Neuro-fuzzy network based adaptive tracking controller for a nonlinear system

Abstract EN

In this paper, a neuro-fuzzy network-based adaptive tracking controller is suggested for controlling a type of nonlinear system.

Where two neuro-fuzzy networks have been used to learn the system dynamics uncertainty bounds by using Lyapunov method.

Then the output of these two networks are used to build a sliding mode controller.

The stability of the control system is proved and stable neuro-fuzzy controller parameters adjustment laws are selected using Lyapunov theory.

Simulation case study shows that the controlled system tracking the reference model effectively with smooth control effort and robust performance has been achieved.