Design of an intelligent exponential-reaching sliding-mode control via recurrent fuzzy neural network

In the presence of modeling inaccuracy, which may have strong adverse effects upon system performance, the sliding-mode control (SMC) can provide a closed-loop system dynamics with an invariance property to uncertainties. This study proposes an intelligent exponential-reaching sliding-mode control (IERSMC) system which provides faster convergence and higher tracking precision. The proposed IERSMC system is composed of a linearization controller and an exponential compensator. The linearization controller including a recurrent fuzzy neural network (RFNN) approximator is the main controller and the exponential compensator is designed to eliminate the effect of the approximation error introduced by the RFNN approximator upon system stability. Finally, the proposed IERSMC system is applied to an inverted pendulum to show its effectiveness. The simulation results demonstrate that the proposed IERSMC system can achieve favorable performance for tracking control problem.