Skip to main navigation Skip to search Skip to main content

Satellite Telemetry Anomaly Detection Based on Gradient Boosting Regression with Feature Selection

  • Zhidong Li*
  • , Bo Sun
  • , Weihua Jin
  • , Lei Zhang
  • , Rongzheng Luo
  • *Corresponding author for this work
  • China Aerospace Science and Technology Corporation
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A data-driven satellite telemetry data anomaly detection method is proposed. The gradient boosting regression algorithm combined with feature selection, including feature scoring and recursive lowest-score feature elimination, can automatically mine the correlative telemetry variables through iterations and establish a nonlinear regression model for their functional association, which can be used as a health baseline for anomaly detection of telemetry data. This method requires no expert to specify correlative telemetry variables based on domain knowledge beforehand. It has the advantage of self-adaption for satellite operating conditions, which can overcome the problem of functional association altering under different operating conditions caused by orbit or sunshine condition changes. The validity and effectiveness of the method is verified by the telemetry data of the power subsystem.

Original languageEnglish
Title of host publicationWireless and Satellite Systems - 11th EAI International Conference, WiSATS 2020, Proceedings
EditorsQihui Wu, Kanglian Zhao, Xiaojin Ding
PublisherSpringer Science and Business Media Deutschland GmbH
Pages210-219
Number of pages10
ISBN (Print)9783030690717
DOIs
StatePublished - 2021
Externally publishedYes
Event11th EAI International Conference on Wireless and Satellite Systems, WiSATS 2020 - Nanjing, China
Duration: 17 Sep 202018 Sep 2020

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume358
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference11th EAI International Conference on Wireless and Satellite Systems, WiSATS 2020
Country/TerritoryChina
CityNanjing
Period17/09/2018/09/20

Keywords

  • Anomaly detection
  • Feature selection
  • Gradient Boosting
  • Satellite

Fingerprint

Dive into the research topics of 'Satellite Telemetry Anomaly Detection Based on Gradient Boosting Regression with Feature Selection'. Together they form a unique fingerprint.

Cite this