Controller design using Walsh-basis-function neural networks

This paper investigates the function approximation problem using Walsh functions to establish a Walsh-basis-function neural network (WBFNN). The proposed novel system avoids the possible heavy computation problem usually existed in the adaptive-neural-based controller design. With the developed adaptation scheme combined with sliding mode control strategy, the proposed WBFNN-based controller can guarantee the global stability of the closed-loop system in the Lyapunov sense and then the tracking error converges to zero asymptotically for a class of nonlinear systems. Simulation validations for a nonlinear unstable system are finally performed to verify the effectiveness of the proposed controller design