Skip to Main Content
In this paper, a novel intelligent-based fault tolerant control (FTC) framework is proposed to solve the fault tolerant tracking control problem for unknown nonlinear multi-input multi-output (MIMO) systems. To eliminate the effect of faults, a neural network model adapted with the extended Kalman filter (EKF) is created to online identify the unknown systems, and then the steepest descent and evolutionary programming (EP) method is utilized to find a self-tuning proportional-integral-derivative (PID) controller for the adapted neural network. The resulted PID FTC controller can not only achieve the tracking objective but also can maintain the stability and the expected performance when faults occur in system. Finally, a numerical example is given to illustrate the effectiveness of the proposed methods.