A fixed-time disturbance rejection control framework based on artificial intelligence for the flight environment testbed system

Abstract

A fixed-time disturbance rejection control framework based on artificial intelligence is proposed to achieve rapid tracking control of the flight environment testbed (FET) system in this study. Firstly, to resist the violent disturbance caused by the change in engine operating conditions and other disturbances, fixed-time extended state observers (FESO) are used in this paper to estimate disturbances in a fixed time and improve the anti-disturbance capability of the system. Then, the anti-saturation fixed-time control (FTC) law is used to prevent the system from collapsing or significant tracking errors due to actuator saturation and ensure the fixed-time convergence of tracking errors. Finally, the gradient descent optimization algorithm based on long short-term memory (LSTM) network is used to optimize the controller parameters and further improve the controller’s adaptive ability. Simulation experiments prove the effectiveness of the proposed method.