Artificial intelligent speed controller using RBF method for separately excited dc motor / Azrin Kamaruddin

This paper presents a Radial Basis Function Neural Network (RBFNN) approach to design a separately excited DC motor speed controller, which behaves similar to PI controller. The RBFNN is set up by writing a program to create a 'black box', which will then applied to MA TLAB-SIMULINK. A closed-loop system is used for testing. From the results obtained it shows that RBFNN is an alternative controller to replace the PI controller.