摘要
针对航空串联电弧故障的检测与识别问题,提出一种基于相关系数和偏态指标的航空电弧故障检测方法。通过提取不同负载电流信号的相关系数和偏态指标,构建二维特征量,分析对比了隐含层节点数对极限学习机性能的影响,引入灰狼优化的极限学习机进行分类识别。对阻性、阻感性、阻容性和非线性负载的大量实验结果表明,所提方法能够有效提取不同负载电弧故障特征,串联电弧故障诊断率高达98%,可为开发新型的航空电弧故障断路器提供可靠参考。
In response to the problem of detecting and identifying aviation series arc fault, a detection method based on correlation coefficient and bias-normal distribution index was proposed. By extracting the correlation coefficient and the bias-normal distribution index of different load current signals, the two-dimensional characteristic quantity was constructed, the influence of the number of hidden layer nodes on the performance of extreme learning machine was analyzed and compared, and the extreme learning machine for grey wolf optimization algorithm was introduced to classify and identify. Through a large number of experiments on resistive, inductive, capacitive and non-linear loads, the results show that the proposed method can effectively extract different load arc fault characteristics, and the series arc fault diagnosis rate is as high as 98%, which can provide reliable reference for developing new type of aviation arc fault detection device.
作者
崔芮华
王洋
李英男
CUI Rui-hua;WANG Yang;LI Ying-nan(State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, Tianjin 300130, China;Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology, Tianjin 300130, China)
出处
《电工电能新技术》
CSCD
北大核心
2019年第1期83-89,共7页
Advanced Technology of Electrical Engineering and Energy
基金
河北省自然科学青年基金项目(E2015202143)
河北省教育厅青年基金项目(QN2014148)
关键词
串联电弧故障
相关系数
偏态指标
航空故障
极限学习机
series-arc fault
correlation coefficient
bias-normal distribution index
aviation fault
extreme learning machine
