Adaptive Control of Servo Systems with Uncertainties Using Self-Recurrent Wavelet Neural Networks

In order to solve the control problem for servo system with model uncertainties, a robust control method is proposed. The proposed controller is a combination of an adaptive backstepping technique and a self-recurrent wavelet neural network (SRWNN). The SRWNN is used to observe the model lumped uncertainties of servo systems. Moreover, a robust controller is designed to compensate the lumped uncertainties including approximation error, high-order terms in Taylor series, external disturbances, LuGre friction and model parameters. From the Lyapunov stability analysis, the weights adaptation laws are derived, and the uniformly ultimately boundedness of all signals in a closed-loop adaptive system is proved. Finally, simulation results are utilized to validate the good position tracking performance and robust against uncertainties.