Sliding mode recurrent wavelet neural network control for robust positioning of uncertain dynamic systems

Abstract

For an uncertain dynamic system, a hybrid control system composed of sliding mode and recurrent wavelet neural network control with friction estimation (SRWNF) has been proposed to achieve robust motion performance. In the present study, a model-free adaptive controller that does not require the system dynamics to be determined in advance is developed by the proposed recurrent wavelet neural network (RWNN). The adaptive laws of the SRWNF control system and friction estimator have been constructed from the approximation theory and the sense of the Lyapunov stability analysis for RWNN technology to mimic ideal control laws in a sliding-mode control. In addition, an adaptive bound estimation law is employed to estimate the upper boundary of approximation errors. The friction state and parameters are estimated using an adaptive friction estimation based on the LuGre friction model. The boundary of the constraint sets has also been studied. The performance of the proposed control scheme in the presence of uncertainty and friction has been verified by some simulation and an experiment.