2024年第1期

2024年第1期

2024年第1期共收录43篇

1. Hierarchical Multi-label Classification of Agricultural Pest and Disease Interrogative Questions

Accession number: 20240915634821

Title of translation: 基于层级多标签的农业病虫害问句分类方法

Authors: Wei, Tingting (1); Ge, Xiaoyue (1); Xiong, Juntao (1)

Author affiliation: (1) College of Matheinatical Sciences and Information, South China Agricultural University, Guangzhou; 510642, China

Corresponding author: Xiong, Juntao(xiongjt2340@163.com)

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 263-269

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: With the rapid advancement of infonnation technology, it has become a trend for fanners to address offline agricultural issues through online intelligent question-and-answer systems. Question classification plays a crucial role in question-and-answer systems, as its accuracy directly determines the correctness of the final answers. Traditional single-label text classification models often struggle to accurately capture the precise intent of agricultural queries. Moreover, the lack of large-scale publicly available query datasets about agricultural pest and disease poses a significant challenge to existing research methods. To address these challenges, a hierarchical classification framework for queries about agricultural pest and disease was established based on a tree-like structure. This framework progressively refined the classification from the ambiguity of queries towards precision, aiming to overcome the semantic complexity of agricultural queries. Additionally, adversarial training method was introduced. By constructing adversarial samples and incorporating them into the training of large-scale language models, the model’s generalization capabilities were enhanced, while mitigating issues arising from limited training data. Experimental validation conducted on real question-and-answer corpora demonstrated that the proposed method significantly enhanced the classification performance of queries about agricultural pest and disease. The research result can provide an effective means of identifying the intent behind agricultural queues, thereby offering support for advancing agricultural informatization. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 19

Main heading: Semantics

Controlled terms: Agriculture? - ?Classification (of information)? - ?Computational linguistics? - ?Informatization? - ?Large datasets? - ?Online systems? - ?Query processing? - ?Text processing

Uncontrolled terms: Adversarial training? - ?Agricultural pest and disease? - ?Agricultural pests? - ?Hierarchical multi-label classifications? - ?Language model? - ?Large-scales? - ?Offline? - ?Query classification? - ?Question and answer system? - ?Question classification

Classification code: 716.1 Information Theory and Signal Processing? - ?721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory? - ?722.4 Digital Computers and Systems? - ?723.2 Data Processing and Image Processing? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?903.1 Information Sources and Analysis? - ?903.3 Information Retrieval and Use

DOI: 10.6041/j.issn.1000-1298.2024.01.025

Funding Details: Number: 20YJC740067,72101091, Acronym: NSFC, Sponsor: National Natural Science Foundation of China;

Funding text: 广州市基础与应用基础研究项目(202201010184), 国家自然科学基金项目(72101091)和教育部人文社会科学研究一般项目 (20YJC740067)

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

2. Lightweight Identification of Rice Diseases Based on Improved ECA and MobileNetV3Small

Accession number: 20240915637096

Title of translation: 基于MobileNetV3SmaU - ECA的水稻病害轻量级识别研究

Authors: Yuan, Peisen (1); Ouyang, Liujiang (1); Zhai, Zhaoyu (1); Tian, Yongchao (1, 2)

Author affiliation: (1) College of Artificial Intelligence, Nanjing Agricultural University, Nanjing; 210095, China; (2) College of Agriculture, Nanjing Agricultural University, Nanjing; 210095, China

Corresponding author: Tian, Yongchao(yctian@njau.edu.cn)

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 253-262

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: In order to realize the lightweight identification and detection of rice diseases, the ECA attention mechanism was used to improve the MobileNetV3Small model, and shared parameter transfer learning was used to carry out intelligent lightweight identification and detection of rice diseases. Pre-training was perfolined on the PlantVillage dataset, and the shared parameters obtained from the pretraining were transferred to the rice disease recognition model for fine-tuning and optimization. Experiments were on the open-source rice disease dataset. The experimental results showed that the recognition accuracy rate reached 97. 47% under non-transfer learning, and 99.92% under transfer learning, while reducing the number of parameters by 26. 69%. Secondly, the Grad — CAM was used for visualization. Compared with other attention mechanisms CB AM and SENET, the results generated by the ECA module were more consistent with the position and color of the disease spots in the image, indicating that the network can better focus on rice diseases. Characteristics, and the causes of misclassification were analyzed through visualization and each rice disease. The proposed method realized the lightweight of the rice disease recognition model, so that it can be deployed in resource-constrained scenarios such as mobile devices, and achieved the purpose of fast, efficient and portable. At the same time, an Android-based rice disease identification system was developed, which can facilitate the identification and analysis of rice diseases at the edge. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 32

