A novel adversarial transfer learning in deep convolutional neural network for intelligent diagnosis of gas-insulated switchgear insulation defect A DATCNN for GIS insulation defect diagnosis

被引:18
|
作者
Wang, Yanxin [1 ]
Yan, Jing [1 ]
Jing, Qianzhen [1 ]
Qi, Zhenkang [2 ]
Wang, Jianhua [1 ]
Geng, Yingsan [1 ]
机构
[1] Xi An Jiao Tong Univ, Stare Key Lab Elect Insulat & Power Equip, Xian 710049, Shaanxi, Peoples R China
[2] Tsinghua Univ, State Key Lab Power Syst, Beijing 100084, Peoples R China
关键词
PARTIAL DISCHARGE PATTERNS; FAULT-DIAGNOSIS; RECOGNITION;
D O I
10.1049/gtd2.12255
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Recently, numerous data-driven fault diagnosis methods have been developed, and the tasks involving the same distribution of training and test data have been well solved. However, considering the particularity of gas-insulated switchgear (GIS), collecting massive data, especially with the same distribution, is difficult. Therefore, existing fault diagnosis methods hardly achieve satisfactory insulation defect diagnosis with small datasets. Aiming at solving this problem, a novel domain adversarial transfer convolutional neural network (DATCNN) is proposed, realising the diagnosis of GIS insulation defects on small samples. First, a residual CNN is built to learn feature representations from the source and target domains. Second, the domain adversarial training strategy is used for feature transfer, where a conditional adversarial mechanism is introduced, and the joint distribution of features and labels is improved to a random linear combination, which realises the simultaneous adaptation of features and labels. Finally, the Nesterov accelerated gradient descent optimisation algorithm is used to speed up the gradient convergence. DATCNN has 99.15% and >= 89.5% diagnosis accuracy for GIS insulation defects in the laboratory and on-site, respectively. Comprehensive experiment results show the effectiveness and superiority of the proposed method in diagnosing GIS insulation defects with small samples.
引用
收藏
页码:3229 / 3241
页数:13
相关论文
共 43 条
  • [1] A Novel Domain Adversarial Graph Convolutional Network for Insulation Defect Diagnosis in Gas-Insulated Substations
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Qi, Zhenkang
    Wang, Jianhua
    Geng, Yingsan
    [J]. IEEE TRANSACTIONS ON POWER DELIVERY, 2023, 38 (01) : 442 - 452
  • [2] Gas-Insulated Switchgear Insulation Defect Diagnosis via a Novel Domain Adaptive Graph Convolutional Network
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Qi, Zhenkang
    Wang, Jianhua
    Geng, Yingsan
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [3] A Novel Federated Transfer Learning Framework for Intelligent Diagnosis of Insulation Defects in Gas-Insulated Switchgear
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Dai, Yuannan
    Wang, Jianhua
    Geng, Yingsan
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [4] A novel hybrid meta-learning for few-shot gas-insulated switchgear insulation defect diagnosis
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Qi, Zhenkang
    Wang, Jianhua
    Geng, Yingsan
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2023, 233
  • [5] Meta-autoencoder-based zero-shot learning for insulation defect diagnosis in gas-insulated switchgear
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Wang, Zhanbei
    Wang, Jianhua
    Geng, Yingsan
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (06)
  • [6] A Classification System for Insulation Defect Identification of Gas-Insulated Switchgear (GIS), Based on Voiceprint Recognition Technology
    Yao, Weijia
    Xu, Yongpeng
    Qian, Yong
    Sheng, Gehao
    Jiang, Xiuchen
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (11):
  • [7] Intelligent Diagnosis for GIS with Small Samples Using a Novel Adversarial Transfer Learning in Convolutional Neural Network
    Wang, Yanxin
    Yan, Jing
    Wang, Jianhua
    Geng, Yingsan
    Liu, Zhiyuan
    [J]. Diangong Jishu Xuebao/Transactions of China Electrotechnical Society, 2022, 37 (09): : 2150 - 2160
  • [8] Recurrent Neural Network for Partial Discharge Diagnosis in Gas-Insulated Switchgear
    Minh-Tuan Nguyen
    Viet-Hung Nguyen
    Yun, Suk-Jun
    Kim, Yong-Hwa
    [J]. ENERGIES, 2018, 11 (05)
  • [9] A novel federated deep learning framework for diagnosis of partial discharge in gas-insulated switchgear
    Wang, Yanxin
    Yan, Jing
    Jing, Qianzhen
    Wang, Jianhua
    Geng, Yingsan
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2022, 33 (09)
  • [10] A Domain Adaptive Deep Transfer Learning Method for Gas-Insulated Switchgear Partial Discharge Diagnosis
    Wang, Yanxin
    Yan, Jing
    Yang, Zhou
    Jing, Qianzhen
    Qi, Zhengkang
    Wang, Jianhua
    Geng, Yingsan
    [J]. IEEE TRANSACTIONS ON POWER DELIVERY, 2022, 37 (04) : 2514 - 2523