摘要
运用气相色谱法对6类植物油(大豆油、花生油、茶籽油、菜籽油、玉米油、橄榄油)的脂肪酸组成进行分析,构建植物油的指纹图谱,对植物油进行鉴别和分类。本工作采用遗传-偏最小二乘法(GA-PLS)筛选出7个有效特征变量作为输入变量,采用主成分分析法(PCA)和有监督模式识别法(径向基函数神经网络(RNF-ANN),线性判别分析(LDA)和最小二乘-支持向量机(LSSVM))进行建模分析。结果表明,PCA能够较好地区分六类植物油,而在植物油种类判别分析中,LDA的预报结果最佳。本文提出的方法能够准确直观地区分植物油种类,可用于食用植物油的鉴别和掺杂食用植物油的鉴定。
Gas chromatography （GC） was used to determinate the composition and contents vegetable oils, including soybean oil, peanut oil, tea seed oil, rapeseed oil, corn oil and olive of fatty acids in oil, and the GC fingerprint profile was employed for the species classification of the 6 vegetable oils. Based on the fatty acid analysis, feature variables were selected by applying genetic algorithm-partial least squares （GA-PLS） regression. Then, principal component analysis （PCA） and 3 types of supervised pattern recognition models, radial basis function artificial neural natwork （RBF-ANN） , least square-support vector machine （LS-SVM） and linear discriminant analysis （LDA） , were established to predict the vegetable oils. The results demonstrated that a clear clustering of object respect to the species was obtained by PCA. LDA model with classification rate of 97.8% perfected better than the other two models. The method could be used to distinguish the species of vegetable oils, and might be applicable for the identification of edible vegetable oils
出处
《分析试验室》
CAS
CSCD
北大核心
2016年第11期1254-1258,共5页
Chinese Journal of Analysis Laboratory
基金
广东省省级科技计划项目(2013B091603005)
广东省省级科技计划项目(2014A040401032)资助
关键词
植物油
橄榄油
气相色谱
指纹图谱
化学计量学
Vegetable oils
Olive oil
Gas chromatography
Fingerprint
Chemometrics