Main heading: Visualization

Controlled terms: Transfer learning

Uncontrolled terms: Attention mechanisms? - ?ECA attention mechanism? - ?Fine tuning? - ?Mobile deployment? - ?Mohilenetv3small? - ?Parameter transfers? - ?Pre-training? - ?Recognition models? - ?Rice disease identification? - ?Transfer learning

Classification code: 723.4 Artificial Intelligence

Numerical data indexing: Percentage 4.70E+01%, Percentage 6.90E+01%, Percentage 9.992E+01%

DOI: 10.6041/j.issn.1000-1298.2024.01.024

Funding text: 国家自然科学基金项目 (61502236)和江苏省农业科技冃主创新资金项目 (CX(21)3059)

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

3. Analysis of Formation of Benzenoids Volatile Compounds of Japanese Apricot Fruit

Accession number: 20240915642670

Title of translation: 青梅果实芳香族特征香气的形成分析

Authors: Hao, Yadong (1); Liu, Minxin (2); Li, Jingming (3, 4)

Author affiliation: (1) Beijing Haidian District Food and Drug Safety Monitoring Center, Beijing; 100094, China; (2) Luzhou Laojiao Co., Ltd., Luzhou; 646699, China; (3) College of Food Science and Nutritional Engineering, China Agricultural University, Beijing; 100083, China; (4) CAU - SCCSD Advanced Agricultural and Industrial Institute, Chengdu; 611430, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 379-385

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Benzenoids volatile compounds significantly contribute to the distinctive aroma of both Japanese apricot fruit and its processed products. However, the accumulation pattern and formation mechanism of such characteristic aroma have not been sufficiently studied. In order to investigate the formation and accumulation of the characteristic aroma substances in Japanese apricot fruit and their origin mechanisms, Japanese apricot fruit at different ripening stages were analyzed by headspace - solid - phase microextraction - gas chromatography - mass spectrometry (HS - SPME - GC - MS), and correlation analysis was performed by combining specific amino acids and other precursors. The results showed that the aroma characteristics varied significantly during the ripening process, and the metabolism of aroma substances was the most active and the amino acid content was the lowest in the middle stage of ripening (80 ~ 100 d after flowering). The changes in the accumulation of characteristic aroma substances in Japanese apricot fruit indicated that the aromatic aroma substances originated from the phenylalanine metabolic pathway, and there was a competitive relationship between the benzaldehyde and phenylacetaldehyde synthesis pathways. Benzaldehyde was formed through the non-(3 oxidation pathway. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 31

Main heading: Amino acids

Controlled terms: Fruits? - ?Gas chromatography? - ?Mass spectrometry? - ?Metabolism? - ?Odors? - ?Volatile organic compounds

Uncontrolled terms: Amino-acids? - ?Apricot fruits? - ?Aroma precursor? - ?Aroma substances? - ?Benzenoid volatile compound? - ?Characteristic aroma? - ?Japanese apricot fruit? - ?Japanese apricots? - ?Processed products? - ?Volatile compounds

Classification code: 801 Chemistry? - ?802.3 Chemical Operations? - ?804.1 Organic Compounds? - ?821.4 Agricultural Products

DOI: 10.6041/j.issn.1000-1298.2024.01.036

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

4. Single Wood Extraction Method Combining LiDAR Data and Spectral Images

Accession number: 20240915637095

Title of translation: 基于LiDAR数据与光谱影像融合的单木提取方法

Authors: Meng, Xiaoqian (1); Li, Junlei (1); Hu, Wei (1); Tian, Maojie (1); Ma, Chuntian (1); Wang, Ruirui (2)

Author affiliation: (1) State Grid Power Space Technology Co., Ltd., Beijing; 102209, China; (2) College of Forestry, Beijing Forestry University, Beijing; 100083, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 203-211 and 262

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Existing airborne data single-tree segmentation methods exhibit low universality for different forest types, particularly in areas with high canopy closure where the extraction accuracy is notably compromised. Spectral images and LiDAR data from the tropical broad-leaved forest region within the jurisdiction of Haikou City, Hainan Province, China, were employed. Initially, a distance thresholdbased single-tree segmentation method was employed to extract tree crown edges from the high-resolution spectral image. Subsequently, the obtained positions of initial detected tree vertices were constrained using the segmented tree crown edges, and precise positioning of single-tree vertices was achieved. Following this, a seed-point-based single-tree segmentation method was applied for final tree extraction in the broad-leaved forest. The results indicated that compared with existing single-tree segmentation methods based on the relative distances between trees, by selecting the optimal segmentation scale in combination with spectral imagery for precise positioning, the issue of over-segmentation caused by traditional single-scale segmentation methods was ameliorated. The accuracy of single-tree identification was improved from 0.67 to 0.92. This method proved to be more effective in the segmentation of forest trees using remote sensing, demonstrating high applicability across various forest types. It established a solid data foundation for subsequent single-tree information extraction and held promising prospects for practical applications. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 27

