Fault diagnosis for spacecraft using probabilistic reasoning and statistical learning with dynamic bayesian networks

The development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. Many researches have been carried on this problem, however these depend only on specific resource; knowledge or data. In this paper, we propose a diagnosis method for spacecraft using Dynamic Bayesian Networks which uses both prior- knowledge and data in a natural way in model-acquisition and perform adaptable and in-depth diagnosis by probabilistic reasoning. The proposed method was applied to the artificial telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed.