摘要
为了实现兰州百合关键营养物质蛋白质和多糖的快速无损检测,在12000~4000 cm^(-1)光谱范围内采集了59份兰州百合粉的近红外光谱(NIRS)。首先运用SG、Normalize、SNV、MSC、Detrend、OSC、SG+1D、SG+Normalize、SG+SNV和SG+Detrend十种预处理方法对原始光谱数据进行处理,确定蛋白质的最佳预处理方法为SG+Detrend、多糖的最佳预处理方法为Detrend;然后运用CARS、SPA和PCA三种算法对预处理的光谱数据进行特征波长筛选,确定蛋白质和多糖的最佳特征波长提取方法均为SPA算法;最后采用PLSR法建立了兰州百合关键营养物质蛋白质和多糖含量的预测模型,结果显示,经过SG+Detrend_SPA处理所建立的蛋白质PLSR模型中,预测集相关系数R;为0.8106,预测集均方根误差RMSEP为1.1953;经过Detrend_SPA处理所建立的多糖PLSR模型中,预测集相关系数R;为0.8109,预测集均方根误差RMSEP为2.0946。考虑到经典PLSR无损预测模型精度的限制,在该研究中提出SOM-RBF神经网络无损预测模型。首先利用SOM网络对数据样本进行聚类,然后将得到的聚类类别数和聚类中心作为RBF网络的隐层节点个数和隐层节点数据中心,以此来优化RBF的结构参数。在建立的蛋白质SOM-RBF神经网络模型中,预测集相关系数R;为0.8666,预测集均方根误差RMSEP为1.0385;建立的多糖SOM-RBF神经网络模型中,预测集相关系数R;为0.8681,预测集均方根误差RMSEP为1.7994。比较PLSR和SOM-RBF两种模型对两种物质的预测结果,确定了SOM-RBF神经网络模型为最优建模方法,最终确定在蛋白质检测中,最优模型为基于SG+Detrend_SPA_SOM-RBF建立的模型,模型的预测集相关系数较PLSR高5.6%,预测集均方根误差较PLSR低0.1568;在多糖检测中,确定的最优模型为基于Detrend_SPA_SOM-RBF建立的模型,模型的预测集相关系数较PLSR高5.72%,预测集均方根误差较PLSR低0.2952。研究结果表明,运用NIR和SOM-RBF技术可以实现对兰州百合关键营养物质蛋白质和多糖的快速无损检测,为今后快速无损检测兰州百合营养物质提供理论依据。
In order to realize the rapid and nondestructive detection of key nutrients protein and polysaccharide of Lanzhou lily,near infrared spectroscopy(NIRS)of 59 Lanzhou lily powder samples were collected in the range of 12000~4000 cm;.Firstly,ten pretreatment methods of SG,Normalize,SNV,MSC,Detrend,OSC,SG+1 D,SG+Normalize,SG+SNV and SG+Detrend were used to process the original spectral data,and the optimal pretreatment method was SG+Detrend,Detrend was the best pretreatment method for polysaccharide.Then,CARS,SPA and PCA were used to screen the characteristic wavelength of the preprocessed spectral data.Finally,the SPA algorithm was used to determine the best extraction method for protein and polysaccharide’s characteristic wavelength.The results showed that the correlation coefficient R;of the prediction set was 0.8106,and the root mean square error of the prediction set RMSEP was 1.1953 in the protein PLSR model established by SG+Detrend_SPA treatment.In the polysaccharide PLSR model established by the Detrend SPA treatment,the correlation coefficient R;of the prediction set was 0.8109,and the root means square error RMSEP of the prediction set was 2.0946.Considering the limitation of precision of the classical PLSR nondestructive prediction model,SOM-RBF neural network nondestructive prediction model is proposed in this paper.Firstly,the SOM network is used to cluster the data samples,and then the number of clustering categories and clustering center obtained is used as the number of hidden layer nodes and the data center of hidden layer nodes of the RBF network to optimize the structural parameters of RBF.In the established protein SOM-RBF neural network model,the correlation coefficient R;of the prediction set is 0.8666,and the root means square error of the prediction set RMSEP is 1.0385.In the SOM-RBF neural network model established for polysaccharides,the correlation coefficient R;of the prediction set was 0.8681,and the root means square error RMSEP of the prediction set was 1.7994.Comparing-PLSR and SOM-RBF prediction results,the SOM-RBF neural network model was determined as the optimal modeling method.Finally,the optimal model was established based on SG+Detrend_SPA_SOM-RBF in protein detection.The correlation coefficient of the prediction set of the model was 5.6%higher than that of PLSR,and the root means square error of the prediction set was 0.1568 lower than that of PLSR.In the detection of polysaccharides,the optimal model was established based on Detrend_SPA_SOM-RBF,and the correlation coefficient of the model was 5.72%higher than that of PLSR,and the root means square error of the model was 0.2952 lower than that of PLSR.The results showed that NIR and SOM-RBF techniques could be used for the rapid and non-destructive detection of key nutrients,proteins and polysaccharides,and the results could provide a theoretical basis for the future rapid and non-destructive detection of nutrients in Lily of Lanzhou.
作者
廉小亲
陈群
汤燊淼
吴静珠
吴叶兰
高超
LIAN Xiao-qin;CHEN Qun;TANG Shen-miao;WU Jing-zhu;WU Ye-lan;GAO Chao(School of Artificial Intelligence,Beijing Technology and Business University,Beijing 100048,China;China Light Industry Key Laboratory of Industrial Internet and Big Data,Beijing Technology and Business University,Beijing 100048,China)
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2022年第7期2025-2032,共8页
Spectroscopy and Spectral Analysis
基金
国家自然科学基金项目(61807001)
北京工商大学研究生培养-研究生教育质量提升计划项目(19008020144)资助。
关键词
兰州百合
蛋白质
多糖
近红外光谱
无损检测
SOM-RBF神经网络
Lanzhou lily
Protein
Polysaccharide
Near infrared spectroscopy
Nondestructive testing
SOM-RBF neural network