Main heading: Remote sensing

Controlled terms: Data fusion? - ?Data mining? - ?Forestry? - ?Image segmentation? - ?Optical radar

Uncontrolled terms: Airborne LiDAR? - ?Broad-leaved forests? - ?Coniferous and broad-leaved mixed forest? - ?Forest type? - ?Mixed forests? - ?Segmentation methods? - ?Single tree segmentation? - ?Spectral images? - ?Tree crowns? - ?Tree segmentation

Classification code: 716.2 Radar Systems and Equipment? - ?723.2 Data Processing and Image Processing? - ?741.3 Optical Devices and Systems? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control

DOI: 10.6041/j.issn.1000-1298.2024.01.019

Funding text: 国家电网有限公司科技项目 (5500-202220144A-1-1-ZN)

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

5. Completeness Measurement and Identification of Geometric Error of Rotary Axis of Boring Machine

Accession number: 20240915642701

Title of translation: 精密镗床旋转轴几何误差完备性测量与辨识

Authors: Guo, Shijie (1, 2); Ding, Qiangqiang (1, 2); Zou, Yunhe (1, 2); Sa, Rina (1, 2); Tang, Shufeng (1, 2)

Author affiliation: (1) College of Mechanical Engineering, Inner Mongolia University oj Technology, Huhhot; 010051, China; (2) Key Laboratory of Special Service Robot of Inner Mongolia Autonomous Region, Huhhot; 010051, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 446-458

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: To address the problem that the number of geometric errors were inconsistent and incompleteness which needed to be measured for the rotary axis of four axis horizontal boring machine, an analyzing methodology of PIGEs formation mechanism based on the shape generation function and a method of the completeness measuring, identifying geometric errors of the rotary axis were proposed for a four axis horizontal boring machine. Firstly, the generation function of PIGEs of horizontal boring machines was constructed based on the shape generation mechanism, and the minimum number of position-independent geometric error (PIGEs) that the rotary axis can be adjusted through error compensation was determined. Secondly, the completeness function model was established consisted of four terms PIGEs, six terms position-dependent geometric error (PDGEs), six terms setup error (SEs) and DBB measurement track radius length of the rotary axis of horizontal boring machine, the Viviani curve measurement track based on DBB was designed based four-axis synchronized motion, and the NURBS characterization of six item PDGEs, identification methods of PIGEs, and SEs of the rotary axis were constructed. Finally, the comparative experiment by error compensating was carried out. The results showed that the error compensation using the geometric error completeness measurement and identification results included four terms PIGEs, six terms PDGEs, and six terms SEs can improve the measurement accuracy of circular trajectory by 40. 69% compared with that of compensate six PDGEs simply. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 31

Main heading: Error compensation

Controlled terms: Geometry

Uncontrolled terms: Completeness measurement? - ?Formation mechanism? - ?Four-axis? - ?Geometric errors? - ?Horizontal boring machine? - ?Identification? - ?Position dependents? - ?Rotary axis? - ?Setup errors? - ?Shape generations

Classification code: 921 Mathematics

Numerical data indexing: Percentage 6.90E+01%

DOI: 10.6041/j.issn.1000-1298.2024.01.043

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

6. Path Tracking and Turning Control Algorithm of Tracked Vehicle Based on ICR

Accession number: 20240915642659

Title of translation: 基于ICR的履带车辆路径跟踪与转向控制算法研究

Authors: Wang, Faan (1, 2); Yang, Quanhe (1, 2); Zhang, Zhaoguo (1, 2); Li, Annan (1, 2); Xu, Hongwei (1, 2)

Author affiliation: (1) Faculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming; 650500, China; (2) Research Center on Mechanization Engineering, Chinese Medicinal Materials in Yunnan University, Kunming; 650500, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 386-395 and 425

