Adaptive attitude control for Supersonic Aircraft based on Backstepping and Neural Networks Controller

A neural network adaptive control strategy is proposed for the attitude tracking problem of six-degree-of-freedom supersonic aircraft. The external environment of the aircraft and the access to the aerodynamic parameters all lead to large disturbances in the aerodynamic parameters. The control strategy of this paper focuses on this kind of disturbance. Firstly, the original six-degree-of-freedom aircraft model is analyzed and simplified, and the model with strict feedback form is obtained. Then a neural network adaptive control law is designed based on the Backstepping method. The control law uses a neural network to estimate the uncertainty of the aerodynamic parameters and compensate for it. In order to solve the problem of difficult calculation of Backstepping method, this paper deduces a simple calculation formula. Finally, based on the Lyapunov stability theory, it is proved that the attitude angle tracking error is locally ultimately bounded. Simulation results show that the control strategy, in the presence of aerodynamic parameters perturbations and external disturbances, has good tracking performance and strong robustness.