• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

基于支持向量机的励磁涌流识别算法

郝文斌 李群湛 黄咏容 韩正庆

郝文斌, 李群湛, 黄咏容, 韩正庆. 基于支持向量机的励磁涌流识别算法[J]. 西南交通大学学报, 2007, 20(4): 490-493.
引用本文: 郝文斌, 李群湛, 黄咏容, 韩正庆. 基于支持向量机的励磁涌流识别算法[J]. 西南交通大学学报, 2007, 20(4): 490-493.
HAO Wenbin, LI Qunzhan, HUANG Yongrong, HAN Zhengqing. New Algorithm for Inrush Current Identification of Transformer Based on Support Vector Machine[J]. Journal of Southwest Jiaotong University, 2007, 20(4): 490-493.
Citation: HAO Wenbin, LI Qunzhan, HUANG Yongrong, HAN Zhengqing. New Algorithm for Inrush Current Identification of Transformer Based on Support Vector Machine[J]. Journal of Southwest Jiaotong University, 2007, 20(4): 490-493.

基于支持向量机的励磁涌流识别算法

详细信息
    作者简介:

    郝文斌(1976- ),男,博士研究生,研究方向为电力系统继电保护及变电所综合自动化,E-mail:hwb760817@163.com

    通讯作者:

    李群湛(1957- ),男,教授,博士生导师,主要研究方向为电力系统分析、牵引供电系统供电理论、电能质量与控制等, E-mail:lqz3431@263.net

New Algorithm for Inrush Current Identification of Transformer Based on Support Vector Machine

  • 摘要: 为提高变压器差动保护识别励磁涌流的能力,将支持向量分类机应用于励磁涌流识别,提出了一种基于支持向量分类机的变压器励磁涌流和内部故障识别新方法.基于励磁涌流和内部故障电流的特点,充分考虑电流互感器饱和的特点提取电流互感器二次侧间断角和二次谐波等特征,并对励磁涌流和内部故障电流的识别方法进行了分析;用EMTDC程序进行仿真,生成训练样本和测试样本,对支持向量机进行了训练和测试.结果表明,应用支持向量分类机对励磁涌流和内部故障进行识别,识别率平均可达99%以上.

     

  • 李贵存.变压器仿真与保护新算法的研究[D].北京:华北电力大学,2001.[2] 王维俭.电气主设备继电保护原理与应用[M].北京:中国电力出版社,2002.[3] 何奔腾,徐习东.波形比较法变压器差动保护原理[J].中国电机工程学报,1998,18(6):395-398.HE Benteng,XU Xidong.Protection based on wave comparison[J].Proceedings of the CSEE,1998,18 (6):395-398.[4] 焦劭华,刘万顺.区分变压器励磁涌流和内部短路的积分型波形对称原理[J].中国电机工程学报,1999,19(8):1-5.JIAO Shaohua,LIU Wanshun.A novel scheme to discriminate inrush current and fault current based on integrating the waveform[J].Proceedings of the CSEE,1999,19(8):1-5.[5] 李贵存,刘万顺,刘建飞,等.用波形拟合法识别变压器励磁涌流和短路电流的新原理[J].电力系统自动化,2001,25(14):15-18.LI Guicun,LIU Wanshun,LIU Jianfei,et al.New principle of discrimination between inrush current and fault current of the transformer based on forecasted waveform[J].Automation of Electric Power Systems,2001,25(14):15-18.[6] 韩正庆,高仕斌,李群湛.基于半波傅里叶算法的励磁涌流识别方法[J].电力系统自动化,2005,29(14):60-63.HAN Zhengqing,GAO Shibin,LI Qunzhan.New method to identify inrush current based on half-wave fourier analysis[J].Automation of Electric Power Systems,2005,29(14):60-63.[7] 潘荣贞,郁惟镛,田寿龙.基于波形记忆和模糊极小-极大神经网络的变压器励磁涌流和内部短路的鉴别[J].电网技术,2002,26(5):4-9.PAN Rongzhen,YU Weiyong,HAN Shoulong.Distinguish transformer magnetizing inrush from its internal faults based on wave shape remembrance and fuzzy minimum-maximum neural network[J].Power System Technology,2002,26(5):4-9.[8] 段玉倩,贺家李,贺继红.基于人工神经网络方法的微机变压器保护[J].中国电机工程学报,1998,3(18):190-194.DUAN Yuqian,HE Jiali,HE Jihong.Computerized transformer protection based on artificial neural network[J].Proceedings of the CSEE,1998,b3(18):190-194.[9] 李贵存,刘万顺,贾清泉,等.一种利用小波原理防止变压器差动保护误动的新算法[J].电网技术,2001,25(7):48-52.LI Guicun,LIU Wanshun,JIA Qingquan,et al.A new algorithm toprevent misoperation of transformer differential protection based on principle of wavelet transform[J].Power System Technology,2001,25(7):48-52.[10] 李海锋,王钢,李晓华,等.电力变压器励磁涌流判别的自适应小波神经网络方法[J].中国电机工程学报,2005,25(7):144-150.LI Haifeng,WANG Gang,LI Xiaohua,et al.Distinguish between inrush and internal fault of transformer based on adaptive wavlet neural network[J].Proceeding of the CSEE,2005,25(12):144-150.[11] 王增平,徐岩,王雪,等.基于变压器模型的新型变压器保护原理的研究[J].中国电机工程学报,2003,23(12):54-58.WANG Zengping,XU Yan,WANG Xue,et al.Study on the novel transformer protection principle based on the transformer model[J].Proceeding of the CSEE,2003,23 (12):54-58.[12] 郑涛,刘万顺,肖仕武,等.一种基于数学形态学提取电流波形特征的变压器保护新原理[J].中国电机工程学报,2004,24(7):18-24.ZHENG Tao,LIU Wanshun,XIAO Shiwu,et al.new algorithm based on the mathematical morphology for power transformer protection[J].Proceeding of the CSEE 2004,24(7):18-24.[13] VAPNIK V N.The nature of statistical learning theory[M].2nd edition.NewYork:Springer-Verlag,1999.[14] SALAT R,OSOWSKI S.Accurate fault location in the power transmission line using support vector machine approach[J].Transactions on power system,2004,19(2):
  • 加载中
计量
  • 文章访问数:  1524
  • HTML全文浏览量:  74
  • PDF下载量:  503
  • 被引次数: 0
出版历程
  • 收稿日期:  2006-10-24
  • 刊出日期:  2007-08-25

目录

    /

    返回文章
    返回