Robust neuro-fuzzy controller design via sliding-mode approach

The computed torque or inverse dynamics control techniques are based on a good understanding of the system dynamics and even its environment. For the real-time applications, the system dynamics is always difficult to obtain. To tackle this drawback, the goal of this paper is to develop a model-free control method which is referred to as the robust neuro-fuzzy sliding-mode control (RNFSMC) system. The proposed RNFSMC system is comprised of a fuzzy controller and a robust controller. The fuzzy controller is utilized to approximate an ideal controller by the developed tuning algorithms, and the robust controller is designed to achieve H^∞ tracking performance index. To investigate the effectiveness of the proposed RNFSMC system, it is applied to control a Chua´s chaotic circuit system. Finally, simulation results demonstrate that the effect of the fuzzy approximation error on the tracking error can be attenuated efficiently by the proposed method without any knowledge of the controlled systems.