Spacecraft telemetry data monitoring by dimensionality reduction techniques

Takehisa Yairi, Minoru Inui, Akihiro Yoshiki, Yoshinobu Kawahara, Noboru Takata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper, we consider a "data-driven" anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites.

Original languageEnglish
Title of host publicationProceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers
PublisherSociety of Instrument and Control Engineers (SICE)
Pages1230-1234
Number of pages5
ISBN (Print)9784907764364
Publication statusPublished - Jan 1 2010

Publication series

NameProceedings of the SICE Annual Conference

Fingerprint

Telemetering
Spacecraft
Monitoring
Satellites

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Yairi, T., Inui, M., Yoshiki, A., Kawahara, Y., & Takata, N. (2010). Spacecraft telemetry data monitoring by dimensionality reduction techniques. In Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers (pp. 1230-1234). [5602754] (Proceedings of the SICE Annual Conference). Society of Instrument and Control Engineers (SICE).

Spacecraft telemetry data monitoring by dimensionality reduction techniques. / Yairi, Takehisa; Inui, Minoru; Yoshiki, Akihiro; Kawahara, Yoshinobu; Takata, Noboru.

Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers. Society of Instrument and Control Engineers (SICE), 2010. p. 1230-1234 5602754 (Proceedings of the SICE Annual Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yairi, T, Inui, M, Yoshiki, A, Kawahara, Y & Takata, N 2010, Spacecraft telemetry data monitoring by dimensionality reduction techniques. in Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers., 5602754, Proceedings of the SICE Annual Conference, Society of Instrument and Control Engineers (SICE), pp. 1230-1234.
Yairi T, Inui M, Yoshiki A, Kawahara Y, Takata N. Spacecraft telemetry data monitoring by dimensionality reduction techniques. In Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers. Society of Instrument and Control Engineers (SICE). 2010. p. 1230-1234. 5602754. (Proceedings of the SICE Annual Conference).
Yairi, Takehisa ; Inui, Minoru ; Yoshiki, Akihiro ; Kawahara, Yoshinobu ; Takata, Noboru. / Spacecraft telemetry data monitoring by dimensionality reduction techniques. Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers. Society of Instrument and Control Engineers (SICE), 2010. pp. 1230-1234 (Proceedings of the SICE Annual Conference).
@inproceedings{21759b45a92b4c01b9e3bede7cd63c8c,
title = "Spacecraft telemetry data monitoring by dimensionality reduction techniques",
abstract = "In this paper, we consider a {"}data-driven{"} anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites.",
author = "Takehisa Yairi and Minoru Inui and Akihiro Yoshiki and Yoshinobu Kawahara and Noboru Takata",
year = "2010",
month = "1",
day = "1",
language = "English",
isbn = "9784907764364",
series = "Proceedings of the SICE Annual Conference",
publisher = "Society of Instrument and Control Engineers (SICE)",
pages = "1230--1234",
booktitle = "Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers",

}

TY - GEN

T1 - Spacecraft telemetry data monitoring by dimensionality reduction techniques

AU - Yairi, Takehisa

AU - Inui, Minoru

AU - Yoshiki, Akihiro

AU - Kawahara, Yoshinobu

AU - Takata, Noboru

PY - 2010/1/1

Y1 - 2010/1/1

N2 - In this paper, we consider a "data-driven" anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites.

AB - In this paper, we consider a "data-driven" anomaly detection framework for spacecraft systems using dimensionality reduction and reconstruction techniques. This method first learns a mapping from the original data space to a low dimensional space and its reverse mapping by applying linear or non-linear dimensionality reduction algorithms to a normal training data set. After the training, it applies the learned pair of mappings to a test data set to obtain a reconstructed data set, and then evaluate the reconstruction errors. We will show the results of applying several representative linear and non-lineardimensionality reduction algorithms with this framework to the electrical power subsystem (EPS) data of actual artificial satellites.

UR - http://www.scopus.com/inward/record.url?scp=78649305969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649305969&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784907764364

T3 - Proceedings of the SICE Annual Conference

SP - 1230

EP - 1234

BT - Proceedings of SICE Annual Conference 2010, SICE 2010 - Final Program and Papers

PB - Society of Instrument and Control Engineers (SICE)

ER -