Fuzzy NEURAL NETWORK OBSERVER-BASED ADAPTIVE SLIDING MODE CONTROL FOR THE TWO-LINK ROBOT

Abstract

In this paper, an observer based on Fuzzy Neural Network (FNN) is combined with sliding mode to design an adaptive robust controller without chattering problems for the two-links robot with unknown dynamics and external disturbances. The adaptive fuzzy logic and neural network approaches are used to approximate the unknown models of the MIMO robot system. The observer design is based on the resulting improved model. Moreover the auxiliary sliding mode control term is included in the control law to attenuate respectively the FNN approximation errors and the external disturbances. The stability of the system is provided by the Lyapunov approach. The simulation results demonstrate the efficiency and robustness of the proposed control scheme