Mars entry fault-tolerant control via neural network and structure adaptive model inversion

Abstract The capability of autonomous fault detection and reconstruction is essential for future manned Mars exploration missions. Considering actuator failures and atmosphere uncertainties, we present a new active fault-tolerant control algorithm for Mars entry by use of neural network and structure adaptive model inversion. First, the online BP neural network is adopted to conduct the fault detection and isolation. Second, based on the structure adaptive model inversion, an adaptive neural network PID controller is developed for Mars entry fault-tolerant control. The normal PID controller will be automatically switched into neural network PID controller when an actuator fault is detected. Therefore, the error between the reference model and the output of the attitude control system would be adjusted to ensure the dynamic property of the entry vehicle. Finally, the effectiveness of the algorithm developed in this paper is confirmed by computer simulation.