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming at the problems of low path tracking accuracy, many control times and large turning deviation of unilateral braking agricultural tracked vehicles in hilly and mountainous areas, the path tracking control of tracked vehicles under different load conditions was studied. Firstly, the turning kinematics of the tracked vehicle was theoretically analyzed, and the kinematics model of the tracked vehicle was established. Secondly, according to the unilateral braking turning characteristics of the tracked vehicles, an instantaneous center of rotation was proposed for instantaneous control, which can plan the optimal turning target point, according to the turning point position of the planned path and the turning instantaneous center of the tracked vehicle, and controlling the tracked vehicle to turn to the required course at the turning target point at one time. Meanwhile, the design of the turning controller was completed. Finally, the simulation and field experiments of the tracked vehicle under three different load conditions were carried out. The simulation results showed that the average error area of the tracking path and the average turning control times generated by the large angle turning control algorithm were reduced by 68. 95% and 68. 77%, respectively. The mean value of the mean lateral deviation of the tracking path, the mean turning control times and the mean minimum deviation of the turning point generated by the large angle turning control algorithm were reduced by 57. 27%, 33. 93% and 62. 29%, respectively. And the path tracking effect was better, which verified the effectiveness of the large angle turning control algorithm. The test results met the requirements of tracked vehicle path tracking and provided a theoretical basis and reference for the path tracking of agricultural tracked vehicles. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 33

Main heading: Tracked vehicles

Controlled terms: Agriculture? - ?Braking? - ?Kinematics

Uncontrolled terms: Agricultural tracked vehicle? - ?Control time? - ?Instantaneous turning center? - ?Load condition? - ?Path tracking? - ?Path tracking control? - ?Target point? - ?Turning center? - ?Turning control? - ?Turning-points

Classification code: 602 Mechanical Drives and Transmissions? - ?663 Buses, Tractors and Trucks? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?931.1 Mechanics

Numerical data indexing: Percentage 2.70E+01%, Percentage 2.90E+01%, Percentage 7.70E+01%, Percentage 9.30E+01%, Percentage 9.50E+01%

DOI: 10.6041/j.issn.1000-1298.2024.01.037

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

7. Potato Sprouting and Surface Damage Detection Method Based on Improved Faster R - CNN

Accession number: 20240915642681

Title of translation: 基于改进Faster R-CNN的马铃薯发芽与表面损伤检测方法

Authors: Liu, Yijun (1, 2); He, Yakai (3, 4); Wu, Xiaomei (1, 2); Wang, Wenjie (3, 4); Zhang, Li’na (1, 2); Lu, Huangzhen (1, 2)

Author affiliation: (1) Chinese Academy of Agricultural Mechanization Sciences Group Co.,Ltd., Beijing; 100083, China; (2) National Key Laboratory of Agricultural Equipment Technology, Beijing; 100083, China; (3) China National Packaging and Food Machinery Corporation, Beijing; 100083, China; (4) Key Laboratory of Agricultural Product Processing Equipment, 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: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 371-378

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Germination and surface damage detection are crucial steps in the commercialization of fresh table potatoes. To address the low accuracy rate of high-pixel image object recognition in the high-throughput grading and sorting process of fresh table potatoes, a method for detecting potato sprouting and surface damage based on improved Faster R - CNN was proposed. Using Faster R - CNN as the baseline network, the feature extraction network in Faster R - CNN was replaced with the residual network (ResNet50), and a feature pyramid network (FPN) integrated with ResNet50 was designed to increase the depth of the neural network. A comparative model assessment and ablation studies were performed to empirically validate the efficacy of the proposed model and its modifications. The findings delineated that the enhanced algorithm demonstrated an average precision rate of 98.89% in identifying potatoes, 97. 52% in discerning sprouting events, and 92. 94% in recognizing surface defects. When benchmarked against the Faster R - CNN model, the adapted model incurred no additional computational time or memory overhead while manifesting a marginal decline of 0. 04 percentage points in potato identification accuracy. Notably, it significantly elevated the average precision in detecting sprouting and surface imperfections by 7.79 percentage points and 34.54 percentage points, respectively. This augmented model was robust in high-resolution imaging environments facilitated by industrial-grade cameras and served as a cornerstone for the methodological advancement of automated grading and sorting processes in the commercial potato industry. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Damage detection

Controlled terms: Grading? - ?Image enhancement? - ?Object recognition? - ?Surface defects

Uncontrolled terms: Commercialisation? - ?Detection methods? - ?Fast R - CNN? - ?Grading process? - ?High resolution? - ?Percentage points? - ?Potato? - ?Sorting process? - ?Sprouting? - ?Surface damages

Classification code: 951 Materials Science

Numerical data indexing: Percentage 5.20E+01%, Percentage 9.40E+01%, Percentage 9.889E+01%

DOI: 10.6041/j.issn.1000-1298.2024.01.035

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

8. Canopy Transpiration Water Consumption Simulation of Orange Forest in Dry and Hot Valley Area Based on Bayesian Analysis

