Intelligent nonsingular terminal sliding-mode control via perturbed fuzzy neural network

Abstract

In this paper, an intelligent nonsingular terminal sliding-mode control (INTSMC) system, which is composed of a terminal neural controller and a robust compensator, is proposed for an unknown nonlinear system. The terminal neural controller including a perturbed fuzzy neural network (PFNN) is the main controller and the robust compensator is designed to eliminate the effect of the approximation error introduced by the PFNN upon the system stability. The PFNN is used to approximate an unknown nonlinear term of the system dynamics and perturbed asymmetric membership functions are used to handle rule uncertainties when it is hard to exactly determine the grade of membership functions. In additional, Lyapunov stability theory is used to discuss the parameter learning and system stability of the INTSMC system. Finally, the proposed INTSMC system is applied to an inverted pendulum and a voice coil motor actuator. The simulation and experimental results show that the proposed INTSMC system can achieve favorable tracking performance and is robust against parameter variations in the plant.