Skip to main content

ORIGINAL RESEARCH article

Front. Energy Res.
Sec. Smart Grids
Volume 12 - 2024 | doi: 10.3389/fenrg.2024.1473472
This article is part of the Research Topic Advancements in Power System Condition Monitoring, Fault Diagnosis and Environmental Compatibility View all 7 articles

Research on Single-phase Grounding Detection Method in Small-current Grounding Systems Based on Image Recognition

Provisionally accepted
Guangfen Wan Guangfen Wan 1*Xuekun Xu Xuekun Xu 2
  • 1 China National Offshore Oil Corporation (China), Beijing, Beijing Municipality, China
  • 2 Nanjing Tech University, Nanjing, China

The final, formatted version of the article will be published soon.

    In small-current grounding systems, when a single-phase grounding fault occurs, the resulting fault current is relatively small and the transient process is complex, leading to low accuracy and poor reliability in single-phase grounding line selection. This paper proposes a single-phase grounding line selection method based on a transfer learning model using Residual Network 50 (ResNet-50). The zero-sequence voltage and zero-sequence current waveforms at the moment of the fault are preprocessed and superimposed to generate the training data required by the residual network. The ResNet-50 model is subsequently trained to perform grounding line selection. Simulation results conducted with Power Systems Computer Aided Design (PSCAD) demonstrate the high accuracy and reliability of the proposed method, achieving a validation accuracy of 99.77% even in noisy environments. These results confirm the feasibility and effectiveness of the method in accurately identifying grounding faults under various conditions.

    Keywords: Small-current grounding system, Grounding fault line selection, Image Recognition, Convolutional Neural Network, Transfer Learning

    Received: 31 Jul 2024; Accepted: 25 Sep 2024.

    Copyright: © 2024 Wan and Xu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Guangfen Wan, China National Offshore Oil Corporation (China), Beijing, 100010, Beijing Municipality, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.