|
Accession number;05A0661069
|
| Title;Spacecraft Diagnosis Using Dynamic Bayesian Networks |
| Author;
KAWAHARA YOSHINOBU
(Univ. Tokyo, Graduate School of Engineering, JPN)
YAIRI TAKEHISA
(Todai Sentankagakugijutsukenkyuse)
MACHIDA KAZUO
(Todai Sentankagakugijutsukenkyuse)
|
Journal Title;Proceedings of the Annual Conference on JSAI (CD-ROM)
|
Journal Code:X0580B
|
ISSN:
|
|
VOL.19th;NO.;PAGE.1D1-01(2005)
|
| Figure&Table&Reference;FIG.6, TBL.1, REF.6 |
| Pub. Country;Japan |
| Language;Japanese |
| Abstract;Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the imporatant problems in space system operation. In this study, we propose a diagnosis method using probabilistic reasoning and statistical learning with Dynamic Bayesian Networks(DBNs). In this method, the DBNs are initially from prior knowledge, then modified or partly re-constructed by statistical learning from operation data, as a result a wide range of anomaly detection and advanced cause investigation are performed by probabilistic reasoning using the DBNs. This method has the both ability which two polar approaches; knowledge-based and data-driven. The proposed method was applied to the telemetry data that simulates malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed. (author abst.) |
|
|
|
Related Articles;
|
