摘要
输电过程中突变电流对电网影响极大,因此精准识别弧光接地故障非常重要。利用小波变换和BP神经网络算法对弧光接地故障进行分类判断。首先选用db3小波基对10 kV架空线路三相同步录波信号进行小波变换,通过对故障电流信号奇异点检测,完成三相同步录波信号模极大值的提取,并作为BP神经网络的训练样本,最后重构获得测试样本空间的分类结果。以实际采集的三相同步录波信号及状态标签为标准,基于小波变换和神经网络预测的分类结果准确率达到99%以上。
In view of the great impact of sudden current on the power grid during the transmission process,it is very important to accurately identify arc grounding fault.The arc grounding fault is classified and judged by wavelet transform and BP neural network algorithm in the paper.Firstly,db3 wavelet base is selected to perform wavelet transform on three-phase synchronous oscillograph signal of 10kV overhead line.By detecting the singularity of the fault current signal,the module maximum of the three-phase synchronous oscillograph signal is extracted and used as the training sample of the BP neural network.Finally,the classification results of the test sample space are reconstructed.The accuracy of classification results based on wavelet transform and neural network prediction is more than 99%based on the actual three-phase synchronous recording signals and status tags.
作者
陈雨娟
顾涛
CHEN Yujuan;GU Tao(School of Safety Engineering,North China Institute of Science and Technology,Yanjiao,065201,China;School of Computing,North China Institute of Science and Technology,Yanjiao,065201,China)
出处
《华北科技学院学报》
2023年第1期56-62,共7页
Journal of North China Institute of Science and Technology
基金
中央高校基本科研业务费资助项目(3142015024)
河北省物联网监控工程技术研究中心基金项目(3142016020)。
关键词
单相弧光接地
小波奇异性检测
BP神经网络
模极大值
single phase arc grounding
wavelet singularity detection
BP neural network
modulus maximum
作者简介
陈雨娟(1998-),女,河南周口人,华北科技学院安全工程学院在读硕士研究生,研究方向:安全生产自动化与信息化。E-mail:1432456831@qq.com;通讯作者:顾涛(1973-),男,安徽蚌埠人,硕士,华北科技学院副教授,研究方向:ARM嵌入式系统、配电网故障定位技术、噪音中的信号检测。E-mail:1432456831@qq.com。
