INVESTIGADORES
BOSCHETTI Carlos Eugenio
artículos
Título:
A new genetic algorithm applied to the near-infrared analysis of gasolines
Autor/es:
CARLOS EUGENIO BOSCHETTI; ALEJANDRO OLIVIERI
Revista:
JOURNAL OF NEAR INFRARED SPECTROSCOPY
Editorial:
NIR Publications Ltd
Referencias:
Lugar: London; Año: 2004 vol. 12 p. 85 - 91
ISSN:
0967-0335
Resumen:
A new genetic algorithm is presented for wavelength selection, in order to predict the octane number and the content of benzene, toluene and total aromatics in gasolines, based on partial least-squares multivariate calibration of near-infrared spectral data. The algorithm separately labels each of the selected wavenumber ranges with a relative inclusion ranking. Overfitting is conveniently handled without preparing independent test sample sets. Relative prediction errors achieved after sensor selection are: octane number, 0.5%, benzene, 0.6%, toluene, 0.6% and total aromatics, 1.1%. The results are compared with those provided by the standard research method and gas chromatography.