基于谱聚类集成的变压器在线故障诊断

doi:10.3969/j.issn.0372-2112.2017.10.025

电子学报 ›› 2017, Vol. 45 ›› Issue (10): 2491-2497.DOI: 10.3969/j.issn.0372-2112.2017.10.025

基于谱聚类集成的变压器在线故障诊断

刘荣胜¹, 彭敏放¹, 肖祥慧²

1. 湖南大学电气与信息工程学院, 湖南长沙 410082;
2. 长沙理工大学电气与信息工程学院, 湖南长沙 410114

收稿日期:2015-11-28 修回日期:2017-03-06 出版日期:2017-10-25 发布日期:2017-10-25
通讯作者: 彭敏放
作者简介:刘荣胜,男,1981年生,湖南娄底人,现为湖南大学博士研究生,主要研究方向为电力系统故障分析及其设备状态监测.E-mail:258920025@qq.com
基金资助:
国家自然科学基金（No.61472128，No.61173108）；湖南省自然科学基金重点项目（No.14JJ2150）；国家电网公司总部科技项目（No.5216A514001K）

The Transformer On-line Fault Diagnosis Based on Spectral Clustering Ensemble

LIU Rong-sheng¹, PENG Min-fang¹, XIAO Xiang-hui²

1. College of Electrical and Information Engineering, Hunan University, Changsha, Hunan 410082, China;
2. College of Electrical and Information Engineering, Changsha University of Science and technology, Changsha, Hunan 410114, China

Received:2015-11-28 Revised:2017-03-06 Online:2017-10-25 Published:2017-10-25

摘要/Abstract

摘要： 为了提高基于油中溶解气体分析技术（DGA）的变压器故障诊断准确率，本文提出了一种基于谱聚类集成的变压器在线故障诊断（TOFD-SCE）方法.以加权二次抽样算法抽取样本、构建基础谱聚类的样本集，以基础谱聚类学习问题的局部知识；平衡多样性与正确性选择集成成员；集成多个成员谱聚类的结果来提高变压器故障诊断的准确率.传统变压器故障诊断方法基于历史数据建立模型，缺乏在线学习的能力；TOFD-SCE利用历史与在线新增两种DGA数据来训练、修正模型，提高了其故障诊断的准确率.对SSP300000/500型变压器的故障诊断实验结果表明：TOFD-SCE的准确率优于IEC三比值法、BP神经网络法及支持向量机法，验证了其有效性.

关键词: 故障诊断, 变压器, 谱聚类集成, 油中溶解气体分析, 信号处理

Abstract: To improve the accuracy of the transformer fault diagnosis based on dissolved gas analysis in oil(DGA),a transformer on-line fault diagnosis based on spectral clustering ensemble (TOFD-SCE) was proposed in this paper.The weighted double sampling algorithm create the samples set of the basic spectral clustering,which learned the local knowledge of the problems.The accuracy was improved by integrating the results of ensemble members,which were picked up form the basic spectral clustering in terms of the accuracy and variety.The conventional models are only trained by the historical data,and can't learn on-line.TOFD-SCE is trained and modified by both historical and new online data,and the accuracy is improved.The TOFD-SCE was validated by diagnosing the fault of SSP300000/500 transformers.Comparing with IEC three ratio,BP-neural networks and support vector machine,TOFD-SCE is more outstanding.

Key words: fault diagnosis, power transformer, spectral clustering ensemble, dissolved gas analysis in oil, signal processing

中图分类号:

TM411+.2

刘荣胜, 彭敏放, 肖祥慧. 基于谱聚类集成的变压器在线故障诊断[J]. 电子学报, 2017, 45(10): 2491-2497.

LIU Rong-sheng, PENG Min-fang, XIAO Xiang-hui. The Transformer On-line Fault Diagnosis Based on Spectral Clustering Ensemble[J]. Acta Electronica Sinica, 2017, 45(10): 2491-2497.

