EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-optimized wavelet packet transform for synchronous condenser fault prediction

Dongqing Zhang, Chaofeng Zhang, Michel Kadoch iD, Tao Hong, Shenglong Li, Wenqiang Zhao

PLOS One · 2025

DOI: 10.1371/journal.pone.0330429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Dongqing Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: DC Technical Center of State Grid Corporation of China, Beijing, China. Hauptthemen laut MEDLINE: Wavelet Analysis. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes an innovative approach for predicting faults in synchronous condensers in ultra-high voltage direct current (UHVDC) transmission systems. The framework combines Wavelet Packet Transform (WPT) for intelligent feature extraction with an enhanced Gated Recurrent Unit (GRU) network augmented by multi-head attention mechanisms. WPT is employed for efficient decomposition of fault signals into multiple frequency sub-bands, facilitating the extraction of fault features such as energy, entropy, and statistical moments. By applying Large Language Models (LLM) to WPT, an intelligent feature selection mechanism significantly improves both detection accuracy and processing efficiency. The Multi-Head Attention GRU (MHA-GRU) network architecture is designed to capture complex temporal dependencies in fault signals while maintaining computational efficiency. Comprehensive experimental results demonstrate that our framework consistently outperforms state-of-the-art methods across all performance metrics, including classification accuracy, detection time, and false alarm rate. The system exhibits robust stability under varying load conditions with particularly significant improvements in air-gap eccentricity fault detection. The proposed approach provides a reliable solution for early fault prediction in UHVDC synchronous condensers, enabling timely maintenance intervention before minor issues develop into critical failures.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wavelet AnalysisAlgorithmsModels, Theoretical

Autor:innen und Institutionen

  • DC Technical Center of State Grid Corporation of China, Beijing, China.
  • State Grid Hunan Extra High Voltage Substation Company and Substation Intelligent Operation and Inspection Laboratory of State Grid Hunan Electric Power Co., Ltd., Changsha, China.
  • Cross-Strait Tsinghua Research Institute (CTRI), Xiamen, Fujian, China.
  • School of Electronics and Information Engineering, Beihang University, Beijing, China.
  • State Grid Qinghai Electric Power Research Institute, Xining, China.

ORCID-Profile: Michel Kadoch

Zitieren

APA

Zhang, D., Zhang, C., Kadoch, M., Hong, T., Li, S., & Zhao, W. (2025). LLM-optimized wavelet packet transform for synchronous condenser fault prediction. PLOS One. https://doi.org/10.1371/journal.pone.0330429

Vancouver

Zhang D, Zhang C, Kadoch M, Hong T, Li S, Zhao W. LLM-optimized wavelet packet transform for synchronous condenser fault prediction. PLOS One. 2025. doi:10.1371/journal.pone.0330429

BibTeX
@article{Zhang2025,
  author = {Zhang, Dongqing and Zhang, Chaofeng and Kadoch, Michel and Hong, Tao and Li, Shenglong and Zhao, Wenqiang},
  title = {LLM-optimized wavelet packet transform for synchronous condenser fault prediction},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0330429}
}
Kostenlos starten →