Regulation Quality Investigation on Different Plant Model Usage While Neural Network Training for DC Motor Control

Mathematical model of the current control system of a DC motor with independent excitation using the NARMA 2 neurocontroller was built. The task was to carry out a comparative analysis of the operation of a control system based on a neurocontroller using a plant model of varying degrees of sophistication, namely, a complete electrical model of a DC motor with independent excitation, a simplified model built taking into account two time constants, as well as a simple model that takes into account only the mechanical time constant. The neurocontroller was trained using the above plant models. The obtained results were compared with the use of a neurocontroller as a torque regulator.