基于PLS-LDA和拉曼光谱快速定性识别食用植物油

Rapid qualitative identification method of edible vegetable oil based on PLS-LDA and Raman

以6种食用油共计23个样本为分析对象,采用偏最小二乘线性判别分析法(PLS-LDA)和拉曼光谱进行单一种类(橄榄油、花生油和玉米油)食用油快速定性检测,通过自适应迭代惩罚最小二乘法(airPLS)对拉曼信号进行背景扣除,以及蒙特卡洛无信息变量消除法筛选波长变量,不但有效减少了波长点数,降低了建模运算量,而且提高了单一种类食用油的识别率,使得总体识别率均高于90%,并在此基础上进一步提出了采用PLS-LDA进行多种类食用油识别的检测流程。实验结果表明PLS-LDA在食用油定性识别检测中具有较好的应用前景和可行性,该方法也可为定性检测食品及农产品品质提供借鉴。

This paper choose 6 kinds of edible vegetable oils for a total of 23 samples as a typical tested object. Partial Least Squares-Linear Discriminant Analysis（PLS-LDA） method was employed to quickly identify a certain kind of edible vegetable oil（olive oil, peanut oil and corn oil） based on Raman. Raman backgrounds were subtracted by adaptive iteratively reweighted Penalized Least Squares（airPLS） method and wavelength variables were selected by Monte Carlo Uninformative Variable Elimination（MCUVE） method. The above spectra preprocessing not only effectively reduced the wavelength points and modeling computation,but also improved the general recognition rates higher than 90%, respectively. The process of identifying different kinds of edible oil using PLS-LDA method was suggested further on above basis. The experimental results showed that the PLS-LDA method had good application prospects and feasibility to identify edible oil species. This method provided a reference for processing the similar problems in food and agricultural products quality detection.