An intelligent Fault Detection and Recovery scheme for reaction wheel actuator of satellite attitude control systems

In this paper, a Fault Detection and Recovery scheme is proposed for a reaction wheel type actuator of satellite attitude control systems. A state-space approach is used and a nonlinear-in-parameters neural network (NLPNN) is employed to identify the general unknown fault. The estimated fault is then used to reconfigure the controller. The recurrent network configuration is obtained by a combination of feedforward network architectures and dynamical elements in the form of stable filters. The neural network weights are updated based on a modified backpropagation scheme. The stability of the overall fault detection scheme is shown using Lyapunov´s direct method. The effectiveness of the proposed fault diagnosis strategy is demonstrated via simulations carried out on a highly accurate dynamical model of a reaction wheel actuator.