Physical and chemical indexes of synthetic base oils based on a wavelet neural network and genetic algorithm

摘要

Purpose The purpose of this paper is to use the wavelet neural network and genetic algorithm to study the effects of polyalphaolefin, TMP108 and OCP0016 on the kinematic viscosity, viscosity index and pour point of lubricating oil. Design/methodology/approach Wavelet neural network is used to train the known samples, test the unknown samples and compare the obtained results with those obtained with a traditional empirical formula. Findings It is found that the wavelet neural network prediction value is closer to the experimental value than the traditional empirical formula calculation value. Originality/value The results show that the wavelet neural network can be used to study the physical and chemical indexes of lubricating oil.