision? - ?821.4 Agricultural Products? - ?921.6 Numerical Methods

Numerical data indexing: Percentage 4.00E 00%, Time 7.00E-03s

DOI: 10.6041/j.issn.1000-1298.2023.06.025

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

3. Effects of Straw Returning and Application of Stable Nitrogen Fertilizer on Water and Nitrogen Use Efficiencies of Wheat Maize Rotation

Accession number: 20233014437880

Title of translation:

Authors: Zhao, Zhengxin (1, 2); Wang, Xiaoyun (1, 2); Li, Fuyang (1, 2); Wang, Rui (1, 2); Tian, Yajie (1, 2); Cai, Huanjie (1, 2)

Author affiliation: (1) College of Water Resources and Architectural Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Institute of Water-saving Agriculture in Arid Areas of China, Northwest A&F University, Shaanxi, Yangling; 712100, China

Corresponding author: Cai, Huanjie(caihj@nwsuaf.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 350-360

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to explore the comprehensive impact of straw returning with stable nitrogen fertilizer on crop growth and water and nitrogen utilization of wheat maize rotation system in Guanzhong region, and determine reasonable high-yield and efficient fertilization management measures, two straw returning modes ( no straw returning, full straw returning) and two nitrogen application measures ( conventional urea and reduced application of stable nitrogen fertilizer ) were set up in a completely random combination, and straw free returning and no fertilization were set as control, a total of five treatments were set to study and analyze crop yield, aboveground biomass, soil ammonia volatilization accumulation, soil moisture content, soil nitrate nitrogen residue and water and nitrogen utilization efficiency. The results showed that straw returning to the field could significantly increase the yield of summer maize and winter wheat by 28.03% ~ 39.63% and 90. 10% ~ 112.52%, respectively, and increase the aboveground biomass by 27.88% ~ 34.00% and 78.96% ~ 107.64%. The application of stable nitrogen fertilizer reduced the soil ammonia volatilization accumulation by 50. 18% ~ 59. 32% and 68.21% -73.43% during the whole growth period of summer maize season and winter wheat season respectively compared with the application of conventional urea. Straw returning to the field could significantly increase the soil moisture content of 0 ~ 10 cm soil in summer maize season by 6. 29% ~ 21. 38%, and that of 0 ~ 10 cm soil in winter wheat season by 6. 80% ~ 25. 06% . Under the same fertilization measures, straw returning to the field could significantly reduce the NO3-- N residues in the 0 ~ 100 cm soil of summer maize and winter wheat at harvest time by 7. 34% ~ 10. 78% and 6. 57% ~ 11.24%. Under the same straw returning mode, the application of stable nitrogen fertilizer could significantly reduce the NO3-- N residues in the 0 ~ 100 cm soil of summer maize and winter wheat at harvest time by 28. 96% -31. 63% and 4. 16% ~ 9. 54% compared with that of application of urea. Under the same fertilization measures, straw returning significantly improved water use efficiency, nitrogen partial productivity and nitrogen agronomic efficiency in summer maize season and winter wheat season by 4. 55% -7.85%, 5.79% ~ 12. 08%, 25. 22% -41.43% and 7. 36% -9.73%, 2.25% -14. 38% and 4. 33% - 30. 35% . Under the same straw returning mode, the application of stable nitrogen fertilizer significantly improved the partial productivity of nitrogen fertilizer, agronomic efficiency of nitrogen fertilizer, nitrogen absorption efficiency, nitrogen recovery efficiency of 43. 75% -52.29%, 42.01% -60.39%, 62.07% -66.67%, 52.50% -72.73% and 21.93% -36.41%, 11.37% -39. 14%, 50.67% -53.85%, 60.00% -64. 15%, respectively, in summer maize season and winter wheat. Therefore, straw returning with stable nitrogen fertilizer would significantly improve water and nitrogen use efficiency of wheat maize rotation system, reduce nitrogen volatilization loss and nitrogen leaching risk. Based on comprehensive consideration, 180 kg/hm stable nitrogen fertilizer and 150 kg/hm stable nitrogen fertilizer were reasonable fertilization measures for realizing high yield and efficiency of summer maize and winter wheat in Guanzhong area. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 40

Main heading: Nitrogen fertilizers

Controlled terms: Agricultural pollution? - ?Ammonia? - ?Biomass? - ?Crop rotation? - ?Efficiency? - ?Metabolism? - ?Moisture determination? - ?Soil moisture? - ?Urea? - ?Water supply

Uncontrolled terms: Ammonia volatilization? - ?Fertilisation? - ?Nitrogen utilization? - ?Soil NO3--N? - ?Stable nitrogen fertilizer? - ?Straw returning? - ?Summer maize? - ?Water utilization? - ?Winter wheat? - ?Yield

Classification code: 446.1 Water Supply Systems? - ?454.2 Environmental Impact and Protection? - ?483.1 Soils and Soil Mechanics? - ?804 Chemical Products Generally? - ?804.1 Organic Compounds? - ?804.2 Inorganic Compounds? - ?821.2 Agricultural Chemicals? - ?913.1 Production Engineering? - ?944.2 Moisture Measurements

Numerical data indexing: Mass 1.50E 02kg, Mass 1.80E 02kg, Percentage 1.00E 01%, Percentage 1.0764E 02%, Percentage 1.124E 01%, Percentage 1.1252E 02%, Percentage 1.137E 01%, Percentage 1.40E 01%, Percentage 1.50E 01%, Percentage 1.60E 01%, Percentage 1.80E 01%, Percentage 2.193E 01% to 3.641E 01%, Percentage 2.20E 01% to 4.143E 01%, Percentage 2.25E 00%, Percentage 2.788E 01%, Percentage 2.803E 01%, Percentage 2.90E 01%, Percentage 3.20E 01%, Percentage 3.30E 01%, Percentage 3.40E 01%, Percentage 3.50E 01%, Percentage 3.60E 01% to 9.73E 00%, Percentage 3.80E 01%, Percentage 3.963E 01%, Percentage 4.201E 01% to 6.039E 01%, Percentage 5.067E 01% to 5.385E 01%, Percentage 5.25E 01% to 7.273E 01%, Percentage 5.40E 01%, Percentage 5.50E 01% to 7.85E 00%, Percentage 5.70E 01%, Percentage 5.79E 00%, Percentage 6.00E 00%, Percentage 6.00E 01%, Percentage 6.207E 01% to 6.667E 01%, Percentage 6.30E 01%, Percentage 6.821E 01% to 7.343E 01%, Percentage 7.50E 01% to 5.229E 01%, Percentage 7.80E 01%, Percentage 7.896E 01%, Percentage 8.00E 00%, Percentage 8.00E 01%, Percentage 9.60E 01%, Size 0.00E00m to 1.00E-01m, Size 0.00E00m to 1.00E00m

DOI: 10.6041/j.issn.1000-1298.2023.06.036

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

4. Spatiotemporal Characteristics and Prediction under Future Scenarios of ET0 in Sanjiang Plain

Accession number: 20233014437870

Title of translation: ET0

Authors: Xing, Zhenxiang (1, 2); Wang, Hongli (1); Wang, Xinlei (3); Yu, Yi (1); Duan, Weiyi (1); Fu, Qiang (1, 2)

Author affiliation: (1) School of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin; 150030, China; (2) Key Laboratory of High Efficiency Use of Agricultural Water Resources, Ministry of Agriculture and Rural Affairs, Northeast Agricultural University, Harbin; 150030, China; (3) Heilongjiang Provincial River and Lake Mayor System Security Center, Harbin; 150001, China

Corresponding author: Wang, Xinlei(wxlei_xx@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 328-339

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The prediction of reference crop evapotranspiration (ET0) is great significant for crop water requirement calculation and field water management, which can provide an important scientific basis for agricultural water conservation and efficient use of water resources. Based on the day-by-day meteorological data of six meteorological stations in the Sanjiang Plain from 1961 to 2010, the Penman -Monteith formula was used to calculate ET0and analyze the spatiotemporal characteristics of ET0and related meteorological elements from 1961 to 2010; based on the NCEP reanalysis data and the output data of the daily series of the CanESM2 forecast factor of the atmospheric circulation model, the statistical downscaling model ( SDSM ) was used to predict ET0under two emission scenarios, RCP4. 5 and RCP8. 5. The results showed that the ET0from 1961 to 2010 showed an increasing trend, the multi-year annual mean temperature and ET0trend were the same, while the annual mean wind speed, relative humidity and net radiation showed an overall decreasing trend, and the spatial distribution of multi-year annual mean ET0showed a general trend that the central part was higher than the periphery, and the western part was higher than the eastern part; in terms of simulation accuracy test, the ET0simulation values of ¡°historical¡± simulation under CanESM2 model and the calculated values of the P - M formula corresponded to the Nash efficiency coefficient ( NSE ) range of 0. 46 ~ 0. 61 and the coefficient of determination R range of 0. 53 ~ 0. 61 for the regular validation period ( 1961 - 2005 ), which implied that the SDSM simulation was effective. The trends of the monthly average daily values of ET0in the three future time periods of 2011 - 2040, 2041 - 2070, and 2071 - 2100 under the two scenarios in the future 2011 - 2100 intra-annual ET0changes were relatively consistent, all resembling a parabola with a downward opening, with May - July significantly higher than the level of the historical period ( 1961 - 2010), January - April and August slightly higher than the historical period, and September - December gradually converged with the historical period. The future change of ET0between 2011 - 2100 would on an upward trend compared with the historical period, and the three time periods of 2011 - 2040, 2041 - 2070, and 2071 - 2100 under RCP4. 5 scenario would be increased by 11.11%, 18.70%, and 20. 24%, respectively, compared with the historical period, with the multi-year ET0in the time period of 2011 - 2040 on a more obvious upward trend. The overall downward trend would slower in the 2041 - 2070 and 2071 - 2100 time periods; the three time periods under the RCP8. 5 scenario would be increased by 13.01%, 24.05%, and 34.46%, respectively, compared with the historical period, and the multi-year ET0would on the rise in all three time periods. The future increase of ET0in the study area may lead to aggravation of water shortage problem, and the results of the study may provide scientific reference for optimal water resources management and irrigation system formulation in the study area. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 34

Main heading: Water management

Controlled terms: Atmospheric humidity? - ?Crops? - ?Efficiency? - ?Evapotranspiration? - ?Forecasting? - ?Meteorology? - ?Water conservation? - ?Wind

Uncontrolled terms: Annual mean? - ?ET0? - ?Historical periods? - ?Penman-Monteith formula? - ?Sanjiang plain? - ?Spatiotemporal characteristics? - ?Statistical downscaling? - ?Statistical downscaling model? - ?Time-periods? - ?Trend analysis

Classification code: 443.1 Atmospheric Properties? - ?444 Water Resources? - ?821.4 Agricultural Products? - ?913.1 Production Engineering

Numerical data indexing: Percentage 1.111E 01%, Percentage 1.301E 01%, Percentage 1.87E 01%, Percentage 2.405E 01%, Percentage 2.40E 01%, Percentage 3.446E 01%, Size 0.00E00m

DOI: 10.6041/j.issn.1000-1298.2023.06.034

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

5. Detection of Young Apple Fruits Based on YOLO v7-ECA Model

Accession number: 20233014444951

Title of translation: YOLO v7-ECA

Authors: Song, Huaibo (1, 2); Ma, Baoling (1, 2); Shang, Yuying (1, 2); Wen, Yuchen (1, 2); Zhang, Shujin (1, 2)

Author affiliation: (1) College of Mechanical and Electronic Engineering, Northwest a and F University, Shaanxi, Yangling; 712100, China; (2) Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Shaanxi, Yangling; 712100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 233-242

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to detect young apple fruits quickly and accurately in the natural environment, an improved YOLO v7 model (YOLO v7-ECA) was proposed to solve the problems of high similarity, small size, dense distribution and difficult identification between young apple fruits and leaves. By inserting the ECA mechanism into the three reparameterized paths of the model, the local cross-channel interaction of adjacent channels could be carried out without reducing the channel dimension, which can effectively emphasize the important information of young apple fruits, suppress redundant and useless features, and improve the efficiency of the model. Totally 2557 images of young apple fruits were collected as training samples, totally 547 images as validation samples, and 550 images as test samples in the natural environment, and input them into the model for training and testing. The YOLO v7-ECA model was trained to have a precision of 97.2%, a recall rate of 93.6%, an mAP of 98.2%, and F1 value of 95.37%. Compared with the Faster R-CNN, SSD, Scaled-YOLO v4, YOLO v5, YOLO v6, YOLO v7 models, its mAP was increased by 15.5, 4.6, 1.6, 1.8, 3.0 and 1.8 percentage points, its precision was increased by 49.7, 0.9, 18.5, 1.2, 0.9 and 1.0 percentage points, its F1 value was increased by 33.53, 2.81, 9.16, 1.26, 2.38 and 1.43 percentage points, and its recall rate was increased by 5.0, 4.5, 1.3, 3.7 and 1.8 percentage points for Faster R-CNN, SSD, YOLO v5, YOLO v6 and YOLO v7 models, respectively; the image detection time was 28.9ms, which could realize efficient detection of young apple fruits. Aiming at the fuzzy, shadowing and severe occlusion of young fruit targets, totally 550 test images were used to test the robustness of the model. The mAP of YOLO v7-ECA was 91.1% and the F1 value was 89.8% under the condition of adding noise and fuzziness. Compared with the Faster R-CNN, SSD, Scaled-YOLO v4, YOLO v5, YOLO v6 and YOLO v7 models, its mAP was increased by 26.3, 21.0, 5.4, 8.0, 11.5 and 8.9 percentage points, and its F1 value was increased by 27.19, 7.08, 8.50, 4.20, 3.94 and 4.67 percentage points, respectively. The mAP of YOLO v7-ECA was 97.5% and the F1 value was 95.36% in the shadow. Compared with the Faster R-CNN, SSD, Scaled-YOLO v4, YOLO v5, YOLO v6 and YOLO v7 models, its mAP was increased by 14.8, 8.8, 2.1, 2.4, 5.4 and 2.5 percentage points, and its F1 value was increased by 21.51, 2.60, 10.49, 1.53, 3.23 and 2.56 percentage points, respectively. The mAP of YOLO v7-ECA was 98.6% and the F1 value was 94.8% under severe occlusion. Compared with that of the Faster R-CNN, SSD, Scaled-YOLO v4, YOLO v5, YOLO v6 and YOLO v7 models, its mAP was increased by 21.7, 13.7, 2.3, 2.4, 4.8 and 2.2 percentage points, and its F1 value was increased by 28.29, 3.50, 6.45, 0.96, 1.36 and 1.36 percentage points, respectively. Experiments showed that the proposed model was of high accuracy and speed, it was also robust to different interference situations such as blurred scene, shadow and severe occlusion. The research result can provide an effective reference for the detection system of apple young fruit. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 29

Main heading: Computer vision

Controlled terms: Fruits

Uncontrolled terms: Apple fruits? - ?Attention mechanisms? - ?Detection? - ?Efficient channel attention mechanism? - ?Efficient channels? - ?F1 values? - ?Machine-vision? - ?Percentage points? - ?YOLO v7? - ?Young apple fruit

Classification code: 723.5 Computer Applications? - ?741.2 Vision? - ?821.4 Agricultural Products

Numerical data indexing: Percentage 8.98E 01%, Percentage 9.11E 01%, Percentage 9.36E 01%, Percentage 9.48E 01%, Percentage 9.536E 01%, Percentage 9.537E 01%, Percentage 9.72E 01%, Percentage 9.75E 01%, Percentage 9.82E 01%, Percentage 9.86E 01%, Time 2.89E-02s

DOI: 10.6041/j.issn.1000-1298.2023.06.024

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

6. Mechanism Analysis and Parameter Optimization of Soybean Combine Harvester Reel

Accession number: 20233014437872

Title of translation:

Authors: Jin, Chengqian (1, 2); Qi, Yandong (1); Liu, Gangwei (1); Yang, Tengxiang (1); Ni, Youliang (1)

