A combined backstepping and wavelet neural network control approach for mechanical system

A combined backstepping and wavelet neural network control approach for mechanical system is proposed in this paper. The proposed control approach comprises a neural controller and a robust compensator. The neural controller using a wavelet neural network (WNN) is the main controller based on backstepping method; and the parameters of WNN are on-line tune by adaptation laws from the Lyapunov stability theorem. The robust compensator is designed to dispel the approximation error, so the asymptotic stability of the system can be guaranteed. Finally, a mass-spring-damper system is performed to verify the effectiveness of the proposed control scheme.