Broad learning system-based model-free adaptive robust control for hypersonic morphing aircraft with appointed-time prescribed performance

This paper proposes a model-free attitude tracking controller for hypersonic morphing aircraft with appointed-time prescribed performance. An error transformation methodology is developed, ensuring adherence to performance constraints irrespective of initial tracking conditions. Subsequently, an adaptive control scheme for the transformed system is devised, comprising two broad learning system-based adaptive neural network compensators and an adaptive robust integral of the signum of error (RISE) controller. The neural network compensators, featuring a node update strategy, are developed to compensate for uncertain system dynamics and unknown lumped disturbances. Subsequently, the adaptive RISE controller is integrated with the compensators to ensure precise tracking. The stability of the closed-loop system is analyzed by employing the Lyapunov's direct method. Finally, the effectiveness and enhanced performance of the proposed control scheme are validated via numerical simulations.