Author affiliation: (1) Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing; 210014, China; (2) School of Agricultural Engineering and Food Science, Shandong University of Technology, Ziho, 255000, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 104-113

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: At present, there were few studies on the influence of the soybean height on the parameter of reel of soybean combine harvester in China, while the height of soybean plants in different varieties and producing areas varies greatly. In order to change the current situation of soybean combine harvester, due to the lack of theoretical guidance for the parameter adjustment of the reel, the reel parameter is not timely and accurate, resulting in high loss rate of soybean combine harvester harder. ANSYS and ADAMS co-simulation method was used to optimize the parameters of the reel of soybean combine harvester when harvesting soybeans at different heights. The influence rules of the three reel parameters and soybean plant height on the two header loss indexes were analyzed, and the best reel parameter combination at different height was found. The field verification test of the best reel parameter combination of soybean harvester was completed. Based on the analysis of the structure of reel and the principle of reel operation of soybean harvester, the importance of the reel speed ratio, reel height and reel forward displacement to the header loss indexes of soybean combine harvester was obtained. The reel speed ratio, reel height, reel forward displacement and the soybean plant height were used to optimize the four parameters in simulation test. Collision force of reel to soybean stem and effect degree of reel were used to optimize the two indexes of simulation test. The model of test indexes under test factors was established. The objective optimization equations were established. There was linear relationship between optimal parameters of reel of soybean combine harvester and soybean plant height. The order of influence of soybean combine harvester reel parameters on the two indexes was as follows: reel speed ratio, reel height, and reel forward displacement. The simulation test was carried out with the collision force of the reel to the soybean stem and the degree of action of the reel as the index, and the field test with the loss rate of the header as the index in the case of soybean plant height of 751.5 mm. The average deviation of the collision force between the model calculation and the simulation was 1. 18 N and the average deviation of the effect degree of reel was 4. 80%, which showed that the simulation model was accurate. The optimal parameters combination of reel was reel speed ratio of 1. 66, reel forward displacement of 40 mm and reel height of 1 052 mm. This solution as field experiment factor had the smallest loss rate in the experiment. The research results can provide a basis for the optimization of the allocation reel parameters of soybean combined harvest at different heights and the reduction of cutting loss. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 24

Main heading: Harvesters

Uncontrolled terms: Combine harvesters? - ?Different heights? - ?Forward displacements? - ?Loss rates? - ?Mechanism analysis? - ?Parameter optimization? - ?Plant height? - ?Soybean combine harvester? - ?Soybean plants? - ?Speed ratio

Classification code: 821.1 Agricultural Machinery and Equipment

Numerical data indexing: Force 1.80E 01N, Percentage 8.00E 01%, Size 4.00E-02m, Size 5.20E-02m, Size 7.515E-01m

DOI: 10.6041/j.issn.1000-1298.2023.06.011

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

7. Apple Location and Classification Based on Improved SSD Convolutional Neural Network

Accession number: 20233014438438

Title of translation: SSD

Authors: Zhang, Lijie (1); Zhou, Shuhua (1); Li, Na (1); Zhang, Yanqiang (1); Chen, Guangyi (1); Gao, Xiao (1)

Author affiliation: (1) School of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding; 071001, China

Corresponding author: Li, Na(res_lina@126.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 223-232

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: An apple localization and grading algorithm was proposed based on an improved SSD convolutional neural network to achieve fast and accurate automatic grading of apple fruit diameter and shape. The efficiency of apple grading was improved by improving the input layer of the original SSD network. Channel separation was performed on the color apple image obtained from the top, and the two channels in the separation channel that had the most significant impact on the apple recognition accuracy were extracted. A fused image was composed of the two channels and the apple depth image from the top based on the binocular camera. The longitudinal diameter-related information of the apple was calculated in the fused image. Moreover, multiple apple shape grading and information output based on the fused image were realized through this method. The depthwise-separable convolution module was used to replace part of the standard convolution in the original SSD network backbone feature extraction network, which achieved the light weighting of the network. The recognition recall, accuracy, mAP and Fl values of the trained model under the verification set were 93.68%, 94.89%, 98.37% and 94.25%, respectively. By comparing and analyzing the differences in recognition accuracy among the four input layers, the experimental results showed that the highest recognition and grading mAP for apples was achieved when the image channel combination of the input layer was DGB. The actual recognition localization and grading effects of the original SSD, Faster R - CNN and YOLO v5 algorithms for apples with different numbers of fruits were compared by using the same input layer and evaluated in terms of mAP. The experimental results showed that the improved SSD had a comparable mAP to the original SSD for dense apples, which was higher than that of Faster R - CNN by 1. 33 percentage points and higher than YOLO v5 by 14. 23 percentage points. The advantages of the algorithm localization and grading efficiency were verified under different hardware conditions. The detection time of an image was 5. 71 ms under GPU and 15. 96 ms under CPU, and the actual frame rate of the detected video reached 175. 17 f/s and 62. 64 f/s. The research result can provide a theoretical basis for automated grading equipment to accurately locate and grade apples in a high-speed environment. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 28

Main heading: Object detection

Controlled terms: Classification (of information)? - ?Convolution? - ?Convolutional neural networks? - ?Efficiency? - ?Fruits? - ?Grading

Uncontrolled terms: Apple classification? - ?Convolutional neural network? - ?Fused images? - ?Improved SSD? - ?Input layers? - ?Localisation? - ?Objects detection? - ?Percentage points? - ?Recognition accuracy? - ?Two channel

Classification code: 716.1 Information Theory and Signal Processing? - ?723.2 Data Processing and Image Processing? - ?821.4 Agricultural Products? - ?903.1 Information Sources and Analysis? - ?913.1 Production Engineering

Numerical data indexing: Percentage 9.368E 01%, Percentage 9.425E 01%, Percentage 9.489E 01%, Percentage 9.837E 01%, Time 7.10E-02s, Time 9.60E-02s

DOI: 10.6041/j.issn.1000-1298.2023.06.023

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

8. River Extraction Method from Remote Sensing Images of Cold and Arid Regions Based on Self-supervised Comparative Learning

Accession number: 20233014438748

Title of translation:

Authors: Shen, Yu (1); Wang, Hailong (1); Liang, Dong (2); Niu, Dongxing (2); Yan, Yuan (1); Li, Yangyang (1)

Author affiliation: (1) School of Electronic and Information Engineering, Lanzhou Fiaotong University, Lanzhou; 730070, China; (2) China Railway Academy Co., Ltd., Chengdu; 610032, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 125-135

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming at the problems of high cost of manual labeling of river data samples in remote sensing images and difficulty in obtaining a large number of them, as well as poor effect of network extraction of river image edge details, a self-supervised comparative learning method was proposed to use a large number of unlabeled remote sensing river image data for encoder pre-training, and a small amount of label data was used to fine-tune the encoder after pre-training. Meanwhile, a semantic segmentation network based on non-uniform sampling was used in the codec structure. Self-supervised comparative learning can use a large number of unlabeled data for pre-task model training, and only a small amount of label data was needed to fine-tune the downstream river extraction task model. The non-uniform sampling method can obtain clear boundary information between different categories in the image and details in the same category by intensive sampling in the high frequency region and sparse sampling in the low frequency region, thus reducing the redundancy of the model. Experiments on river data sets showed that the pixel accuracy, intersection over union and recall rate of the pre-trained network can reach 90. 4%, 68. 6% and 83. 2%, respectively, when 360 labeled datas was used to fine-tune the network, which was comparable to the performance of the supervised AFR - LinkNet network trained with 1 200 labeled datas. After fine-tuning with all data labels, the pixel accuracy, intersection ratio and recall rate of the network reached 93. 7%, 73. 2% and 88. 5%, respectively. Compared with AFR - LinkNet, DeepLabv3 , LinkNet, ResNet50 and UNet networks, the pixel accuracy was increased by 3. 1, 7.6, 12.3, 14.9, 19.8 percentage points, the intersection over union was increased by 3. 5, 8.7, 10.5, 16.9, 24.0 percentage points, and the recall rate was increased by 2. 1, 4.8, 6.7, 9.4, 12.9 percentage points, respectively. The effectiveness of the model to accurately extract rivers from river images was verified. This algorithm model was of great significance for solving the lack of a large number of labeled data and analyzing the distribution of rivers in cold and arid regions, water disaster warning, rational utilization of water resources and agricultural irrigation development. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 26

Main heading: Extraction

Controlled terms: Learning systems? - ?Pixels? - ?Remote sensing? - ?Rivers? - ?Semantic Segmentation? - ?Semantics

Uncontrolled terms: AFR - linknet? - ?LinkNet? - ?Nonuniform sampling? - ?Percentage points? - ?Pre-training? - ?Recall rate? - ?Remote sensing images? - ?River extraction? - ?Self-supervised comparative learning? - ?Semantic segmentation

Classification code: 723.4 Artificial Intelligence? - ?802.3 Chemical Operations

Numerical data indexing: Percentage 2.00E 00%, Percentage 4.00E 00%, Percentage 5.00E 00%, Percentage 6.00E 00%, Percentage 7.00E 00%

DOI: 10.6041/j.issn.1000-1298.2023.06.013

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

9. Characteristics, Drivers and Control of Non-grain Production on Permanent Basic Farmland Based on Plot Scale

Accession number: 20233014444745

Title of translation:

Authors: Chen, Wenguang (1, 2); Liao, Yubo (1, 2); Kong, Xiangbin (1, 2); Lei, Ming (1, 2); Wen, Liangyou (1, 2); Zhang, Bangbang (3)

Author affiliation: (1) College of Land Science and Technology, China Agricultural University, Beijing; 100193, China; (2) Key Laboratory of Farmland Quality and Monitoring, Ministry of Natural Resources, Beijing; 100193, China; (3) College of Economics and Management, Northwest a and F University, Shaanxi, Yangling; 712100, China

Corresponding author: Kong, Xiangbin(kxh@cau.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 114-124

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Mastering the plot characteristics, spatial agglomeration, and drivers of non-grain production on permanent basic farmland can provide a reference for optimizing the spatial layout of crops and improving the fine control strategy of cultivated land. Based on the data of the Third National Land Survey of Guangxi Zhuang Autonomous Region, the current status, types, and plot characteristics of non-grain production on permanent basic farmland were analyzed. The spatial exploratory analysis method, ordinary least square, and geographically weighted regression models were used to identify the spatial aggregation characteristics, drivers, and the spatial variation in their effects of non-grain production on permanent basic farmland in the Guangxi Zhuang Autonomous Region. The results showed that the non-grain production plots of permanent basic farmland were mainly distributed in the central, western, and northern parts of the region, and the non-grain production types were mainly fruit trees and arbor, accounting for 88. 85% of the non-grain production area. The quality and irrigation conditions of non-grain production plots were lower than that of the regional average of permanent basic farmland, but they were concentrated in areas with flat terrain, with 77. 86% of plots with field surface slopes no more than 6¡ã. The non-grain rate of permanent basic farmland in the counties of the region presented a significant positive spatial autocorrelation. The H H agglomeration was mainly distributed in the central and southwestern parts of the region, the L - L agglomeration was mainly distributed in the eastern and northwestern parts of the region, and the H - L type was concentrated in the west. Field size, per capita permanent basic farmland area, per capita disposable income of rural residents, and distance from each county to the provincial capital were positively correlated with county-level permanent basic farmland non-grain production. Quality and irrigation guarantee rates were negatively correlated with non-grain production of permanent basic farmland in the county, with significant spatial variability in the impact of different drivers on non-grain production. In the future, the control of non-grain production plots of permanent basic farmland in the region should be strengthened in terms of optimizing crop layout, strengthening quality construction, regulating attribute characteristics, and improving protection compensation. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 38

Main heading: Agglomeration

Controlled terms: Crops? - ?Grain (agricultural product)? - ?Irrigation? - ?Least squares approximations? - ?Orchards? - ?Quality control? - ?Regression analysis

Uncontrolled terms: Driving factors? - ?Grain production? - ?Guangxi? - ?GWR model? - ?Management and controls? - ?Non-grain production? - ?Per capita? - ?Permanent basic farmland? - ?Plot scale? - ?Spatial layout

Classification code: 802.3 Chemical Operations? - ?821.3 Agricultural Methods? - ?821.4 Agricultural Products? - ?913.3 Quality Assurance and Control? - ?921.6 Numerical Methods? - ?922.2 Mathematical Statistics

Numerical data indexing: Percentage 8.50E 01%, Percentage 8.60E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.012

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

10. Soil Salinity Monitoring Model of Shahaoqu Irrigation Area Based on EnKF and PF Algorithm

Accession number: 20233014437800

Title of translation: EnKFPF

Authors: Zhang, Zhitao (1, 2); Chen, Ce (1, 2); Jia, Jiangdong (1, 2); Yin, Haoyuan (1, 2); Yao, Yifei (1, 2); Huang, Xiaoyu (1, 2)

Author affiliation: (1) College of Water Resources and Architectural Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Key Laboratory Oj Agricultural Soil and Water Engineering in Arid and Semiarid Areas, Ministry of Education, Northwest A&F University, Shaanxi, Yangling; 712100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 361-372

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to explore the feasibility of different data assimilation algorithms in monitoring soil salinity on the spatio-temporal scale, the Shahaoqu Canal Irrigation Area in Hetao Irrigation District of Inner Mongolia was taken as the research area, and the Gaofen - 1 satellite remote sensing image was used as the data source. The assimilation observation operator and model operator of EnKF algorithm and PF algorithm were used to obtain the changes of soil salinity in the spatio-temporal range. The observation operator was divided into two steps, firstly, the PLS - VIP criterion was used to filter the spectral index as the independent variable, and then the ELM model was used to establish the remote sensing monitoring soil salinity model based on different depths at different times; the model operator was a mathematical simulation monitoring soil salinity model based on the Hydrus - ID model. The results showed that in the ELM-based soil salinity model, the average IOA at the depths of 0 ~ 20 cm, 20 ~ 40 cm and 40 -60 cm were above 0. 74, and the average ME was below 0. 14%, indicating that the inversion model had good accuracy; in the Hydrus - ID-based mathematical simulation monitoring soil salinity model, the average IOA at the three depths was between 0. 79 and 0. 89 and the average ME was between 0. 128% and 0. 137%, which could better reflect the transport of soil salts in the time series; the EnKF algorithm had IOA above 0. 820 for three depths, ME between 0. 141% and 0. 157% and NMB between 0. 141 and 0.252, and the PF algorithm had IOA above 0.89 for three depths and ME ranged from 0.090% to 0. 142% and NMB ranged from 0. 075 to 0. 097, with better accuracy than the EnKF algorithm, which can well reflect the distribution of soil salinity in time and space. The assimilation scheme of Hydrus - ID model and ELM model based on EnKF and PF algorithms improved the accuracy of monitoring soil salinity, which can provide a basis for subsequent monitoring of soil salinity on a long time and large spatial and temporal scale, and can also provide a reference for the research of precision agriculture to control soil salinity. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 57

Main heading: Remote sensing

Controlled terms: Irrigation? - ?Kalman filters? - ?Machine learning? - ?Mathematical operators? - ?Soils

Uncontrolled terms: Data assimilation? - ?Ensemble Kalman filtering? - ?Extreme learning machine? - ?Hydrus - ID? - ?Irrigation area? - ?Learning machines? - ?Model-based OPC? - ?Particle Filtering? - ?Salinity models? - ?Soil salinity

Classification code: 483.1 Soils and Soil Mechanics? - ?723.4 Artificial Intelligence? - ?821.3 Agricultural Methods

Numerical data indexing: Percentage 1.28E 02%, Percentage 1.37E 02%, Percentage 1.40E 01%, Percentage 1.41E 02%, Percentage 1.42E 02%, Percentage 1.57E 02%, Percentage 9.00E-02% to 0.00E00%, Size 0.00E00m to 2.00E-01m, Size 2.00E-01m to 4.00E-01m, Size 4.00E-01m to 6.00E-01m

