摘要
一般利用故障电弧产生时的电流波形特性进行电弧故障检测。随着线路负载种类的日益增多,故障电弧产生时的电流波形与某些负载无弧情况下的电流波形十分相似,难以通过简单的电流时频域特征进行电弧故障检测,影响电弧故障检测的准确性。针对该问题,提出一种自组织特征映射网络与滑窗法相结合的电弧故障检测方法,在自组织特征映射网络自主挖掘电流数据内在特征的基础上,利用相邻周期电流样本之间的关联性与连续性,对电流信号进行连续检测,提高电弧故障检测准确率。所提方法能有效实现电弧故障检测,电弧故障检测准确率可达99%。
Fault arcs are generally identified by characteristics of the current waveform when arc faults occur.As the types of loads are increasing,the fault current waveforms are very similar to the current waveforms of some loads without arc.It is difficult to detect the arc fault by the simple time or frequency domain characteristics of the current,which affects the accuracy of the arc fault detection.In order to solve this problem,an arc fault detection method of combining self-organizing feature mapping network with sliding window method is proposed.Based on the intrinsic characteristics of current data obtained by the selforganizing feature mapping network,by making use of the correlation and continuity between the adjacent periodic current samples,the current signal is detected continuously to improve the accuracy of arc fault detection.The proposed method can effectively detect the arc fault,and the accuracy of arc fault detection reaches 99%.
作者
林靖怡
王尧
李奎
田明
LIN Jingyi;WANG Yao;LI Kui;TIAN Ming(State Key Laboratory of Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300130,China;Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province,Hebei University of Technology,Tianjin 300130,China)
出处
《电力自动化设备》
EI
CSCD
北大核心
2020年第8期210-216,共7页
Electric Power Automation Equipment
基金
国家自然科学基金资助项目(51607055)。
关键词
故障电弧
电流波形
自组织特征映射网络
滑窗法
电弧故障检测
fault arcs
current waveform
self-organizing feature mapping network
sliding window method
arc fault detection