Online-SVR-compensated nonlinear generalized predictive control for hypersonic vehicles

This paper is concerned with the problem of hypersonic vehicle (HSV) attitude control system in uncertain flight conditions. The problem can be expressed as the adaptive robust control for a class of uncertain nonlinear systems. Based on the description of the aerodynamic structure and the model of flight control system of a certain kind of HSV, the ideal nonlinear generalized predictive control (NGPC) law based on uncertain nonlinear model is raised first to optimize the receding-horizon criterion of tracking errors. Then the online support vector regression (SVR) is employed to identify the uncertain item in the ideal control law. It is the compensating part of the controller. In addition, the stability of the close-loop system is analyzed using the Lyapunov method. The developed control strategy is well-implemented in this HSV attitude control system, and the simulation results compared with both nominal NGPC and RBF neural network disturbance observer show the good robustness and disturbance attenuation ability of this strategy and demonstrate the efficiency of online SVR algorithm.