A Fault-Line Selection Method for Small-Current Grounded System Based on Deep Transfer Learning

被引:4
|
作者
Su, Xianxin [1 ]
Wei, Hua [1 ]
机构
[1] Guangxi Univ, Guangxi Key Lab Power Syst Optimizat & Energy Tec, Nanning 530004, Peoples R China
基金
中国国家自然科学基金;
关键词
small-current grounded system; single-phase grounding fault; fault-line selection; deep transfer learning; deep learning;
D O I
10.3390/en15093467
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Usually, data-driven methods require many samples and need to train a specific model for each substation instance. As different substation instances have similar fault features, the number of samples required for model training can be significantly reduced if these features are transferred to the substation instances that lack samples. This paper proposes a fault-line selection (FLS) method based on deep transfer learning for small-current grounded systems to solve the problems of unstable training and low FLS accuracy of data-driven methods in small-sample cases. For this purpose, fine-turning and historical averaging techniques are proposed for use in transfer learning to extract similar fault features from other substation instances and transfer these features to target substation instances that lack samples to improve the accuracy and stability of the model. The results show that the proposed method obtains a much higher FLS accuracy than other methods in small-sample cases; it has a strong generalization ability, low misclassification rate, and excellent application value.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Fault-Line Selection Method for Small-Current Grounded System Based on Multi-classifier
    Su, Xianxin
    Wei, Hua
    Wei, Hongbo
    Lyu, Zhongliang
    Zhang, Xuan
    Gao, Wei
    JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2023, 18 (02) : 941 - 952
  • [2] Fault-Line Selection Method for Small-Current Grounded System Based on Multi-classifier
    Xianxin Su
    Hua Wei
    Hongbo Wei
    Zhongliang Lyu
    Xuan Zhang
    Wei Gao
    Journal of Electrical Engineering & Technology, 2023, 18 : 941 - 952
  • [3] Research on Fault Line Selection in Small-current Neutral Grounding Power System
    Cheng, Hai-Jun
    Meng, Hui
    Jiang, Pi-Jie
    2013 IEEE INTERNATIONAL CONFERENCE ON VEHICULAR ELECTRONICS AND SAFETY (ICVES), 2013, : 206 - 209
  • [4] A new approach to fault-line selection of small current neutral grounding system
    Chen, Yujie
    Chen, Huiwei
    Song, Baoye
    Liu, Yanni
    Liu, Peixue
    SYSTEMS SCIENCE & CONTROL ENGINEERING, 2018, 6 (03): : 28 - 34
  • [5] Research on Extension Method and Detection of Fault-Line Selection in Resonant Grounded Systems
    Li Bin
    Shu Hongchun
    2008 JOINT INTERNATIONAL CONFERENCE ON POWER SYSTEM TECHNOLOGY (POWERCON) AND IEEE POWER INDIA CONFERENCE, VOLS 1 AND 2, 2008, : 723 - 726
  • [6] A Fault Line Selection Method for Small Current Grounding System Based on Big Data
    Shao, Zheng
    Wang, Liancheng
    Zhang, Han
    2016 IEEE PES ASIA-PACIFIC POWER AND ENERGY ENGINEERING CONFERENCE (APPEEC), 2016, : 2470 - 2474
  • [7] Fault Line Selection Method for Small Current Grounding System Based on Improved GoogLeNet
    Hao S.
    Zhang X.
    Ma R.
    Wen H.
    Ma X.
    An B.
    Li J.
    Dianwang Jishu/Power System Technology, 2022, 46 (01): : 361 - 368
  • [8] The fault line selection method of small current grounding system based on wavelet transformation
    Li, Hua
    Li, Lingling
    Huang, Shanshan
    Li, Fengqiang
    PROGRESS IN POWER AND ELECTRICAL ENGINEERING, PTS 1 AND 2, 2012, 354-355 : 149 - 152
  • [9] Fault Line Selection Method of Small Current to Ground System Based on Atomic Sparse Decomposition and Extreme Learning Machine
    Wang, Xiaowei
    Wei, Yanfang
    Zeng, Zhihui
    Hou, Yaxiao
    Gao, Jie
    Wei, Xiangxiang
    JOURNAL OF SENSORS, 2015, 2015
  • [10] Distributed small-current grounding fault locating method based on power distribution network automation system
    Song Y.
    Li T.
    Xue Y.
    Huang J.
    Chen H.
    Xu B.
    Dianli Zidonghua Shebei/Electric Power Automation Equipment, 2018, 38 (04): : 102 - 109