Development of a Neural Network for a Boiler Unit Generating Water Vapour Control

Abstract

This article raises the question of neural networks application to control a boiler unit as a multidimensional system. The use of neural networks for managing technological processes helps to solve the problems of the operation of a complex control system, it improves its fail safety. The article proposes to apply a neural network to solve these problems. Technological process as a multidimensional system has been studied and described, the algorithm of the boiler has been described, neural network for controlling a boiler designed to produce water vapour under pressure has been developed, trained and tested. Development, training and testing of the neural network was carried out in Matlab program.