期刊
FUEL
卷 87, 期 17-18, 页码 3706-3709出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.fuel.2008.06.016
关键词
Principal component analysis; Infrared; Gasoline
资金
- FINEP/CTPETRO
- CNPq
- CAPES/PROCAD
A set of 160 gasoline samples was collected from commercial stations in five Brazilian states and analyzed by ASTM methods for 13 properties. Principal component analysis (PCA) was employed to investigate the effect of infrared spectral region (near or middle), calibration algorithm (principal component regression, partial least squares or multiple linear regression) and pre-processing procedure (derivative, smoothing and variable selection) in the resulting root-mean-square error of prediction (RMSEP). The PCA score plots revealed that all properties can be satisfactorily predicted by multiple linear regression in the 1600-2500 nm region, with variables selected by a genetic algorithm, using any pre-processing technique. (C) 2008 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据