DOI: 10.6041/j.issn.1000-1298.2023.06.037

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

11. Cotton Boll Tracking and Counting Based on Improved Faster R-CNN and Deep Sort

Accession number: 20233014437888

Title of translation: Faster R-CNNDeep Sort

Authors: Huang, Chenglong (1); Zhang, Zhongfu (1); Hua, Xiangdong (1); Yang, Junya (1); Ke, Yuxi (1); Yang, Wanneng (2)

Author affiliation: (1) College of Engineering, Huazhong Agricultural University, Wuhan; 430070, China; (2) National Key Laboratory of Crop Genetic Improvement, Huazhong Agricultural University, Wuhan; 430070, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 205-213

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Cotton boll is an important yield and quality organ of cotton. The research on phenotypic traits such as boll number per plant, boll length and width is of great importance in cotton genetics and breeding research. In order to obtain the accurate number of bolls, a boll tracking and counting method was proposed based on the improved Faster R - CNN and Deep Sort to realize cotton boll measurement based on the rotating video. First of all, a simple video captured device was designed for the cotton plant. And then the feature pyramid network ( FPN), Guided Anchoring and Soft NMS methods were adopted to improve the original Faster R - CNN detection network, in which the FPN was used to promote the ability for small targets recognition, Guided Anchoring was applied to generate the Anchors with appropriate size, and the Soft NMS was adopted to mitigate the mistaken deletion of overlapping targets. As a result, the improved Faster R - CNN outperformed the other models, including RetinaNet, SSD, Faster R - CNN, YOLO v5 and YOLOF. The mAP75 and Fl of improved Faster R - CNN was 0. 97 and 0. 96 respectively, which was 0. 02 and 0. 01 higher than that of the original Faster R - CNN model. After that, Deep Sort was used to realize the match of the same target in different frames through Kalman filter and deep association metric, and the ID of the same target was matched. In order to solve the ID switch problem, the mask collision mechanism was developed. When the matched cotton boll passed through the mask region from right to left, the ID of the cotton boll would be recorded and the number of the cotton boll would be added, which was proved to significantly reduce the mistaken counting caused by ID switch. Finally, the specialized software was designed based on the improved Faster R - CNN, Deep Sort and mask collision mechanism. The results showed that the tracking result RMOTAwas 0. 91, which was 0.02 higher than that of Tracktor algorithm, and 0. 15 better than that of Sort algorithm, respectively. The measurement results of coefficient of determination, mean square error, mean absolute error and mean absolute percentage error of the bolls number were 0.96, 1. 19, 0.81 and 5.92% respectively, which had high consistence with the manual measurement, and it could realize the high precision counting of cotton bolls based on the specialized software. In conclusion, the research demonstrated an effective tool for cotton bolls measurement, which was beneficial to the cotton breeding research. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 40

Main heading: Object detection

Controlled terms: Cotton? - ?Errors? - ?Mean square error? - ?Tracking (position)

Uncontrolled terms: Anchorings? - ?Collision mechanisms? - ?Cotton boll counting? - ?Deep sort? - ?Fast R - CNN? - ?Feature pyramid? - ?Object Tracking? - ?Objects detection? - ?Pyramid network? - ?Specialized software

Classification code: 723.2 Data Processing and Image Processing? - ?821.4 Agricultural Products? - ?922.2 Mathematical Statistics

Numerical data indexing: Percentage 5.92E 00%, Percentage 8.10E-01%

DOI: 10.6041/j.issn.1000-1298.2023.06.021

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

12. Application Evaluation of Different SPEI Index Calculation Methods in Sichuan Province

Accession number: 20233014437878

Title of translation: SPEI

Authors: Kang, Yinhong (1); Wang, Jiachi (1); Song, Xin (1, 2); Wu, Jianfei (3); He, Shuai (1)

Author affiliation: (1) College of Water Conservancy and Hydropower Engineering, Sichuan Agricultural University, Ya¡¯an; 625014, China; (2) Agriculture and Rural Affairs Bureau of Fucheng District, Mianyang; 621000, China; (3) Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang; 453002, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 340-349

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Drought episodes have become the main natural hazards all over the world, resulting in a serious limitation to agricultural production. Based on the daily meteorological data of 34 meteorological stations in Sichuan Province from 1967 to 2016, the reference crop evapotranspiration (ET0) was calculated by comparing the Penman - Monteith method (PM) and seven simplified ET0methods. The simplified ET0methods included Hargreaves - Samani ( HS ) method, Blaney - Criddle (BC) method, Priestley - Taylor (PT) method, Makkink (MK) method, FAO - 24Radiation (FAO-Ra) method, Rohwer (Ro) method and World Meteorological Organization (WMO) method. The standardized precipitation evapotranspiration index (SPEI) was calculated based on PM and the three ET0methods with better performances. To obtain the best calculation methods and assess its adaptability, Sichuan Province was divided into three regions, such as western plateau, southwestern mountain, and central Sichuan basin. The applicability of corresponding SPEI was evaluated with different ET0methods in each region by time series analysis, error analysis, K - S test and wavelet analysis. The results showed that there were significant differences in the calculation accuracy of seven methods in different regions. The PT method had the best applicability in western plateau and southwestern mountain although the root mean square error (RMSE) of PT method was below 99. 11 mm and the relative error (RE) of most sites was -3. 8% ~ 14. 2% . The MK and Ro methods had the stable performances in three regions since the RMSE of both were below 160 mm. The SPEI calculated on the basis of PM, MK, Ro and PT ET0methods had the same trend in the same region. In the year with actual drought event, the minimum values of SPEI were less than 0 so it can identify historical drought events. SPEI_PT and SPEI_PM had the most similar periodic oscillation changes, and the periodic gap between SPEI_Ro and SPEI_PM was the largest. The SPEI correlation at 1-month timescale was better than that at 3-month and 12-month timescales. There was the best correlation between SPEI_MK and SPEI_PM at 1-month timescale, with the correlation coefficient (r) of 0. 99 and RMSE of 0. 15. Therefore, SPEI_MK can be used as an alternative to SPEI_PM under the condition of missing data. This research can provide a theoretical evidence for drought monitoring and mitigation in Sichuan Province, and it can also give a reference for research in other areas. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 31

Main heading: Evapotranspiration

Controlled terms: Crops? - ?Drought? - ?Errors? - ?Mean square error? - ?Time series analysis

Uncontrolled terms: Applicability analysis? - ?Penman-Monteith method? - ?Priestley-Taylor? - ?Reference crop evapotranspirations? - ?Root mean square errors? - ?Sichuan province? - ?Standardized precipitation evapotranspiration index? - ?Taylor diagrams? - ?Taylor methods? - ?Temporal and spatial distribution

Classification code: 443.3 Precipitation? - ?444 Water Resources? - ?821.4 Agricultural Products? - ?922.2 Mathematical Statistics

Numerical data indexing: Percentage 2.00E 00%, Percentage 8.00E 00%, Size 1.10E-02m, Size 1.60E-01m

DOI: 10.6041/j.issn.1000-1298.2023.06.035

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

13. Individual Identification and Automatic Counting System of Laying Hens under Complex Environment

Accession number: 20233014437819

Title of translation:

Authors: Yang, Duanli (1, 2); Wang, Yongsheng (1, 2); Chen, Hui (3, 4); Sun, Erdong (5); Wang, Lianzeng (6)

Author affiliation: (1) College of Information Science and Technology, Hebei Agricultural University, Baoding; 071001, China; (2) Hebei Key Laboratory of Agricultural Big Data, Baoding; 071001, China; (3) College of Animal Science and Technology, Hebei Agricultural University, Baoding; 071001, China; (4) Key Laboratory of Broiler and Layer Facilities Engineering, Ministry of Agriculture and Rural Affairs, Baoding; 071001, China; (5) Hebei Taomu Geda Agricultural Science and Technology Co. ,Ltd., Baoding; 074300, China; (6) Hebei Layer Industry Technology Research Institute, Handan; 056007, China

Corresponding author: Chen, Hui(531613107@qq.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 297-306

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Hen counting is a very important task in hen farm asset valuation. The current manual counting methods used in hen farms suffer from low efficiency and unstable counting accuracy. To resolve this problem, a method for identifying and counting individual laying hens was proposed based on improved YOLO v5s. The method introduced the SimAM attention mechanism in the Neck part of the YOLO v5s model in order to eliminate the interference brought by facilities such as laying boxes and feeding troughs on the identification of individual laying hens in the real complex environment; in order to expand the sensory field of the model and solve the problem of small individual laying hens and difficulties in identification, the spatial pyramid pooling module ( SPPF) of the YOLO v5s model was replaced by the SPPCSPC module; in order to extract as many effective features of laying hens as possible, the detection accuracy of the model was further improved by adding the adaptive feature fusion module ASFF to the Neck structure of YOLO v5s, which fused the imaging feature information of laying hens at different scales. On this basis, the counting of individual laying hens and the calculation of the housing density were realized by calling the model detection interface and adding counting functions and counting target numbers inside the interface. The improved model was packaged by PyQt toolkit, and the system of individual laying hens identification and automatic counting was developed. The test results showed that the precision, recall and mAP of the improved YOLO v5s model were 89. 91%, 79. 24% and 87. 53%, respectively, which were 2. 37, 2. 55 and 2. 20 percentage points higher than those of the YOLO v5s model. The average accuracy of this model in counting 120 ~ 247 laying hen houses was 94. 77%, which was 2. 49 percentage points better than that of the YOLO v5s model. The laying hens counting system developed was applied in a farm base in Hebei, providing a reliable and effective method for counting the number of laying hens on a farm. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 32

Uncontrolled terms: Attention mechanisms? - ?Automatic counting? - ?Complex environments? - ?Counting system? - ?Features fusions? - ?Individual identification? - ?Individual identification and counting system for laying hen? - ?Laying hens? - ?Real environments? - ?YOLO v5s

Numerical data indexing: Percentage 2.40E 01%, Percentage 5.30E 01%, Percentage 7.70E 01%, Percentage 9.10E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.031

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

14. Experimental Investigation of Liquid Sloshing Suppression in Plant Protection UAV Based on Floating Plate Structure

Accession number: 20233014437831

Title of translation:

Authors: Zheng, Jizhou (1, 2); Li, Yanpeng (1); Lin, Qingming (1); Xue, Xinyu (3)

Author affiliation: (1) College of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian; 271018, China; (2) Shandong Provincial Key Laboratory of Horticultural Machineries and Equipments, Taian; 271018, China; (3) Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing; 210014, China

Corresponding author: Xue, Xinyu(735178312@qq.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 94-103

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The serious liquid sloshing in the medicine tank of plant protection unmanned aerial vehicles ( UAV) leads to poor flight stability. Aiming at solving this problem, a liquid sloshing restraining device, elastically constrained floating plate, was proposed by taking the weight reduction requirement of UAVs into consideration. A system of liquid sloshing force measurement was constructed based on a six degree of freedom motion simulation platform. A series of tests were conducted to investigate the sloshing suppression effect of the floating plate under various liquid depths and excitation frequencies. The effects of the structural and constraint properties of the floating plate on the sloshing suppression were analyzed. The results were as follows: the sloshing suppression ability was relatively weak when the floating plate was free. A good sloshing suppression ability can be got at a certain range of liquid depths for a rigid constrained floating plate. The range of liquid depths at which the sloshing suppression ability was excellent can be enlarged for an elastically constrained floating plate. When the floating plate was located near the free surface of the liquid and the elastic rope can be pulled by the plate, the liquid sloshing force was only 1/3 -1/2 of the original even if the excitation frequency was near the natural frequency. However, the sloshing suppression ability basically disappeared when the floating plate located deeply below the free liquid surface. The location of floating plate was affected by the length of the elastic rope. The length needed to be selected according to the varies of the liquid depths. The larger the aera of the floating plate was, the better the sloshing suppression ability was. However, good sloshing suppression can also be obtained for a smaller aera under some conditions. On the other hand, the elastic constrained floating plate accelerated the decay of the free liquid surface and significantly improved the damping ratio of the oscillatory system. It showed a good practical value for plant protection UAVs whose attitude changed frequently and the liquid in the tank was prone to sloshing greatly. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 20

Main heading: Degrees of freedom (mechanics)

Controlled terms: Antennas? - ?Liquid sloshing? - ?Plates (structural components)? - ?Rope? - ?Simulation platform? - ?Tanks (containers)? - ?Unmanned aerial vehicles (UAV)

Uncontrolled terms: Aerial vehicle? - ?Elastically constrained floating plate? - ?Excitation frequency? - ?Experimental investigations? - ?Floating plates? - ?Free liquid surface? - ?Plant protection? - ?Sloshing suppression? - ?Suppression? - ?Unmanned aerial vehicle

Classification code: 408.2 Structural Members and Shapes? - ?619.2 Tanks? - ?631.1 Fluid Flow, General? - ?652.1 Aircraft, General? - ?723.5 Computer Applications? - ?931.1 Mechanics

DOI: 10.6041/j.issn.1000-1298.2023.06.010

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

15. Cotton Leaf Area Index Estimation Combining UAV Spectral and Textural Features

Accession number: 20233014438465

Title of translation:

Authors: Shao, Yajie (1, 2); Tang, Qiuxiang (1); Gui, Jianping (2, 3); Li, Xiaojuan (4); Wang, Liang (2, 3); Lin, Tao (2, 3)

Author affiliation: (1) College of Agriculture, Xinjiang Agricultural University, Urumqi; 830052, China; (2) Institute of Cash Crops, Xinjiang Academy of Agricultural Sciences, Urumqi; 830091, China; (3) Key Laboratory of Physiological Ecology and Cultivation of Desert Oasis Crops, Ministry of Agriculture and Rural Affairs, Urumqi; 830091, China; (4) College of Mechanical Engineering, Xinjiang University, Urumqi; 830046, China

Corresponding author: Lin, Tao(27427732@qq.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 186-196

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Accurate prediction of crop leaf area index (LAI) at farm scale is important for studying the response of population structure to yield and management practices. The inversion of the LAI of crops by spectral features from drones is now commonly used as an important basis for diagnosing crop growth and canopy structure, and it remains to be investigated whether the accuracy of its estimation can be improved. Crop surface features, such as greyscale and colour, can change under different levels of structural complexity. For this reason, the influence of LAI was taken into account by setting different planting densities and nitrogen levels to create a differentiated canopy structure, using an unmanned aerial vehicle with a multispectral sensor to obtain canopy images of cotton during the main fertility periods to obtain vegetation indices and second-order probability-based statistical filtering (co-occurrence measures) in the near infrared band to extract mean ( MEA), variance ( VAR), synergy ( HOM ), contrast (CON), dissimilarity (DIS), information entropy (ENT), second-order moments (SEM) and correlation (COR) of the eight texture feature values. Finally, support vector regression (SVR), partial least squares regression ( PLSR) and deep neural networks ( DNN) were used to develop models for estimating cotton LAI based on spectral features, texture features and a combination of the two, respectively, and to compare the differences. The results showed that the vegetation indices VL(nir/green)VI(nir/red), GNDVI, OSAVI and mean had high correlation with LAI; the LAI estimation accuracy established by SVR was the highest (R2=0.78, RMSE was 0.22, RRMSE was 0. 10) ; among three estimation models, the SVR model combining Vis and texture features improved the accuracy by 7. 89% (Vis) and 32. 26% (TFs), respectively, over the single parameter type model. Thus the LAI estimation model incorporating UAV spectral information and image texture provided a feasible and accurate method for the diagnosis of cotton canopy structure in dense crops. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 45

Main heading: Unmanned aerial vehicles (UAV)

Controlled terms: Antennas? - ?Cotton? - ?Crops? - ?Deep neural networks? - ?Farms? - ?Image texture? - ?Infrared devices? - ?Learning systems? - ?Least squares approximations? - ?Support vector machines ? - ?Textures? - ?Vegetation

