Neural network model of the process of supercritical water oxidation of utilization of industrial effluent water

Abstract

In order to create a complex of control and prediction of optimal reaction conditions with a minimum value of chemical oxygen demand, a neural network model of supercritical water oxidation of industrial effluent water utilization process of hydroperoxide epoxidation of propylene at PJSC “Nizhnekamskneftekhim” was created. A full application Windows Forms, which implemented functions of loading a training sample from a file, setting the necessary training accuracy, entering a vector for obtaining results of neural network operation and graph plotting, was created.