基于近红外光谱技术的饲料混合均匀度检测  

Mixed Uniformity Determination of Feed Based on Near Infrared Spectrum Technology

作　　者：撖淙武 王春光[1] 

机构地区：[1]内蒙古农业大学机电工程学院,呼和浩特010018

出　　处：《农机化研究》2015年第3期191-194,共4页Journal of Agricultural Mechanization Research

基　　金：国家自然科学基金项目(50865005)

摘　　要：模拟了几种常用饲料原料在卧式混合机中的混合过程,通过美国ASD公司的QualitySpec5070近红外光谱仪全程采集了样本的近红外光谱数据,对样本数据进行了适当的预处理与波段选择,并建立了3种不同的有监督定性分析模型来判别饲料混合均匀状态。结果表明,模型的预测准确率均大于85%,为快速、准确、稳定地检测饲料混合均匀度提供了新的途径。The experiment studied using the near infrared spectrum technology for feed mixing uniformity determination , I have mixed several feed raw materials through the small horizontal mixer and gathered the samples of real -time spectral data , preprocessed the data and made the qualitative analysis of pattern recognition ,then compared the prediction effects of methods .In the end I summed up the three kinds of the data processing methods to provide a feasible and convenient method of feed uniformity testing for future .

关 键 词：近红外 混合均匀度 饲料 SIMCA LDA SVM 

分 类 号：S817.11[农业科学—畜牧学]