Diagnosis method for spacecraft using dynamic bayesian networks

Yoshinobu Kawahara, Takehisa Yairi, Kazuo Machida

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. In this study, we propose a diagnosis method for spacecraft 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 with operation data, as a result adaptable and in-depth diagnosis is performed by probabilistic reasoning using the DBNs. The proposed method was applied to the telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed.

Original languageEnglish
Pages (from-to)649-656
Number of pages8
JournalEuropean Space Agency, (Special Publication) ESA SP
Issue number603
Publication statusPublished - Dec 15 2005
Eventi- SAIRAS 2005 - The 8th International Symposium on Artificial Intelligence, Robotics and Automation in Space - Munich, Germany
Duration: Sep 5 2005Sep 8 2005

Fingerprint

Bayesian networks
Spacecraft
spacecraft
learning
malfunctions
rendezvous
telemetry
maneuvers
Telemetering
anomalies
method
anomaly

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Diagnosis method for spacecraft using dynamic bayesian networks. / Kawahara, Yoshinobu; Yairi, Takehisa; Machida, Kazuo.

In: European Space Agency, (Special Publication) ESA SP, No. 603, 15.12.2005, p. 649-656.

Research output: Contribution to journalConference article

@article{6feddca28b2a4d12b78eba7e6e9e67ec,
title = "Diagnosis method for spacecraft using dynamic bayesian networks",
abstract = "Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. In this study, we propose a diagnosis method for spacecraft 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 with operation data, as a result adaptable and in-depth diagnosis is performed by probabilistic reasoning using the DBNs. The proposed method was applied to the telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed.",
author = "Yoshinobu Kawahara and Takehisa Yairi and Kazuo Machida",
year = "2005",
month = "12",
day = "15",
language = "English",
pages = "649--656",
journal = "European Space Agency, (Special Publication) ESA SP",
issn = "0379-6566",
publisher = "European Space Agency",
number = "603",

}

TY - JOUR

T1 - Diagnosis method for spacecraft using dynamic bayesian networks

AU - Kawahara, Yoshinobu

AU - Yairi, Takehisa

AU - Machida, Kazuo

PY - 2005/12/15

Y1 - 2005/12/15

N2 - Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. In this study, we propose a diagnosis method for spacecraft 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 with operation data, as a result adaptable and in-depth diagnosis is performed by probabilistic reasoning using the DBNs. The proposed method was applied to the telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed.

AB - Development of sophisticated anomaly detection and diagnosis methods for spacecraft is one of the important problems in space system operation. In this study, we propose a diagnosis method for spacecraft 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 with operation data, as a result adaptable and in-depth diagnosis is performed by probabilistic reasoning using the DBNs. The proposed method was applied to the telemetry data that simulates the malfunction of thrusters in rendezvous maneuver of spacecraft, and the effectiveness of the method was confirmed.

UR - http://www.scopus.com/inward/record.url?scp=28744444993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28744444993&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:28744444993

SP - 649

EP - 656

JO - European Space Agency, (Special Publication) ESA SP

JF - European Space Agency, (Special Publication) ESA SP

SN - 0379-6566

IS - 603

ER -