The brushless DC (BLDC) motor has the advantages including simple to construct, high torque capability, small inertia, low noise and long life operation. Unfortunately, it is a non-linear system whose internal parameter values will change slightly with different input commands and environments. In this paper, an adaptive fuzzy wavelet neural control (AFWNC) system which is composed of a neural controller and a robust controller is proposed. The neural controller uses a fuzzy wavelet neural network (FWNN) to online mimic an ideal controller, and the robust controller is designed to dispel the effect of minimum approximation error introduced by the neural controller. The controller parameters tuning algorithms of the AFWNC system are derived based on the Lyapunov stability theorem and gradient decent method. Finally, the hardware implementation of the AFWNC scheme is developed on a field programmable gate array (FPGA) chip in a real-time mode. A comparison among the fuzzy sliding-mode control, the adaptive wavelet neural control and the proposed AFWNC is made. Experimental results verify that a favourable tracking response can be achieved by the proposed AFWNC method even under the change of position command frequency after training of FWNN.
International Journal of Advanced Mechatronic Systems 2(5/6), pp.297-305