Adaptive RBF Network-Based Sliding-Mode Fault-Tolerant Control for Hypersonic Vehicles With Model Uncertainties

This paper introduces a fault-tolerant control methodology for hypersonic vehicles encountering actuator faults and model uncertainties. The initial step involves the construction of a nonlinear dynamic model for Hypersonic Vehicles (HSV), founded on published data regarding the Winged-Cone aircraft. Subsequently, a finite-time nonsingular terminal sliding mode controller is devised to mitigate the adverse effects of lumped interference, encompassing actuator faults, model uncertainties, and external disturbances. Then, a finite-time adaptive Radial Basis Function (RBF) neural network is developed to estimate the lumped interference, bolstering system robustness while ensuring control quantity continuity. Furthermore, a finite-time disturbance observer is integrated into the approach to gauge the estimation error of the RBF neural network and acquire the essential parameters for controller adjustments. Finally, the efficacy and robustness of the proposed control strategy are substantiated through a combination of theoretical analysis and simulation results.