Cable incipient fault classification and identification based on optimized convolution neural network

被引：0
作者：
Wang Y. [1 ]
Sun J. [1 ]
Xiao X. [1 ]
Lu H. [1 ]
Yang X. [1 ]
机构：
[1] College of Electrical Engineering, Sichuan University, Chengdu
来源：
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2020年 / 48卷 / 07期
基金：
中国国家自然科学基金;
关键词：
Cable incipient fault; Classification identification; Convolution neural network; Deep learning; Modified loss function;
D O I：
10.19783/j.cnki.pspc.190581
中图分类号：
学科分类号：
摘要：
It is necessary to identify the cable incipient faults in order to eliminate the hidden faults in time. This paper proposes a method for cable incipient fault classification and identification based on Convolution Neural Network (CNN). This method can identify the cable incipient fault from the over-current disturbance waveforms, including the waveforms of constant impedance fault, inrush current, capacitance switching disturbance waveform, and so on. The features of the over-current waveforms are extracted by wavelet transform, which are used as the input of CNN. By training the mapping relationship between input features and class coding, the parameter is chosen and the CNN is formed. CNN is optimized by modifying the loss function and adopting the method of adaptive learning rate, for solving the problem of over-fitting and learning efficiency. The simulation results show that the proposed method can classify the overcurrent signals effectively and identify cable incipient fault accurately, which is with high engineering application value. © 2020, Power System Protection and Control Press. All right reserved.
引用
收藏
页码：10 / 18
页数：8
相关论文
共 22 条
  • [1] DAI Ming, Discussion methods of incipient fault detection and identification in 10 kV underground cables, (2012)
  • [2] SIDHU T S, XU Z., Detection of incipient faults in distribution underground cables, IEEE Transactions on Power Delivery, 25, 3, pp. 1363-1371, (2010)
  • [3] KULKARNI S, SANTOSO S, SHORT T A., Incipient fault location algorithm for underground cables, IEEE Transactions on Smart Grid, 5, 3, pp. 1165-1174, (2014)
  • [4] YAO Haiyan, ZHANG Jing, LIU Yi, Et al., A method of Incipient cable fault detection and identification based on multi-scale wavelet criterion and time-frequency feature correlation, Power System Protection and Control, 43, 9, pp. 115-123, (2015)
  • [5] DJURIC M B, TERZIJA V V., A new approach to the arcing faults detection for fast autoreclosure in transmission systems, IEEE Transactions on Power Delivery, 10, 4, pp. 1793-1798, (1995)
  • [6] ZHANG Wenhai, XIAO Xianyong, ZHOU Kai, Et al., Multi-cycle incipient fault detection and location for medium voltage underground cable, IEEE Transactions on Power Delivery, 32, 3, pp. 1450-1459, (2017)
  • [7] ZHANG Chao, KANG Xiaoning, MA Xiuda, Et al., On-line incipient faults detection in underground cables based on single-end sheath currents, IEEE PES-Pacific Power and Energy Engineering Conference, pp. 795-799, (2016)
  • [8] WANG Ying, LU Hong, YANG Xiaomei, Et al., Cable incipient fault identification based on stacked autoencoder and S-transform, Electric Power Automation Equipment, 38, 8, pp. 124-131, (2018)
  • [9] REN Hao, QU Jianfeng, CHAI Yi, Et al., Deep learning for fault diagnosis: the state of the art and challenge, Control and Decision, 32, 8, pp. 1345-1358, (2017)
  • [10] LIN Musong, GUO Kun, ZHANG Sheng, Et al., Progress in flexible conductive stress-strain materials, Polymer Materials Science & Engineering, 33, 12, pp. 149-155, (2017)
123