Self-tuning adaptive neurocontroller for brushless DC motors

Abstract

This paper describes a self-tuning adaptive neurocontroller for brushless DC motors. Nonlinear and unknown motor dynamics are identified by using a multilayer neural network and the control input for the motor is derived from the identified model. The effect of the load torque on the control system is damped by filtering the control input. Simulation and experimental results show that the self-tuning adaptive neurocontrol has a good tracking performance but needs an adaptive filter and a parallel PI controller in the case of disturbances.