Neural Network-based Actuator Fault Diagnosis for Attitude Control Subsystem of a Satellite

The main objective of this paper is to develop a neural network-based fault detection and isolation scheme (FDI) for the attitude control subsystem (ACS) of a satellite. Towards this end, a neural network architecture is considered. A dynamic neural network residual generator for detection is constructed based on the dynamic multilayer perceptron (DMLP) network. Based on a given set of input-output data pairs collected from a 3-axis ACS of a satellite, the network parameters are adjusted to minimize a performance index specified by the output estimation error. The proposed neural FDI structure is applied for detecting and isolating various faults in the reaction wheel (RW), that is often used as an actuator in the ACS of a satellite, and its performance and capabilities is investigated and compared to a model-based linear observer residual generator that is to detect various fault scenarios.