Speed Control of Separately Excited DC Motor Using NARMA-L2 Controller

An Intelligent Neural Network (NN) based nonlinear Autoregressive-moving average (NARMA-L2) Controller is developed for speed control of separately excited D.C. Motor by performing the features of Artificial Neural Networks (ANN). The aim of the proposed approach is to improve tracking performance of separately excited D.C. motor as compared to the conventional (PI) control approach. Performance Comparison of SEDM for NARMA-L2 controller and the conventional PI controller is also discussed. The entire speed control mechanism for SEDM is modelled by using the MATLAB 8.0 toolbox. The intelligent NARMA-L2 controller is operated in two steps: - the first, the variations in external loads is performed to check the speed control performance of NARMA-L2. The second, the controller is operated at various reference speed. Simulation results shows the effectiveness, advantages and good performance of the NARMA-L2 which is described through the comparison of conventional PI controller and NARMA-L2 controller. Excellent results added to the simplicity of the drive system, makes the ANN based NARMA-L2 controller strategy very suitable for a wide range of applications such as industries, paper mills etc.