EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection

Zhilei Zhao iD, Zhao Xiao, Jie Tao iD

Sensors · 12.11.2024 · 24 (22) · 7218

DOI: 10.3390/s24227218 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.11.2024. Verfasst von Zhilei Zhao und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Research and Development Program of People's Republic of China, Hunan Outstanding Youth Fund Project, the Hunan Provincial Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A large number of sensors are typically installed in industrial plants to collect real-time operational data. These sensors monitor data with time series correlation and spatial correlation over time. In previous studies, GNN has built many successful models to deal with time series data, but most of these models have fixed perspectives and struggle to capture the dynamic correlations in time and space simultaneously. Therefore, this paper constructs a multi-scale dynamic graph neural network (MSDG) for anomaly detection in industrial sensor data. First, a multi-scale sliding window mechanism is proposed to input different scale sensor data into the corresponding network. Then, a dynamic graph neural network is constructed to capture the spatial–temporal dependencies of multivariate sensor data. Finally, the model comprehensively considers the extracted features for sequence reconstruction and utilizes the reconstruction errors for anomaly detection. Experiments have been conducted on three real public datasets, and the results show that the proposed method outperforms the mainstream methods.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectiongraph neural networkindustrial equipmentlong short-term memorymulti-scale sliding window mechanismmultivariate sensor monitoring dataspatial–temporal correlations

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, China.
  • School of Mechanical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China.

ORCID-Profile: Zhilei Zhao, Jie Tao

Förderung

  • the National Key Research and Development Program of People's Republic of China
  • Hunan Outstanding Youth Fund Project
  • the Hunan Provincial Natural Science Foundation of China
  • Hunan Science and Technology Innovation Plan
  • National Key Research and Development Program of People’s Republic of China
  • Hunan Provincial Natural Science Foundation of China
  • science and technology innovation Program of Hunan Province

Zitieren

APA

Zhao, Z., Xiao, Z., & Tao, J. (2024). MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection. Sensors, 24(22), 7218. https://doi.org/10.3390/s24227218

Vancouver

Zhao Z, Xiao Z, Tao J. MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection. Sensors. 2024;24(22):7218. doi:10.3390/s24227218

BibTeX
@article{Zhao2024,
  author = {Zhao, Zhilei and Xiao, Zhao and Tao, Jie},
  title = {MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {22},
  pages = {7218},
  doi = {10.3390/s24227218}
}
Kostenlos starten →