EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Substation Inspection Safety Risk Identification Based on Synthetic Data and Spatiotemporal Action Detection

Chengcheng Liu iD, Weihua Zhang, Weijin Xu, Bo Lu, Weijie Li iD, Xuefeng Zhao iD

Sensors · 25.04.2025 · 25 (9) · 2720

DOI: 10.3390/s25092720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.04.2025. Verfasst von Chengcheng Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Coastal and Offshore Engineering, School of Civil Engineering, Dalian University of Technology, Dalian 116024, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Science and Technology Project of State Grid Jilin Electric Power Company Limited.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

During substation inspection, operators are often exposed to hazardous working environments. It is necessary to use visual sensors to determine work status and perform action detection to distinguish between normal and dangerous actions in order to ensure the safety of operators. However, due to information security, privacy protection, and the rarity of dangerous scenarios, there is a scarcity of related visual action datasets. To address this issue, this study first introduces a virtual work platform, which includes a controller for the parameterized control of scenarios and human resources. It can simulate realistic substation inspection operations and generate synthetic action datasets using domain randomization and behavior tree logic. Subsequently, a spatiotemporal action detection algorithm is utilized for action detection, employing YOLOv8 as the human detector, Vision Transformer as the backbone network, and SlowFast as the action detection architecture. Model training is conducted using three datasets: a real dataset, a synthetic dataset generated via a VWP, and a mixed dataset comprising both real and synthetic data. Finally, using the model trained on the real dataset as a baseline, the evaluation results on the test set shows that the use of synthetic datasets in training improves the model’s average precision by up to 10.7%, with a maximum average precision of 73.61%. This demonstrates the feasibility, effectiveness, and robustness of synthetic data.

Schlagwörter

Stichwörter der Autor:innen

Vision Transformercondition monitoringoptical imagessafety riskspatiotemporal action detectionsynthetic data

Autor:innen und Institutionen

  • State Key Laboratory of Coastal and Offshore Engineering, School of Civil Engineering, Dalian University of Technology, Dalian 116024, China.
  • State Grid Changchun Power Supply Company, Changchun 130021, China.

ORCID-Profile: Chengcheng Liu, Weijie Li, Xuefeng Zhao

Förderung

  • the Science and Technology Project of State Grid Jilin Electric Power Company Limited

Zitieren

APA

Liu, C., Zhang, W., Xu, W., Lu, B., Li, W., & Zhao, X. (2025). Substation Inspection Safety Risk Identification Based on Synthetic Data and Spatiotemporal Action Detection. Sensors, 25(9), 2720. https://doi.org/10.3390/s25092720

Vancouver

Liu C, Zhang W, Xu W, Lu B, Li W, Zhao X. Substation Inspection Safety Risk Identification Based on Synthetic Data and Spatiotemporal Action Detection. Sensors. 2025;25(9):2720. doi:10.3390/s25092720

BibTeX
@article{Liu2025,
  author = {Liu, Chengcheng and Zhang, Weihua and Xu, Weijin and Lu, Bo and Li, Weijie and Zhao, Xuefeng},
  title = {Substation Inspection Safety Risk Identification Based on Synthetic Data and Spatiotemporal Action Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2720},
  doi = {10.3390/s25092720}
}
Kostenlos starten →