Uncontrolled terms: Canopy structure? - ?Estimation models? - ?Leaf Area Index? - ?Machine-learning? - ?Multi-spectral? - ?Spectral feature? - ?Support vector regressions? - ?Textural feature? - ?Texture features? - ?Vegetation index

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?652.1 Aircraft, General? - ?723 Computer Software, Data Handling and Applications? - ?723.2 Data Processing and Image Processing? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.4 Agricultural Products? - ?921.6 Numerical Methods

Numerical data indexing: Percentage 2.60E 01%, Percentage 8.90E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.019

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

16. Soil Moisture Monitoring Model Based on UAV-Satellite Remote Sensing Scale-up

Accession number: 20233014437808

Title of translation: -

Authors: Ma, Yi (1); Huang, Zugui (2, 3); Jia, Jiangdong (2, 3); Luo, Linyu (2, 3); Wang, Shuang (2, 3); Yao, Yifei (2, 3)

Author affiliation: (1) Electric Power Science Research Institute, Yunnan Power Grid Co., Ltd., Kunming; 650217, China; (2) College of Water Resources and Architectural Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (3) Key Laboratory of Agricultural Soil and Water Engineering in Arid Areas, Ministry of Education, Northwest A&F University, Shaanxi, Yangling; 712100, China

Corresponding author: Yao, Yifei(yifeiyao@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 307-318

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Soil moisture is the key to the study of energy and material exchange in the soil - plant - atmosphere circulatory system. Using the scale conversion method to push up the remote sensing data from the UAV to correct the satellite data can effectively improve the accuracy of the satellite remote sensing inversion model. Taking Hetao Irrigation Area as the research object, the resampling and TsHARP scale-up method were adopted respectively, and algorithms such as multiple linear regression (MLR), BP neural network (BPNN) and support vector machine ( SVM ) were introduced to construct UAV - satellite scale-up soil moisture content inversion model under different soil depths. The research results showed that the overall accuracy of the resampling scale-up method was SVM, MLR and BPNN from high to low in different soil depths, among which the SVM model was the best when the soil depth was 0-60 cm, R2was 0. 571, and RMSE was 0. 022% . The overall accuracy of the model of TsHARP scale-up method under different soil depths was BPNN, SVM and MLR from high to low, among which the BPNN model was the best under 0 ~ 60 cm soil depth, R2was 0. 829, and RMSE was 0. 015% . Compared with the corresponding soil depth model before scaling up, both scale-up methods can significantly improve the retrieval accuracy of soil moisture content from satellite remote sensing, but TsHARP scale-up method was better than resampling method as a whole; R2of resampling method was increased from 0. 413 to 0. 571, and RMSE was decreased from 0. 026% to 0. 022% ( a decrease of 15. 4% ) ; R2of TsHARP scale-up method was increased from 0. 428 to 0. 829, and RMSE was decreased from 0. 025% to 0.015% (a decrease of 40. 0% ). The research result can provide theoretical and technical support for high-precision monitoring of soil moisture in large-scale irrigation areas. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 38

Main heading: Soil moisture

Controlled terms: Cardiovascular system? - ?Irrigation? - ?Moisture determination? - ?Multiple linear regression? - ?Neural networks? - ?Remote sensing? - ?Satellites? - ?Support vector machines? - ?Unmanned aerial vehicles (UAV)

Uncontrolled terms: BP neural networks? - ?Different soils? - ?GF - 1? - ?Inversion models? - ?Irrigation area? - ?Monitor models? - ?Multiple linear regressions? - ?Satellite remote sensing? - ?Scale-up? - ?Soil depth

Classification code: 461.2 Biological Materials and Tissue Engineering? - ?483.1 Soils and Soil Mechanics? - ?652.1 Aircraft, General? - ?655.2 Satellites? - ?723 Computer Software, Data Handling and Applications? - ?821.3 Agricultural Methods? - ?922.2 Mathematical Statistics? - ?944.2 Moisture Measurements

Numerical data indexing: Percentage 0.00E00%, Percentage 1.50E 01%, Percentage 2.20E 01%, Percentage 2.50E 01% to 1.50E-02%, Percentage 2.60E 01% to 0.00E00%, Percentage 4.00E 00%, Size 0.00E00m to 6.00E-01m

DOI: 10.6041/j.issn.1000-1298.2023.06.032

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

17. Influence of Agricultural Tire Technology Innovation on Soil Compaction in Black Soil Region Northeast China

Accession number: 20233014439487

Title of translation:

Authors: Yang, Minli (1, 2); Peng, Jian (1, 2); Jin, Jian (3); Yang, Xiao (1); Song, Zhenghe (1); Li, Dong (3)

Author affiliation: (1) College of Engineering, China Agricultural University, Beijing; 100083, China; (2) China Agricultural Mechanization Development Research Center, China Agricultural University, Beijing; 100083, China; (3) Michelin (China) Investment Co., Ltd., Shanghai; 200335, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 85-93

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to explore the influence of different agricultural tires on soil compaction in northeast black soil area, explore effective ways to reduce soil compaction, improve farmland ecology and protect black land, typical black soil cultivated land in northeast China was taken as object, and field operation comparative experiments were carried out based on different agricultural tires in the link of corn seeding. Two types of agricultural tires, ultra-low pressure radial tire and ordinary radial tire, were set up in the experiment. Four key soil physical property parameters, namely soil compactness, soil moisture content, soil bulk density and soil porosity, were calculated by scientific sampling method. On this basis, a comprehensive evaluation model of soil compaction was established based on CRITIC - Entropy weight method, and the soil compaction status of ordinary radial tire ( CK) and ultra-low pressure radial tire ( VF) at depth of 5 cm, 10 cm, 15 cm and 20 cm was evaluated statistically. The test results showed that in 0 ~ 20 cm soil depth, compared with radial tire, ultra-low pressure radial tire reduced soil compactness by 11. 38%, 7. 97%, 5. 36% and 4. 55%, and increased soil moisture content by 11. 06%, 10. 07%, 7.37% and 5.95%, respectively. Soil bulk density was reduced by 3.71%, 3.81%, 3. 12% and 2. 73%, and soil porosity was increased by 11. 13%, 12. 25%, 8. 92% and 5. 86%, respectively. The soil comprehensive evaluation scores of different treatments in descending order were VF5, VF10, CK5, VF15, CK10, VF20, CK15, CK20, indicating that under the same conditions, the soil comprehensive condition of compacting ultra-low pressure radial tire was better than that of ordinary radial tire. The results showed that ultra-low pressure radial tire had positive effects on reducing compaction of black soil and maintaining soil physical environment, which was helpful to protect black soil and ensure national food security. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 26

Main heading: Radial tires

Controlled terms: Compaction? - ?Entropy? - ?Food supply? - ?Land use? - ?Moisture determination? - ?Porosity? - ?Seed? - ?Soil mechanics? - ?Soil moisture? - ?Soil testing

Uncontrolled terms: Agricultural tire? - ?Black soil? - ?Compaction models? - ?CRITIC - entropy weight method? - ?Entropy weight method? - ?Low pressures? - ?Physical characteristics? - ?Radial tyres? - ?Soil compaction? - ?Soil physical characteristic

Classification code: 403 Urban and Regional Planning and Development? - ?483.1 Soils and Soil Mechanics? - ?641.1 Thermodynamics? - ?821.4 Agricultural Products? - ?822.3 Food Products? - ?931.2 Physical Properties of Gases, Liquids and Solids? - ?944.2 Moisture Measurements

Numerical data indexing: Percentage 1.20E 01%, Percentage 1.30E 01%, Percentage 2.50E 01%, Percentage 3.60E 01%, Percentage 3.71E 00%, Percentage 3.80E 01%, Percentage 3.81E 00%, Percentage 5.50E 01%, Percentage 5.95E 00%, Percentage 6.00E 00%, Percentage 7.00E 00%, Percentage 7.30E 01%, Percentage 7.37E 00%, Percentage 8.60E 01%, Percentage 9.20E 01%, Percentage 9.70E 01%, Size 0.00E00m to 2.00E-01m, Size 1.00E-01m, Size 1.50E-01m, Size 2.00E-01m, Size 5.00E-02m

DOI: 10.6041/j.issn.1000-1298.2023.06.009

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

18. Biomass Estimation of High-density Forest Harvesting Based on Multi-temporal UAV Images

Accession number: 20233014437854

Title of translation:

Authors: Zhou, Xiaocheng (1); Wang, Pei (1); Tan, Fanglin (2); Chen, Chongcheng (1); Huang, Hongyu (1); Lin, Yu (3)

Author affiliation: (1) Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou University, Fuzhou; 350108, China; (2) Fujian Academy of Forestry, Fuzhou; 350012, China; (3) Fujian Minhou Baisha State-owned Forest Farm, Fuzhou; 350102, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 168-177

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Forest harvesting is a forest carbon source. Accurate estimation of forest harvesting biomass is helpful for accurate measurement of forest carbon sinks. Aiming at the challenging problem of using single time-phase visible light UAV image to estimate the biomass of high-density forest harvesting, a high-precision estimation method of forest harvesting biomass was studied based on multi-temporal visible light UAV image before and after logging. Taking a coniferous forest in Fuzhou City of Fujian Province Baisha forest cutting small class as the experimental zone, collecting resolution better than 10 cm long before and after cutting, unmanned aerial vehicle ( UAV) visible light image, the local maximum dynamic window method was adopted to get high precision of cutting plants and single tree height information, and then based on the UAV image after cutting, detection and extraction by the method of YOLO v5 cut pile diameter of information, the DBH information of the cut wood was estimated according to the DBH - pile diameter model, and the biomass of the cut wood was estimated by using the binary biomass formula of tree height and DBH, which was verified by the measured data. The precision of tree number and average tree obtained by dynamic window local maximum method was 96. 35% and 99. 01%, respectively. The overall accuracy of pile cutting target detection by YOLO v5 method was 77. 05%, and the accuracy of average DBH estimated by pile cutting diameter was 90. 14% . Finally, the accuracy of forest harvesting biomass was 83. 08% . The results showed that this method had great application potential. Using multitemporal UAV visible light remote sensing before and after harvesting can realize effective estimation of forest harvesting biomass, which can help to reduce the cost of manual investigation, and provide effective technical support for the government and relevant departments to accurately measure carbon sinks. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 26

Main heading: Biomass

Controlled terms: Aircraft detection? - ?Antennas? - ?Binary trees? - ?Carbon? - ?Forestry? - ?Harvesting? - ?Piles? - ?Remote sensing? - ?Unmanned aerial vehicles (UAV)

Uncontrolled terms: Aerial vehicle? - ?Forest? - ?Forest harvesting? - ?Harvesting biomass? - ?High-precision? - ?Multi-temporal? - ?Multi-temporal unmanned aerial vehicle image? - ?Vehicle images? - ?Visible light? - ?Visible-light remote sensing

Classification code: 408.2 Structural Members and Shapes? - ?652.1 Aircraft, General? - ?716.2 Radar Systems and Equipment? - ?804 Chemical Products Generally? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.3 Agricultural Methods

Numerical data indexing: Percentage 1.00E00%, Percentage 1.40E 01%, Percentage 3.50E 01%, Percentage 5.00E 00%, Percentage 8.00E 00%, Size 1.00E-01m

DOI: 10.6041/j.issn.1000-1298.2023.06.017

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

19. Regional Winter-wheat Yield Estimation Based on Coupling of Machine Learning Algorithm and Crop Growth Model

Accession number: 20233014437988

Title of translation:

Authors: Ma, Zhanlin (1); Wen, Feng (1); Zhou, Yingjie (2); Lu, Chunyang (1); Xue, Huazhu (3); Li, Changchun (3)

Author affiliation: (1) School of Surveying and Urban Spatial Information, Henan University of Urban Construction, Pingdingshan; 467001, China; (2) School of Management, Henan University of Urban Construction, Pingdingshan; 467001, China; (3) School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo; 454003, China

Corresponding author: Lu, Chunyang(luchunyang@hncj.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 136-147

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: To realize the regional winter wheat yield estimation accurately, efficiently and in real-time, Shiqiao Village, Qi County, Hebi City, Henan Province, was taken as the study area. The ensemble Kalman filter (EnKF) was used to assimilate the time-series leaf area index (LAI) ,which were estimated by the PROSAIL radiation transfer model, into PyWOFOST crop growth model to estimate a certain number of winter wheat site yield points with different growth. And those site yield points provided training data for random forest regression (RFR) algorithm to establish machine learning model. Finally, the established machine learning model and the time-series optical remote sensing images of Sentinel - 2 with 10 m resolution were used to estimate the regional winter wheat yield, so as to realize the application of coupling crop growth model and machine learning algorithm, and establish a new regional winter wheat yield estimation mode. Based on Sobol parameter sensitivity analysis algorithm, the sensitivity parameters of TWSO and LAImaxwere quantified. The TDWI, TBASE, CVS and CVL sensitivity parameters related to LAImaxwere optimized by time-series LAI data and particle swarm optimization ( PSO) algorithm. And inputting them into the PyWOFOST model, using the EnKF algorithm and time-series LAI data to adjust the AMAXTB1, TDWI, TSUMEM, and CVO sensitivity parameters of TWSO to improve the accuracy of the single-point yield estimation. Compared with the site yield points, the R2, RMSE, MAE, and Bias of estimation were 0. 866 5, 468. 64 kg/hm2, 385. 70 kg/hm2and 103. 08, respectively, providing accurate site points yield of training data for establishing the RFR region yield estimation algorithm. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 34

Main heading: Time series

Controlled terms: Crops? - ?Forestry? - ?Kalman filters? - ?Learning algorithms? - ?Optical remote sensing? - ?Parameter estimation? - ?Particle swarm optimization (PSO)? - ?Sensitivity analysis

Uncontrolled terms: Crop growth model? - ?Ensemble Kalman Filter? - ?Leaf Area Index? - ?PyWOFOST crop growth model? - ?Sentinel - 2 satellite? - ?Times series? - ?Winter wheat? - ?Winter wheat yields? - ?Yield estimation? - ?Yield points

Classification code: 723 Computer Software, Data Handling and Applications? - ?723.4.2 Machine Learning? - ?741.3 Optical Devices and Systems? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.4 Agricultural Products? - ?921 Mathematics? - ?921.5 Optimization Techniques? - ?922.2 Mathematical Statistics

Numerical data indexing: Mass 6.40E 01kg, Mass 7.00E 01kg, Size 1.00E 01m

DOI: 10.6041/j.issn.1000-1298.2023.06.014

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

20. Lightweight Dairy Cow Body Condition Scoring Method Based on Improved YOLO v5s

Accession number: 20233014437845

Title of translation: YOLO v5s

Authors: Huang, Xiaoping (1, 2); Feng, Tao (1); Guo, Yangyang (1, 2); Liang, Dong (1, 2)

Author affiliation: (1) School of Internet, Anhui University, Hefei; 230039, China; (2) National Engineering Research Center for Agro-Ecological Big Data Analysis and Application, Hefei; 230039, China

Corresponding author: Guo, Yangyang(guoyangyang113529@ahu.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 287-296

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Cow body condition score is an important indicator to evaluate the productivity and physical health of cows. At present, with the development of modern farming, intelligent detection technology has been applied to precision farming of dairy cows. In view of the problems of large number of parameters and large calculation of the current detection algorithm, an improved lightweight cow body condition scoring model (YOLO - MCE) was proposed based on YOLO v5s. Firstly, a 2D camera was used to acquire the cow tail images at the cow milking lane, and those images were filtered to obtain the final BCS dataset. Secondly, the coordinate attention ( CA) mechanism was integrated into the MobileNetV3 network to build the M3CA network, which was used to replace the YOLO v5s backbone network to reduce the complexity of the model, and make the network feature extraction pay more attention to the location and spatial information of the cow tail area. Finally, the EIoU Loss function was used in the prediction layer of YOLO v5s to optimize the regression convergence speed of the target bounding box and generate a prediction bounding box with accurate positioning. The experimental results showed that the improved YOLO v5s model had a detection precision of 93. 4%, a recall rate of 85. 5%, an mAP@ 0. 5 of 91. 4%, a FLOPs of 2. 0 ¡Á 109, and a model size of 2. 28 MB. Compared with the original YOLO v5s model, the FLOPs and model size of YOLO - MCE were reduced by 87. 3% and 83. 4%, respectively, which further showed that the proposed method can achieve efficient scoring of cow body conditions under the condition of low model complexity and high real-time performance. In addition, the overall performance of the improved YOLO v5s model was superior to that of the Fast R - CNN, SDD and YOLO v3 object detection models. The research result can provide a theoretical basis and research ideas for the commercialization of dairy cow body condition scoring, and offer a research direction for the application of intelligent algorithms. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 30

