工夫红茶咖啡碱和5种儿茶素组分近红外快速测定方法的研究

Research of rapid measurement methods of caffeine and five kinds of catechin components quality ingredients of congou black tea using near infrared spectroscopy

提出一种利用近红外光谱技术无损快速检测工夫红茶咖啡碱（Caffeine）和5种儿茶素（儿茶素（Cateehin，C）、表儿茶素（Epicatechin，Ec）、表没食子儿茶素（Epigalloeateehin，EGC）、表儿茶素没食子酸酯（Epicatechingallate，ECG）、表没食子儿茶素没食子酸酯（Epigallocatechin gallate，EGCG））组分含量的新方法。实验样品共计240个，手动选择180个样品作为校正级。剩余60个样品作为预测集；利用OPUS7．0软件优化出各模型最佳波数段和最佳预处理方法，平滑点数17，维数1，结合咖啡碱（Caffeine）和5种儿茶素组分C、EC、ECG、EGC、EGCG含量建立预测模型，分析预测模型的预测性能。结果表明：各预测模型预测精准度高，均可用于咖啡碱和5种儿茶素组分C、EC、ECG、EGC、EGCG检测。其中，各模型校正相关系数（Rc）为91．85％-99．49％，校正均方根误差（RMSEC）为0．0187—0．353；预测相关系数（Rp）为97．12％-99．88％，预测均方根误差（RMSEP）为0．00759～0．0773。各模型校正集和预测集均有较高的拟合度，模型预测性能咖啡碱〉EGC〉EC〉ECG〉EGCG〉C。结论：近红外光谱图结合咖啡碱（Caffeine）和5种儿茶素组分C、EC、ECG、EGC、EGCG含量建立的各预测模型预测性能优，可用于工夫红茶咖啡碱（Caffeine）和5种儿茶素组分C、EC、ECG、EGC、EGCG含量快速无损检测。

A new method about detecting the caffeine and five kinds of catechin components including Catechin, Epicatechin,Epigallocatechin, Epicatechin gallate, Epigallocatechin gallate of Congou black tea by near infrared spectroscopy was established.There were 240 test samples, ]80 samples of them used to be a correction stage as the remaining 60 samples a prediction set.Each model was optimized the best waves of the number of segments and best pretreatment method for model inguse to establish the quantitative prediction model by OPUS 7.0 software.The Smooth points were 17 and dimension was 1. Combined with caffeine and five kinds of catechin component including C, EC, ECG, EGC, EGCG content,the prediction model was established, and the performance of the prediction model was analyzed.The model predicted a high accuracy which can be used to predict the caffeine and five kinds of catechin component including C, EC, ECG, EGC, EGCG quality of Congou black tea.The calibration correlation coefficient（Rc） was 9].85 % -99.49%, correcting root mean square error（RMSEC） was 0.0187 ~0.353 ; predictive correlation coefficient （Rp）was 97.12%-99.88%, and the RMSEP was 0.00759 -0.0？？3. Each model calibration set and prediction set had a higher degree of fit,the prediction performance model of caffeine 〉 EGC 〉 EC 〉 ECG 〉 EGCG 〉 C.The combination of near -infrared spectra of each prediction model to predict the performance had an excellent organoleptic results and can be used in the caffeine and five kinds of catechin component C, EC, ECG, EGC, EGCG content rapid non -destructive testing of congou black tea.