Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems

Takehisa Yairi; Yoshinobu Kawahara; Ryohei Fujimaki; Yuichi Sato; Kazuo Machida

doi:10.1109/SMC-IT.2006.79

Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems

Takehisa Yairi, Yoshinobu Kawahara, Ryohei Fujimaki, Yuichi Sato, Kazuo Machida

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

42 Citations (Scopus)

Abstract

For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us.

Original language	English
Title of host publication	Proceedings - SMC-IT 2006
Subtitle of host publication	2nd IEEE International Conference on Space Mission Challenges for Information Technology
Pages	466-473
Number of pages	8
DOIs	https://doi.org/10.1109/SMC-IT.2006.79
Publication status	Published - Dec 1 2006
Externally published	Yes
Event	SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology - Pasadena, CA, United States Duration: Jul 17 2006 → Jul 20 2006

Publication series

Name	Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology
Volume	2006

Conference

Conference	SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology
Country/Territory	United States
City	Pasadena, CA
Period	7/17/06 → 7/20/06

All Science Journal Classification (ASJC) codes

Computer Science(all)
Aerospace Engineering

Access to Document

10.1109/SMC-IT.2006.79

Cite this

Yairi, T., Kawahara, Y., Fujimaki, R., Sato, Y., & Machida, K. (2006). Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems. In Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology (pp. 466-473). [1659593] (Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology; Vol. 2006). https://doi.org/10.1109/SMC-IT.2006.79

Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems. / Yairi, Takehisa; Kawahara, Yoshinobu; Fujimaki, Ryohei et al.
Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology. 2006. p. 466-473 1659593 (Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology; Vol. 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yairi, T, Kawahara, Y, Fujimaki, R, Sato, Y & Machida, K 2006, Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems. in Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology., 1659593, Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology, vol. 2006, pp. 466-473, SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology, Pasadena, CA, United States, 7/17/06. https://doi.org/10.1109/SMC-IT.2006.79

Yairi T, Kawahara Y, Fujimaki R, Sato Y, Machida K. Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems. In Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology. 2006. p. 466-473. 1659593. (Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology). doi: 10.1109/SMC-IT.2006.79

Yairi, Takehisa ; Kawahara, Yoshinobu ; Fujimaki, Ryohei et al. / Telemetry-mining : A machine learning approach to anomaly detection and fault diagnosis for space systems. Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology. 2006. pp. 466-473 (Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology).

@inproceedings{fcc03ee8b35c460cacd14257d1c709b7,

title = "Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems",

abstract = "For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us.",

author = "Takehisa Yairi and Yoshinobu Kawahara and Ryohei Fujimaki and Yuichi Sato and Kazuo Machida",

year = "2006",

month = dec,

day = "1",

doi = "10.1109/SMC-IT.2006.79",

language = "English",

isbn = "0769526446",

series = "Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology",

pages = "466--473",

booktitle = "Proceedings - SMC-IT 2006",

note = "SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology ; Conference date: 17-07-2006 Through 20-07-2006",

}

TY - GEN

T1 - Telemetry-mining

T2 - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology

AU - Yairi, Takehisa

AU - Kawahara, Yoshinobu

AU - Fujimaki, Ryohei

AU - Sato, Yuichi

AU - Machida, Kazuo

PY - 2006/12/1

Y1 - 2006/12/1

N2 - For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us.

AB - For any space mission, safety and reliability are the most important issues. To tackle this problem, we have studied anomaly detection and fault diagnosis methods for spacecraft systems based on machine learning (ML) and data mining (DM) technology. In these methods, the knowledge or model which is necessary for monitoring a spacecraft system is (semi-)automatically acquired from the spacecraft telemetry data. In this paper, we first overview the anomaly detection / diagnosis problem in the spacecraft systems and conventional techniques such as limit-check, expert systems and model-based diagnosis. Then we explain the concept of ML/DM-based approach to this problem, and introduce several anomaly detection / diagnosis methods which have been developed by us.

UR - http://www.scopus.com/inward/record.url?scp=34247205903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34247205903&partnerID=8YFLogxK

U2 - 10.1109/SMC-IT.2006.79

DO - 10.1109/SMC-IT.2006.79

M3 - Conference contribution

AN - SCOPUS:34247205903

SN - 0769526446

SN - 9780769526447

T3 - Proceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology

SP - 466

EP - 473

BT - Proceedings - SMC-IT 2006

Y2 - 17 July 2006 through 20 July 2006

ER -

Telemetry-mining: A machine learning approach to anomaly detection and fault diagnosis for space systems

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this