Accession number: 20240915637116

Title of translation: 基于贝叶斯分析的干热河谷区橙子林冠层蒸腾耗水模拟

Authors: Zhang, Jingying (1); Chen, Dianyu (1); Ma, Yongsheng (2); Hu, Xiaotao (1); Du, Jingbin (2); Wang, Shujian (1)

Author affiliation: (1) Key Laboratory of Agricultural Soil, Water Engineering in Arid and Semiarid Areas, Ministry of Education, Northwest A&F University, Shaanxi, Yangling; 712100, China; (2) Yan’an Fruit Industry Research and Development Center, Luochuan, 727400, China

Corresponding author: Chen, Dianyu(875948920@qq.com)

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 305-315

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The mechanism of water consumption is the basis for management and regulation of water in farmland/orchards. Focusing on the transpiration mechanism of water consumption, the simulation effect of different Jarvis - Stewart model configurations on transpiration consumption in orange forests in dry and hot valleys was compared based on Bayesian parameter estimation methods, and the applicability of Jarvis - Stewart model in the simulation of transpiration water consumption under the condition of strong interaction effect of influence factors was explored. The results showed that considering different influencing factors and their limiting functions would have a great impact on the simulation effect, among which considering soil moisture content and leaf area index had obvious effects on the improvement of the simulation effect, while the introduction of saturated water vapor pressure difference and air temperature would reduce the simulation accuracy to varying degrees. The more impact factors considered, the more complex the model structure was, and the better the simulation effect was. The best model structure screened out basically realized the reliable simulation of water consumption of transpiration in orange forest, but there was still obvious room for improvement in the simulation effect, so the model complexity, simulation accuracy and uncertainty should be comprehensively considered to further explore the appropriate model structure. The research can provide scientific basis for the establishment of water?saving irrigation technology system and water management optimization in orchards, and also provide data support for the further development and improvement of water consumption models. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 42

Main heading: Transpiration

Controlled terms: Citrus fruits? - ?Forestry? - ?Information management? - ?Parameter estimation? - ?Soil moisture? - ?Water management

Uncontrolled terms: ‘Dry’ [? - ?Bayesian parameter estimation? - ?Dry and hot valley area? - ?Jarvis — stewart model? - ?Orange forest? - ?Simulation accuracy? - ?Simulation effects? - ?Transpiration water consumption simulation? - ?Valley areas? - ?Water consumption

Classification code: 461.9 Biology? - ?483.1 Soils and Soil Mechanics? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.4 Agricultural Products

DOI: 10.6041/j.issn.1000-1298.2024.01.029

Funding text: 国家自然科学基金青年基金项目 (51909232) 和中国博士后基金面上项目 (2019M663588)

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

9. Review on Path Tracking Control of Unmanned Articulated Steering Vehicles

Accession number: 20240915630256

Title of translation: 无人驾驶絞接转向车辆路径跟踪控制研究综述

Authors: Zhu, Qingyuan (1); Cheng, Jiaqi (1); Chen, Xuanwei (1); Yang, Changlin (1); Gao, Yunlong (1); Shao, Guifang (1)

Author affiliation: (1) Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen; 361005, China

Corresponding author: Shao, Guifang(gfshao@xmu.edu.cn)

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 1-21

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: The path tracking of unmanned articulated steering vehicles is the key to accurately and smoothly carrying out operational tasks, which can effectively improve the operational efficiency and safety of articulated steering vehicles in industries such as agriculture, forestry, mining, and construction. The research on path tracking control typically included three aspects : vehicle model construction, control algorithm design, and algorithm validation and evaluation, from which the research progress of path tracking control technology for articulated steering vehicles was systematically analyzed. Firstly, the geometric, kinematic, and dynamic models of articulated steering vehicles were reviewed, and then the applicable scenarios and limitations of these models in path tracking control research were discussed. Above that, the research status of path tracking algorithms for articulated steering vehicles was elaborated, and the advantages and disadvantages of each algorithm as well as its scope of application were summarized in comparison, with further generalization about the methods of validation and evaluation of the algorithms. The research focuses and directions of articulated steering vehicle path tracking technology were proposed as follows : the research of vehicle modeling considering vehicle dynamics factors and dynamic time-varying characteristics of model parameters, the design of multi?condition adaptive control algorithms incorporating the adaptation of different algorithms and combining the intelligent algorithms, the development of standardized and process-oriented high-fidelity simulation scenarios, and the research of evaluation methods for integrating multiple performances included accuracy, stability, and security. This review can serve as a valuable reference for further research on the path tracking strategies of articulated steering vehicles. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 146

Main heading: Dynamic models

Controlled terms: Accident prevention? - ?Automobile steering equipment? - ?Forestry? - ?Petroleum reservoir evaluation? - ?Steering

