EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bidirectional Gated Recurrent Unit Neural Network for Fault Diagnosis and Rapid Maintenance in Medium-Voltage Direct Current Systems

Bohyung Lee, Yeseul Kim, Hyunyong Lee iD, Changmook Kang iD

Sensors · 24.01.2025 · 25 (3) · 693

DOI: 10.3390/s25030693 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.01.2025. Verfasst von Bohyung Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Hanyang University, Seoul 04763, Republic of Korea. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning (KETEP), Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the growing penetration of renewable energy sources, ensuring the stability and reliability of Medium-Voltage Direct Current (MVDC) systems has become more critical than ever. A single fault in MVDC systems can cause significant disturbances, necessitating rapid and precise diagnostics to prevent equipment damage and maintain continuous power supply. In this work, we present a Bidirectional Gated Recurrent Unit (Bi-GRU) model that both classifies and locates MVDC faults. By capturing the temporal behavior of voltage signals, the Bi-GRU framework surpasses traditional algorithms such as Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. Furthermore, the proposed approach addresses multiple fault scenarios including PTP (Pole-to-Pole), PPTG (Positive Pole-to-Ground), and NPTG (Negative Pole-to-Ground) while preserving real-time diagnostic capabilities. In extensive tests, our model achieves an overall accuracy of 95.54% and an average fault detection time below 1.3 ms, meeting real-world operational requirements. To assess robustness, sensor noise was artificially introduced to emulate realistic conditions. Despite these challenging inputs, our method consistently maintained high diagnostic accuracy, confirming its practicality and reliability. Consequently, the proposed scheme demonstrates a significant contribution toward improving the safety and dependability of MVDC systems, even under noisy conditions.

Schlagwörter

Stichwörter der Autor:innen

DC faultMVDC systembidirectional gated recurrent unit (Bi-GRU)deep learningfault diagnosis

Autor:innen und Institutionen

  • Department of Electrical Engineering, Hanyang University, Seoul 04763, Republic of Korea.
  • Department of Electrical Engineering, Incheon National University, Incheon 22012, Republic of Korea.
  • Energy System Research Section, Honam Research Center, Electronics and Telecommunications Research Institute (ETRI), Daejeon 61012, Republic of Korea.

ORCID-Profile: Hyunyong Lee, Changmook Kang

Förderung

  • Korea Institute of Energy Technology Evaluation and Planning (KETEP)
  • Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE)

Zitieren

APA

Lee, B., Kim, Y., Lee, H., & Kang, C. (2025). Bidirectional Gated Recurrent Unit Neural Network for Fault Diagnosis and Rapid Maintenance in Medium-Voltage Direct Current Systems. Sensors, 25(3), 693. https://doi.org/10.3390/s25030693

Vancouver

Lee B, Kim Y, Lee H, Kang C. Bidirectional Gated Recurrent Unit Neural Network for Fault Diagnosis and Rapid Maintenance in Medium-Voltage Direct Current Systems. Sensors. 2025;25(3):693. doi:10.3390/s25030693

BibTeX
@article{Lee2025,
  author = {Lee, Bohyung and Kim, Yeseul and Lee, Hyunyong and Kang, Changmook},
  title = {Bidirectional Gated Recurrent Unit Neural Network for Fault Diagnosis and Rapid Maintenance in Medium-Voltage Direct Current Systems},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {3},
  pages = {693},
  doi = {10.3390/s25030693}
}
Kostenlos starten →