基于高光谱技术的穿心莲药材中穿心莲内酯类成分检测研究

Research on the Detection of Andrographolide Components in Andrographis Paniculata Based on Hyperspectral Technology

基于高光谱技术结合化学计量学,建立不同种质穿心莲药材中穿心莲内酯类成分含量的检测方法。采集穿心莲样品的高光谱信息,获得原始光谱数据(Raw Data)。采用一阶导数(D1)、二阶导数(D2)、SG平滑(SG)、乘性散射校正(MSC)对Raw Data预处理,结合偏最小二乘判别分析(PLS-DA)建立分类模型,结合偏最小二乘回归(PLSR)、反向传播神经网络(BPNN)、随机森林回归(RFR)建立回归模型。应用连续投影算法(SPA)简化模型。不同种质的穿心莲最佳分类模型为D1-PLS-DA。穿心莲内酯、新穿心莲内酯、去氧穿心莲内酯、脱水穿心莲内酯4种穿心莲内酯类化合物总含量的最佳回归模型分别为SG-PLSR、MSC-PLSR、Raw Data-SPA-BPNN、MSC-SPA-BPNN和Raw Data-PLSR。应用高光谱技术可实现穿心莲品质的快速准确检测。

Based on hyperspectral technology combined with chemometrics,to establish a method for detecting the content of andrographolide components in different germplasm of Andrographis paniculata.The hyperspectral information of Andrographis paniculata samples was collected to obtain the raw spectral data(Raw Data).The Raw Data was preprocessed using first derivative(D1),second derivative(D2),savitzky-golay(SG),multiplicative scatter correction(MSC),and a classification model was established using partial least squares discriminant analysis(PLS-DA).Regression models were established using partial least squares regression(PLSR),back propagation neural network(BPNN),and random forest regression(RFR).The application of successive projection algorithm(SPA)simplified the model.The optimal classification model for different germplasm of Andrographis paniculata is D1-PLS-DA.The optimal regression models for andrographolide,neoandrographolide,deoxyandrographolide,dehydroandrographolide,and total content of the four andrographolide components mentioned are SG-PLSR,MSC-PLSR,Raw Data-SPA-BPNN,MSC-SPA-BPNN,and Raw Data-PLSR,respectively.The application of hyperspectral technology can achieve rapid and accurate detection of the quality of Andrographis paniculata.