^1HNMR-偏最小二乘法-判别法分析椰奶的质量  

Analysis of coconut milk based on ^1HNMR -PLS -DA

作　　者：彭晓姣[1] 杨晓燕[2] 冉坚[1] 刘淼[1] 许浩然[1] 张琦[2] 黄静[1] 

机构地区：[1]四川大学华西药学院,四川成都610041 [2]西南民族大学生命科学与技术学院,四川成都610041

出　　处：《华西药学杂志》2015年第1期81-83,共3页West China Journal of Pharmaceutical Sciences

基　　金：海南省重点科技计划项目(090121);海口市重大科技创新项目(海科工信立[2010]002号)

摘　　要：目的建立一种基于核磁共振-模式识别技术来鉴别椰奶质量的新方法。方法利用1HNMR测定椰奶样品,采集信息并转化成数据矩阵;利用模式识别方法中的PLS-DA法对数据进行分析,并建立鉴别模型。结果 5个厂家的椰奶样品均能获得有效的鉴别,含有添加物的椰奶样品也能有效地与正常椰奶样品鉴别开来。结论所用方法可靠、快速,能有效地鉴别椰奶的品质。OBJECTIVE To establish a new quality control method of coconut milk based on ^1HNMR - PLS - DA. METHODS The ^1HNMR was used for obtaining the data which was transformed into data matrix. And the partial least squares - discriminate analy- sis （PLS -DA） was used to analyze the data and establish the identification model. RESULTS The coconut milk samples from 5 manufacturers were effectively distinguished by ^1HNMR - PLS - DA methods. The samples of coconut milk and the samples containing additives were effectively distinguished by ^1HNMR - PLS - DA methods. CONCLUSION The method of ^1HNMR - PLS - DA is reliable, fast and effective identification for coconut milk.

关 键 词：椰奶 核磁共振 偏最小二乘法-判别分析 鉴别 质量控制 矩阵 添加物 

分 类 号：R917[医药卫生—药物分析学]