A real-time neural network based controller for brushless DC motor drives

In this paper, a high performance controller with simultaneous real-time identification and control is developed for brushless DC motors. The dynamics of the motor are modelled "on-line", and controlled using a three layer feedforward artificial neural network, as the system runs. The control architecture adapts to the uncertainties of the motor dynamics and, in addition, learns their inherent nonlinearities. Extensive simulation studies were conducted and good performance of the brushless DC motor to follow a number of reference tracks was observed. The simulations illustrated that a neuro-controller used in conjunction with adaptive control schemes can result in a flexible control device which may be utilized in a wide range of environments.