Advanced
search

To read this content please select one of the options below:

Using genetic algorithms to improve support vector regression in the analysis of atomic spectra of lubricant oils

Carlos Fernandez-Lozano (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)
Francisco Cedrón (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)
Daniel Rivero (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)
Julian Dorado (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)
José Manuel Andrade-Garda (Analytical Chemistry Department, University of A Coruña, A Coruña, Spain)
Alejandro Pazos (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)
Marcos Gestal (Information and Communications Technologies Department, University of A Coruña, A Coruña, Spain)

Engineering Computations

ISSN: 0264-4401

Article publication date: 13 June 2016

148

Abstract

Purpose

The purpose of this paper is to assess the quality of commercial lubricant oils. A spectroscopic method was used in combination with multivariate regression techniques (ordinary multivariate multiple regression, principal components analysis, partial least squares, and support vector regression (SVR)).

Design/methodology/approach

The rationale behind the use of SVR was the fuzzy characteristics of the signal and its inherent ability to find nonlinear, global solutions in highly complex dimensional input spaces. Thus, SVR allows extracting useful information from calibration samples that makes it possible to characterize physical-chemical properties of the lubricant oils.

Findings

A dataset of 42 spectra measured from oil standards was studied to assess the concentration of copper into the oils and, thus, evaluate the wearing of the machinery. It was found that the use of SVR was very advantageous to get a regression model.

Originality/value

The use of genetic algorithms coupled to SVR was considered in order to reduce the time needed to find the optimal parameters required to get a suitable prediction model.

Keywords

Citation

Fernandez-Lozano, C., Cedrón, F., Rivero, D., Dorado, J., Andrade-Garda, J.M., Pazos, A. and Gestal, M. (2016), "Using genetic algorithms to improve support vector regression in the analysis of atomic spectra of lubricant oils", Engineering Computations, Vol. 33 No. 4, pp. 995-1005. https://doi.org/10.1108/EC-03-2015-0062

Publisher

:

Emerald Group Publishing Limited

Copyright © 2016, Emerald Group Publishing Limited

Related articles

Manage cookies

We’re listening — tell us what you think

Join us on our journey