Main heading: Object detection

Controlled terms: Complex networks? - ?Electric current measurement? - ?Farms

Uncontrolled terms: Attentional mechanism? - ?Body condition? - ?Body condition score? - ?Bounding-box? - ?Dairy cow? - ?Lightweight? - ?Model size? - ?Physical health? - ?Scoring methods? - ?Targets detection

Classification code: 722 Computer Systems and Equipment? - ?723.2 Data Processing and Image Processing? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?942.2 Electric Variables Measurements

Numerical data indexing: Percentage 3.00E 00%, Percentage 4.00E 00%, Percentage 5.00E 00%

DOI: 10.6041/j.issn.1000-1298.2023.06.030

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

21. Energy Dissipation Device Design and Influencing Factors of Diversion Water Transmission Network

Accession number: 20233014437855

Title of translation:

Authors: Yu, Liming (1); Zhang, Yusheng (1); Cui, Jilin (2); Li, Na (1); Yang, Wenhan (3); Hao, Zhiming (1)

Author affiliation: (1) Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming; 650500, China; (2) Southwest Nonferrous Kunming Exploration Surveying and Designing (Institute) Co., Ltd., Kunming; 650217, China; (3) Yunnan Point Run Water Saving Equipment Manufacturing Co., Ltd., Kunming; 650600, China

Corresponding author: Cui, Jilin(64908149@qq.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 319-327

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to ensure the safety of mountain water transmission network, the diversion type energy dissipation deviee was designed. The device was composed of an upper shell, an energy dissipation cavity and a lower shell, which was provided with an inlet end and an outlet end. The energy dissipation cavity was provided with an evenly spaced energy dissipation plate and a diversion hole. Fluent numerical simulation and experiments were used to verify the test method. Three inlet velocity rates, three diversion aperture ratios and the presence or absence of diversion plates were set to carry out all-factor tests, and energy dissipation rate comparison tests were carried out on the diameters of two diversion holes. The results showed that under the guarantee of overflow capacity, the inlet velocity and diversion aperture both played a leading role in energy dissipation rate. The larger the inlet velocity was, the larger the flow rate was, the better the energy dissipation rate would be. The energy dissipation rate was negatively correlated with the diversion aperture, and the smaller the diversion aperture was, the better the energy dissipation was. When the base aperture was the same, in order to satisfy the overflow capacity at the same time and ensure the dissipation of energy to achieve a better effect, it was recommended to choose the diversion aperture ratio unchanged arrangement. When the inlet velocity was 1. 0 m/s, the local head loss accounts was 96. 3% of the total head loss, so when calculating the total head loss, frictional head loss can be ignored. When inlet velocity was less than 4. 0 m/s, when choosing not to install the deflector, it can be up to 4. 0 m/s, the presence of deflector dissipation was flat, when it was more than 5. 0 m/s, the effect was better when choosing to install deflector energy dissipation. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 34

Main heading: Energy dissipation

Controlled terms: Inlet flow? - ?Numerical methods

Uncontrolled terms: Aperture ratio? - ?Diversion hole? - ?Diversion plate? - ?Energy dissipation cavity? - ?Energy dissipation plate? - ?Energy dissipation rate? - ?Inlet velocity? - ?Mountain? - ?Water transmission? - ?Water transmission network

Classification code: 525.4 Energy Losses (industrial and residential)? - ?631.1 Fluid Flow, General? - ?921.6 Numerical Methods

Numerical data indexing: Percentage 3.00E 00%, Velocity 0.00E00m/s

DOI: 10.6041/j.issn.1000-1298.2023.06.033

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

22. Class-special Real-time Dairy Goat Tracking Method Based on DiMP

Accession number: 20233014438073

Title of translation: DiMP

Authors: Ning, Jifeng (1, 2); Zhang, Jing (1); Yang, Shuqin (2, 3); Hu, Shenrong (4); Lan, Xianyong (4); Wang, Yongsheng (5)

Author affiliation: (1) College of Information Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Shaanxi, Yangling; 712100, China; (3) College of Mechanical and Electronic Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (4) College of Animal Science and Technology, Northwest A&F University, Shaanxi, Yangling; 712100, China; (5) College of Animal Medical, Northwest A&F University, Shaanxi, Yangling; 712100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 280-286 400

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In the process of fine breeding of dairy goats, the accurate and real-time tracking of goat targets is an important basis for their behavior recognition and disease abnormality warning. Based on the DiMP tracking model, a kind specific target tracking model was designed for dairy goats, which can effectively overcome the disadvantage of insufficient positioning accuracy of DiMP algorithm in tracking specific targets. The migration training of the tracking algorithm was carried out by using the constructed dairy goat video tracking data training set to accelerate the convergence speed of the model and make the boundary box predicted by the evaluation network more fit the position and size of the real frame of the dairy goat. In the online tracking stage, aiming at the disadvantage that the target template only used the first frame features to produce the modulation vector of the whole sequence, which led to unrepresentative characteristics of the modulation vector relative to the whole tracking stage, the training set was used to produce the class modulation vector containing various poses of the dairy goat, and the proportion between the class modulation vector of the dairy goat and the modulation vector of the first frame was updated by exponential ablation to enhance the discrimination between characteristics and background of dairy goats in the boundary box regression task. The AUC and accuracy of the proposed algorithm on the test set were 76. 20% and 60. 19%, respectively, which were 6. 17 and 14. 18 percentage points higher than that of the DiMP method. The tracking speed was 30 frames per second (f/s), which met the requirements of real-time tracking. The experimental results showed that the proposed target tracking method can be used to monitor the movement of milk goats in complex scenes, and it can provide technical support for fine management of dairy goats. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 34

Main heading: Dairies

Controlled terms: Behavioral research? - ?Clutter (information theory)? - ?Dairy products? - ?Target tracking? - ?Vectors

Uncontrolled terms: Class-specific? - ?Dairy goat? - ?DiMP? - ?Modulation vectors? - ?Object Tracking? - ?Real time tracking? - ?Targets tracking? - ?Tracking method? - ?Tracking models? - ?Transfer learning

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?716.1 Information Theory and Signal Processing? - ?822.1 Food Products Plants and Equipment? - ?822.3 Food Products? - ?921.1 Algebra? - ?971 Social Sciences

Numerical data indexing: Percentage 1.90E 01%, Percentage 2.00E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.029

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

23. Rapid Monitoring of Key Quality Indicators of Red Wines Based on UV-Vis Spectroscopy

Accession number: 20233014437816

Title of translation:

Authors: Liu, Caiyun (1); Li, Huiying (1); Zhang, Qianwei (1); Fan, Shuyue (1); Tao, Yongsheng (1, 2); Li, Yunkui (1, 2)

Author affiliation: (1) College of Enology, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Ningxia Helan Mountain¡¯s East Foothill Wine Experiment and Demonstration Station, Northwest A&F University, Yongning; 750104, China

Corresponding author: Li, Yunkui(ykli@nwsuaf.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 401-409

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Consumer demand for high-quality and safely produced wines requires high standards in terms of quality assurance and process control methods, which in turn requires proper analysis of wines during and after production. The role of phenolics and color characteristics in ensuring wine quality at all stages of the production process is gradually gaining recognition and importance. However, traditional chemical analysis methods required cumbersome pre-treatment, expensive instrumentation requirements, time-consuming determination procedures, and harsh operating conditions. The evolution of phenolics and color was monitored, as well as UV - Vis absorption spectral characteristics, and a partial least squares regression ( PLSR ) model was developed for phenolics and color parameters based on UV - Vis spectroscopy during wine fermentation and aging. The results showed that the content of total phenols, total tannins and total flavanols were increased continuously during fermentation and decreased gradually during aging. In contrast, total flavonoids were increased and then decreased during fermentation and gradually decreased during aging. In addition, the maceration process and the early stage of fermentation were the critical periods for color formation, while the color was gradually aged during the aging. The calibration set correlation coefficients -Rcal and validation set correlation coefficients ffTal of the UV - Vis spectroscopy-based phenolic and color parameter prediction models were both no less than 0. 84, and the residual predictive deviation (RPD) was no less than 2. 54, thus the models could achieve the prediction purpose. Therefore, UV - Vis spectroscopy combined with chemometrics was a simple, economical and efficient way to monitor phenolic compounds and color evolution during red wine fermentation and aging. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 33

Main heading: Fermentation

Controlled terms: Color? - ?Forecasting? - ?Least squares approximations? - ?Phenols? - ?Process control? - ?Quality assurance? - ?Raman spectroscopy? - ?Spectrum analysis? - ?Ultraviolet visible spectroscopy? - ?Wine

Uncontrolled terms: Chemometrices? - ?Color parameter? - ?Phenolics? - ?Quantitative prediction? - ?Rapid monitoring? - ?Red wine? - ?Red wine color? - ?UV/ Vis spectroscopy? - ?Wine color? - ?Wine-aging

Classification code: 741.1 Light/Optics? - ?804.1 Organic Compounds? - ?822.3 Food Products? - ?913.3 Quality Assurance and Control? - ?921.6 Numerical Methods

DOI: 10.6041/j.issn.1000-1298.2023.06.041

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

24. Straw Moisture Content Control System of Mobile Straw Compactor

Accession number: 20233014439491

Title of translation:

Authors: Wang, Wei (1); Gong, Yuanjuan (1); Bai, Xuewei (1); Tan, Rui (1); Li, Nannan (2); Li, Hongyu (2)

Author affiliation: (1) School of Engineering, Shenyang Agricultural University, Shenyang; 110866, China; (2) Liaoning Ningyue Agricultural Machinery Equipment Co., Ltd., Jinzhou; 121400, China

Corresponding author: Gong, Yuanjuan(yuanjuangong@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 386-393

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming at the problems of large crack, poor quality and low molding rate of straw particles produced by straw compactor due to its low moisture content in the field, a moisture content control model was constructed, and a moisture content control system of straw compactor was proposed based on SSA -Smith - LADRC. The system used smith predictor to solve the time-delay problem of the system, and used sparrow search algorithm ( SSA) to optimize the parameters of linear active disturbance rejection controller ( LADRC) to achieve accurate control of moisture content. The simulation experiment showed that SSA - Smith - LADRC had no overshoot, and the adjustment time was 1.53 s. After the water content control system was stable, the time to recover from interference was 0. 62 s, and the overshoot was 0. After the stable state was restored again, there was no oscillation. The experiment in the factory showed that the system had no overshoot, the maximum error was 2. 0%, and the average error was 1. 5% . The experiment in the filed showed that when the moisture content of straw was not regulated in normal operation, the shaping rate of straw particles was 62. 4% . When the moisture content of straw was controlled by manual experience, the error of moisture content was changed greatly, the average error was 9. 83%, and the molding rate was 82. 1%. When the water content control system was regulated, the average error of water content was 2. 82%, and the molding rate was 93. 4% . Compared with Smith - PID, SSA - Smith - LADRC reduced the adjustment time by 4.05 s, overshoot by 86.5%, maximum error by 42. 0%, minimum error by 50. 8%, and mean square error by 60. 2%, respectively. The moisture content control system proposed can effectively track the change of straw moisture content, improve the molding rate of straw particles. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Controllers

Controlled terms: Delay control systems? - ?Disturbance rejection? - ?Errors? - ?Mean square error? - ?Molding? - ?Quality control

Uncontrolled terms: Active disturbance rejection? - ?Active disturbance rejection controller? - ?Adjustment time? - ?Average errors? - ?Content control? - ?Control model? - ?Maximum error? - ?Search Algorithms? - ?Smith-predictor? - ?Straw compactor

Classification code: 731 Automatic Control Principles and Applications? - ?731.1 Control Systems? - ?732.1 Control Equipment? - ?913.3 Quality Assurance and Control? - ?922.2 Mathematical Statistics

Numerical data indexing: Percentage 0.00E00%, Percentage 1.00E00%, Percentage 2.00E 00%, Percentage 4.00E 00%, Percentage 5.00E 00%, Percentage 8.00E 00%, Percentage 8.20E 01%, Percentage 8.30E 01%, Percentage 8.65E 01%, Time 1.53E 00s, Time 4.05E 00s, Time 6.20E 01s

DOI: 10.6041/j.issn.1000-1298.2023.06.039

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

25. Adaptive Fast Integrating Terminal Sliding Mode Tracking Control Technique for Weeding Robot

Accession number: 20233014437841

Title of translation:

Authors: Ji, Jie (1); He, Qing (1); Zhao, Lijun (1, 2); Li, Ping (3); Liu, Yang (1); Wang, Xiaokang (1)

Author affiliation: (1) College of Engineering and Technology, Southwest University, Chongqing; 404100, China; (2) College of Intelligent and Manufacturing Engineering, Chongqing University of Arts and Sciences, Chongqing; 402160, China; (3) Institute of Agricultural Machinery, Chongqing Academy of Agricultural Sciences, Chongqing; 404100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 55-64

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: When the intelligent weeding robot was working in the lawn, it was easy to be affected by external disturbance and system uncertainty, which led to long tracking convergence time and poor tracking effect. Therefore, an adaptive fast integrating terminal sliding mode control algorithm for trajectory tracking was designed. Firstly, the dynamics model of the weeding robot was established by considering the dynamic characteristics of the driving wheel and uncertainties such as unmodeled errors, external interference and dynamic and static friction. Then based on the established dynamic model, an adaptive fast integrating terminal sliding mode controller was designed. The proposed controller combined the advantages of fast terminal sliding mode, integral sliding mode and adaptive estimation technology to achieve the desired tracking performance and suppress control signal jitter. At the same time, without specifying the upper bound of the system uncertainty and external interference, the designed adaptive estimation can be used for real-time compensation to improve the robustness of the system. Finally, the effectiveness of the proposed method was verified by simulation and experiment. The experimental results showed that the designed controller can make the tracking error converge quickly in a limited time, and the absolute value of the lateral error was no more than 0. 097 9 m, the absolute value of the longitudinal error was no more than 0. 102 6 m, and the absolute value of the heading angle error was no more than 0. 057 8 rad, which can ensure the robot to track the working path accurately and have strong robustness. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Errors

Controlled terms: Controllers? - ?Dynamic models? - ?Intelligent robots? - ?Robustness (control systems)? - ?Sliding mode control? - ?Stiction

Uncontrolled terms: Absolute values? - ?Adaptive estimation? - ?Dynamics models? - ?External interference? - ?Fast integrating terminal sliding mode? - ?Sliding mode tracking? - ?System uncertainties? - ?Terminal sliding mode? - ?Trajectory-tracking? - ?Weeding robots

Classification code: 731.1 Control Systems? - ?731.6 Robot Applications? - ?732.1 Control Equipment? - ?921 Mathematics

Numerical data indexing: Absorbed dose 8.00E-02Gy, Size 6.00E 00m, Size 9.00E 00m

DOI: 10.6041/j.issn.1000-1298.2023.06.006

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

26. Design and Experiment of Seed Separation Tray of Air-suction Roller Dibbler for Peanut

Accession number: 20233014437874

Title of translation:

Authors: Zhang, Chunyan (1); Kang, Jianming (1); Zhang, Ningning (1); Peng, Qiangji (1); Zhang, Hui (2); Wang, Xiaoyu (1)

Author affiliation: (1) Shandong Academy of Agricultural Machinery Sciences, Ji¡¯nan; 250010, China; (2) Engineering Research Center for Production Mechanization of Oasis Special Economic Crop, Ministry of Education, Shihezi; 832061, China

