基于BP-ANN和PLS的近红外光谱无损检测李果实品质的研究  

Quantitative Analysis of Soluble Solids and Titratable Acidity Content in Angeleno Plum by Near-Infrared Spectroscopy With BP-ANN and PLS

作　　者：赵志磊[1,2,3,4] 王雪妹 刘冬冬 王艳伟 顾玉红[5] 滕佳鑫 牛晓颖[1,2,3,4] ZHAO Zhi-lei;WANG Xue-mei;LIU Dong-dong;WANG Yan-wei;GU Yu-hong;TENG Jia-xin;NIU Xiao-ying(College of Quality and Technical Supervision,Hebei University,Baoding 071002,China;National&Local Joint Engineering Research Center of Metrology Instrument and System,Hebei University,Baoding 071002,China;Hebei Key Laboratory of Energy Metering and Safety Testing Technology,Hebei University,Baoding 071002,China;Institute of Geographical Indications,Hebei University,Baoding 071002,China;College of Life Science,Hebei Agricultural University,Baoding 071002,China)

机构地区：[1]河北大学质量技术监督学院,河北保定071002 [2]计量仪器与系统国家地方联合工程研究中心,河北保定071002 [3]河北省能源计量与安全检测技术重点实验室,河北保定071002 [4]河北大学地理标志研究院,河北保定071002 [5]河北农业大学生命科学学院,河北保定071002

出　　处：《光谱学与光谱分析》2022年第9期2836-2842,共7页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(31872907);河北省自然科学基金项目(C2021201011)资助。

摘　　要：可溶性固形物(SSC)和可滴定总酸(TA)含量是影响李果实品质的重要指标,经典的破坏性检测方法不适用于果实按品质分级,近红外光谱(NIRS)检测方法具有速度快、操作简便、可无损检测果实品质。为实现NIRS无损快速检测安哥诺李果实可溶性固形物和可滴定总酸含量,利用NIRS采集李果实的漫反射光谱,同时采用糖度计测定安哥诺李果实的SSC,采用滴定法测定了李果实TA含量,使用杠杆值和F概率值剔除异常样品,采用软件优化结合人工筛选光谱波段,使用了消除常数偏移量、减去一条直线、矢量归一化(SNV)、最大-最小归一化、多元散射校正(MSC)、一阶和二阶导数结合平滑处理、一阶导数结合减去一条直线和平滑处理、以及一阶导数结合SNV或MSC校正等光谱预处理方法,分别采用偏最小二乘法(PLS)和主成分分析结合反向传播人工神经网络(BP-ANN)建立李果实SSC、TA的定量分析模型。结果表明,李果实SSC和TA的最佳PLS建模效果波段范围分别为4000~8852和4605~6523 cm^(-1)。SSC的PLS模型的最佳光谱预处理方法为MSC校正,最佳模型校正相关系数(R_(c))为0.9144,预测相关系数(R_(p))为0.8785,校正均方根误差(RMSEC)为0.91,预测均方根误差(RMSEP)为1.00。经一阶微分结合SNV和9点平滑的方法预处理后,TA的PLS模型效果最佳,R_(c),R_(p),RMSEC,RMSEP分别为0.8603,0.8196,0.80和0.86。提取了李果实SSC和TA光谱数据的主成分,并基于前10个主成分得分建立了李果实SSC和TA最佳BP-ANN定量分析模型,其R_(c),R_(p),RMSEC和RMSEP分别为0.9767,0.8897,0.75和0.99;TA的BP-ANN模型的相应参数值依次为0.9743,0.8977,0.62和0.83,与采用PLS算法建立的定量模型相比较,BP-ANN模型具有较高的R_(c),R_(p)和较低的RMSEC,RMSEP,因此BP-ANN模型对SSC和TA指标的定量分析结果更佳。Soluble solid content(SSC)and titratable acidity(TA)are important indexes affecting the fruit quality and the fruit quality grading.Classical destructive detection methods are not suitable for fruit classification by quality.NIRS detection method is fast,easy to operate and can detect fruit quality without damage.In order to achieve non-destructive and rapid determination of SSC and TA in Angeleno plum fruits by near-infrared spectroscopy(NIR),diffuse reflectance spectra of plum fruits were collected by NIR spectrometer,SSC was measured by saccharometer,and TA content was determined by titration.Using leverage and F probability value to eliminate abnormal samples and software optimization combined with a manual screening of spectral bands,eliminating constant offset,subtracting a straight line,standard normal variate(SNV),max-minimum normalization,and multiplicative scatter correction(MSC),first and the second derivative combined smoothing,the first derivative combined minus a straight line and smoothing,and the first derivative combined with SNV or MSC correction.Partial least squares(PLS)and back propagation artificial neural network(BP-ANN)were used to establish the quantitative models of SSC and TA of plum fruit.Results indicated that the best Band ranges of plum fruit SSC and TA are 4000~8852 and 4605~6523 cm^(-1)respectively.The best spectral preprocessing method of the PLS model of SSC was MSC correction.The best model correction correlation coefficient(R_(c))was 0.9144,the prediction correlation coefficient(R_(p))was 0.8785,the correction root means square error(RMSEC)was 0.91,and the prediction root means square error(RMSEP)was 1.00.After the first order differential combined with SNV and 9-point smoothing,the PLS model of TA was the best,and the R_(c),R_(p),RMSEC and RMSEP were 0.8603,0.8196,0.80 and 0.86.The principal components of SSC and TA spectral data of plum fruits were extracted,and the optimal BP-ANN quantitative analysis model of SSC and TA were established based on the first 10 principal comp

关 键 词：李果实 偏最小二乘法 反向传播人工神经网络 近红外光谱 

分 类 号：O657.33[理学—分析化学]