基于多特征融合的交流系统串联电弧故障诊断.pdfVIP

38 卷 3 期 电 网 技 术 Vol. 38 No. 3 20 14 年3 月 Power System Technology Mar. 20 14 文章编号：1000-3673 （20 14）03-0795-07 中图分类号：TM 50 1 文献标志码：A 学科代码：470 4027 基于多特征融合的交流系统串联电弧故障诊断 刘晓明，赵洋，曹云东，侯春光 （沈阳工业大学 电气工程学院，辽宁省 沈阳市 110870 ） Multi-Feature Fusion Based Diagnosis of Series Arc Faults in AC System LIU Xiaoming, ZHAO Yang, CAO Yundong, HOU Chunguang (School of Electrical Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning Province, China) ABSTRACT: To diagnose series arc faults occurred in 多层前馈神经网络构建特征向量与电弧故障之间的映射关 low-voltage side at power utilization system accurately, 系。测试结果表明，该方法可减小电弧燃烧对诊断结果的影 according to three features of low-voltage series arc fault 响，实现对串联电弧故障的诊断分类。 signals, namely the singularity, the uncertainty and the energy 关键词：电弧故障；小波变换；多特征融合；故障诊断；神 features, in AC power system and based on simulation 经网络 experiment results of series arc faults under different loads DOI 10.13335/j.1000-3673.pst.2014.03.038 carried out by the self-constructed experimental platform, a multi-feature fusion based series arc fault diagnosis method is 0 引言 proposed. According to the three features of signal and 现代工业的发展导致居民用电量不断增加，电 combining with wavelet transform theory, the proposed method 气火灾现已成为造成人身安全及财产损失的巨大 performs principal component analysis (PCA) for sampled [1] signals, whose noise is preprocessed and extr