电器与能效管理技术 ›› 2022, Vol. 0 ›› Issue (8): 33-38.doi: 10.16628/j.cnki.2095-8188.2022.08.005

• 研究论文 • 上一篇    下一篇

基于边缘计算和小波神经网络的配电网故障定位研究

许欣, 张颖   

  1. 长沙理工大学 电气与信息工程学院, 湖南 长沙 410114
  • 收稿日期:2022-02-01 出版日期:2022-08-30 发布日期:2022-10-11
  • 作者简介:许欣(1996—),男,硕士研究生,研究方向为配电网故障定位。|张颖(1963—),男,教授,研究方向为配电网新技术及网络技术的应用。

Research on Fault Location of Distribution Network Based on Edge Computing and Wavelet Neural Network

XU Xin, ZHANG Ying   

  1. College of Electrical & Information Engineering,Changsha University of Science & Technology,Changsha 410114,China
  • Received:2022-02-01 Online:2022-08-30 Published:2022-10-11

摘要:

随着电力物联网的迅速发展,为进一步提高配电网故障定位的精准度,提出了一种基于边缘计算和小波神经网络的配电网故障定位方法。首先对终端进行重新划分,将其分为具有计算功能的汇集终端和故障信息收集的采集终端,然后对故障电流信号进行小波变换和小波包频带分解得到故障特征向量,最后通过神经网络训练,输出诊断结果。仿真算例验证了所提方法能够减少故障诊断时间,提高故障定位精准度。

关键词: 配电网, 故障定位, 边缘计算, 小波神经网络

Abstract:

With the rapid development of the power internet of things,in order to further improve the accuracy of fault location in the distribution network,a method of distribution network fault location based on the edge computing and wavelet neural network is proposed.Firstly,the terminal is redivided into a collection terminal with calculation function and a collection terminal for fault information collection.Then,the fault current signal is subjected to wavelet transform and wavelet packet frequency band decomposition to obtain the fault feature vector.Finally,through the neural network training,the output diagnostic result the is obtained.The simulation results show that this method can reduce the time of fault diagnosis and improve the accuracy of fault location.

Key words: distribution network, fault location, edge computing, wavelet neural network

中图分类号: