Artificial Neural Networks Implementation in Ethylbenzene Oxidation Data Processing

Abstract

An intelligent system for processing data of liquid-phase oxidation reactions for an industrial method of obtaining valuable oxygen-containing compounds has been developed. The scheme is based on a multilayer artificial neural network for digital signal processing. Clear simulations on the effect of the catalytic system and catalytic additives used in the process of ethylbenzene oxidation on the concentrations and selectivity for hydroperoxide of ethylbenzene, acetophenone, methyl phenyl carbinole, were obtained and analyzed for different catalysts by the means of an artificial neural network. The obtained predictions allow experimenters to select the most promising direction during the determination for the concentration of active catalytic substances.