采用近红外光谱漫反射模式, 结合简易分类技术（soft independent modeling of class analogy, SIMCA）对不同品牌乳粉进行了分类溯源研究。 实验共采集了四种不同品牌乳粉, 包括光明乳粉54组, 荷兰乳粉43组, 雀巢乳粉33组以及伊利乳粉8组共138组样品的近红外光谱, 通过对预处理后的训练集全谱段数据变量进行主成分分析, 得出前三个主成分的累积方差贡献率为99.07%。 利用SIMCA类建模法建立的乳粉主成分回归模型对预测集乳粉进行分类, 研究结果表明, 光明乳粉、 荷兰乳粉、 雀巢乳粉的识别率分别为78%, 75%, 100%, 拒绝率分别为100%, 87%, 88%。 因此, 近红外光谱结合SIMCA建立的模型具备较好的乳粉品牌溯源能力, 为快速、 准确鉴别乳粉品牌提供了新思路。

Brand traceability of several different kinds of milk powder was studied by combining near infrared spectroscopy diffuse reflectance mode with soft independent modeling of class analogy (SIMCA) in the present paper. The near infrared spectrum of 138 samples, including 54 Guangming milk powder samples, 43 Netherlands samples, and 33 Nestle samples and 8 Yili samples, were collected. After pretreatment of full spectrum data variables in training set, principal component analysis was performed, and the contribution rate of the cumulative variance of the first three principal components was about 99.07%. Milk powder principal component regression model based on SIMCA was established, and used to classify the milk powder samples in prediction sets. The results showed that the recognition rate of Guangming milk powder, Netherlands milk powder and Nestle milk powder was 78%, 75% and 100%, the rejection rate was 100%, 87%, and 88%, respectively. Therefore, the near infrared spectroscopy combined with SIMCA model can classify milk powder with high accuracy, and is a promising identification method of milk powder variety.