基于红外光谱和PLS-DA掺杂牛奶判别方法研究

Discrimination of Adulterated Milk Based on Infrared Spectroscopy and Partial Least Square Discriminate Analysis

将红外光谱与偏最小二乘判别法（PLS-DA）结合起来对掺杂牛奶与纯牛奶进行判别分析。分别配置含有不同浓度三聚氰胺（0．02-1g／L）和蔗糖（0．1-12g／L）的牛奶溶液。采集了所有样品的红外光谱，在研究掺杂牛奶与纯牛奶红外光谱特性的基础上，选择1200-1800cm。波段为建模区间，分别建立掺杂三聚氰胺牛奶与纯牛奶、掺杂蔗糖牛奶与纯牛奶及其两种掺杂牛奶与纯牛奶的PLS—DA判别模型。各模型对未知样品的判别正确率分别为93．3％、86．7％、83．3％。研究可用于掺杂牛奶的快速判定或初筛，对于维护乳制品市场稳定，保护消费者权益具有非常重要的意义。

Abslract Infrared spectrometry and partial least square discriminate analysis （PLS-DA） were used to investigate the adulteration of milk. Firstly, pure milk samples and adulterated milk samples added different concentrations of melamine （0.02-1 g/L） and cane sugar （0.1-12 g/L） were prepared. Then, the infrared spectra of the pure and adulterated milk samples were measured and the characteristic was studied. At last, the PLS-DA calibration models of melamine-tainted milk and pure milk, cane sugar-tainted milk and pure milk, and two types adulterated milk and pure milk were constructed respectively in the range of 1 200-1 800 cm^-1. The results showed the correct prediction rates were 93.3%, 86.7%, 83.3%, respectively. The method can be used for fast discrimination on whether the milk is adulterated, which is meaningful for the maintenance of the dairy market stability and the protection of consumers＇ interests.