A real-time fault diagnosis method of SACS based on combination of offline identification and online observing

Abstract

A novel fault diagnosis method based on the combination of offline identification and online observing is proposed in this paper, which can meet the requirement of both model complexity and real-time need for the satellite attitude control system. Accurate neural network models, both normal mode and faulty mode, can be obtained by off-line identification based on the data of fault simulation in different fault modes. With a parallel estimator derived from all models With all, fault determination based on threshold logic is designed for online fault detecting and isolating. Real-time simulation results, on the embedded fault simulation platform of satellite attitude control system, illustrate the effectiveness and superiority.