Study on the Gasoline Classification Methods Based on near Infrared Spectroscopy

Abstract

The purpose of this paper is to classify 93# and 97# gasoline by using principal component analysis (PCA) with self-organizing competitive neural network method and to establish near infrared transmission spectroscopy and reflectance spectroscopy qualitative identification model in 1100-1700nm spectral region. The spectral data is condensed by PCA method before modeling, and three principal components are chosen because their cumulative credibility has reached 97%. A three-layer self-organizing competitive neural network model is established based on the PCA method. Thirty-two wavelengths' absorbance is served as inputs of the self-organizing competitive neural network. The learning parameter is set as 0.01 and the training iteration is taken as 500. The conclusion is that it is feasible to apply near infrared transmission spectroscopy and reflectance spectroscopy qualitative identification model to discriminate the gasoline products as the PCA and self-organizing competitive neural networks method is used.