Uncontrolled terms: Articulated steering? - ?Articulated steering vehicle? - ?Control strategies? - ?Dynamics models? - ?Operational tasks? - ?Path tracking? - ?Path tracking control? - ?Unmanned drivings? - ?Vehicle modelling? - ?Verification evaluation

Classification code: 512.1.2 Petroleum Deposits : Development Operations? - ?662.4 Automobile and Smaller Vehicle Components? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?914.1 Accidents and Accident Prevention? - ?921 Mathematics

DOI: 10.6041/j.issn.1000-1298.2024.01.001

Funding text: 国家自然科学基金面上项目（52075461）

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

10. Synergistic Estimation of Soil Salinity Based on Sentinel-1/2 Improved Polarization Combination Index and Texture Features

Accession number: 20240915640265

Title of translation: 基于 Sentinel – 1/2 改进极化指数和纹理特征的土壤含盐量反演模型

Authors: Zhang, Zhitao (1, 2); He, Yujie (1, 2); Yin, Haoyuan (1, 2); Xiang, Ru (1, 2); Chen, Junying (1, 2); Du, Ruiqi (1, 2)

Author affiliation: (1) College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling, Shaanxi, 712100, China; (2) Key Laboratory of Agricultural Soil and Water Engineering in Arid and Semiarid Areas, Ministry of Education, NorthwestA&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: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 175-185

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Most of the current studies on Sentinel – 1/2 synoptic inversion of vegetation soil salinity were based on Sentinel–2 spectral information and Sentinel – 1 backscattering coefficients, without considering the two aspects that Sentinel – 2 spectral information was susceptible to soil brightness and Sentinel – 1 backscattering coefficients were susceptible to soil roughness and moisture. Therefore, in order to further improve the accuracy of Sentinel – 1/2 synoptic inversion of vegetation soil salinity, the Sentinel - 1 backscatter coefficients were corrected with a water cloud model to eliminate the influence of vegetation. Then, the corrected backscatter coefficients and Sentinel – 2 texture features screened by VIP, 00B and PCA were used to construct soil salinity inversion models based on RF, ELM and Cubist. The results showed that the correlation between the radar backscatter coefficient and the soil salinity was improved to some extent after the removal of vegetation effects by the water cloud model. For the coupled models of different variable selection methods and different machine learning methods, 00B had the best performance in soil salinity inversion when being coupled with RF, ELM and Cubist, with R2 above 0. 750 for both modeling and validation sets. And 00B - Cubist model had the highest accuracy and [Formula presented] was 0. 955, which had good robustness. It provided some ideas for further applications of machine learning in collaboration with physical models and optical satellites in collaboration with radar satellites in soil salinity inversion. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 52

Main heading: Machine learning

Controlled terms: Backscattering? - ?Cloud computing? - ?Soils? - ?Textures? - ?Vegetation

Uncontrolled terms: Backscatter coefficients? - ?Improving polarization index? - ?Machine-learning? - ?Polarization indices? - ?Sentinel – 1/2? - ?Sentinel-1? - ?Soil salinity? - ?Spectral information? - ?Texture features? - ?Water cloud models

Classification code: 483.1 Soils and Soil Mechanics? - ?722.4 Digital Computers and Systems? - ?723.4 Artificial Intelligence

DOI: 10.6041/j.issn.1000-1298.2024.01.016

Funding Details: Number: 2022YFD1900404,51979232,52179044,52279047, Acronym: NSFC, Sponsor: National Natural Science Foundation of China;

Funding text: 国家自然科学基金项目(51979232、52279047、52179044) 和国家重点研发计划项目 (2022YFD1900404)

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

11. Automated Measurement Method of Phenotypic Parameters of Edible Mushroom Mycelium Based on VGG-UNet

Accession number: 20240915637713

Title of translation: 基于VGG UNet的食用菌菌丝体表型参数自动测量方法

Authors: Chen, Yan (1, 2); Lu, Jiahao (1); Hu, Xiaochun (3); Qi, Liangliang (4)

Author affiliation: (1) College of Computer and Electronic Information, Guangxi University, Nanning; 530004, China; (2) Guangxi Key Laboratory of Multiinedia Communications Network Technology, Nanning; 530004, China; (3) College of Big Data and Artificial Intelligence, Guangxi University of Finance and Economics, Nanning; 530003, China; (4) Microbiology Research Institute, Guangxi Academy of Agricultural Sciences, Nanning; 530007, China

Corresponding author: Hu, Xiaochun(hxch@gxufe.edu.cn)

