Speed Control of SEDC Motor Using Artificial Neural Network

Abstract

This project designed the speed control of a separately excited direct current (DC) motor by using an Artificial Neural Network (ANN). Any conventional controller such as proportional-integral (PI) can be used to control the speed of a DC Motor. However, the limitation of the conventional controller in controlling the speed of the dc motor is inaccuracy in the ability to obtain the actual speed and maintain the stability of the motor speed in the dynamic condition. Thus, the ANN controller had been introduced to solve the problem involving the limitation of another conventional controller. The neural network is used in this project to control or estimate the motor speed by training the neural network and getting the desired result using MATLAB/SIMULINK software. In this project, the ANN has proven its ability to control motor speed compared to the PI controller effectively and has good performance in a nonlinear system. The simulation results show the advantages and efficiency of an ANN with minimum speed error which is approximately zero rpm.