本文采用近红外光谱技术,结合SIMCA模式识别技术,研究区分花生油、大豆油、棉籽油、菜籽油、米糠油、芝麻油以及棕榈油等七种植物油脂的测定方法。以植物油脂的光谱信息作变量,应用NIR Cal 5.2软件的SIMCA分析技术进行数据分析,并讨论如何通过采用光谱与处理方法来提高模式识别技术(SIMCA)的分类判别效果。研究了不同来源的七种植物油脂168个样品的近红外透射光谱,随机取2/3的样品作训练集,1/3作验证集。结果显示,SIMCA可以对七种植物油脂分别聚类并识别,主成分数分别为9、5、8、5、6、2和9时,各种油脂的SIMCA分析的聚类精度均为100%,验证准确率100%。
【英文论文摘要】
In this work,an analytical procedure SIMCA was developed to discriminate and analysis 168 vegetable oil and fat using near-infrared(NIR)spectroscopy and pattern recognition.SIMCA and spectra pretreated using the cluster technique of NIR Cal 5.2 were able to classify the samples as pure oil and fat based on their transmission spectra.The spectra information as variance was used in the processing of spectra pretreated.The results showed that seven models were found when 9,5,8,5,6,2 and 9 principal components ...
| 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
