EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on partial discharge signal recognition and classification of power transformer based on acoustic-VMD and CNN-LSTM

Liang Chen iD, You Wen, Huaquan Su, Ke Xiong, Dani Chen

PLOS One · 20.11.2025 · 20 (11) · e0335447

DOI: 10.1371/journal.pone.0335447 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 20.11.2025. Verfasst von Liang Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, South China University of Technology, Guangzhou, China. Hauptthemen laut MEDLINE: Acoustics, Signal Processing, Computer-Assisted, Neural Networks, Computer, Electric Power Supplies. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Partial discharge (PD) detection in power transformers is critical for preventing insulation failures in modern power grids, yet remains challenging due to signal complexity and environmental noise. Existing methods struggle with accurate PD classification under strong electromagnetic interference and varying load conditions. This study proposes a novel hybrid Acoustic-VMD and CNN-LSTM model featuring: (1) sample entropy-optimized variational mode decomposition (automatically determining modes and penalty factor), (2) parallel 1D-CNN (5 layers and bidirectional LSTM (2 layers, 256 units) branches, and (3) hierarchical attention mechanisms (8 heads) for dynamic feature fusion. Experimental results demonstrate superior performance with 96.2% classification accuracy for multi-source defects (38% improvement over wavelet methods), 5.8mm mean absolute localization error (53% better than TDOA), and consistent 4.2 ° angular accuracy under high noise, while maintaining practical 0.8s processing time. The research conclusively establishes that synergistic integration of adaptive signal processing and attention-based deep learning significantly advances PD diagnostics, achieving both computational efficiency and robust performance in complex operational environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AcousticsSignal Processing, Computer-AssistedNeural Networks, ComputerElectric Power SuppliesAlgorithmsNoise

Autor:innen und Institutionen

  • School of Software, South China University of Technology, Guangzhou, China.
  • Guangdong Power Grid Co., Ltd., Information Center, Guangdong, Guangzhou, China.

ORCID-Profile: Liang Chen

Zitieren

APA

Chen, L., Wen, Y., Su, H., Xiong, K., & Chen, D. (2025). Research on partial discharge signal recognition and classification of power transformer based on acoustic-VMD and CNN-LSTM. PLOS One, 20(11), e0335447. https://doi.org/10.1371/journal.pone.0335447

Vancouver

Chen L, Wen Y, Su H, Xiong K, Chen D. Research on partial discharge signal recognition and classification of power transformer based on acoustic-VMD and CNN-LSTM. PLOS One. 2025;20(11):e0335447. doi:10.1371/journal.pone.0335447

BibTeX
@article{Chen2025,
  author = {Chen, Liang and Wen, You and Su, Huaquan and Xiong, Ke and Chen, Dani},
  title = {Research on partial discharge signal recognition and classification of power transformer based on acoustic-VMD and CNN-LSTM},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {11},
  pages = {e0335447},
  doi = {10.1371/journal.pone.0335447}
}
Kostenlos starten →