Intelligent dynamic sliding-mode neural control using recurrent perturbation fuzzy neural networks

In this paper, a recurrent perturbation fuzzy neural network (RPFNN) is used to online approximate an unknown nonlinear term in the system dynamics. A sine-cosine perturbed membership function is used to handle rule uncertainties when it is hard to exactly determine the grade of the value of fuzzy sets. Unlike type-2 fuzzy sets use an extra type reduction operation to find the output, the proposed RPFNN does not require heavy computational loading. Meanwhile, this paper proposes an intelligent dynamic sliding-mode neural control (IDSNC) system which is composed of a neural controller and an exponential compensator. The neural controller is designed as the main controller via dynamic sliding-mode approach, and the exponential compensator is designed to obtain a faster reaching time and a good robustness. The parameter adaptation laws of the IDSNC system are derived based on the Lyapunov function, so that the system stability can be guaranteed. Finally, the IDSNC system is applied to an inverted pendulum problem and a chaotic synchronization problem. The simulation results demonstrate that the IDSNC system can achieve favorable control performance and is robust against parameter variations and external disturbances.