Corresponding author: Zhang, Hui(shzuzhanghui@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 28-37

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to solve the problem of low single seed rate caused by air-suction roller dibbler for peanut decreases due to the unstable performance of the first seed feeding, the seed separation tray was added between the seed collecting tray and the secondary seed feeding mechanism of the air-suction roller dibbler for peanut. The seeds were limited in a small tooth shaped space, and the seeds were moved along a predetermined track to improve the accuracy and precision of seed delivery of the air-suction roller dibbler for peanut. The tooth shape of seed separation tray and the position relationship between seed separation tray and seed collecting tray were designed and analyzed, and the structure and position parameters of seed separation tray were determined. The working process of air-suction roller dibbler for peanut was studied, the movement track of seeds in seed carrying area was analyzed, and the mechanism of missed seeding and replanting was clarified by using DEM - CFD coupling method. Three factors quadratic rotation orthogonal combination test was conducted with qualification index, missed seeding index and replaying index as evaluation indexes. The effects of tooth shape direction angle, installation angle and operation speed on seed delivery performance were analyzed. The results showed that when the direction angle of the tooth shape was -4. 55¡ã, the installation angle was 14. 99¡ã and the operating speed was 4. 01 km/h, the seed metering performance of the air-suction roller dibbler for peanut was the best. The qualification index was 94. 99%, the missed seeding index was 2. 49%, and the replanting index was 2. 52% . Based on the optimal combination, the field contrast test was conducted, and the test results met the technical requirements of single seed precision sowing machine for peanut. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 24

Main heading: Rollers (machine components)

Controlled terms: Oilseeds

Uncontrolled terms: Air suction? - ?Air-suction roller dibble? - ?DEM - CFD? - ?Direction angle? - ?Installation angle? - ?Peanut? - ?Performance? - ?Seed separation tray? - ?Single seeds? - ?Suction rollers

Classification code: 601.2 Machine Components? - ?821.4 Agricultural Products

Numerical data indexing: Percentage 4.90E 01%, Percentage 5.20E 01%, Percentage 9.90E 01%, Size 1.00E 03m

DOI: 10.6041/j.issn.1000-1298.2023.06.003

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

27. Remote Sensing Inversion of Leaf Area Index of Mulched Winter Wheat Based on Feature Downscaling and Machine Learning

Accession number: 20233014437813

Title of translation: LAI

Authors: Gu, Xiaobo (1); Cheng, Zhikai (1); Zhou, Zhihui (1); Chang, Tian (1); Li, Wenlong (1); Du, Yadan (1)

Author affiliation: (1) Key Laboratory of Agricultural Soil and Water Engineering in Arid and Semiarid Areas, Ministry of Education, Northwest A&F University, Shaanxi, Yangling; 712100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 148-157 167

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: To further improve the ability of UAV remote sensing to rapidly monitor the leaf area index (LAI) of winter wheat under mulehing conditions, a UAV with a five-channel multispectral sensor was used to acquire remote sensing image data of winter wheat during the emergence, overwintering, rejuvenation, plucking, tasseling and filling stages from 2021 to 2022, using supervised classification to remove background and calculate 50 visible and near-infrared vegetation indices. The LAI inversion models of mulched winter wheat with different input feature variables were developed and evaluated in terms of accuracy by using six machine learning algorithms; partial least squares, ridge regression, support vector machine, random forest, extreme gradient boosting and artificial neural network. The results showed that removing the mulched background would make the reflectance of winter wheat canopy closer to the real value and improve the inversion accuracy. The inversion accuracy and stability of mulched winter wheat LAI can be improved by using a suitable feature reduction method combined with machine learning algorithm, and the inversion accuracy before feature reduction cannot be optimized by principal component analysis and correlation coefficient method, and the decision tree ranking was only applicable to random forest and extreme gradient boosting algorithm based on tree model, and the optimization effect of genetic algorithm was obvious, genetic algorithm - artificial neural network model inversion effect reached the optimal (R2was 0. 80, RMSE was 1. 10, MAE was 0. 69, and deviation was 1. 25% ). The research results can provide theoretical reference for UAV remote sensing to monitor the growth condition of mulched winter wheat. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 43

Main heading: Genetic algorithms

Controlled terms: Adaptive boosting? - ?Crops? - ?Decision trees? - ?Image enhancement? - ?Infrared devices? - ?Least squares approximations? - ?Neural networks? - ?Principal component analysis? - ?Regression analysis? - ?Remote sensing ? - ?Support vector machines? - ?Unmanned aerial vehicles (UAV)? - ?Vegetation mapping

Uncontrolled terms: Down-scaling? - ?Feature downscaling? - ?Inversion accuracy? - ?Leaf Area Index? - ?Machine-learning? - ?Mulching? - ?Multi-spectral? - ?UAV multispectral? - ?Vegetation index? - ?Winter wheat

Classification code: 405.3 Surveying? - ?652.1 Aircraft, General? - ?723 Computer Software, Data Handling and Applications? - ?821.4 Agricultural Products? - ?921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory? - ?921.6 Numerical Methods? - ?922.2 Mathematical Statistics? - ?961 Systems Science

Numerical data indexing: Percentage 2.50E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.015

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

28. Design and Experiment of Double-row Chain Planting Device for Cabbage Substrate Block Seedlings

Accession number: 20233014437865

Title of translation:

Authors: Cui, Zhichao (1, 2); Guan, Chunsong (2); Xu, Tao (3); Fu, Jingjing (2); Chen, Yongsheng (2); Zheng, Shuhe (1)

Author affiliation: (1) College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou; 350100, China; (2) Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing; 210014, China; (3) Institute of Agricultural Facilities and Equipment, Jiangsu Academy of Agricultural Science, Nanjing; 210014, China

Corresponding author: Zheng, Shuhe(zsh@fafu.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 46-54

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In view of the problems of different planting depths, high lodging rate and seedling injury rate in traditional cabbage planting devices, which affect the workability of machine harvesting, a double-row chain planting device was designed for cabbage substrate block seedlings, through theoretical analysis of the device and key components, the operating parameters of the device were determined. A double-row chain planting device test bench for cabbage substrate block seedlings was built, and the three-factor five-level quadratic regression orthogonal rotation combination test was carried out on lodging rate and seedling injury rate with forward speed, planting frequency, and clamping force of splint in the planter as test factors; through Design-Expert 8.0.6 software, the regression model of each influencing factor on the index was established, and the relationship between influencing factors on the index was analyzed, while the response surface method was used to optimize the influencing factors comprehensively, and the optimal combination of parameters was obtained; forward speed was 1.6 km/h, planting frequency was 57 plants/min, internal splint clamping force was 91. 83 N, corresponding to the lodging rate of 2. 9% and seedling injury rate of 2. 83% . The combination of parameters was verified by bench test, the lodging rate was 3. 13% and the seedling injury rate was 3. 07%, which were basically consistent with the optimization results, which verified the rationality of the built model and the optimized parameters. Field test results showed that the lodging rate was 3. 35%, the seedling injury rate was 3. 14%, and the relative errors with optimized results of the two indicators were 0. 45% and 0. 31%, indicating that the device had high stability. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 23

Main heading: Software testing

Controlled terms: Clamping devices? - ?Machine components? - ?Regression analysis? - ?Seed

Uncontrolled terms: Cabbage? - ?Clamping Force? - ?Double rows? - ?Double-row chain? - ?Forward speed? - ?Injury rate? - ?Planting device? - ?Plantings? - ?Substrate block seedling? - ?Transplanter

Classification code: 601.2 Machine Components? - ?723.5 Computer Applications? - ?821.4 Agricultural Products? - ?922.2 Mathematical Statistics

Numerical data indexing: Force 8.30E 01N, Percentage 1.30E 01%, Percentage 1.40E 01%, Percentage 3.10E 01%, Percentage 3.50E 01%, Percentage 4.50E 01%, Percentage 7.00E 00%, Percentage 8.30E 01%, Percentage 9.00E 00%, Size 1.60E 03m

DOI: 10.6041/j.issn.1000-1298.2023.06.005

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

29. Individual Identification of Dairy Cows under Unrestricted Conditions Based on Fusion of Deep and Traditional Features

Accession number: 20233014444934

Title of translation:

Authors: Si, Yongsheng (1, 2); Wang, Zhaoyang (1, 2); Zhang, Yan (1); Wang, Kejian (1, 2); Liu, Gang (3)

Author affiliation: (1) College of Information Science and Technology, Hebei Agricultural University, Baoding; 071001, China; (2) Key Laboratory of Agricultural Big Data of Hebei Province, Baoding; 071001, China; (3) Key Laboratory of Agricultural Information Acquisition Technology, China Agricultural University, Ministry of Agriculture and Rural Affairs, Beijing; 100083, China

Corresponding author: Liu, Gang(pac@cau.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 272-279

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Cow individual recognition is the premise of automatic cow behavior analysis and disease detection, which is important for achieving precision animal husbandry. An individual identification method of dairy cows under unrestricted conditions based on the fusion of deep features and traditional features was proposed. Firstly, Mask R - CNN was used to identify cows in standing and lying positions. Secondly, two methods were used to extract the feature probability vectors of dairy cows. Convolutional neural network ( CNN) was used to extract the deep features in the form of probability vectors of Softmax layer. The traditional features were manually extracted and selected by neighbourhood component analysis (NCA), and input into the support vector machine ( SVM) model to output the probability vector. Finally, the two features were fused. Based on the fused features, SVM was used to classify the dairy cows. The experiment of cow individual identification was carried out on the image data set of 58 cows in standing and lying positions. The results showed that for cows in standing and lying cows, the feature fusion method improved the accuracy by about 3 percentage points and 2 percentage points compared with that using deep features alone, and the accuracy of the feature fusion method was improved by about 5 percentage points and 10 percentage points for cows in standing and lying postures, respectively, compared with traditional features alone. The accuracy of the method proposed reached 98. 66% and 94. 06% for standing and lying cows, respectively. The results can provide effective technical support for intelligent cow behavior analysis, disease detection, etc. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 26

Main heading: Computer vision

Controlled terms: Convolutional neural networks? - ?Multilayer neural networks? - ?Support vector machines? - ?Vectors

Uncontrolled terms: Condition? - ?Dairy cow? - ?Features extraction? - ?Features fusions? - ?Individual identification? - ?Individual recognition? - ?Machine-vision? - ?Percentage points? - ?Probability vector? - ?Unrestricted condition

Classification code: 723 Computer Software, Data Handling and Applications? - ?723.5 Computer Applications? - ?741.2 Vision? - ?921.1 Algebra

Numerical data indexing: Percentage 6.00E 00%, Percentage 6.60E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.028

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

30. Design and Experiment of Intelligent Feed-pushing Robot Based on Information Fusion

Accession number: 20233014451350

Title of translation:

Authors: Zhang, Qin (1); Ren, Hailin (1); Hu, Jiahui (1)

Author affiliation: (1) School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou; 510641, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 78-84 93

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The regular pushing of feed is an essential part of feeding process of dairy cows. Aiming at the problem that the existing feed-pushing robots have single function, which cannot collect and transport the feed according to the cows¡¯ position to meet their needs, an intelligent feed-pushing robot for dairy cows was developed. Firstly, YOLACT instance segmentation model was used to identify cows, feed, and square rod and obtain the mask. Secondly, dynamic objects were removed at ORB - SLAM3 by using the mask to improve the positioning accuracy, and then the real-time robot position was obtained. Thirdly, the location of foraging cows was calculated by combining the mask, stereo camera depth image and the robot position, and the distance between the robot and the cattle barn was calculated by using mask and depth image with the square rod as reference. Finally, during the working process of the robot, the distance between the robot and the cattle barn was kept unchanged, and the independent decisions were made by the robot according to the foraging cows position and the feeding time, so as to realize the multi-mode feeding functions of push, collect-transport and clean, so it can improve the feed utilization efficiency and meet the free feeding needs of cows. The research and experimental results showed that on the TUM RGB - D dataset, compared with ORB - SLAM3 , the proposed algorithm can effectively reduce the positioning error in dynamic environments; the foraging cows position calculation accuracy was ¡À0. 1 m, and each cow can be recognized; the distance calculation accuracy between the robot and the cattle barn was ¡À 0. 8 cm; the working mode selection accuracy was 100% ; and the algorithm running rate was 12 f/s. The robot met the requirements of intelligent feeding of robots in complex environments. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 27

Main heading: Feeding

Controlled terms: Farm buildings? - ?Intelligent robots? - ?Stereo image processing

Uncontrolled terms: Cow? - ?Dairy cow? - ?Depth image? - ?Dynamic object elimination? - ?Dynamic objects? - ?Instance segmentation? - ?Intelligent feed-pushing? - ?Robot positions? - ?Square rods? - ?Visual SLAM

Classification code: 402.1 Industrial and Agricultural Buildings? - ?691.2 Materials Handling Methods? - ?723.2 Data Processing and Image Processing? - ?731.6 Robot Applications? - ?821.6 Farm Buildings and Other Structures

Numerical data indexing: Percentage 1.00E 02%, Size 1.00E00m, Size 8.00E-02m

DOI: 10.6041/j.issn.1000-1298.2023.06.008

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

31. Research Progress in Intelligent Diagnosis and Prescription Recommendation of Crop Diseases

Accession number: 20233014437989

Title of translation:

Authors: Zhang, Lingxian (1, 2); Han, Mengyao (1); Ding, Junqi (1); Li, Kaiyu (1)

Author affiliation: (1) College of Information and Electrical Engineering, China Agricultural University, Beijing; 100083, China; (2) Key Laboratory of Agricultural Informatization Standardization, Ministry of Agriculture and Rural Affairs, Beijing; 100083, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 1-18

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The plant electronic medical records formed by the ¡°plant clinic¡± provide new ideas for the prescription recommendation of crop diseases. How to efficiently mine electronic medical record data and assist crop disease prescription recommendation is still a hot research issue, and needs to be solved urgently at home and abroad. On the basis of summarizing and sorting out the existing domestic and foreign research literature, the key technologies of crop disease diagnosis and prescription recommendation, such as spores recognition based on microscopic image, crop disease diagnosis based on spectrum, crop disease prescription recommendation based on electronic medical records, were systematically analyzed and discussed. The results showed that centering on the infection process of crop disease pathogens, the research on crop disease prescription recommendation based on electronic medical record data mining would become a research focus, guided by intelligent prescription recommendation demand. In the process of crop disease prescription recommendation, due to the characteristics and difficulties of crop disease pathogenesis complex, crop varieties and disease types, disease dynamic changes and characteristics, it would be an important direction to research on the analysis of crop disease pathogenesis, diagnostic reasoning, intelligent prescription recommendation and its application strategy based on electronic medical record data mining. It was of greater practical significance to explore the data mining analysis and research of crop disease electronic medical record based on key technologies such as knowledge graph analysis, big data mining and machine learning algorithm reasoning, and visually analyze the pathogenic mechanism of crop disease, and the correlation between characteristics from the regional macro perspective in order to realize single crop disease prescription recommendation based on diagnostic reasoning, and multiple crop disease prescription recommendation based on semantic matching for practical application scenarios. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 149

Main heading: Data mining

Controlled terms: Crops? - ?Data visualization? - ?Diagnosis? - ?Learning algorithms? - ?Machine learning? - ?Medical computing? - ?Medical imaging? - ?Semantics

Uncontrolled terms: Crop disease? - ?Diagnostic reasoning? - ?Disease detection? - ?Disease diagnosis? - ?Intelligent diagnosis? - ?Key technologies? - ?Medical record? - ?Pathogen spore recognition? - ?Plant electronic medical record? - ?Prescription recommendation

Classification code: 461.1 Biomedical Engineering? - ?461.6 Medicine and Pharmacology? - ?723.2 Data Processing and Image Processing? - ?723.4 Artificial Intelligence? - ?723.4.2 Machine Learning? - ?723.5 Computer Applications? - ?746 Imaging Techniques? - ?821.4 Agricultural Products

