Using principal component analysis to find the best calibration settings for simultaneous spectroscopic determination of several gasoline properties

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 compo...

Full description

Saved in:
Bibliographic Details
Published in:Fuel (Guildford) 2008-12, Vol.87 (17), p.3706-3709
Main Authors: Honorato, Fernanda Araújo, Neto, Benício de Barros, Pimentel, Maria Fernanda, Stragevitch, Luiz, Galvão, Roberto Kawakami Harrop
Format: Article
Language:English
Subjects:
Applied sciences
Crude oil, natural gas and petroleum products
Energy
Exact sciences and technology
Fuels
Gasoline
Infrared
Petroleum products, gas and fuels. Motor fuels, lubricants and asphalts
Principal component analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0016-2361
1873-7153
DOI:10.1016/j.fuel.2008.06.016