Speed Control of Permanent Magnet D.C. Motor Using Neural Network Control

Abstract

This paper proposes the speed control of a permanent magnet direct current(PMDC) motor by varying armature voltage. The objective is to control therotor angular speed to follow the desired value. The main feature of theproposed controller is neural network, which captures the nonlinearity system ofthe motor. Neural network (NN) performance is compared with theconventional controller performance like PI (Proportional-Integral) controller toshow that NN performance is excellent. Numerous work reported in recent pasthave shown that Artificial Neural Network (ANN) controller has a potential toreplace the conventional PI controller. Artificial Neural Network controlapparently offers a possibility of obtaining an improvement in the quality of thespeed response, compared to PI control. This research proposes NARMA-L2(Nonlinear Autoregressive-Moving Average) as an improved ANNtechnique,and trained as a close loop controller, which gives an ideal performance ascompared with PI controller to control the angular speed of rotor in a permanentmagnet dc (PMDC) motor. Simulation results show the effectiveness of theproposed control scheme.The entire system has been modeled using MATLABtoolbox.