DOI: 10.6041/j.issn.1000-1298.2023.06.001

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

32. UAV Measurement of Plant Height of Breeding Wheat Based on Fine-scale Correction

Accession number: 20233014444790

Title of translation:

Authors: Wu, Tingling (1); Liu, Xinzhe (1); Nie, Ruiqi (2); Liu, Jia (2); Wu, Lu (1); Li, Tao (1)

Author affiliation: (1) College of Mechanical and Electronic Engineering, Northwest a and F University, Shaanxi, Yangling; 712100, China; (2) College of Agriculture, Northwest a and F University, Shaanxi, Yangling; 712100, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 158-167

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In the field experiment of wheat breeding, an important measurement index is the plant height of the plot population. To solve the problem of low accuracy of wheat plant height measurement based on UAV remote sensing, two methods were proposed, including a nearest neighbor correction method (NNCM) and a spectral index correction method (SICM). NNCM based on the true value of manual measurement, the height information of the community group was obtained, the elevation correction was carried out in combination with the ridge, and then the accurate plant height of the community was obtained by sliding correction according to the true value of the neighbor. SICM of multi-spectral RGB data fusion, by calculating vegetation index and performing index optimization, an accurate inversion model of plant height-vegetation index was constructed. The test results showed that the relative root mean square error (RMSEIOO) of the traditional UAV crop height measurement method in the six periods with ground truth were 11. 15% , 59. 44% , 11. 76% , 12. 31% , 8. 05% and 59. 76% ; the RMSEIOO of NNCM were 7. 17% , 8. 18% , 5. 70% , 5. 62% , 5. 65% and 7. 74% ; the RMSEIOO of SICM were 7.33%, 8.17%, 6.05%, 6.15%, 6.45% and 10.50%; the NNCM and SICM kernel density distribution curves were closer to the ground truth, and the median, quartile, maximum, and minimum deviations did not exceed 0. 5% . These indicated that both the proposed methods can correct the plant height traits on the grain size of breeding plots measured by UAV. The two models proposed had high accuracy and strong robustness. NNCM was suitable for the scene of random sampling of ground truth on the ground, while SICM was used for plant height detection of large-scale farmland, and different methods were selected according to the using conditions. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 35

Main heading: Unmanned aerial vehicles (UAV)

Controlled terms: Data fusion? - ?Electromagnetic wave attenuation? - ?Mean square error? - ?Remote sensing? - ?Vegetation

Uncontrolled terms: Correction method? - ?High throughput phenotype? - ?High-throughput? - ?Multispectral imaging? - ?Nearest-neighbour? - ?Plant height? - ?Spectral indices? - ?UAV remote sensing? - ?Vegetation index? - ?Wheat

Classification code: 652.1 Aircraft, General? - ?711 Electromagnetic Waves? - ?723.2 Data Processing and Image Processing? - ?922.2 Mathematical Statistics

Numerical data indexing: Percentage 1.05E 01%, Percentage 1.50E 01%, Percentage 1.70E 01%, Percentage 1.80E 01%, Percentage 3.10E 01%, Percentage 4.40E 01%, Percentage 5.00E 00%, Percentage 6.05E 00%, Percentage 6.15E 00%, Percentage 6.20E 01%, Percentage 6.45E 00%, Percentage 6.50E 01%, Percentage 7.00E 01%, Percentage 7.33E 00%, Percentage 7.40E 01%, Percentage 7.60E 01%, Percentage 8.17E 00%

DOI: 10.6041/j.issn.1000-1298.2023.06.016

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

33. Improved Probability Path Graph Method for Robots Based on Goal-oriented Sampling

Accession number: 20233114478838

Title of translation:

Authors: Chen, Zhiyong (1); Wu, Jinghua (1)

Author affiliation: (1) School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou; 350108, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 410-418 426

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Due to the complete randomness of sampling, the traditional PRM algorithm was often difficult to be applied to the robot path planning in the working environment, including narrow channels. To this end, an improved probabilistic roadmap method (Improved PRM) integrating global goal-oriented sampling and local node enhancement was proposed and utilized to the path planning of a planar grid map scene and a 6-DOF robot. Firstly, the global goal-directed sampling was combined with the random sampling in the proposed Improved PRM, and the probability of global sampling points falling into narrow channels was raised by the mixed sampling, so as to achieve the heuristic map enhancement. Secondly, nodes in narrow channels were extracted by using the node weight idea, and a local node enhancement strategy based on Gaussian distribution was used to expand new nodes in narrow channels to enhance the connectivity of the map and the success rate of path planning. Finally, the redundant node elimination strategy was presented to optimize the initial path planned by the algorithm. The simulation results of the Improved PRM algorithm in the planar grid map showed that the success rate of the algorithm for robot path planning was more than 89.3%. Besides, the comprehensive evaluation and path quality evaluation were both higher than that of other algorithms. In the simulation experiment of a 6-DOF robot, the average path cost obtained by the Improved PRM algorithm was about 42.7% lower than that of the traditional PRM algorithm. Meanwhile, the probability of successfully passing through the narrow channel was also 68 percentage points higher than that of the traditional PRM algorithm. Therefore, compared with other algorithms, the Improved PRM algorithm had advantages in improving the success rate of path planning, reducing path nodes, and ensuring path quality in the working environment with narrow channels. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Motion planning

Controlled terms: Agricultural robots? - ?Quality control? - ?Robot programming

Uncontrolled terms: Global goal-oriented sampling? - ?Goal-oriented? - ?Grid map? - ?Improved probabilistic roadmap method? - ?Narrow channel? - ?Path graphs? - ?Planar grids? - ?Probabilistic roadmap methods? - ?Robot path-planning? - ?Working environment

Classification code: 723.1 Computer Programming? - ?731.5 Robotics? - ?821.1 Agricultural Machinery and Equipment? - ?913.3 Quality Assurance and Control

Numerical data indexing: Percentage 4.27E 01%, Percentage 8.93E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.042

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

34. Design and Test of Key Components of Vegetable Grafting Robot for Plug Seedlings

Accession number: 20233014444918

Title of translation:

Authors: Wang, Jiasheng (1); Zhang, Mei (1); Gao, Chunfeng (1); Shang, Shuqi (1); Wang, Dongwei (1)

Author affiliation: (1) College of Mechanical and Electrical Engineering, Qingdao Agricultural University, Qingdao; 266109, China

Corresponding author: Wang, Dongwei(w88030661@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 38-45

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to improve the efficiency of vegetable grafting in large-scale planting, taking solanaceous vegetable plug seedlings as the object of operation, automatic grafting techniques and key mechanisms of vegetable grafting robot were studied. Based on the splitting method, the overall structure scheme of a grafting robot for synchronous grafting of six solanaceous vegetable seedlings was proposed. It can continuously realize the functions of automatic feeding of plug seedlings, cutting and plugging of rootstocks and scions, directional sequencing of grafting clips, and holding and clamping. The key mechanisms of the grafting machine, such as the horizontal cutting mechanism of rootstock, the splitting mechanism of rootstock, the pushing cutting mechanism of scion, the plugging mechanism of rootstock and scion, the vibration sorting and clamping device and the holding and clamping mechanism were designed, and the key structural parameters of each mechanism were determined. Taking pepper seedlings as the grafting object, orthogonal experiments on cutting quality of grafting robot was carried out. The results showed that improving the clamping accuracy and cutting speed of the seedlings, and reducing the fiber hardness of the stems were beneficial to improving the cutting quality. The cutting speed was set at 1. 5 m/s, and a prototype performance verification test was conducted on the grafted pepper seedlings. The results showed that the cutting qualification rate of the rootstock and scion was 98. 6% , the grafting qualification rate was 97. 1% , the grafting survival rate was 96. 2% , and the grafting efficiency was 720 plants/h, which met the design requirements. This study provides support for the development of efficient multi-seedlings synchronous grafting robots. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 22

Main heading: Machine design

Controlled terms: Cutting? - ?Efficiency? - ?Grafting (chemical)? - ?Robots? - ?Seed? - ?Vegetables

Uncontrolled terms: Cutting mechanisms? - ?Cutting quality? - ?Cutting speed? - ?Design and tests? - ?Directional sorting of grafting clip? - ?Grafting robots? - ?Mechanism design? - ?Plug seedling? - ?Six seedling in one group? - ?Solanaceous vegetable

Classification code: 601 Mechanical Design? - ?731.5 Robotics? - ?802.2 Chemical Reactions? - ?821.4 Agricultural Products? - ?913.1 Production Engineering

Numerical data indexing: Percentage 1.00E00%, Percentage 2.00E 00%, Percentage 6.00E 00%, Velocity 5.00E 00m/s

DOI: 10.6041/j.issn.1000-1298.2023.06.004

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

35. Design and Experiment of Passive Anti-winding Stubble Breaking and Ridge Cleaning Device for No-tillage Planter

Accession number: 20233014437860

Title of translation:

Authors: Lin, Jing (1); L¨¹, Zhouyi (1); Li, Hongzhe (2); Wang, Xinyu (1); Wang, Dongrui (1)

Author affiliation: (1) College of Engineering, Shenyang Agricultural University, Shenyang; 110866, China; (2) Tieling County Modern Agricultural Development Service Center, Tiding, 112600, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 19-27

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Currently, during the no-tillage planting operation of corn ridge in Northeast China, there are issues such as entanglement and blockage of working parts, soil disturbance reduction, and improvement of stubble breaking and ditching quality. To address these issues, the anti-winding stubble breaking and clearing device was optimized, consisting of the Archimedes spiral serrated notch disc stubble cutter and star ridge cleaning wheel. Through theoretical analysis, the main parameters affecting the performance of the stubble clearing and ridge cleaning device were identified as the tool forward speed, the depth of the stubble cutter in soil, and the offset angle of the ridge clearing wheel installation. To determine the optimal working parameters of the device, the second-order regression orthogonal rotation combination simulation experiment was conducted by using the discrete element software EDEM. Through this experiment, the optimal working parameter combination of the device was obtained, which included a tool forward speed of 7 km/h, a stubble cutter depth of 75 mm, and a ridge clearing wheel installation offset angle of 30¡ã. Field experiments were conducted to verify the optimal parameter combination, and the results indicated that the stubble breaking rate of the Archimedes spiral sawtooth notch disc stubble breaker was 92.21% and the stubble clearing rate was 93.49%, which significantly improved the trafficability of machines and tools. The simulation theory results were verified by field experiments, meeting the technical requirements for the integration of ridge planting and no-tillage sowing agronomy and agricultural machinery in Northeast China. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 35

Main heading: Wheels

Controlled terms: Agricultural machinery? - ?Agriculture? - ?Computer software? - ?Winding

Uncontrolled terms: Anti-winding? - ?Archimede spiral? - ?Breakings? - ?Cleaning devices? - ?Discrete elements method? - ?No tillage? - ?No-till planters? - ?Northeast China? - ?Plantings? - ?Stubble breaking and ridge clearing device

Classification code: 601.2 Machine Components? - ?691.2 Materials Handling Methods? - ?723 Computer Software, Data Handling and Applications? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.1 Agricultural Machinery and Equipment

Numerical data indexing: Percentage 9.221E 01%, Percentage 9.349E 01%, Size 7.00E 03m, Size 7.50E-02m

DOI: 10.6041/j.issn.1000-1298.2023.06.002

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

36. Visual Navigation Path Extraction Algorithm in Orchard under Complex Background

Accession number: 20233014444892

Title of translation:

Authors: Xiao, Ke (1, 2); Xia, Weiguang (1); Liang, Congzhe (1)

Author affiliation: (1) College of Information Science and Technology, Hebei Agricultural University, Baoding; 071001, China; (2) Hebei Key Laboratory of Agricultural Big Data, Baoding; 071001, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 197-204 252

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: To solve the problem of autonomous travel and U-turn between rows for orchard visual navigation robots, a navigation line extraction method based on Mask R - CNN and a tree line extraction method based on random sample consensus (RANSAC) algorithm were proposed. Firstly, road and tree trunks were identified based on the Mask R - CNN model, and road segmentation mask and trunk bounding box coordinates were extracted. Secondly, after generating inter-row navigation lines, the improved RANSAC algorithm was used to extract the front row line of trees. Then, the distance from the coordinate point of the trunk bounding box to the front row line was calculated, and the coordinate points of the back row trunk was filtered to generate the back row line by least squares fitting. Finally, the U-turn direction can be determined by analyzing the front and back row tree lines information combined with the end of row distance and the proposed U-turn path planning method. The experimental results showed that the average segmentation accuracy and bounding box detection accuracy of the model were both 97.0% in the six orchards under different lighting, weed and weather environments. The average deviation of navigation target point extraction was within 5. 3%, and the accuracy rate of tree line detection was higher than 87% . The average deviation of the vehicle position from the center of the road after the U-turn was 7. 8 cm. It can be proved that the proposed method can navigate effectively for visual autonomous navigation in the orchard environment. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 21

Main heading: Orchards

Controlled terms: Agricultural robots? - ?Extraction? - ?Motion planning? - ?Navigation? - ?Roads and streets? - ?Trees (mathematics)? - ?Visual servoing

Uncontrolled terms: Consensus algorithms? - ?Improved random sample consensus algorithm? - ?Line extraction? - ?Navigation lines? - ?Orchard environment? - ?Random sample consensus? - ?Row line? - ?Tree line? - ?U-turn? - ?Visual Navigation

Classification code: 406.2 Roads and Streets? - ?731.5 Robotics? - ?802.3 Chemical Operations? - ?821.1 Agricultural Machinery and Equipment? - ?821.3 Agricultural Methods? - ?921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory

Numerical data indexing: Percentage 3.00E 00%, Percentage 8.70E 01%, Percentage 9.70E 01%, Size 8.00E-02m

DOI: 10.6041/j.issn.1000-1298.2023.06.020

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

37. Pest Identification Method in Apple Orchard Based on Improved Mask R-CNN

Accession number: 20233014437847

Title of translation: Mask R-CNN

Authors: Wang, Jinxing (1, 2); Ma, Bo (1); Wang, Zhen (1, 3); Liu, Shuangxi (1, 4); Mu, Junlin (1); Wang, Yunfei (1)

Author affiliation: (1) College of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian; 271018, China; (2) Shandong Agricultural Equipment Intelligent Engineering Laboratory, Taian; 271018, China; (3) College of Horticulture Science and Engineering, Shandong Agricultural University, Taian; 271018, China; (4) Shandong Provincial Key Laboratory of Horticultural Machinery and Equipment, Taian; 271018, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 253-263 360

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming at the problem that the basic convolutional neural network is vulnerable to background interference and the expression ability of important features is not strong in apple orchard pest recognition, an apple orchard pest recognition method based on improved Mask R - CNN was proposed. Firstly, based on Haar feature method, the apple orchard pest images collected from multiple points were iteratively preliminarily segmented, the single pest image sample was extracted, and multi-channel amplification on the sample was performed to obtain the amplified sample data for deep learning. Secondly, the feature extraction network in Mask R - CNN was optimized, and the ResNeXt network embedded in the attention mechanism module CBAM was used as the Backbone of the improved model, which increased the extraction of pest space and semantic information by the model, and effectively avoided the influence of background on performance of the model. At the same time, the Boundary loss function was introduced to avoid the problem of missing edge of pest mask and inaccurate positioning. Finally, the original Mask R - CNN model was used as the control model, and the mean average precision (mAP) was used as the evaluation index to conduct experiments. The results showed that the mean average precision of the improved Mask R - CNN model reached 96. 52% . Compared with the original Mask R - CNN model, the mean average precision was increased by 4. 21 percentage points. The results showed that the improved Mask R - CNN can accurately and effectively identify pests in apple orchards. The research result can provide technical support for green control of apple orchard pests and diseases. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 30

Main heading: Extraction

Controlled terms: Convolutional neural networks? - ?Deep learning? - ?Disease control? - ?Fruits? - ?Iterative methods? - ?Orchards? - ?Semantics

