食品科学 ›› 2012, Vol. 33 ›› Issue (12): 154-158.doi: 10.7506/spkx1002-6630-201212030

• 分析检测 • 上一篇    下一篇

近红外光谱法鉴别奶牛饲料中三聚氰胺甲醛树脂的可行性研究

刘 星1,单 杨1,2,3,*,张 欣1,杨桂森4   

  1. 1.中南大学研究生院隆平分院 2.湖南省食品测试分析中心 3.湖南省农产品加工研究所 4.中国科学院上海应用物理研究所
  • 出版日期:2012-06-25 发布日期:2012-07-27
  • 基金资助:
    “十一五”国家科技支撑计划项目(2009BADB7B07);中南大学学位论文创新资助项目(2010ssxt256)

Feasibility Study of Identifying Melamine-Formaldehyde Resin in Cow Feed by Near Infrared Spectroscopy

LIU Xing1,SHAN Yang1,2,3,*,ZHANG Xin1,YANG Gui-sen4   

  1. (1. Longping Branch, Graduate School, Central South University, Changsha 410125, China;2. Hunan Food Testing and Analysis Center, Changsha 410125, China;3. Hunan Agricultural Product Processing Institute, Changsha 410125, China; 4. Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201800, China)
  • Online:2012-06-25 Published:2012-07-27

摘要: 收集国内常用的、具有代表性的奶牛精补料33个样品,制备99个三聚氰胺甲醛树脂(MF)掺假样品,在全光谱范围内进行近红外透反射光谱扫描,选择合适的前处理方法,采用BP神经网络方法和PLS-LDA方法分别建立判别模型。建立的BP神经网络判别分析模型的预测正确率为100%,建立的PLS-LDA判别分析模型的交互验证最低错误率为0.0778,模型错分率为0.0667,模型预测错误率为0.1429。说明利用近红外透反射光谱建立定性分析模型来检测奶牛饲料中是否掺有MF的研究是可行的。

关键词: 奶牛饲料, 三聚氰胺甲醛树脂, 近红外光谱, BP神经网络, PLS-LDA

Abstract: Thirty-three samples of typical cow feed concentrate supplement without melamine-formaldehyde resin (MFR) and 99 ones adulterated with different concentrations of MFR were subjected to full wavelength near-infrared transmission and reflectance spectroscopic scanning. A discrimination model was established by BP (back propagation) neural network or PLS-LDA (partial least squares-linear discriminant analysis). The BP neural network model showed 100% accurate prediction. The minimum cross validation error rate of the PLS-LDA model was 0.0778, misclassification rate 0.0667, and prediction error rate 0.1429. Therefore, it is feasible to establish a predictive model for detecting MFR adulteration in cow feed by means of near-infrared transmission and reflectance spectroscopy.

Key words: cow feed, melamine-formaldehyde resin, near infrared spectroscopy, back propagation(BP) neural network, partial least squares-linear discriminant analysis (PLS-LDA)

中图分类号: