A self-tuning fuzzy inference sliding mode control scheme for a class of nonlinear systems

A self-tuning fuzzy inference sliding mode control method is presented for single inverted pendulum position tracking control. Sliding mode control is a special nonlinear control method which has a quick response, is insensitive to parameters' variation and disturbance; and is very suitable for nonlinear system control. Neuro-fuzzy logic systems are used to directly generate the equivalent control term. In this case, a neuro-fuzzy system was described as a self-tuning fuzzy inference system optimized online using Takagi-Sygeno type of rules and a back-propagation algorithm to minimize a cost function. The cost function is made up of a quadratic error term and a weight decay term that prevents an excessive growth of parameters. The definition of sliding mode control was presented, and on the basis of the inverted pendulum system the sliding mode controller was designed. Stability of the proposed control scheme is proved by the Lyapunov theorem and the control scheme is applied to an inverted pendulum system. Simulation studies show that the method is effective and can be applied to a nonlinear control system.