Uncontrolled terms: Apple orchards? - ?Attention mechanisms? - ?CNN models? - ?Convolutional neural network? - ?Deep learning? - ?Identification method? - ?Loss functions? - ?Mask R-CNN? - ?Pest identification? - ?Pests images

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?802.3 Chemical Operations? - ?821.3 Agricultural Methods? - ?821.4 Agricultural Products? - ?921.6 Numerical Methods

Numerical data indexing: Percentage 5.20E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.026

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

38. Measurement of Maize Stem Cross Section Parameters Based on Semantic Segmentation and Instance Segmentation

Accession number: 20233014438575

Title of translation:

Authors: Chen, Yan (1, 2); Li, Xiang (1); Cao, Mian (1); Hu, Xiaochun (3); Wang, Lingqiang (4)

Author affiliation: (1) College of Computer and Eleetronie Information, Guangxi University, Nanning; 530004, China; (2) Guangxi Key Laboratory of Multimedia Communications Network Technology, Nanning; 530004, China; (3) School of Bigdata and Artificial Intelligence, Guangxi University of Finance and Economics, Nanning; 530007, China; (4) College of Agriculture, Guangxi University, Nanning; 530004, China

Corresponding author: Hu, Xiaochun(huxch999@163.com)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 214-222

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Stem microstructure is closely related to its mechanical properties and affects lodging resistance in crops. But crop microphenotypic parameters are difficult to obtain manually. Therefore, automated measurement methods are urgently needed. The lack of measurement methods for high-throughput vascular bundle parameters seriously restricts the in-depth study. Based on the deep learning architecture, ResNet and Unet network were merged to construct the semantic segmentation model Res -Unet to segment function zones in maize stem cross section. In view of the small area, large number and dense distribution of vascular bundle in maize stem cross section, EfficientDet was used as the basic network architecture. According to the characteristics of small size of vascular bundles, the number of layers of BiFPN was reduced to improve reasoning speed and reduce the occupation of video memory. Mask segmentation branches were added to construct a new network Eiff - BiFPN to segment vascular bundles. The results showed that the DICE of each function zone could reach an average DICE of 88. 17%, and the vascular bundle segmentation task could reach 88. 78% and 72. 80% on AP50and AP50:70, respectively. Therefore, the proposed method was accurate, real-time and available, which can be used for automatic determination of microstructure parameters of maize stem, and a technical basis was established for the study of crop lodging resistance. According to the segmentation results, the crosssectional size of corn stem, the size of each functional area, the number and area of vascular bundles and other microstructure parameters can be obtained. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 24

Main heading: Microstructure

Controlled terms: Crops? - ?Deep learning? - ?Network architecture? - ?Semantic Segmentation? - ?Semantics

Uncontrolled terms: Automated measurement? - ?Instance segmentation? - ?Lodging resistance? - ?Maize stem? - ?Measurement methods? - ?Measurements of? - ?Microstructure parameters? - ?Section parameter? - ?Semantic segmentation? - ?Vascular bundle

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?723.4 Artificial Intelligence? - ?821.4 Agricultural Products? - ?951 Materials Science

Numerical data indexing: Percentage 1.70E 01%, Percentage 7.80E 01%, Percentage 8.00E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.022

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

39. Design and Experiment of Farmland Information Collection Robot

Accession number: 20233014438096

Title of translation:

Authors: Wang, Xiaoehan (1, 2); Li, Zesheng (1); Chen, Yanyu (1); Huang, Xuekai (1); Zhang, Xiaolei (1, 2)

Author affiliation: (1) College of Engineering, Nanjing Agricultural University, Nanjing; 210031, China; (2) Jiangsu Province Engineering Laboratory for Modern Facility Agriculture Technology and Equipment, Nanjing; 210031, China

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 65-77

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Under the background of rapid development of intelligent agriculture with information, knowledge and equipment as the core, intelligent robots have gradually replaced the traditional methods of farmland information collection and received more and more attention. In order to adapt to the complex agronomic conditions such as paddy field walking and different ridge widths, an upland gap four-wheel drive farmland information acquisition robot with adjustable wheel spacing was designed. By using SolidWorks, the overall structure was designed and analyzed and parts were selected. The trial-production of the robot was completed. A combined navigation and path tracking control system based on GNSS and INS was designed. The results showed that the four-wheel drive mode of the robot had good speed consistency and strong anti-interference ability. The error rates of the ground gap and wheel pitch adjusting mechanism were 1. 33% and 0. 73% . A comprehensive path tracking algorithm based on double tangent circle line was proposed. Compared with the pure tracking algorithm, the amplitude of oscillation was reduced by 75.0% and the convergence time was reduced by 28.5%. The average lateral error of the robot linear path tracking was 6. 8 cm, and the average convergence time of right-angle turns was 25. 6 s. The maximum speed of the robot was 1 m/s, and the average time of single point information acquisition was 24.5 s. All kinds of data collected by the sensor met the application requirements. The information acquisition robot can complete the work of farmland information acquisition quickly, efficiently and accurately under the complex conditions of paddy field. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 26

Main heading: Wheels

Controlled terms: Agricultural robots? - ?Digital storage? - ?Farms? - ?Intelligent robots? - ?Navigation? - ?Tracking (position)

Uncontrolled terms: Condition? - ?Convergence time? - ?Farmland information? - ?Four-wheel drives? - ?Information acquisitions? - ?Information collections? - ?Integrated navigation? - ?Paddy fields? - ?Path tracking? - ?Tracking algorithm

Classification code: 601.2 Machine Components? - ?722.1 Data Storage, Equipment and Techniques? - ?731.5 Robotics? - ?731.6 Robot Applications? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.1 Agricultural Machinery and Equipment

Numerical data indexing: Percentage 2.85E 01%, Percentage 3.30E 01%, Percentage 7.30E 01%, Percentage 7.50E 01%, Size 8.00E-02m, Time 2.45E 01s, Time 6.00E 00s, Velocity 1.00E00m/s

DOI: 10.6041/j.issn.1000-1298.2023.06.007

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

40. Real-time Production Prediction of Kiwifruit in Orchard Based on Video Tracking Algorithm

Accession number: 20233014439472

Title of translation:

Authors: Guo, Mingyue (1); Liu, Yachen (1); Li, Weifu (1); Chen, Hong (1); Li, Shanjun (2); Chen, Yaohui (2)

Author affiliation: (1) College of Informatics, Huazhong Agricultural University, Wuhan; 430070, China; (2) College of Engineering, Huazhong Agricultural University, Wuhan; 430070, China

Corresponding author: Chen, Yaohui(yaohui.chen@mail.hzau.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 178-185

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The use of machine vision to quickly and accurately estimate fruit yield is of great significance for the development of smart agriculture. In view of the characteristics of dwarf dense planting and wide distribution of kiwifruit cultivated in greenhouses, orchard crawler trolleys were used to shoot and obtain videos of kiwifruit orchards, and a dataset of kiwifruit detection and tracking was established combined with artificial labeling. Considering the small proportion and dense distribution of kiwifruit in the self-made dataset, the YOLO v7 model and Soft - NMS were proposed to detect kiwifruit in each frame. Based on the prediction results of the Kalman filter, the VGG16 network was introduced to extract the features of kiwifruit, and the Hungarian algorithm was used to complete the target matching of the before and after frames. Finally, the ID counting method based on YOLO v7 DeepSort tracking algorithm was used to realize kiwifruit yield estimation. The experimental results showed that the improved YOLO v7 model performed well on the kiwifruit detection dataset, with an Fl score of 90. 09% . The average accuracy of the adopted tracking algorithm on the kiwifruit tracking dataset was 89. 87%, the precision of each target can be correctly matched was 82. 34% and a large video tracking speed of 20. 19 f/s. Under the condition of low environmental impact, the ID counting accuracy was 97. 49% . This method can provide technical support for yield estimation and harvest planning in the intelligent management of kiwifruit orchards. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Large dataset

Controlled terms: Environmental impact? - ?Orchards? - ?Video recording

Uncontrolled terms: Deepsort? - ?Kiwifruits? - ?Machine-vision? - ?Production prediction? - ?Real-time production? - ?Soft-NMS? - ?Tracking algorithm? - ?Video-tracking? - ?Yield estimation? - ?YOLO v7

Classification code: 454.2 Environmental Impact and Protection? - ?716.4 Television Systems and Equipment? - ?723.2 Data Processing and Image Processing? - ?821.3 Agricultural Methods

Numerical data indexing: Percentage 3.40E 01%, Percentage 4.90E 01%, Percentage 8.70E 01%, Percentage 9.00E 00%

DOI: 10.6041/j.issn.1000-1298.2023.06.018

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

41. Kinetic Analysis of Hemicellulose Hydrolysis in Corn Stover Based on PAM Pretreatment

Accession number: 20233014437875

Title of translation: PAM

Authors: Lu, Qian (1); Tan, Yufeng (1); Zhang, Hui (1); Lin, Hao (1); Xiao, Weihua (1)

Author affiliation: (1) College of Engineering, China Agricultural University, Beijing; 100083, China

Corresponding author: Xiao, Weihua(xiaoweihua@cau.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 394-400

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Previous work has shown that peracetic acid and maleic acid (PAM) pretreatment can achieve cellulose enrichment from corn stover by dissolving lignin and hemicellulose, while the degradation products of hemicellulose in the pretreatment liquor of PAM pretreatment were mainly dominated by xylose. However, the degradation of hemicellulose in corn stover during PAM pretreatment was still uncertain. The kinetic features of hemicellulose hydrolysis associated with PAM pretreatment of corn stover was investigated. Time profiles of xylan hydrolysis in the range of 90 ~ 120¡ãC were analyzed by using biphasic model with PA pretreatment as a control. The results indicated that xylan was composed of two different fragments ( one for the fast hydrolysis portion and one for a slowly hydrolyzed portion of xylan). Slow-to-hydrolyze fraction of hemicellulose was decreased with the increase of temperature. Compared with PA pretreatment, PAM pretreatment could not only significantly reduce the activation energy of fast-to-hydrolyze xylan and slow-to-hydrolyze xylan to 71.4 kj/mol and 79.1 kj/mol, but also enhance the hydrolysis reaction rate of xylan. The validity of the proposed kinetic model was verified by the experimental data. The obtained information revealed the kinetic mechanism of PAM pretreatment to promote the hydrolysis of hemicellulose, which provided a theoretical basis for efficient hydrolysis and product utilization of the hemicellulose in lignocellulosic biomass. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 35

Main heading: Hydrolysis

Controlled terms: Activation energy? - ?Cellulose? - ?Degradation? - ?Kinetics

Uncontrolled terms: Acid pretreatment? - ?Corn stover? - ?Hemicellulose? - ?Hemicellulose hydrolysis? - ?Hydrolysis kinetics? - ?Kinetic analysis? - ?Maleic acids? - ?Peracetic acid and maleic acid? - ?Peracetic acids? - ?Pre-treatments

Classification code: 631.1 Fluid Flow, General? - ?802.2 Chemical Reactions? - ?811.3 Cellulose, Lignin and Derivatives? - ?815.1.1 Organic Polymers? - ?931 Classical Physics; Quantum Theory; Relativity

Numerical data indexing: Energy 7.14E 04J, Energy 7.91E 04J, Temperature 3.63E 02K to 3.93E 02K

DOI: 10.6041/j.issn.1000-1298.2023.06.040

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

42. Transformer Optimization and Application in Named Entity Recognition of Apple Diseases and Pests

Accession number: 20233014438579

Title of translation: Transformer

Authors: Pu, Pan (1); Zhang, Yue (1); Liu, Yong (1); Nie, Yanming (1); Huang, L¨¹iwen (1, 2)

Author affiliation: (1) College of Information Engineering, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Shaanxi, Yangling; 712100, China

Corresponding author: Huang, L¨¹iwen(huanglvwen@nwsuaf.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 266-271

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming to improve the accuracy of entity identification in apple production field, a new Transformer optimization model was proposed. Firstly, in order to address the lack of apple production dataset, a corpus focusing on diseases and pests was constructed based on the knowledge and experience of horticultural experts in related field of apple cultivation. The accuracy of semantic representation of text was improved by combining word vector and character vector. Secondly, since the location information was crucial to text semantics, but the traditional Transformer model lacks the directionality of location information, in order to take advantage of the location features of text, an attention mechanism with direction and distance perception was introduced in Transformer encoder. And the contextual longdistance dependence features of BiLSTM was integrated on average to enhance semantic representation. Lastly, with imposing restrictions on labeling results by conditional random fields ( CRF ), the Transformer optimization model was obtained. The experimental results showed that the Fl score of the proposed method was 92. 66% in Chinese named entity recognition of Apple diseases and pests. It indicated that the method proposed could effectively identify the named entities of apple diseases and pest, and provide a technical means for the accurate and intelligent identification of other agricultural named entities. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 24

Main heading: Semantics

Controlled terms: Cultivation? - ?Fruits? - ?Location? - ?Natural language processing systems? - ?Optimization? - ?Random processes

Uncontrolled terms: Apple disease? - ?Apple knowledge map? - ?Apple production? - ?Disease and pest? - ?Knowledge map? - ?Language processing? - ?Named entity recognition? - ?Natural language processing? - ?Natural languages? - ?Transformer

Classification code: 723.2 Data Processing and Image Processing? - ?821.3 Agricultural Methods? - ?821.4 Agricultural Products? - ?921.5 Optimization Techniques? - ?922.1 Probability Theory

Numerical data indexing: Percentage 6.60E 01%

DOI: 10.6041/j.issn.1000-1298.2023.06.027

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.

43. Parallel Computing Method of FEM-DEM with Multiple-time Step Based on Overlapping Boundary

Accession number: 20233014444909

Title of translation:

Authors: Li, Tong (1, 2); Jin, Xianlong (1, 2); Wang, Xiaowei (3); Pan, Junming (3); Yang, Peizhong (1, 2)

Author affiliation: (1) School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai; 200240, China; (2) State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai; 200240, China; (3) Shanghai Spaceflight Precision Machinery Institute, Shanghai; 201600, China

Corresponding author: Yang, Peizhong(pzyang@sjtu.edu.cn)

Source title: Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery

Abbreviated source title: Nongye Jixie Xuebao

Volume: 54

Issue: 6

Issue date: 2023

Publication year: 2023

Pages: 419-426

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The development of computer hardware technology has made numerical calculations of large-scale complex mechanical problems more efficient. To reduce the computational time in the fields of coupled finite-element and discrete-element (FEM - DEM) , an efficient asynchronous step integration parallel computational algorithm based on overlapping boundary was proposed. The whole model was divided into an FEM subdomain and a DEM subdomain, where the integral step size was depended on the element characteristics of the subdomain. An explicit time integral scheme was adopted in both subdomains. The method of overlapping boundary was adopted to handle the interface coupling problem, introducing the continuity transfer of overlapping boundary data into parallel computing, utilizing dynamic overlapping boundary methods and interprocess communication to transfer boundary information between adjacent subdomains, without the interpolation process in the subcycling process. The use of overlapping bonndaries can effectively reduce computational erros, and compared to the transition errors and the transition layer algorithm, the overlapping boundary area was small and easy to operate. Numerical examples showed that the algorithm proposed can improve the computational efficiency with a high computational accuracy. The research result can provide ideas for the calculation of large-scale coupled finite element discrete element problems. ? 2023 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 43

Main heading: Finite element method

Controlled terms: Computational efficiency? - ?Computer hardware

Uncontrolled terms: Asynchronoi step? - ?Computing methods? - ?Discrete elements? - ?Hybrid FEM? - ?Hybrid FEM -DEM? - ?Large-scales? - ?Multiple time step? - ?Overlapping boundary? - ?Parallel com- puting? - ?Subdomain

Classification code: 722 Computer Systems and Equipment? - ?921.6 Numerical Methods

DOI: 10.6041/j.issn.1000-1298.2023.06.043

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

Compilation and indexing terms, Copyright 2023 Elsevier Inc.