EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STGLR: A Spacecraft Anomaly Detection Method Based on Spatio-Temporal Graph Learning

Yi Lai iD, Ye Zhu, Li Li iD, Qing Lan iD, Yizheng Zuo iD

Sensors · 07.01.2025 · 25 (2) · 310

DOI: 10.3390/s25020310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.01.2025. Verfasst von Yi Lai und 4 weiteren Autor:innen. Beteiligte Einrichtung: Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201304, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Excellent Fund of Youth Innovation Promotion Association of Chinese Academy of Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomalies frequently occur during the operation of spacecraft in orbit, and studying anomaly detection methods is crucial to ensure the normal operation of spacecraft. Due to the complexity of spacecraft structures, telemetry data possess characteristics such as high dimensionality, complexity, and large scale. Existing methods frequently ignore or fail to explicitly extract the correlation between variables, and due to the lack of prior knowledge, it is difficult to obtain the initial relationship of variables. To address these issues, this paper proposes a new method, namely spatio-temporal graph learning reconstruction (STGLR), for spacecraft anomaly detection. STGLR employs a dynamic graph learning module to infer the initial relationships among telemetry variables. It then constructs a spatio-temporal feature extraction module to capture complex spatio-temporal dependencies among variables, leveraging a graph sample and aggregation network to learn embedded features and incorporating an attention mechanism to adaptively select salient features. Finally, a reconstruction module is used to learn the latent representations of features, capturing the normal patterns in telemetry data and achieving anomaly detection. To validate the effectiveness of the proposed method, experiments were conducted on two public spacecraft datasets, and the results demonstrate that the performance of the STGLR method surpasses existing anomaly detection methods, with an average F1 score exceeding 0.97.

Schlagwörter

Stichwörter der Autor:innen

GraphSAGEanomaly detectiondynamic graph learningspacecraft telemetry datavariational auto-encoder

Autor:innen und Institutionen

  • Innovation Academy for Microsatellites of Chinese Academy of Sciences, Shanghai 201304, China.
  • University of Chinese Academy of Sciences, Beijing 101408, China.
  • Key Lab for Satellite Digitalization Technology of Chinese Academy of Sciences, Shanghai 200031, China.

ORCID-Profile: Yi Lai, Li Li, Qing Lan, Yizheng Zuo

Förderung

  • Excellent Fund of Youth Innovation Promotion Association of Chinese Academy of Sciences

Zitieren

APA

Lai, Y., Zhu, Y., Li, L., Lan, Q., & Zuo, Y. (2025). STGLR: A Spacecraft Anomaly Detection Method Based on Spatio-Temporal Graph Learning. Sensors, 25(2), 310. https://doi.org/10.3390/s25020310

Vancouver

Lai Y, Zhu Y, Li L, Lan Q, Zuo Y. STGLR: A Spacecraft Anomaly Detection Method Based on Spatio-Temporal Graph Learning. Sensors. 2025;25(2):310. doi:10.3390/s25020310

BibTeX
@article{Lai2025,
  author = {Lai, Yi and Zhu, Ye and Li, Li and Lan, Qing and Zuo, Yizheng},
  title = {STGLR: A Spacecraft Anomaly Detection Method Based on Spatio-Temporal Graph Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {2},
  pages = {310},
  doi = {10.3390/s25020310}
}
Kostenlos starten →