马文强,张漫,李源,杨莉玲,朱占江,崔宽波.核桃仁脂肪含量的近红外光谱无损检测[J].农业机械学报,2019,50(Supp):374-379.
MA Wenqiang,ZHANG Man,LI Yuan,YANG Liling,ZHU Zhanjiang,CUI Kuanbo.Non-destructive Detection for Fat Content of Walnut Kernels by Near Infrared Spectroscopy[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(Supp):374-379.
摘要点击次数: 1449
全文下载次数: 747
核桃仁脂肪含量的近红外光谱无损检测   [下载全文]
Non-destructive Detection for Fat Content of Walnut Kernels by Near Infrared Spectroscopy   [Download Pdf][in English]
投稿时间:2019-04-20  
DOI:10.6041/j.issn.1000-1298.2019.S0.057
中文关键词:  核桃仁  脂肪含量  近红外光谱  特征波段  支持向量机回归
基金项目:新疆维吾尔自治区自然科学基金计划特培项目(2019D03007)、新疆农业科学院青年科技骨干创新能力培养项目(xjnkq-2019007)和新疆农业科学院科技创新重点培育专项(xjkcpy-004)
作者单位
马文强 中国农业大学
新疆农业科学院农业机械化研究所 
张漫 中国农业大学 
李源 新疆农业科学院土壤肥料与农业节水研究所 
杨莉玲 新疆农业科学院农业机械化研究所 
朱占江 新疆农业科学院农业机械化研究所 
崔宽波 新疆农业科学院农业机械化研究所 
中文摘要:为了实现核桃仁脂肪含量的快速无损检测,在1040~2560nm光谱范围内采集了核桃仁近红外光谱。首先,通过多元散射校正和标准正态化组合方法对原始光谱信息进行预处理,采用马氏距离法剔除异常样本;然后,运用竞争性自适应重加权采样算法与相关系数法相结合,进行特征波段筛选;最后,采用偏最小二乘回归和支持向量机回归算法建立了核桃仁脂肪含量的预测模型。结果显示,以筛选出的6个特征波段为输入,采用偏最小二乘回归算法建立的核桃仁脂肪质量分数预测模型的验证集决定系数为0.86,均方根误差为1.5849%;采用支持向量机回归算法建立的模型验证集决定系数为0.88,均方根误差为1.3716%;表明支持向量机回归算法的建模质量优于偏最小二乘回归算法。采用特征波段建立的支持向量机回归预测模型能大幅降低建模复杂度,实现核桃仁脂肪含量的快速无损检测。
MA Wenqiang  ZHANG Man  LI Yuan  YANG Liling  ZHU Zhanjiang  CUI Kuanbo
China Agricultural University;Agricultural Mechanization Institute, Xinjiang Academy of Agricultural Sciences,China Agricultural University,Soil Fertilizer and Agricultural Water Saving Research Institute, Xinjiang Academy of Agricultural Sciences,Agricultural Mechanization Institute, Xinjiang Academy of Agricultural Sciences,Agricultural Mechanization Institute, Xinjiang Academy of Agricultural Sciences and Agricultural Mechanization Institute, Xinjiang Academy of Agricultural Sciences
Key Words:walnut kernel  fat content  near infrared spectroscopy  feature bands  support vector machine regression
Abstract:Fat content is an important indicator of the quality of walnuts. In order to achieve the rapid non destructive detection of walnut fat content, the near infrared spectrum of walnut kernel was collected in the spectral range of 1040~2560nm. Multivariate scatter correction and standard normalized variate were used to pre processing the original spectral information. And abnormal samples were eliminated by the Mahalanobis distance method. Then the feature bands were screened by the method, which combined competitive adaptive re weighting sampling (CARS) and correlation coefficient method (CCM) algorithm. Finally, the partial least squares regression and the support vector machine regression algorithm were used to establish prediction model for the fat content of walnut kernels. The results showed that with the six feature bands selected as input, the validation set coefficient of the walnut kernel fat content prediction model established by partial least squares regression algorithm was 0.86, and the root mean square error was 1.5849%. The validation set coefficient of model established by the support vector machine regression algorithm was 0.88 and the root mean square error was 1.3716%. It was showed that the modeling quality of the support vector machine regression algorithm was better than the partial least squares regression algorithm. The support vector machine regression prediction model established by the feature bands could sharply reduce the modeling complexity and realize the rapid non destructive detection of the fat content of walnut kernel.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器