[关键词]
[摘要]
为提高近红外光谱分析方法快速实现对测定红茶在制品中的茶褐素的定量模型精度无损、快速检测,本文试验利用近红外光谱技术对以英红九号发酵叶中茶褐素进行采集、提取和分析的检测为例,对其近红外定量检测模型的构建与优化进行了研究。首先,采用规范化处理(Normalize)、基线校正(Baseline)、S-G一阶导数(Savitzky-Golay, 1st S-G)、S-G二阶导数(2nd S-G)、标准正态变量变换(Standard Normal Variate transform, SNV)五种预处理方法对原始光谱进行预处理分析。然后,采用效果最好的一阶导数预处理方法进行波长特征提取,分别使用间隔偏最小二乘算法(interval Partial least square, iPLS)、竞争自适应加权算法(Competitive Adaptive Reweighted Sampling, CARS)、变量迭代空间收缩方法(the Variable Iterative Space Shrinkage Approach,VISSA)提取波长特征。最后,使用偏最小二乘回归(partial least square,PLS)预测模型进行回归建模。研究结果表明:使用一阶导数进行预处理、同时使用CARS方法建立的1st-CARS-PLS模型效果特征更显著,特征值数量为53个。研究表明,本试验采用的模型方法能够快速、无损地检测英红九号发酵叶中的茶褐素含量。
[Key word]
[Abstract]
In the fermentation process of black tea, the near-infrared spectrum was used for the rapid detection of the fermentation sample. Firstly, the original spectra were preprocessed and analyzed by five preprocessing methods: Normalize, Baseline, S-G first derivative (Savitzky-Golay, 1st S-G), S-G second derivative (2nd S-G) and standard normal variable transform (SNV). Then, 1st S-G is used to extract the wavelength features, and the interval partial least squares algorithm (iPLS), competitive adaptive weighting algorithm (CARS) and the variable iterative space shrinkage approach (VISSA) are used to extract the wavelength features respectively. Finally, partial least squares regression (PLS) prediction model is used for regression modeling. The results show that the 1st-CARS-PLS model, which is pretreated with the first derivative and established by cars method, has the best effect. The number of eigenvalues is 53.
[中图分类号]
[基金项目]
茶青与在制品精准化保鲜保质技术研究与示范(粤财农[2020]20号);茂名实验室自主科研项目(2021ZZ003)