公茂法,魏景禹,姜文,接怡冰,公政,王万乐

• 1:山东科技大学电气与自动化工程学院
• 2:国网山东电力潍坊供电公司

摘要(Abstract)：

为解决传统傅里叶变换和小波分解对变压器局部放电信号非平稳性的分析缺陷,以及BP神经网络易陷入局部极小点等问题,提出一种基于希尔伯特能量聚类和概率神经网络的变压器局部放电识别算法。算法利用希尔伯特-黄变换提取局部放电信号的希尔伯特能量谱,然后进行指数族聚类计算获得特征值,最后利用概率神经网络进行分类识别。分别对油中悬浮放电、沿面放电等放电类型进行模拟实验,并用此算法进行分析,实验结果表明,该算法所提取的特征值有较高的可分性,且分类识别率高,可以有效地识别变压器局部放电故障类型。

关键词(KeyWords)： 希尔伯特-黄变换;概率神经网络;指数聚类;模态分解;局部放电;变压器

Abstract:

Keywords:

基金项目(Foundation): 山东省自然科学基金(ZR2012EEM021)~~

作者(Author): 公茂法,魏景禹,姜文,接怡冰,公政,王万乐

DOI: 10.16652/j.issn.1004-373x.2018.09.033

参考文献(References)：

• [1]李剑,宁佳欣,金卓睿,等.变压器局部放电在线监测超高频Hilbert分形天线研究[J].电力自动化设备,2007,27(6):31-35.LI Jian,NING Jiaxin,JIN Zhuorui,et al.Research on UHF Hilbert fractal antenna for online transformer PD monitoring[J].Electric power automation equipment,2007,27(6):31-35.
• [2]王旭,彭畅,张振先.基于EEMD的共振解调技术在列车轴承故障诊断中的应用[J].现代电子技术,2015,38(21):24-27.WANG Xu,PENG Chang,ZHANG Zhenxian.Application of EEMD based resonance demodulation technology in train bearing fault diagnosis[J].Modern electronics technique,2015,38(21):24-27.
• [3]DANIKAS M G,GAO N,ARO M.Partial discharge recognition using neural networks:a review[J].Electrical engineering,2003,85(2):87-93.
• [4]HOZUMI N,OKAMOTO T,IMAJO T.Discrimination of partial discharge patterns using neural network[J].IEEE transactions on electrical insulation,1992,27(3):550-556.
• [5]邓雨荣,郭丽娟,郭飞飞,等.引入二代小波的自适应BP神经网络局部放电故障识别[J].电力建设,2013,34(6):87-91.DENG Yurong,GUO Lijuan,GUO Feifei,et al.Partial discharge fault identification by using adaptive BP neural network based on second generation wavelet[J].Electric power construction,2013,34(6):87-91.
• [6]任先文,薛雷,宋阳,等.基于分形特征的最小二乘支持向量机局部放电模式识别[J].电力系统保护与控制,2011,39(14):143-147.REN Xianwen,XUE Lei,SONG Yang,et al.The pattern recognition of partial discharge based on fractal characteristics using LS-SVM[J].Power system protection and control,2011,39(14):143-147.
• [7]袁国森,张彼德,李明昆,等.基于极值比值法和神经网络的逆变器故障诊断[J].电测与仪表,2016(14):34-38.YUAN Guosen,ZHANG Bide,LI Mingkun,et al.Fault diagnosis for inverter based on extremum value ratio and probabilistic neural network[J].Electrical measurement&instrumentation,2016(14):34-38.
• [8]卢丽.EMD方法在局部放电超声信号提取中的应用[J].现代电子技术,2009,32(3):137-139.LU Li.Application of EMD method in extracting ultrasonic signals of transformer partial discharge[J].Modern electronics technique,2009,32(3):137-139.
• [9]许峰,李开成,王可.基于EMD和卡尔曼滤波的振荡信号检测[J].电测与仪表,2015,52(24):60-64.XU Feng,LI Kaicheng,WANG Ke.The detection of oscillation signal based on EMD and Kalman filter[J].Electrical measurement&instrumentation,2015,52(24):60-64.
• [10]李成榕,王彩雄,唐志国,等.基于聚类分析的变压器局部放电智能诊断的研究[J].华北电力大学学报(自然科学版),2008,35(6):7-12.LI Chengrong,WANG Caixiong,TANG Zhiguo,et al.Study of intelligent diagnosis of transformers partial discharge based on cluster analysis[J].Journal of North China Electric Power University(natural science edition),2008,35(6):7-12.
• [11]PERERA N,RAJAPAKSE A.Recognition of fault transients using a probabilistic neural-network classifier[J].IEEE transactions on power delivery,2011,26(1):410-419.