EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DecPD: A Deconstructed Deep Learning Approach for Partial Discharge Pattern Recognition

Yucheng Wu, Hao Yang, Shengwei Li, Fanghong Guo

Energies · 28.11.2025 · 18 (23) · 6245

DOI: 10.3390/en18236245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 28.11.2025. Verfasst von Yucheng Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, partial discharge pattern recognition (PDPR) for transmission cables has garnered increasing attention due to the severe power outages, equipment damage, and even major safety incidents resulting from the failure of partial discharge (PD) detection. However, existing PD data samples usually suffer from highly similar features and unbalanced distribution. Determining how to precisely realize the PDPR has become a challenge. In this study, an effective PDPR approach is proposed based on a newly designed deconstructed PD (DecPD) model and a customized loss function for PDPR. Notably, the refined deep learning network captures the discriminative features in both temporal and spatial dimensions through a dual-channel learning architecture. Additionally, an adaptive focal loss function is designed, which introduces a peak factor to establish focusing parameters for PDPR, thereby addressing the class imbalance issues. A comprehensive experimental evaluation using real datasets generated on a physical platform is conducted to verify our proposed method. Compared to other existing methods, our DecPD approach demonstrates superior performance, achieving an overall accuracy of 96.65% in the presence of environment noise.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wu, Y., Yang, H., Li, S., & Guo, F. (2025). DecPD: A Deconstructed Deep Learning Approach for Partial Discharge Pattern Recognition. Energies, 18(23), 6245. https://doi.org/10.3390/en18236245

Vancouver

Wu Y, Yang H, Li S, Guo F. DecPD: A Deconstructed Deep Learning Approach for Partial Discharge Pattern Recognition. Energies. 2025;18(23):6245. doi:10.3390/en18236245

BibTeX
@article{Wu2025,
  author = {Wu, Yucheng and Yang, Hao and Li, Shengwei and Guo, Fanghong},
  title = {DecPD: A Deconstructed Deep Learning Approach for Partial Discharge Pattern Recognition},
  journal = {Energies},
  year = {2025},
  volume = {18},
  number = {23},
  pages = {6245},
  doi = {10.3390/en18236245}
}
Kostenlos starten →