• HOME
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • Chinese
Site search        
文章摘要
基于机器学习的中压配电网断线不接地故障检测
Disconnected Unground Fault Detection in Medium Voltage Distribution Network Based on Machine Learning
Received:August 07, 2018  Revised:August 07, 2018
DOI:
中文关键词: 中压配电网  断线故障检测  三相用电  特征选择  随机森林
英文关键词: medium voltage distribution network  disconnection detection  three-phase power supply  feature selection  random forest
基金项目:国家电网公司科技项目(52094016002B)
Author NameAffiliationE-mail
Su Yun Electric Power Research Institute,SMEPC oppenvi@163.com 
Zhao Qi* Fudan University 17210180035@fudan.edu.cn 
Qu Haini Electric Power Research Institute,SMEPC hattiequ@126.com 
Hits: 1662
Download times: 789
中文摘要:
      由于中压配电网变电站常采用中性点不接地方式,所以当线路单相断线后断口两侧的导线均不接地或是非电源侧导线落地等情况发生时,没有明显的故障特征产生,且无法通过变电站内现有的继电保护装置对故障进行检测。为解决这一难题,我们基于配用电信息系统数据和改进的随机森林算法,用纯数据驱动的方法,提出了一套可用于中压配电网的断线智能检测系统的方法,可应用于实时的故障检测,这是本文的一大创新之处。其次,以华东某地区配用电信息系统中的历史数据为依据进行实际算例分析,该方法在测试集中的分类的准确度高达91.44%,而且找出了电压为判断配电网断线的主要标准,这为配电网断线不接地故障检测的进一步研究提供了科学的依据。
英文摘要:
      As medium-voltage distribution network substations often use the neutral point is ungrounded, so it will not form some characteristics when a single break line both sides of the wire is ungrounded or non-power side of the wire landing. At present, it is still not possible to determine the fault by the relay protection device in the substation. In order to solve this problem, we propose a system that intelligently detects the disconnection of the distribution network based on data and improved random forest algorithm with electrical information systems and pure data-driven methods,which can be applied to real-time fault detection. This is the major innovation in this article. Besides, based on the historical data from an electrical information system in an area in East China, a practical example is analyzed. The accuracy of classification of this method in the test set is as high as 91.44%, and the voltage is judged as the main criterion in the disconnection of the distribution network, which provides a scientific basis for further research on disconnected unground fault detection in distribution networks.
View Full Text   View/Add Comment  Download reader
Close
  • Home
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • 中文页面
Address: No.2000, Chuangxin Road, Songbei District, Harbin, China    Zip code: 150028
E-mail: dcyb@vip.163.com    Telephone: 0451-86611021
© 2012 Electrical Measurement & Instrumentation
黑ICP备11006624号-1
Support:Beijing Qinyun Technology Development Co., Ltd