EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Gas‐insulated switchgear partial discharge classification method based on deep transfer learning using experimental and field data

Xutao Han, Haotian Wang, Jie Cui, Yang Zhou, Tianyi Shi, Xuanrui Zhang, Junhao Li

High Voltage · 2025-08 · 10 (4) · 845-855

DOI: 10.1049/hve2.70088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift High Voltage, online erschienen am 18.08.2025. Verfasst von Xutao Han und 6 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gas‐insulated switchgear (GIS) plays a critical role in ensuring the reliability of power systems, but partial discharge (PD) is a primary cause of failures within GIS equipment. Traditional PD diagnostic methods rely heavily on laboratory data, which differ significantly from that under the complex conditions of field data, leading to a marked drop in recognition accuracy when they are applied to field PD diagnosis. This study addresses the challenge by integrating field data into the training process, utilising a deep transfer learning approach that combines laboratory and field data to improve diagnostic accuracy for GIS PD. The research collected PD data from laboratory models representing five defect types and field data gathered from operational GIS equipment. A deep residual network (ResNet50) was pretrained using laboratory data and fine‐tuned with field data through deep transfer learning to optimise the recognition of PD in field conditions. The results show that the proposed model achieves a significantly higher recognition accuracy (93.7%) for field data compared to traditional methods (60%–70%). The integration of deep transfer learning ensures that both low‐dimensional general features from laboratory data and high‐dimensional specific features from field data are effectively utilised. This research significantly contributes to improving the diagnostic accuracy of PD in GIS under field conditions, providing a robust method for defect detection in operational equipment.

Zitieren

APA

Han, X., Wang, H., Cui, J., Zhou, Y., Shi, T., Zhang, X., & Li, J. (2025). Gas‐insulated switchgear partial discharge classification method based on deep transfer learning using experimental and field data. High Voltage, 10(4), 845-855. https://doi.org/10.1049/hve2.70088

Vancouver

Han X, Wang H, Cui J, Zhou Y, Shi T, Zhang X, et al. Gas‐insulated switchgear partial discharge classification method based on deep transfer learning using experimental and field data. High Voltage. 2025;10(4):845-855. doi:10.1049/hve2.70088

BibTeX
@article{Han2025,
  author = {Han, Xutao and Wang, Haotian and Cui, Jie and Zhou, Yang and Shi, Tianyi and Zhang, Xuanrui and Li, Junhao},
  title = {Gas‐insulated switchgear partial discharge classification method based on deep transfer learning using experimental and field data},
  journal = {High Voltage},
  year = {2025},
  volume = {10},
  number = {4},
  pages = {845--855},
  doi = {10.1049/hve2.70088}
}
Kostenlos starten →