基于红外光谱PCA-LDA统计分析的麻纤维鉴别研究OA北大核心CSTPCD

Flax,hemp and ramie fibers have been important raw materials for textile products since ancient times.Due to the difference in use and output,there has been a significant gap in the market price of these three different species of bast fibers in recent years,and the illegal phenomenon of low-price bast fibers posing as high-price bast fibers often occurs.The composition,physical and chemical properties of flax,hemp and ramie fibers are very close.At present,the standard method for identifying bast fibers in China is FZ/T 01057.3-2007 The Method for Identification of Textile Fibers-Part 3:Microscopy.However,the microscopic morphology of flax,hemp and ramie is highly similar,and the accuracy of identifying bast fibers according to this method is insufficient.The identification of these three species of easily confused bast fibers has always been a difficult task in the field of textile inspection and testing,so it is necessary to improve the identification technology of bast fibers to maintain market stability and strengthen quality supervision. Although the predecessors have found that there are relatively slight infrared spectral differences between different kinds of bast fibers,no rapid and accurate classification method for bast fibers based on the differences in infrared spectral data has been reported.In our study,the principal component analysis(PC A)and linear discriminant analysis(LDA)on attenuated total reflection Flourier transformed infrared spectroscopy(ATR-FTIR)of different kinds of bast fibers were proposed to establish a discriminant model to identify these three kinds of easily confused bast fibers. In this study,60 groups of flax,hemp and ramie fibers were selected as sample sets for degumming cleaning treatment and their ATR-FTIR spectra were collected.After spectral normalization,infrared spectra in the range of 800-2 000 cm-1 were compressed to scores of sets of principal components(PCs)by PCA.The PCA results show that:with the increase of the number of PCs,the PC scores gradually display a clustering trend according to the species of bast fibers,and the cumulative variance contribution rate of the first 12 PCs to the normalized spectral data reaches 99.5％.With the first 12 PC scores as the independent variable and the species of fiber samples as the dependent variable,a discriminant model of the bast fibers including typical discriminant functions and classification functions was established by LDA.The discriminant model verification results show that:the typical discriminant functions can make the first 12 PC scores achieve a excellent cluster according to the species of fiber samples,and the classification functions can reach a classification accuracy of 100％for all fiber samples in the training set and the test set.In addition,the classification accuracy of the PCA-LDA model can still reach 99.6％by leave-one-out cross-validation.These results prove that the differences between ATR-FTIR spectra of flax,hemp,and ramie can be discerned and utilized for the rapid and accurate identification of these easily confused textile bast fibers by PCA-LDA statistic analysis. In the follow-up study,we will introduce more laboratories and samples to participate in the construction and verification of the PCA-LDA model,so as to further improve the applicability of the bast fiber classification and identification model.