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 233-240

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Mycelium phenotypic characteristics of edible mushroom are an important basis for the evaluation of edible mushroom germplasm resources and scientific breeding. To address the problems of traditional threshold segmentation method to extract mycelium regions which are easily disturbed by uneven light, irregular growth of mycelium and metabolites produced in the petri dishes, an image dataset of edible mycelium was made and a deep learning-based automatic measurement method for edible mycelium phenotype parameters was proposed. The U — Net network encoder was partially replaced with the first 13 convolutional layers of VGG16, and pre-training weights were introduced to constmct a VGG — UNet model applicable to mycelium segmentation. The average cross-merge ratio of this model reached 98. 18%, which was 0. 93 percentage points higher than that of the original U — Net model. After obtaining mycelium segmentation images by this model, the five phenotypic parameters of radius, perimeter, area, coverage, and roundness of mycelium were calculated by using OpenCV correlation functions. A linear regression analysis was performed between the manual measurement method, and the R2 of mycelium radius, perimeter, area and coverage were 0. 979 5, 0. 991 5, 0. 975 0 and 0. 975 0, respectively, and the RMSE were 2. 20 mm, 4. 73 mm, 176. 74 mm2 and 3. 16%, respectively. The method was tested to accurately accomplish the task of automatic* measurement of phenotypic parameters of edible mycelium, which provided a theoretical basis for the study of phenotypic analysis of edible mushrooms. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 25

Main heading: Mycelium

Controlled terms: Conservation? - ?Deep learning? - ?Metabolites? - ?Parameter estimation? - ?Semantic Segmentation? - ?Semantics

Uncontrolled terms: Automated measurement? - ?Deep learning? - ?Edible mushroom? - ?Edible mushroom mycelium? - ?Images processing? - ?Measurement methods? - ?Mushroom Mycelium? - ?Phenotypic parameter? - ?Semantic segmentation? - ?VGG — unet

Classification code: 461.4 Ergonomics and Human Factors Engineering? - ?461.8 Biotechnology? - ?723.4 Artificial Intelligence? - ?811.2 Wood and Wood Products

Numerical data indexing: Area 7.40E-05m2, Percentage 1.60E+01%, Percentage 1.80E+01%, Size 2.00E-02m, Size 7.30E-02m

DOI: 10.6041/j.issn.1000-1298.2024.01.022

Funding text: 广西科学研究与技术开发计划项目（桂科 AA20302002-3）、广西创新驱动发展专项资金项目（桂科 AA0302012-1）和财政部和农业农村部：国家现代农业产业技术体系建设项目（CARS-20）

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

12. Vision Detection Method for Picking Robots Based on Improved Faster R-CNN

Accession number: 20240915630263

Title of translation: 基于改进 Faster R — CNN 的苹果采摘视觉定位与检测方法

Authors: Li, Cuiming (1); Yang, Ke (1); Shen, Tao (1); Shang, Zhengyu (1)

Author affiliation: (1) School of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou; 730050, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 47-54

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: To address the issue of poor detection and positioning capabilities of fruit picking robots in scenes with densely distributed targets and fruits occluding each other, a method to improve the fruit detection and positioning of Faster R — CNN was proposed by introducing an efficient channel attention mechanism (ECA) and a multiscale feature fusion pyramid (FPN). Firstly, the commonly used VGG16 network was replaced with a ResNet50 residual network with strong expression capability and eliminate network degradation problem, thus extracting more abstract and rich semantic information to enhance the model’s detection ability for multiscale and small targets. Secondly, the ECA module was introduced to enable the feature extraction network to focus on local and efficient information in the feature map, reduce the interference of invalid targets, and improve the model’s detection accuracy. Finally, a branch and leaf grafting data augmentation method was used to improve the apple dataset and solve the problem of insufficient image data. Based on the constructed dataset, genetic algorithms were used to optimize K-means + + clustering and generate adaptive anchor boxes. Experimental results showed that the improved model had average precision of 96.16% for graspable apples and 86.95% for non-graspable apples, and the mean average precision was 92.79%, which was 15.68 percentages higher than that of the traditional Faster R — CNN. The positioning accuracy for graspable and non-directly graspable apples were 97.14% and 88.93 %, respectively, which were 12.53 percentages and 40.49 percentages higher than that of traditional Faster R — CNN. The weight was reduced by 38.20%. The computation time was reduced by 40.7 %. The improved model was more suitable for application in fruit-picking robot visual systems. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 20

Main heading: Fruits

Controlled terms: Agricultural robots? - ?Feature extraction? - ?Genetic algorithms? - ?Image enhancement? - ?K-means clustering? - ?Semantics

