The design of a motor drive based on neural network

The brushless DC motors (BLDC) have been widely applied to the motion control over a wide range of industrial applications because of its superior characteristics of high efficiency, high power density, easy control and maintenance, in recent years. However high performance motor drives require fast and quick speed response caused from system disturbance and parameter variations. In order to obtain the dynamic speed response due to these problems, a PID control method based on a radial basis function neural network (RBFNN) is proposed in this paper. The gain parameters of PID controller are tuned by performing the RBFNN according to the variations of parameters. A prototype of RBFNN based motor drive is designed and implemented in this paper. The experimental results demonstrate the feasibility of the complete designed system.