参考文献

[1] Norazhar Anu BAKAR,ABU-SIADA A,ISLAM S.A review of dissolved gas analysis measurement and interpretation techniques[J].IEEE Electrical Insulation Magazine,2014,30(3):39-49.
[2] LIU Zhi-xiong,SONG Bin,LI En-wen,et al.Study of "code absence" in the IEC three-ratio method of dissolved gas analysis[J].IEEE Electrical Insulation Magazine,2015,31(6):6-12.
[3] IEC60599.Mineral Oil-Impregnated Electrical Equipment in Service Guide to the Interpretation of Dissolved and Free Gases Analysis[S].
[4] Vinicius G M CRUZ,Andre L H COSTA,Marcio L L PAREDES.Development and evaluation of a new DGA diagnostic method based on thermodynamics fundamentals[J].IEEE Transactions on Dielectrics and Electrical Insulation,2015,22(2):888-894.
[5] 廖瑞金,姚陈果,等.多专家合作诊断变压器绝缘故障的黑板型专家系统[J].电工技术学报,2002,17(1):85-90. LIAO Ruijin,YAO Chenguo,et al.Blackboard expert system of multi-expert cooperating diagnosis in transformers' insulation[J].Transactions of China Electrotechnical Society,2002,17(1):85-90.(in Chinese).
[6] Vladimiro MIRANDA,et al.Diagnosing faults in power transformers with autoassociative neural networks and mean shift[J].IEE Transactions on Power Delivery,2012,27(3):1350-1356.
[7] ABU-SIADA A,HMOOD S,ISLAM S.A new fuzzy logic approach for consistent interpretation of dissolved gas-in-oil analysis[J].IEEE Transactions on Dielectrics and Electrical Insulation,2013,20(6):2343-2349.
[8] WEI Chenghao,TANG Wenhu,WU Qinghua.Dissolved gas analysis method based on novel feature prioritization and support vector machine[J].IET Electric Power Applications,2014,8(8):320-328.
[9] 朱永利,尹金良.组合核相关向量机在电力变压器故障诊断中的应用研究[J].中国电机工程学报,2013,33(22):68-74. ZHU Yongli,YIN Jinliang.Study on application of multi-kernel learning revelance vector machines in fault diagnosis of power transformers[J].Proceedings of the CSEE,2013,33(22):68-74.(in Chinese)
[10] Shakeb A KHAM,Md Danish EQUBAL,Tarikul ISLAM.A comprehensive comparative study of DGA based transformer fault diagnosis using fussy logic and ANFIS models[J].IEEE Transactions on Dielectrics and Electrical Insulation,2015,22(1):590-596.
[11] YANG Ming-Ta,HU Li-Siang.Intelligent fault types diagnostic system for dissolved gas analysis of oil-immersed power transformer[J].IEEE Transactions on Dielectrics and Electrical Insulation,2013,60(6):2317-2324.
[12] Hiba ZBIB,Sandrine MOUYSSET,Simon STUTE,et al.Unsupervised spectral clustering for segmentation of dynamic PET images[J].IEEE Transactions on Nuclear Science,2015,28(5):830-583.
[13] 邓晓政,焦李成,卢山.基于非负矩阵分解的谱聚类集成SAR图像分割[J].电子学报,2011,39(12):2905-2909. DENG Xiao-zheng,JIAO Li-cheng,LU Shan.Spectral clustering ensemble applied to SAR image segmentation using nonnegative matrix factorization[J].Acta Electronica Sinica,2011,39(12):2905-2909.(in Chinese)
[14] 孔万增,孙志海,等.基于本征间隙与正交特征向量的自动谱聚类[J].电子学报,2010,38(8):1880-1891. KONG Wan-zeng,SUN Zhi-hai,et al.Automatic spectral clustering based on eigengap and orthogonal eigenvector[J].Acta Electronica Sinica,2010,38(8):1880-1891.(in Chinese)
[15] 于重重,田蕊,谭励,等.非平衡样本分类的集成迁移学习算法[J].电子学报,2012,40(7):1358-1363. YU Chong-chong,TIAN Rui,TAN Li,et al.Integrated transfer learning algorithmic for unbalanced samples classification[J].Acta Electronica Sinica,2012,40(7):1358-1363.(in Chinese)
[16] 夏学文,桂凌,戴志锋.基于多尺度选择性学习和探测收缩机制的PSO算法[J].电子学报,2016,5(1):1090-1100. XIA Xue-wen,GUI Ling,DAI Zhi-feng,et al.A PSO algorithm based on multiscale-selective-learning and detecting-shrinking strategies[J].Acta Electronica Sinica,2016,5(1):1090-1100.(in Chinese)

