基于电子舌的白酒检测与区分研究

Detecting and Classification of Wine Using an Electronic Tongue

白酒是重要的饮品,为了对不同品牌与档次的白酒进行等级区分,测试了市售的同一档次不同品牌的银剑南、泰山特曲、茅台国典白酒和同一品牌不同档次的伊力特曲、伊力特(五年陈)、伊力老陈酒(十年陈)白酒对α-Astree电子舌传感器的响应信号,并采用主成分分析法、判别因子分析法对响应信号分析。结果表明,电子舌传感器对同一档次不同品牌的银剑南、泰山特曲、茅台国典白酒的响应信号有明显区别,对同一品牌不同档次的伊力特曲、伊力特(五年陈)、伊力老陈酒(十年陈)的响应信号变化较小;主成分分析法和判别因子分析法既能够区分同一档次不同品牌的银剑南、泰山特曲、茅台国典白酒,也能够区分同一品牌不同档次的伊力特曲、伊力特(五年陈)、伊力老陈酒(十年陈)白酒,且判别因子分析法的区分效果优于主成分分析法。

In order to distinguish different brand and grade wine, response signals of some kinds of wine to α- Astree electronic tongue were detected. The excremental samples include different brand wine with the same grade such as Ymjiannan, Taishantequ, Maotaiguodian and different grade wine with the same brand such as Yilitequ, Yilite and Yililaoehen. Principal component analysis （PAC）and distinguish factor analysis diseriminant factorial analysis （DFA）were employed as data treatment. Classification experimental results show response signals of electronic tongue to different brand wine with the same grade such as Yinjiannan, Taishantequ, Maotaiguodian are distinguished obviously, while the changes is not apparent to different grade wine with the same brand such as Yilitequ, Yilite and Yililaochen. It also indicates that the principal component analysis can be applied to classify different brand wine with the same grade and different grade wine the same brand, so is the distinguish factor analysis. Moreover the classification effect of the latter are more super than that of the former.