Finite-Time Composite Adaptive Neural Control for Automatic Carrier Landing with Actuator Fault

This paper presents a finite-time composite adaptive neural control method for an automatic carrier landing system that addresses critical challenges including model uncertainties, airwake disturbances and actuator faults. The proposed control method employs radial basis function neural networks to approximate model uncertainties. It is enhanced by a novel adaptive weight update mechanism to improve the approximation performance of neural networks. Furthermore, adaptive disturbance compensation models are constructed to mitigate the adverse effects of airwake disturbances and actuator faults. By incorporating prediction errors derived from finite-time series-parallel estimation models, the proposed control method achieves simultaneous neural network weight adjustment and disturbance compensation, ensuring robust control performance even under actuator faults. For the coexistence of input saturation and actuator faults, a Nussbaum-type function is employed in the design of the altitude subsystem controller to resolve the issue of the unknown control direction caused by actuator faults. Finally, the finite-time stability of the closed-loop system is demonstrated using the Lyapunov stability theory, and the effectiveness and superiority of the proposed composite adaptive neural control method are verified through simulation.