基于可视化传感阵列的葡萄酒产地鉴别方法

A colorimetric sensor system for identification of different original wine

模拟哺乳动物的嗅觉系统构建了一种对葡萄酒敏感的可视化传感阵列,阵列由13种卟啉化合物和23种染料构成。采用构建的传感阵列对8种不同产地、酒精度为12%的赤霞珠干红正品进行检测,获得了不同产地葡萄酒的可视化指纹图谱。以阵列反应前后的光谱变化数据作为特征值,选用合适的化学计量学方法,取得了较满意的区分效果。用主成分分析获得的前两个主成分所代表的葡萄酒44%的信息量可以将不同产地的葡萄酒完全区分开,8种不同产地的葡萄酒在聚类分析中均能正确归类,建立的判别函数对预测样本的正确判别率达100%。该可视化阵列传感器在葡萄酒产地溯源上有潜在的应用价值。

The typicality and flavor of wine are highly related to their geographic origins, and regarded as a major factor to determine the quality of wine. Eight commercial Cabernet Sauvignon dry red wines （with 12% alcohol） from different regions in china have been analyzed in gas phase using colorimetric sensor arrays that simulated the mammalian olfactory system. The array was made from 13 prophyrin derivatives and 23 dyes printed on a hydrophobic membrane. Digital imaging of the colorimetric sensor array before and after exposure to the Cabernet Sauvignon dry red wines in the gas phase provided a color change profile as a unique fingerprint for the complex analytes. Data analysis was performed by statistical and chemometrics techniques：principal component analysis （PCA）, hierarchical clustering analysis （HCA）, and also linear discriminant analysis （LDA）. The same origin of wines could cluster together and different origin wines could distinguish from each other by the first two principal components obtained from PCA, which only represent 44% of the amount of wine information. No error in classi？ cation by HCA was observed in 40 trials. LDA model showed a 100% of prediction ability for wine from different origins. These results indicate that the colorimetric sensor array may be proved to be useful for the identification of wine with different origins.