ABSTRACTBased on a colorimetric sensor array, five commercial baijiu were analysed by a simple colorimetric artificial nose. Utilizing porphyrin, porphyrin derivatives and chemically responsive dyes as sensitive materials, the sensor array of the artificial nose showed a unique pattern of colorific changes upon its exposure to baijiu. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) were employed to investigate the presence of classes inside the sample and linear discriminant analysis (LDA) was employed to identify baijiu of different fragrances. The results of PCA and HCA analyses suggested that the colorimetric artificial nose might characterize the types of baijiu according to their trace components, rather than the raw materials, fermentation method, manufacturing process and other conditions. The accuracy in terms of the classification of each baijiu flavours using LDA was 100% and confirmed the great potential of colorimetric artificial nose in the detection of baijiu flavour styles. Copyright © 2012 John Wiley & Sons, Ltd.