光学精密工程
 
     首 页 |  期刊介绍  |  编委会  |  投稿指南  |  期刊订阅  |  联系我们  |  留言板 |  English
光学精密工程 2000, 8(3) 238-241  ISSN: 1004-924X CN: 22-1198/TH

本期目录 | 下期目录 | 过刊浏览 | 高级检索                                                            [打印本页]   [关闭]
光谱分析与光谱测量  
PLS定标法在近红外光谱分析仪中的应用研究
张玲
中国科学院长春光学精密机械与物理研究所科技总公司, 吉林 长春 130021
摘要: 近红外光谱分析仪在农产品、水质监测和石油等许多领域有广泛的应用.这是一种在线实时分析仪器.光谱分析仪的定量分析有许多种方法.PLS(PartialLeast-Squares)法是在传统的多元线性回归的基础上发展起来的一种回归方法.文中针对40种烟草样品的红外光谱数据分别采用PLS回归法和MLR(Multiple Linear Regression)回归法进行分析.两种回归方法的结果与样品的化学位对比,表明PLS法是一种比较好的多变量定标方法,比较适合于实时在线定标分析.
关键词 近红外光谱分析仪   PLS方法   定量光谱分析  
Partial least-squares method for calibration with NIR spectrophotometer
ZHANG Ling
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130021, China
Abstract: Near Infrared Reflectance(NIR)spectrophotometer is widely used in analyzing grains, water and oil. The spectrophotometer is able to analyze without destroy the chemical property of sample. There are many methods in its quantitative spectral analyses. Partial Least Squares(PLS)method is a good alternative to the more classical multiple linear regression. 40 tobacco sample data are described to illustrate the spectrophotometer calibration on PLS regression and Multiple Linear Regression(MLR). The result is related to calibration in chemical analysis. The values of components from PLS method is more precise than that from MLR method. It is proved that the PLS regression is a powerful multivariate calibration method and more suitable to the on-line or real-time analysis.
Keywords: NIR spectrophotometer   partial least-squares method   quantitative calibration methods  
收稿日期 1999-12-15 修回日期 2000-02-22 网络版发布日期 2000-06-15 
基金项目:

通讯作者:
作者简介:
作者Email:

参考文献:
[1] Norris K H, Williams P C. Optimization of mathematical treatments of raw near-infrared signal in the measurement of protein in hard red spring wheat. Ⅰ. influence of particle size[J]. Cereal Chemistry, 1984, 61(2): 158-165.
[2] Geladi Paul, Kowalski Bruce R. Partial least-squares regression: a tutorial[J]. Analytica Chimica Acta,1986, 185: 1-17.
[3] Geladi Paul, Kowalski Bruce R. An example of 2-block predictive partial least-squares regression with simulated data[J]. Analytica Chimica Acta, 1986, 185: 19-32.
[4] Haaland David M. Thomas Edward V. Partial least-squares methods for spectral analyses. 1. relation to other quantitative calibration methods and the extraction of qualitative information[J]. Anal. Chem., 1988, 60: 1193-1202.
[5] Mcshane Michael J, Cote Gerard L, Spiegelman Clifford H. Assessment of partial least-squares calibration and wavelength selection for complex near-infrared spectra[J]. Applied Spectroscopy, 1998, 52(6): 878-884.
本刊中的类似文章

Copyright by 光学精密工程