摘要
如果小电流系统中,由于种种原因发生接地故障时,流过故障点的电流很小,长时间运行会影响系统的安全,现有的方法在选线中存在着不足之处,该文提出了一种基于小波分析和GA-SVM的故障选线方法,通过在MATLAB中搭建小电流系统,模拟接地故障,利用小波包变换从零序电流中提取暂态特征值,并且作为GA-SVM的输入特征进行训练,用训练好的SVM对测试集进行检测,得到选线的结果。从结果上看,利用该方法进行选线,能够准确的选出故障线路,并且不受故障相位角和接地电阻等因素的影响。
If the grounding fault occurs in the small current system due to various reasons,the current flowing through the fault point is very small,and long-time operation will affect the safety of the system.The existing methods have shortcomings in line selection.In this paper,a fault line selection method based on wavelet analysis and GA-SVM is proposed,the small current system is built in MATLAB to simulate the grounding fault,and the wavelet packet transform is used the transient characteristic value is extracted from the zero sequence current and trained as the input characteristic of GA-SVM.The trained SVM is used to detect the test set and get the result of line selection.From the results,the fault line can be selected accurately by using this method,and it is not affected by the fault phase angle,grounding resistance and other factors.
作者
张祚淏
王利恒
ZHANG Zuo-hao;WANG Li-heng(School of Electrical and Information Engineering,Wuhan Institute of Technology,Wuhan 430205,China)
出处
《自动化与仪表》
2021年第8期8-12,23,共6页
Automation & Instrumentation
基金
武汉工程大学研究生教育创新基金资助项目(CX2020076)。
关键词
小电流接地系统
遗传算法优化支持向量机
小波分析
零序电流
small current grounding power system
genetic algorithm-support vector machine(GA-SVM)
wavelet analysis
zero sequence current
