近红外光谱技术结合变量选择方法定性检测食用植物油中的腐霉利

Qualitative Detection of Procymidone in Edible Vegetable Oils by Near Infrared Spectroscopy and Variable Selection Methods

利用近红外光谱技术对食用植物油中的腐霉利进行定性检测研究。以国家标准规定的腐霉利最大残留限量为界线,将不同腐霉利含量的食用植物油样本分为合格组和不合格组。采用QualitySpec台式近红外光谱仪采集两类样本的光谱,利用无信息变量消除(UVE)和子窗口重排分析(SPA)方法进行波长变量筛选,并应用线性判别分析(LDA)、偏最小二乘-线性判别分析(PLS-LDA)及判别偏最小二乘(DPLS)方法建立两类样本的分类模型。结果表明,近红外光谱技术可以对两类样本进行分类。UVE方法可以有效筛选有用波长变量,提高分类模型的性能。UVE-DPLS所建立的分类模型性能最优,其预测集样本的分类正确率、灵敏度及特异性分别为98.7%,95.0%和100.0%。

In this research,near infrared（NIR）spectroscopy was used to detect procymidone in edible vegetable oils qualitatively.Edible vegetable oil samples with different procymidone contents were classified to two groups according to boundary line of maximum residue limit of procymidone in national standard.QualitySpec spectrometer was used to acquire spectra of two group samples,then uninformative variable elimination（UVE）and subwindow permutation analysis（SPA）were used to select informative wavelength variables.At last,several methods such as linear discriminant analysis（LDA）,partial least squares-linear discriminant analysis（PLS-LDA）and discriminant partial least squares（DPLS）were used to develop classification models.The results indicate that NIR spectroscopy is feasible to classify the two group samples.UVE method can select informative wavelength variables effectively,and improve the performance of classification model.The best model is developed by UVE-DPLS method,the classification correct rate,sensitivity and specificity of prediction samples in this model are 98.7%,95.0%and 100.0%,respectively.