主元分析和重构贡献在变压器故障检测与诊断中的应用

唐勇波; 桂卫华; 欧阳伟

主元分析和重构贡献在变压器故障检测与诊断中的应用

1.
中南大学信息科学与工程学院, 长沙 410083;
2.
宜春学院物理科学与工程技术学院, 宜春 336000;
3.
中国瑞林工程技术有限公司, 南昌 330002

基金项目:

江西省工业科技重点项目,基于专家系统的大型企业动力厂安全监控和节能运行系统的研发(2007BG27300)资助

详细信息

作者简介:
唐勇波(1975-)，讲师，博士研究生，研究方向为智能控制和故障诊断技术，tyb2003045@yahoo.com.cn

计量
- 文章访问数: 313
- HTML全文浏览量: 23
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2010-12-16
- 刊出日期: 2015-06-10

Appling Principal Component Analysis and Reconstruction-based Contribution to Fault Detection and Diagnosis of Transformer

1.
College of Information Science and Engineering, Central South University, Changsha 410083;
2.
College of Physical Science and Engineering, Yichun University, Yichun 336000;
3.
China Nerin Engineering Co.Ltd, Nanchang 330002

摘要

摘要: 针对常规DGA诊断方法对故障数据不敏感和诊断能力不足等问题,提出了基于主元分析和重构贡献的变压器故障检测与诊断方法。该方法在建立PCA模型后,基于故障重构的思想,定义重构贡献统计量并应用于变压器故障检测,分析了重构贡献法的故障诊断性能并利用重构贡献法进行诊断。实例研究结果表明:该方法的检测正确率超过95%且对检测DGA含量小的故障有一定的效果,同时,也验证了重构贡献法故障诊断的有效性。
- 主元分析 /
- 变压器 /
- 故障检测 /
- 故障诊断 /
- 重构贡献 /
- 贡献图
Abstract: In our opinion,dissolved gas analysis(DGA) is not sensitive to fault data and insufficient for diagnosis.Therefore we propose a new method for diagnosing the faults of a transformer with the principal component analysis(PCA) and the reconstruction-based contribution(RBC).After the PCA model is built,we use the idea of fault reconstruction to define the RBC statistical indices and apply them to the diagnosis of the faults of a transformer.We analyze the performance of the fault diagnosis method that uses the RBC and perform the fault diagnosis.The example study results show that our fault diagnosis method has the effective fault detection rate of 95% and is somewhat effective for detecting the fault whose DGA content is small and that the fault diagnosis method that uses the RBC is also effective for the diagnosis of faults of a transformer.
- principal component analysis /
- transformer /
- fault detection /
- fault diagnosis /
- reconstruction-based con-tribution /
- fault reconstruction

HTML全文

参考文献(21)

[1]	肖燕彩.支持向量机在变压器状态评估中的应用研究[D].北京交通大学,2008
[2]	中华人民共和国电力部.DL/T722-2000变压器油中溶解气体分析和判断导则[S].北京:中国电力出版社,2000
[3]	操敦奎.变压器油中气体分析诊断与故障检查[M].北京:中国电力出版社,2005
[4]	董其国.电力变压器故障与诊断[M].北京:中国电力出版社,2001
[5]	孙才新,陈伟根,李俭等.电气设备油中气体在线监测与故障诊断技术(第1版)[M].北京:科学出版社,2003
[6]	高文胜,严璋,谈克雄.基于油中溶解气体分析的电力变压器绝缘故障诊断方法[J].电工电能新技术,2000,19(1)
[7]	赵立杰,柴天佑,王纲.多元统计性能监视和故障诊断技术研究进展[J].信息与控制,2004,33(2):197～20l
[8]	MacGregor J F,Kourti T.Statistical process control of multivari-ate processes[J].Control Engineering Practice,1995,3(3)
[9]	Jackson J E,Mudholkar G S.Control procedures for residuals as-sociated with principal component analysis[J].Technometrics,1979,21(3):341～349
[10]	Cherry G,Qin S J.Multiblock principal component analysisbased on a combined index for semiconductor fault detection anddiagnosis[J].Institute for Electrical and Electronic Engi-neers Transactions on Semiconductor Manufacturing,2006,19(2)
[11]	Westerhuis J A,Gurden S P,Smilde A K.Generalized contribu-tion plots in multivariate statistical process monitoring[J].Che-mometrics and Intelligent Laboratory Systems,2000,51
[12]	Yoon S,MacGregor J F.Fault diagnosis with multivariate statisti-cal models,part I:Using steady state fault signatures[J].Jour-nal of Process Control,2001,11:387～400
[13]	Dunia R and Qin S J.A unified geometric approach to processand sensor fault identification and reconstruction:the unidimen-sional fault case[J].Computers and Chemistry Engineering,1998,22:927～943
[14]	Dunia R,Qin S J.Subspace approach to multidimensional faultidentification and reconstruction[J].American Institute ofChemical Engineers Journal,1998,44:1813～1831
[15]	Yue H H,Qin S J.Reconstruction-based fault identificationusing a combined index[J].Industrial&Engineering Chem-istry Research,2001,40(20):4403～4414
[16]	Alcala C F,Qin S J.Reconstruction-based contribution forprocess monitoring[J].Automatica,2009,27(2):1～8
[17]	Box G E P.Some theorems on quadratic forms applied in thestudy of analysis of variance problems I effect of inequality of vari-ance in the one-way classification[J].Annals of Mathematicsand Statistics,1954,25:290～302
[18]	Ganyun L V,Cheng H Z,Zhai H B,Dong L X.Fault diagnosisof power transformer based on multi-layer SVM classifier[J].Electric Power Systems Research,2005,74(1):1～7
[19]	熊浩,孙才新,廖瑞金等.基于核可能性聚类算法和油中溶解气体分析的电力变压器故障诊断研究[J].中国电机工程学报,2005,25(20):162～166
[20]	李建坡.基于油中溶解气体分析的电力变压器故障诊断技术的研究[D].吉林大学,2008
[21]	张蕊,郭瑞君,李华等.基于变压器故障分类的DGA特征提取[J].高电压技术,2005,31(4):32～33