GIS Partial Discharge Diagnosis Method Based on Deformable Convolution and Self-supervised Contrastive Learning

被引：0
|
作者：
Zhang, Ruilin [1 ]
Zhang, Yue [2 ]
Sun, Xiaolan [3 ]
Qian, Yong [1 ]
Sheng, Gehao [1 ]
Jiang, Xiuchen [1 ]
机构：
[1] School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai,200240, China
[2] Shibei Power Supply Company, State Grid Shanghai Electric Power Company, Shanghai,200040, China
[3] State Grid Qingdao Power Supply Company, Qingdao,266002, China
来源：
Gaodianya Jishu/High Voltage Engineering | 2024年 / 50卷 / 11期
关键词：
In high-voltage substation; the accuracy of gas insulated switchgear (GIS) partial discharge diagnosis is restricted by the number of labeled samples. In order to solve the problem that unlabeled data cannot be used in conventional partial discharge diagnosis methods; and the difference between training samples and samples to be tested cannot be overcome; a GIS partial discharge diagnosis method based on deformable convolution and self-supervised contrastive learning is proposed in this paper. First; the feature extraction network is trained by comparing the similarity and difference between the unlabeled data samples to obtain the feature representation of the input data. Then; the classifier is trained by the labeled data to learn the defect categories represented by the features of different partial discharge data. Finally; the samples to be tested are input into the model to achieve partial discharge diagnosis. In order to further improve the perception ability of the model in the process of feature extraction; a deformable convolutional neural network and a spatial transform module are introduced to enhance the adaptability of the convolutional check feature map. The results show that self-supervised contrastive learning can make full use of unlabeled data to achieve efficient feature capture. In the case of insufficient labeled data; the model pre-trained by unlabeled data can improve the PD diagnosis accuracy by 9.34% on average. The self-supervised contrastive learning method proposed in this paper can provide a new solution for the partial discharge diagnosis. © 2024 Science Press. All rights reserved;
D O I：
10.13336/j.1003-6520.hve.20231406
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：5022 / 5033
相关论文
共 50 条
  • [31] Contrastive learning based self-supervised time-series analysis
    Poppelbaum, Johannes
    Chadha, Gavneet Singh
    Schwung, Andreas
    APPLIED SOFT COMPUTING, 2022, 117
  • [32] A Contrastive Learning Battery State of Health Estimation Method Based on Self-supervised Aging Representation
    Li, Jiaqi
    Zhu, Jingzhe
    Huang, Ziying
    Fan, Guodong
    Zhang, Xi
    IFAC PAPERSONLINE, 2023, 56 (02): : 6130 - 6135
  • [33] CONTRASTIVE HEARTBEATS: CONTRASTIVE LEARNING FOR SELF-SUPERVISED ECG REPRESENTATION AND PHENOTYPING
    Wei, Crystal T.
    Hsieh, Ming-En
    Liu, Chien-Liang
    Tseng, Vincent S.
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 1126 - 1130
  • [34] Self-Supervised Contrastive Learning for Volcanic Unrest Detection
    Bountos, Nikolaos Ioannis
    Papoutsis, Ioannis
    Michail, Dimitrios
    Anantrasirichai, Nantheera
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [35] DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning
    Nguyen, Thanh
    Pham, Trung Xuan
    Zhang, Chaoning
    Luu, Tung M.
    Vu, Thang
    Yoo, Chang D.
    IEEE ACCESS, 2023, 11 : 21534 - 21545
  • [36] Self-Supervised Contrastive Learning In Spiking Neural Networks
    Bahariasl, Yeganeh
    Kheradpisheh, Saeed Reza
    PROCEEDINGS OF THE 13TH IRANIAN/3RD INTERNATIONAL MACHINE VISION AND IMAGE PROCESSING CONFERENCE, MVIP, 2024, : 181 - 185
  • [37] Self-supervised Contrastive Learning for Predicting Game Strategies
    Lee, Young Jae
    Baek, Insung
    Jo, Uk
    Kim, Jaehoon
    Bae, Jinsoo
    Jeong, Keewon
    Kim, Seoung Bum
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, 2023, 542 : 136 - 147
  • [38] Contrasting Contrastive Self-Supervised Representation Learning Pipelines
    Kotar, Klemen
    Ilharco, Gabriel
    Schmidt, Ludwig
    Ehsani, Kiana
    Mottaghi, Roozbeh
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 9929 - 9939
  • [39] CONTRASTIVE SELF-SUPERVISED LEARNING FOR WIRELESS POWER CONTROL
    Naderializadeh, Navid
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 4965 - 4969
  • [40] Contrastive Self-Supervised Learning for Skeleton Action Recognition
    Gao, Xuehao
    Yang, Yang
    Du, Shaoyi
    NEURIPS 2020 WORKSHOP ON PRE-REGISTRATION IN MACHINE LEARNING, VOL 148, 2020, 148 : 51 - 61
12345