基于质谱与支持向量机的清香型白酒等级判别

Quality grade discrimination of light aroma type liquor based on mass spectrometry and support vector machine

不同等级白酒鉴别对控制白酒质量和保护消费者利益有重要意义,文中以牛栏山酒为例,研究清香型白酒质量等级鉴别方法。运用顶空固相微萃取质谱（HS-SPME-MS）技术获取三类不同等级的57个牛栏山酒样质荷比m/z55~191范围内的离子丰度值数据,分别进行偏最小二乘回归分析（PLS）和主成分回归分析（PCR）,其中PLS模型的预测结果明显优于PCR。同时PLS与PCR模型的回归系数用于选择重要特征离子,其中PLS与PCR回归系数法分别选择了12和10个离子,用选择的离子变量构建支持向量机（SVM）模型,模型对测试集的预测准确率分别为80%和86.7%,其中PCR回归系数法选择的特征离子为m/z 71、103、104、106、127、149、161、179、183和184。

Quality grade discrimination of Chinese liquor was benefit for controlling liquor quality and safeguarding the interests of consumers. In this paper,taking Niulanshan for instance,we studied quality grade discrimination of Chinese liquor with light aroma type. Mass spectra of 57 samples were obtained by head space-solid phase microextraction-mass spectrometry（HS-SPME-MS） technology in the range of m/z 55~191. And then,the partial least squares regression（PLS） and principal component regression（PCR） models were developed by calibration set and predicted the quality grade of validation set. Obviously PLS model was superior to PCR model. The support vector machine（SVM） models were built by different ion selection methods,PLS regression coefficients and PCR regression coefficients;the prediction accuracy of SVM models for the test set was 80%and 86.7%,respectively. The ions,m/z 71,103,104,106,127,149,161,179,183 and 184 were selected by PCR regression coefficients.