基于谱聚类集成的变压器在线故障诊断

The Transformer On-line Fault Diagnosis Based on Spectral Clustering Ensemble

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	于建立, 吴传斌, 冷赫, 鲁志伟. 基于磁场分布特性的接地网故障诊断研究[J]. 电子学报, 2022, 50(3): 598-607.
[2]	董明, 李敬, 索永录, 唐恩贤, 马宏伟, 陈渊, 张广明, 万翔. 基于改进果蝇优化算法正交匹配追踪的超声信号降噪方法[J]. 电子学报, 2022, 50(2): 493-501.
[3]	欧阳丹彤, 刘扬, 宋金彩, 王浩然, 张立明. 结合结构特征基于测试集重排序的故障诊断方法[J]. 电子学报, 2022, 50(1): 63-71.
[4]	郑恩明, 陈新华, 周权斌, 李嶷, 杨鹤, 孟浩. 一种复域压缩感知目标方位估计方法[J]. 电子学报, 2021, 49(11): 2117-2123.
[5]	鲍中新, 文成林, 马雪. 一种基于数据变化率的预处理及主元分析故障诊断方法[J]. 电子学报, 2021, 49(11): 2234-2240.
[6]	董石, 章强, 谢夏风, 钟睿. 非均匀二次声源分布下的2.5D高阶Ambisonics声场合成算法[J]. 电子学报, 2021, 49(1): 14-22.
[7]	张彩霞, 王子涵, 文成林, 刘国文, 余伟. 样本空间基于多级高维特征表示的微小故障诊断[J]. 电子学报, 2020, 48(8): 1647-1654.
[8]	马梦瑶, 赖晓平, 孟海龙. 二维FIR滤波器约束最小二乘设计的最大分划松弛ADMM算法[J]. 电子学报, 2020, 48(3): 510-517.
[9]	王强, 李兵, 王天施, 刘晓琴. 新型单相软开关AC-DC-AC变换器[J]. 电子学报, 2020, 48(3): 616-620.
[10]	王强, 徐有万, 王天施, 刘晓琴. 变压器辅助换流的三相节能型谐振极逆变器[J]. 电子学报, 2020, 48(3): 621-624.
[11]	陈兵兵, 曹欣远, 陈明生, 齐琦, 况晓静, 吴先良, 陈辉. 基于欠定方程的频谱峰值搜索算法及其在连续毫米波雷达系统中的应用[J]. 电子学报, 2020, 48(2): 369-374.
[12]	岳梦云, 白冰. 一种电机FOC算法DSP系统设计及实现[J]. 电子学报, 2020, 48(10): 2041-2046.
[13]	郑近德, 潘海洋, 童靳于, 刘庆运, 丁克勤. 自适应掩膜信号集成局部特征尺度分解及其应用[J]. 电子学报, 2020, 48(10): 2060-2070.
[14]	王强, 李兵, 王天施, 刘晓琴. 具有提升直流环节稳态电压功能的单相全桥谐振直流环节逆变器[J]. 电子学报, 2019, 47(9): 2012-2016.
[15]	刘项洋, 许勇, 郑孝遥, 陈付龙. 矢量基二维DCT修剪在DSP上的内存存取减少方法[J]. 电子学报, 2019, 47(3): 757-763.