Modeling of the belt conveyor control system using artificial intelligence methods

Abstract

The paper is devoted to the development of instrumental and methodological support for the study of conveyor transport systems with intelligent control mathematical models. An optimal control model is constructed for a belt conveyor with a dynamic change in the angle between the horizontal plane and the belt plane. Methods for studying the belt conveyor model based on the design of PID controllers and neural network controllers are proposed. The results of computational experiments using the training of a feedforward neural network and the use of reinforcement learning are presented. A comparative analysis of computational experiments with the use of control based on the synthesis of a fuzzy controller, control using artificial neural networks, and control based on a PID controller is performed. The obtained results can be used in neural network modeling of complex systems and in solving problems of automation of technological and production processes.