Uncontrolled terms: Apple picking robot? - ?Attention mechanisms? - ?Detection methods? - ?Distributed target? - ?Efficient channels? - ?Fast R — CNN? - ?Feature pyramid? - ?Picking robot? - ?Target localization? - ?Targets detection

Classification code: 731.5 Robotics? - ?821.1 Agricultural Machinery and Equipment? - ?821.4 Agricultural Products? - ?903.1 Information Sources and Analysis

Numerical data indexing: Percentage 3.82E+01%, Percentage 4.07E+01%, Percentage 8.695E+01%, Percentage 8.893E+01%, Percentage 9.279E+01%, Percentage 9.616E+01%, Percentage 9.714E+01%

DOI: 10.6041/j.issn.1000-1298.2024.01.004

Funding text: 国家自然科学基金项目（52265065, 51765031）

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

13. Design and Modeling of Novel Three Degree-of-freedom Parallel Robot for Narrow Space

Accession number: 20240915642693

Title of translation: 面向狭长空间的三自由度并联机器人设计与建模

Authors: Xu, Dongmei (1); Liu, Xianglong (1); Yu, Simiao (2); Xu, Chao (1); Yang, Fan (1); Cao, Chuqing (3)

Author affiliation: (1) College of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an; 710054, China; (2) School of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an; 710055, China; (3) Wuhu HIT Robot Technology Research Institute Co., Ltd., Wuhu; 241000, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 426-435

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Parallel robots are widely studied for the advantages of high stiffness, stable structure, large bearing capacity and small motion load, and have been widely used in agricultural and industrial fields. Due to the distribution of branch chains, most of the existing parallel robots cannot work in a long and narrow space while having a large working space. Therefore, for the narrow and long working environment, a three-degree of freedom parallel mechanism was proposed. The whole mechanism was arranged along a linear guide rail direction, reducing the width perpendicular to the guide rail direction, so that it was easy to fit into a narrow space, while having a large working space, and realizing translational motion on three degrees of freedom. The degree of freedom of the mechanism was calculated by G - K formula and the rationality of the design of parallel robot was verified. The kinematics and dynamics of the platform were analyzed. The singularity was analyzed by genetic algorithm. Finally, the kinematics and dynamics simulation were carried out in ADAMS software, by comparing with the mathematical model in Simulink software, the error of the two results was generally less than 0.05%, which showed that the mathematical model was correct. The working space of the mechanism was analyzed by analytical method. The research results can provide an idea and structure for 3-DOF parallel robot working in narrow and long space. It can also provide a theoretical basis for the mathematical modeling of the structure. ? 2024 Chinese Society of Agricultural Machinery. All rights reserved.

Number of references: 22

Main heading: Kinematics

Controlled terms: Agricultural robots? - ?Agriculture? - ?Computer software? - ?Degrees of freedom (mechanics)? - ?Dynamics? - ?Genetic algorithms? - ?Machine design

Uncontrolled terms: Agricultural fields? - ?Design and modeling? - ?High stiffness? - ?Kinematics and dynamics? - ?Large bearings? - ?Narrow spaces? - ?Parallel robots? - ?Stable structures? - ?Three degree of freedoms? - ?Working space

Classification code: 601 Mechanical Design? - ?723 Computer Software, Data Handling and Applications? - ?731.5 Robotics? - ?821 Agricultural Equipment and Methods; Vegetation and Pest Control? - ?821.1 Agricultural Machinery and Equipment? - ?931.1 Mechanics

Numerical data indexing: Percentage 5.00E-02%

DOI: 10.6041/j.issn.1000-1298.2024.01.041

Compendex references: YES

Database: Compendex

Data Provider: Engineering Village

14. Robot Path Planning Based on Artificial Potential Field Method with Obstacle Avoidance Angles

Accession number: 20240915642689

Title of translation: 基于含避障角人工势场法的机器人路径规划

Authors: Wan, Jun (1, 2); Sun, Wei (2); Ge, Min (2); Wang, Kehong (1); Zhang, Xiaoyong (1)

Author affiliation: (1) School of Materials Science and Engineering, Nanjing University of Science and Technology, Nanjing; 210094, China; (2) School of Automobile and Traffic Engineering, Jiangsu University of Technology, Changzhou; 213001, China

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

Abbreviated source title: Nongye Jixie Xuebao

Volume: 55

Issue: 1

Issue date: 2024

Publication year: 2024

Pages: 409-418

Language: Chinese

ISSN: 10001298

CODEN: NUYCA3

Document type: Journal article (JA)

Publisher: Chinese Society of Agricultural Machinery

Abstract: Aiming at the local minima problem of the

期刊浏览

EI收录结果