Adaptive wavelet neural controller design for a DC-DC power converter using an FPGA chip

The DC-DC power converters are widely used; however, the controller design for the DC-DC power converters cannot easily design if the load dynamics vary widely. This paper proposes an adaptive wavelet neural control (AWNC) system for a forward DC-DC power converter. The proposed AWNC system is composed of a neural controller and a robust controller. The neural controller uses a wavelet neural network to online mimic an ideal controller and the robust controller is designed to cope with the approximation error between the neural controller and the ideal controller. A proportional-integral (PI) type parameter tuning mechanism is derived based on the Lyapunov stability theory; thus not only the system stability can be guaranteed but also the convergence of the tracking error can be speeded up. Finally, a comparison among the PI controller, the fuzzy controller, the adaptive neural fuzzy control, the adaptive neuro-wavelet control and the proposed AWNC is made. The experimental results show that the proposed AWNC system is robust with regard to different input voltages and load resistance variations. Key-Words: adaptive control; robust control; sliding-mode control, wavelet neural network; DC-DC power converter.