Sliding mode with neuro-fuzzy network controller for inverted pendulem

Abstract

In this paper, we try to present a sliding mode with fuzzy-neural network controller for nonlinear systems. It is a special nonlinear control method (SMC) which has quick response, insensitive to parameters variation and disturbance. Online identification for plants is not needed, it's very suitable for nonlinear system control, but in reality using the chattering reduction and elimination are key problem in SMC. By using a function-augmented sliding hyper plane, it is guaranteed that the output tracking error converges to zero in finite time which can be set arbitrarily. The fuzzy-neural network mainly Self Tuning Fuzzy Inference System (STFIS) is used to approximate the unknown system functions and switch item. Finally, the sliding-mode with fuzzy-neural network control is used to control single inverted pendulum and confirms the validity of the proposals. Results of simulations containing tests of robustness are presented and realized in MATLAB environment.