Type-2 Fuzzy Neuro System Via Input-to-State-Stability Approach
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Neuro-Adaptive Output Feedback Control for a Class of Nonlinear Non-Minimum Phase Systems
Journal of Intelligent and Robotic Systems
Brief paper: Robust adaptive control of nonlinear non-minimum phase systems with uncertainties
Automatica (Journal of IFAC)
Hi-index | 0.00 |
In this paper, an adaptive parallel control architecture to stabilize a class of nonlinear systems which are nonminimum phase is proposed. For obtaining an on-line performance and self-tuning controller, the proposed control scheme contains recurrent fuzzy neural network (RFNN) identifier, nonfuzzy controller, and RFNN compensator. The nonfuzzy controller is designed for nominal system using the techniques of backstepping and feedback linearization, is the main part for stabilization. The RFNN compensator is used to compensate adaptively for the nonfuzzy controller, i.e., it acts like a fine tuner; and the RFNN identifier provides the system's sensitivity for tuning the controller parameters. Based on the Lyapunov approach, rigorous proofs are also presented to show the closed-loop stability of the proposed control architecture. With the aid of the RFNN compensators, the parallel controller can indeed improve system performance, reject disturbance, and enlarge the domain of attraction. Furthermore, computer simulations of several examples are given to illustrate the applicability and effectiveness of this proposed controller.