Fault Tolerant Control for Near Space Vehicles with Input Saturation Using Disturbance Observer and Neural Networks

摘要

In this paper, a fault tolerant sliding mode control scheme is derived for near space vehicles with actuator faults, unknown external disturbance, system uncertainty and input saturation based on disturbance observer and neural networks (NNs). To deal with actuator faults, the radial basis function NNs are employed. The nonlinear disturbance observer is designed to eliminate the effect of external disturbance and system uncertainty. To tackle input saturation, the known bound of saturation is used to design the control law such that the control input is within the bounded range. Lyapunov stability analysis shows that the closed-loop system is stable and all closed-loop signals are uniformly ultimately bounded. Simulation results demonstrate the effectiveness of the developed fault tolerant control scheme, when actuator faults, unknown external disturbance, system uncertainty and input saturation appear simultaneously.