Learning-based integrated fault-tolerant guidance and control for hypersonic vehicles considering avoidance and penetration

To address the problem of no-fly zone and interceptor avoidance during the reentry phase, a learning-based integrated fault-tolerant guidance and control method for hypersonic vehicles considering avoidance and penetration is proposed. Firstly, to improve the guidance performance of the vehicle in longitudinal guidance, the six degree of freedom model of the vehicle, which includes the attitude fault-tolerant control system, is adopted based on the integrated design concept of guidance and control to predict the range-to-go. In view of the resulting problem of time-consuming in calculation, the deep network is further used to fit the predicting process, so as to improve the real-timeliness of the algorithm. Then, to solve the problem of no-fly zone and interceptor avoidance in lateral guidance, the Interfered Fluid Dynamical System (IFDS) algorithm is introduced to calculate the expected heading angle of the vehicle considering threat factors, and the heading angle error corridor and the flip logic of the bank angle are used to obtain the command, so that the vehicle has the ability of avoidance and penetration. Next, considering the complexity of flight environment, the difference of maneuvering ability of vehicle during the reentry phase, and the influence of dynamic characteristics of attitude control system on guidance performance, the deep reinforcement learning algorithm is employed to train the agent, so that the agent can make online decisions on key parameters of IFDS algorithm according to the real-time state of vehicle, and improve the effectiveness and adaptability of the proposed guidance method. Finally, the results of semi-physical comparison simulation and Monte Carlo simulation show that the proposed method can achieve high performance in avoidance, penetration and guidance.