基于近红外光谱技术的恩施玉露茶保存年份的快速无损鉴别
Identification of Enshi Yulu tea conserved years based on near infrared spectroscopy

为快速、准确、无损鉴别恩施玉露茶的保存年份，扫描在良好条件下连续保存5 a（2010-2014年）的100个恩施玉露茶，获得其近红外光谱，对光谱进行预处理，然后结合主成分分析法（PCA）和最小二乘支持向量机法（LS-SVM）建立绿茶保存年份的近红外光谱预测模型。结果表明，前3个主成分的累计贡献率为99.99%，验证集模型的决定系数（R2）为0.971 7，验证均方差（RMSEP）为0.255 0。初步实现了市售绿茶保存年份的快速鉴别，该方法也为其他茶类保存年份的判别提供参考。
Enshi Yulu tea is a famous steaming green tea with a national geographical indication.Enshi Yulu tea has well-preserved appearance and color under strict storage conditions.To rapidly and non-destructively predict the quality of Enshi Yulu tea conserved years,100 samples continuously stored 5 years (2010-2014) were studied with the near infrared spectroscopy.The least squares support vector machine combined with principal component analysis was used to establish the model for predicting the conservation years.The results showed that the cumulative contribution rate of the first three principal components,the coefficient of determination,and the root mean square error of prediction in the validation set was 99.99%,0.971 7 and 0.255 0,respectively.The initial realization of the rapid identification of conservation years of commercially green tea is available.It will provide a useful reference for discriminating the conservation years of other teas.