Fuzzy–Neural Sliding-Mode Control for DC–DC Converters Using Asymmetric Gaussian Membership Functions

Abstract

A fuzzy-neural sliding-mode (FNSM) control system is developed to control power electronic converters. The FNSM control system comprises a neural controller and a compensation controller. In the neural controller, an asymmetric fuzzy neural network is utilized to mimic an ideal controller. The compensation controller is designed to compensate for the approximation error between the neural controller and the ideal controller. An online training methodology is developed in the Lyapunov sense; thus, the stability of the control system can be guaranteed. Finally, to investigate the effectiveness of the FNSM control scheme, it is applied to control a pulsewidth-modulation-based forward dc-dc converter. Experimental results show that the proposed FNSM control system is found to achieve favorable regulation performances even under input-voltage and load-resistance variations