基于近红外光谱法建立核桃仁可溶性蛋白质含量检测模型  

A model for soluble protein content detection of walnuts based on near infrared spectroscopy

作　　者：罗浪琴 王涛 刘国庆 赵文革 张锐[1,2,3] 于军 陆斌[7] 陈天财 LUO Langqin;WANG Tao;LIU Guoqing;ZHAO Wenge;ZHANG Rui;YU Jun;LU Bin;CHEN Tiancai(School of Horticulture and Forestry,Tarim University,Alar 843300,Xinjiang,China;Key Laboratory of Biological Resources Protec-tion and Utilization in Tarim Basin,Xinjiang Production and Construction Corps,Alar 843300,Xinjiang,China;National and Local Joint Engineering Laboratory for Efficient and High-Quality Cultivation and Deep Processing Technology of Characteristic Fruit Trees in Southern Xinjiang,Alar 843300,Xinjiang,China;School of Information,Tarim University,Alar 843300,Xinjiang,China;Damu Grain and Oil Forest Farm in Wensu County,Aksu 843000,Xinjiang,China;Aksu Zhejiang Fruit Industry Co,Ltd,Aksu 843000,Xinjiang,China;Yunnan Academy of Forestry and Grassland Sciences,Kunming 650000,Yunnan,China)

机构地区：[1]塔里木大学园艺与林学学院,新疆阿拉尔843300 [2]新疆生产建设兵团塔里木盆地生物资源保护利用重点实验室,新疆阿拉尔843300 [3]南疆特色果树高效优质栽培与深加工技术国家地方联合工程实验室,新疆阿拉尔843300 [4]塔里木大学信息学院,新疆阿拉尔843300 [5]温宿县大木粮油林场,新疆阿克苏843000 [6]阿克苏浙疆果业有限公司,新疆阿克苏843000 [7]云南林业和草原科学院,昆明650000

出　　处：《果树学报》2023年第8期1750-1761,共12页Journal of Fruit Science

基　　金：国家重点研发计划(2020YFD1000703);塔大校长基金创新研究团队项目(TDZKCX202101);塔里木大学科研条件项目(TDZKKY202204);温宿核桃科技小院(农技协发字[2022] 16号)。

摘　　要：【目的】核桃仁中的可溶性蛋白质含量是影响核桃品质的重要指标,比较核桃仁可溶性蛋白质含量不同模型之间的预测性能。【方法】以180份核桃仁样品作为研究对象,采集样品的近红外漫反射光谱。使用6种不同预处理方法对光谱信息进行处理,比较BP神经网络法和支持向量回归(SVR)建立核桃仁蛋白质的预测模型。【结果】2种方法对不同组合的预处理方法所建立模型的决定系数均大于0.81,相比于SVR模型的预测模型性能,MSC+FD+BP神经网络所建的预测模型性能更优,建模集的决定系数R~2为0.871,均方根误差为0.089 5,RPD为2.875;验证集的R~2为0.825,均方根误差为0.105 9,RPD值为2.233。【结论】BP神经网络算法在特征波段的核桃仁可溶性蛋白质含量预测建模中,模型质量优于SVR算法。MSC+FD+CARS+BP神经网络建模方式更适用核桃仁可溶性蛋白质含量的预测,为使用近红外光谱分析核桃仁质量提供了参考依据。【Objective】The primary goal of this research was to compare the modeling methods of Support Vector Regression(SVR) and Back-Propagation network and seak for the best pre-processing combination method with the modeling method.The protein content prediction model of walnut kernel was established using near-infrared spectroscopy technology.The protein content of walnut kernels is one of the important indicators affecting the quality of walnuts.At present,the detection method for protein content mainly depends on the national standard method,the process is cumbersome,and multiple indicators can not be determined at the same time.【Methods】180 walnut samples from 9 different orchards were collected as research materials,the row spacing of the walnut trees in each orchard is 4 m×6 m,and the tree age is 10 years.Firstly,the diffuse reflectance spectra of the samples were collected at room temperature(around 25 ℃) using an Antaris Ⅱ Fourier transform NIR spectrometer made in the United States,the spectra were obtained in the wave number range of 4000-10 000 cm^(-1)(780-2500 nm)with a resolution of 8 cm^(-1) and a gain of 2x.With the built-in background of the instrument as the reference,each sample was scanned 3 times repeatedly as the original spectrum of the sample.The average spectrum was obtained after 32 final scans.Secondly,the protein content of 180 walnuts was determined by the Kaumas Brilliant Blue method.After the six outliers were removed by the Marginal distance,the SPXY algorithm was used to divide 174 samples into 132 Correction sets and 42 Validation sets in a 3∶1 ratio.The Competitive Adaptive Reweighted Sampling(CARS) method was used to extract the feature wavelengths.The spectral information was processed by six different pretreatment combination methods:Standard Normal Variables transformation(SNV),First-Derivative(FD),Multivariate,Scattering,Correction(MSC) +First-Derivative(FD),Second-Derivative(SD),Savitzky Golay convolution smoothing(SG)+Second-Derivative(SD),Standard Normal Variables

关 键 词：核桃仁 可溶性蛋白质含量 BP神经网络 支持向量回归(SVR) 

分 类 号：S664.1[农业科学—果树学]