首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于高光谱成像技术的鲜食核桃仁水分检测研究
引用本文:牛瑞敏,张淑娟,陈彩虹,孙海霞,高庭耀.基于高光谱成像技术的鲜食核桃仁水分检测研究[J].农业工程,2021,11(1):58-61.
作者姓名:牛瑞敏  张淑娟  陈彩虹  孙海霞  高庭耀
作者单位:山西农业大学农业工程学院,山西 晋中030800
基金项目:山西省应用基础研究项目(项目编号:201801D121252);山西省重点研发计划项目(项目编号:201903D221027)
摘    要:为实现对货架期内青皮核桃仁水分的快速预测,利用高光谱成像技术采集货架期核桃青皮光谱数据,测定核桃仁含水量,利用连续投影法(SPA)提取11个特征波长,建立了偏最小二乘法(PLS)、多元线性回归(MLR)和最小二乘支持向量机(LS-SVM)模型。结果表明,LS-SVM建模效果最好,预测集的相关系数RP=0.800 7,均方根误差RRMSEP=2.189 7。研究表明,利用高光谱成像技术可以实现货架期青皮核桃仁水分快速预测,为青皮核桃的贮运销提供指导。 

关 键 词:高光谱成像    青皮核桃    货架期    水分
收稿时间:2020/11/9 0:00:00
修稿时间:2021/1/8 0:00:00

Moisture Detection of Fresh Walnut Kernels Based on Hyperspectral Imaging Technology
NIU Ruimin,ZHANG Shujuan,CHEN Caihong,SUN Haixi,GAO Tingyao.Moisture Detection of Fresh Walnut Kernels Based on Hyperspectral Imaging Technology[J].Agricultural Engineering,2021,11(1):58-61.
Authors:NIU Ruimin  ZHANG Shujuan  CHEN Caihong  SUN Haixi  GAO Tingyao
Institution:(College of Agricultural Engineering,Shanxi Agricultural University,Jinzhong Shanxi 030800,China)
Abstract:In order to realize rapid prediction of fresh walnut kernel moisture during shelf period, hyperspectral technology was used to collect spectral data of walnut green peel and moisture content of walnut kernel was measured. Eleven characteristic wavelengths were extracted by continuous projection method(SPA) to establish partial least squares(PLS), multiple linear regression(MLR), least squares-support vector machine(LS-SVM) model. Results showed that the LS-SVM modeling effect was the best, correlation coefficientRPof the prediction set was 0. 800 7, and root mean square errorRRMSEPwas 2. 189 7. Studies have shown that the use of hyperspectral technology could achieve rapid prediction of moisture of fresh peel walnut kernels during shelf life, providing guidance for storage, transportation and marketing of fresh peel walnuts.
Keywords:hyperspectral imaging  fresh walnut  shelf life  moisture
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《农业工程》浏览原始摘要信息
点击此处可从《农业工程》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号