近红外光谱的主成分分析——马氏距离分类法应用于品牌卷烟烟丝的快速鉴别

Rapid Identification of Different Cut Tobacco by the Classification of Principal Component Analysis-Mahalanobis Distance Combined with Near-Infrared Spectroscopy

研究了对成品卷烟烟丝进行快速分类鉴别的一种方法。利用傅里叶变换近红外光谱对国内部分不同品牌的卷烟烟丝主成分进行分析,应用主成分分析——马氏距离法分类建模,结果建立了两个不同的近红外光谱判别分类模型,一个用于同一厂家生产的3个品牌成品卷烟的分类鉴别,另外一个用于云南省某知名品牌卷烟同省外同一价位的6个知名品牌卷烟的判别分类鉴别。两个模型对校验集烟丝的类归属的正确率为100%,该研究方法对成品卷烟烟丝能够进行快速、准确的定性鉴别。

Rapid identification of different cut tobacco was studied by a new method. Two models of cut tobacco were established by the classification of principal component analysis （PCA） -Mahalanobis distance combined with near-infrared spectroscopy which had been applied to identify different cut tobacco. Many unknown samples were identified successfully by the two discriminating models. The recognition rate was 100%. This model was reliable. So this study can offer a new approach to the rapid identification of varieties of cut tobacco.