Fault Line Selection Method for Power Distribution Network Based on Graph Transformation and ResNet50 Model

被引:1
|
作者
Wang, Haozhi [1 ]
Shi, Yuntao [1 ]
Guo, Wei [1 ]
机构
[1] North China Univ Technol, Sch Elect & Control Engn, Beijing 100044, Peoples R China
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
low-current grounding fault line selection; single-phase grounding fault; Euler's rule; convolutional neural network; SINGLE-PHASE; LOCATION;
D O I
10.3390/info15070375
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Low-current grounding systems are the main grounding method used in power distribution networks and belong to non-direct grounding systems. The most common fault in this type of system is a single-phase grounding fault, which may cause electrical fires and endanger personal safety. Due to the difficulty of troubleshooting, the selection of fault lines in low-current grounding systems has always been an important research topic in power system relay protection. This study proposes a new approach for fault identification of power lines based on the Euler transformation and deep learning. Firstly, the current signals of the distribution network are rapidly Fourier-transformed to obtain their frequencies for constructing reference signals. Then, the current signals are combined with the reference signals and transformed into images using Euler transformation in the complex plane. The images are then classified using a residual network model. The convolutional neural network in the model can automatically extract fault feature vectors, thus achieving the identification of faulty lines. The simulation was conducted based on the existing model, and extensive data training and testing were performed. The experimental results show that this method has good stability, fast convergence speed, and high accuracy. This technology can effectively accomplish fault identification in power distribution networks.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] An adaptive fault line selection method based on atomic comprehensive measure values for distribution network
    Wei, Xiangxiang
    Yang, Dechang
    Wen, Boying
    Wang, Xiaowei
    Yin, Chenhui
    Gao, Jie
    INTERNATIONAL TRANSACTIONS ON ELECTRICAL ENERGY SYSTEMS, 2017, 27 (06):
  • [32] Fault Line Selection Method Based on Sparse Decomposition and Comprehensive Measure Values for Distribution Network
    Yang D.
    Wei X.
    Wen B.
    Wang X.
    Gaodianya Jishu/High Voltage Engineering, 2017, 43 (05): : 1526 - 1534
  • [33] Single-Phase Fault Line Selection in Distribution Network Based on Signal Injection Method
    Niu, Lin
    Wu, Guiqing
    Xu, Zhangsheng
    IEEE ACCESS, 2021, 9 : 21567 - 21578
  • [34] On Fault Line Selection System in Distribution Network
    Li, Bo
    PROCEEDINGS OF THE 31ST CHINESE CONTROL CONFERENCE, 2012, : 7493 - 7496
  • [35] Adaptive semi-supervised facial expression recognition method based on improved ResNet50
    Lin, Z.Q.
    Wang, S.W.
    International Journal of Intelligent Systems Technologies and Applications, 2024, 22 (03) : 313 - 332
  • [36] A Stay Cable Icing Identification Method Based on the Fusion of U-Net and ResNet50
    Yang, Zhiyong
    Xiong, Feng
    Pei, Yaoyao
    Chen, Zhi
    Zhan, Chuanhai
    Hu, Enjie
    Zhang, Guanghao
    APPLIED SCIENCES-BASEL, 2024, 14 (07):
  • [37] Modified ResNet50 model and semantic segmentation based image co-saliency detection
    Mangal, Anuj
    Garg, Hitendra
    Bhatnagar, Charul
    JOURNAL OF INFORMATION & OPTIMIZATION SCIENCES, 2023, 44 (06): : 1035 - 1042
  • [38] A Bootstrapped Transfer Learning Model Based on ResNet50 and Xception to Classify Buildings Post Hurricane
    Wan, Zijin
    Gu, Tianyang
    2021 2ND INTERNATIONAL CONFERENCE ON BIG DATA & ARTIFICIAL INTELLIGENCE & SOFTWARE ENGINEERING (ICBASE 2021), 2021, : 265 - 270
  • [39] A Fault Line Selection Method for DC Distribution Network Using Multiple Observers
    Zhang, Xipeng
    Tai, Nengling
    Wu, Pan
    Zheng, Xiaodong
    Huang, Wentao
    ENERGIES, 2019, 12 (07)
  • [40] Diagnosis of Various Skin Cancer Lesions Based on Fine-Tuned ResNet50 Deep Network
    Abd ElGhany, Sameh
    Ibraheem, Mai Ramadan
    Alruwaili, Madallah
    Elmogy, Mohammed
    CMC-COMPUTERS MATERIALS & CONTINUA, 2021, 68 (01): : 117 - 135