• Home
  • Search
  • Partial Discharge Diagnosis Using Semi-Supervised Learning and Complementary Labels in Gas-Insulated Switchgear
  • Cite Icon5
  • https://doi.org/10.1109/access.2025.3556353Copy DOI Icon

Partial Discharge Diagnosis Using Semi-Supervised Learning and Complementary Labels in Gas-Insulated Switchgear

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep neural networks have proven to be highly efficient in fault detection and classification using partial discharges (PDs) in gas-insulated switchgear (GIS). However, previous studies have not fully addressed the issue of limited labeled training data, which significantly impacts the performance of these models. Existing semi-supervised learning (SSL) approaches typically discard low-confidence pseudo-labels from unlabeled PD samples, because these unreliable labels can mislead the model. This gap in current research overlooks the potential value of low-confidence samples, which, despite their uncertain class, are unlikely to belong to the classes with the lowest probabilities. In this study, we aim to overcome this limitation by proposing a novel semi-supervised contrastive complementary learning (SCCL) method. Our SCCL approach generates a larger set of reliable negative pairs using complementary labels, allowing us to utilize the entire set of unlabeled PD samples effectively. We validate the feasibility of SCCL using phase-resolved PDs (PRPDs) and onsite noise data collected through an ultrahigh-frequency (UHF) PD measurement system. Experimental results indicate that the SCCL method achieves an impressive accuracy of 96.23% by effectively leveraging low-confidence unlabeled PD samples to improve classification performance in GIS under restricted labeling conditions.

Similar Papers
  • Research Article
  • Citations8

Semi-Supervised Learning-Based Partial Discharge Diagnosis in Gas-Insulated Switchgear

  • Jan 01, 2024
  • IEEE Access
  • Ho Trong Tai +3
  • Dissertation
  • Citations1

Advanced signal processing techniques for online power transformer insulation diagnosis

  • Oct 23, 2015
  • The University of Queensland
  • Chi Ho Chan
  • Research Article
  • Citations19

Partial Discharge Diagnosis in GIS based on Pulse Sequence Features and Optimized Machine Learning Classification Techniques

  • Jun 15, 2022
  • Electric Power Systems Research
  • Diaa-Eldin A Mansour +3
  • Conference Article
  • Citations7

Combined broad and narrow band multichannel PD measurement system with high sensitivity for GIS

  • Jan 01, 1999
  • S.M Neuhold
  • PDF
  • Research Article
  • Citations32

Deep Ensemble Model for Unknown Partial Discharge Diagnosis in Gas-Insulated Switchgears Using Convolutional Neural Networks

  • Jan 01, 2021
  • IEEE Access
  • Vo-Nguyen Tuyet-Doan +3
  • Research Article
  • Citations1

A novel modal fusion method using cross-attention for partial discharge pattern recognition in gas insulated switchgear

  • Aug 26, 2025
  • Measurement Science and Technology
  • Yanqi Liu +7
  • Conference Article
  • Citations3

Partial discharge detection at delamination of electrode/epoxy interface in GIS spacers

  • Aug 01, 2009
  • Diaa-Eldin A Mansour +4
  • Research Article
  • Citations15

Multi-source partial discharge pattern recognition algorithm based on DCGAN-Yolov5

  • Jan 01, 2024
  • IEEE Transactions on Power Delivery
  • Min Wu +4
  • PDF
  • Research Article
  • Citations27

Feature Selection for Partial Discharge Severity Assessment in Gas-Insulated Switchgear Based on Minimum Redundancy and Maximum Relevance

  • Oct 01, 2017
  • Energies
  • Ju Tang +6
  • Conference Article
  • Citations4

Simulation Study on Propagation Characteristics of Optical Signals Excited by Partial Discharge in GIS

  • Sep 06, 2020
  • Xutao Han +3
  • Research Article
  • Citations22

Multi-source partial discharge diagnosis in gas-insulated switchgear via zero-shot learning

  • May 16, 2023
  • Measurement
  • Yanxin Wang +6
  • Conference Article

Development of Partial Discharge and Prediction of Short Term Development Trend of Insulators in GIS

  • Sep 06, 2020
  • Wen-Zhi Chang +5
  • Research Article
  • Citations15

Generative Zero-Shot Learning for Partial Discharge Diagnosis in Gas-Insulated Switchgear

  • Jan 01, 2023
  • IEEE Transactions on Instrumentation and Measurement
  • Yanxin Wang +5
  • Research Article
  • Citations24

Partial discharge diagnosis method using electromagnetic wave mode transformation in actual GIS structure

  • Oct 01, 2008
  • IEEE Transactions on Dielectrics and Electrical Insulation
  • S Kaneko +5
  • Research Article
  • Citations42

Partial Discharge Detection in Gas-Insulated Switchgears Using Sensors Integrated With UHF and Optical Sensing Methods

  • Oct 01, 2022
  • IEEE Transactions on Dielectrics and Electrical Insulation
  • Xutao Han +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.