RESEARCH OF AN INTELLIGENT ADAPTIVE CONTROL ALGORITHM BASED ON THE REINFORCEMENT LEARNING METHOD

An algorithm for adaptive control of a DC motor based on the use of machine learning technologywith reinforcement is proposed and investigated. An overview and brief analysis of the state of affairs inthe field of intelligent motor control systems is given. A mathematical model of the DC motor is presented,and a structural scheme for training an intellectual agent is presented. An intelligent adaptive motor speedcontrol system is proposed. The DC motor is represented as a black box with the limited input and output.The control system is based on a zero-order Q-learning algorithm. It is assumed that the output of theintelligent agent is a control applied to the motor input. The intelligent system uses a tabular approximationof the value of each of the control action. In this article, we study the effect of the discreteness of therepresentation of state, the set of control effects used, the applied rewards, and the parameters of thelearning algorithm on the control error. The sensitivity of the control system to the parameters of the motorand an unmeasured moment is investigated. Based on the results of the study, a modified algorithm isproposed, which assumes the measurement or evaluation of the current of the motor stator. The controlalgorithm provides robustness to parameters and external disturbance. Additionally, the approximation ofthe control value function using polynomials and using a neural network are investigated