摘要
故障电弧分为串联电弧和并联电弧,并联电弧故障表现为电流短路、故障电流大,现有电气保护体系能对其保护;而串联电弧故障因受线路负载限制,其故障电流小,以至于现有体系无法实现对串联电弧故障保护,存在电气安全隐患。提出一种方法通过实验获得正常工作和电弧故障时电流波形,并提取小波变换的特征值,将特征值输入概率神经网络模型,参照UL 1699标准,通过计算0.5 s内检测到的故障半周期数是否大于8,大于8则判断为电弧故障。通过MATLAB分析,选择40组测试数据,故障识别率为95%,表明了该方法的有效性。
The arc fault includes parallel arc and series arc.The parallel arc fault is characterized by short circuit current and fault current is large,which can be protected by the current circuit breaker.The series arc fault is limited by the load and fault current is small,which cannot be protected by the current circuit breaker.The current waveform of normal operation and arc fault is obtained through experiments,and the characteristic values of wavelet transform are extracted.The characteristic value was input into the probabilistic neural network model.According to UL1699standard,arc fault is judged by calculating whether the half-cycle fault number is greater than8in0.5s.Using MATLAB simulation,40groups of test data are selected.38groups of test results are correct and2groups are wrong.The fault identification rate is95%,which shows the effectiveness of the method.
作者
吴丰成
曲娜
任行浩
许凯
张鹏辉
Wu Fengcheng;Qu Na;Ren Xinghao;Xu Kai;Zhang Penghui(School of Safety Engineering,Shenyang Aerospace University,Shenyang 110136,China)
出处
《电子技术应用》
2018年第12期65-68,共4页
Application of Electronic Technique
基金
沈阳航空航天大学大学生创新创业训练项目(X1701156
S1701058)
辽宁省教育厅科学研究项目(L201742)
关键词
电弧故障检测
概率神经网络
特征信号值
小波变换
arc fault detection
probalitistic neural network
feature signal value
wavelet transform
作者简介
吴丰成(1996-),男,本科,主要研究方向:电弧故障理论与技术;通信作者,曲娜(1979-),女,硕士,讲师,主要研究方向:电气火灾探测理论与技术,E-mail:mn_qn@qq.com。
