杨帆,宿磊,沈煜,徐丙垠,薛永端,王玮,邹国锋.基于交叉自编码网络的故障漏电电流分离方法[J].电子测量与仪器学报,2021,35(11):185-193
基于交叉自编码网络的故障漏电电流分离方法
Fault leakage current separation method basedon cross auto encoder network
  
DOI:
中文关键词:  故障漏电电流  电气火灾  触电  深度学习  自动编码网络  交叉融合
英文关键词:fault leakage current  electrical fire  electric shock  deep learning  sparse auto encoder network  cross fusion
基金项目:国网湖北省电力有限公司科技项目(52153220001V)资助
作者单位
杨帆 国网湖北省电力有限公司电力科学研究院武汉430077 
宿磊 国网湖北省电力有限公司电力科学研究院武汉430077 
沈煜 国网湖北省电力有限公司电力科学研究院武汉430077 
徐丙垠 山东理工大学电气与电子工程学院淄博255049;山东科汇电力自动化股份有限公司淄博255087 
薛永端 中国石油大学(华东)新能源学院青岛266580 
王玮 山东理工大学电气与电子工程学院淄博255049;山东科汇电力自动化股份有限公司淄博255087 
邹国锋 山东理工大学电气与电子工程学院淄博255049;山东科汇电力自动化股份有限公司淄博255087 
AuthorInstitution
Yang Fan Electric Power Research Institute of State Grid Hubei Electric Power Co., Ltd., Hubei, Wuhan 430077, China 
Su Lei Electric Power Research Institute of State Grid Hubei Electric Power Co., Ltd., Hubei, Wuhan 430077, China 
Shen Yu Electric Power Research Institute of State Grid Hubei Electric Power Co., Ltd., Hubei, Wuhan 430077, China 
Xu Bingyin School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo 255049, China;Shandong Kehui Power Automation Co.,Ltd., Zibo 255087,China; 
Xue Yongduan College of New Energy, China University of Petroleum (East China 
Wang Wei School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo 255049, China;Shandong Kehui Power Automation Co.,Ltd., Zibo 255087,China; 
Zou Guofeng School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo 255049, China;Shandong Kehui Power Automation Co.,Ltd., Zibo 255087,China; 
摘要点击次数: 423
全文下载次数: 0
中文摘要:
      从剩余电流中分离故障支路电流是典型的新数据预测问题,目前故障支路电流分离方法匮乏且准确度较低。本文提出一种小规模交叉自编码深度网络模型构建策略,并将其用于剩余电流中准确分离故障支路电流。首先,在剩余电流和故障漏电电流数据集上分别独立训练自动编码网络;然后,截取剩余电流数据集的特征编码模块和故障漏电电流数据集的特征解码模块,将两者级联构成交叉自编码网络;最后,采用成对剩余电流 故障漏电电流数据微调训练交叉自编码网络,获得剩余电流到故障漏电电流的分离映射模型。误差阈值设置为5时,分离平均准确率达7733%;误差阈值为15时,平均准确率达8867%,能较好地实现了故障漏电电流分离,为智能化电流分离式剩余电流保护器设计提供了技术支持。
英文摘要:
      Accurate separation of fault leakage current from residual current was a typical new data prediction problem, the methods of fault leakage current separation were scarce and the accuracy was low. In this paper, we proposed a construction strategy of small scale cross auto encoder deep network, and applied the model to separate fault leakage current from the residual current. First, two independent auto encoder networks were learned on the residual current dataset and the fault leakage current dataset respectively. Then, the feature encoding module of residual current and the feature decoding module of fault leakage current were cascaded to form a cross auto encoder network. Finally, separation mapping model of residual current to fault leakage current was obtained by using the paired residual current and fault leakage current for fine tuning training of the cross auto encoder network. Experiment results showed that the average separation accuracy was 7733% when the error threshold was set to 5. When the error threshold was 15, the accuracy was up to 8867%. Obviously, the method can realize the separation of fault leakage current and provide the technical support for the design of intelligent current separation residual current protection device.
查看全文  查看/发表评论  下载PDF阅读器