Diagnosing Power Transformer Winding Faults Using a Feature Fusion Method for Multidimensional Oscillating Wave Signals

IF 1.5 4区 工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Zhenyu Wu, Xiang Wu, Rui Sun, Wenping Cao, Cungang Hu
{"title":"Diagnosing Power Transformer Winding Faults Using a Feature Fusion Method for Multidimensional Oscillating Wave Signals","authors":"Zhenyu Wu,&nbsp;Xiang Wu,&nbsp;Rui Sun,&nbsp;Wenping Cao,&nbsp;Cungang Hu","doi":"10.1049/elp2.70059","DOIUrl":null,"url":null,"abstract":"<p>A highly efficient testing method (oscillating wave method) completes several transformer tests via one connection and presents high sensitivity to winding faults. Existing methods extract independent features directly from the detection signals and merely combine them without considering the correlation and complementarity between these features. This oversight leads to insufficient characterisation of fault information, thereby reducing diagnostic accuracy. Therefore, a high-correlation feature screening and combination method is proposed for processing oscillating wave signals. First, a multidimensional transformation method for oscillating wave signals is developed. Secondly, the time–domain signals acquired through the oscillating wave method are transformed into a time–frequency domain image, from which colour and texture features are extracted. Next, single features from different dimensions are integrated into multiple composite features by employing a feature fusion technique. Then optimal multifeatures are selected using the standardised cluster-centre parameter. Based on the multifeatures, the intelligent algorithm completes the classification. Finally, simulation results demonstrate that the multifeature fusion method, which incorporates colour and texture features, can accurately identify fault types, degrees and locations. This approach offers crucial technical support for the automated analysis of oscillating wave signals.</p>","PeriodicalId":13352,"journal":{"name":"Iet Electric Power Applications","volume":"19 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/elp2.70059","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Electric Power Applications","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/elp2.70059","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

A highly efficient testing method (oscillating wave method) completes several transformer tests via one connection and presents high sensitivity to winding faults. Existing methods extract independent features directly from the detection signals and merely combine them without considering the correlation and complementarity between these features. This oversight leads to insufficient characterisation of fault information, thereby reducing diagnostic accuracy. Therefore, a high-correlation feature screening and combination method is proposed for processing oscillating wave signals. First, a multidimensional transformation method for oscillating wave signals is developed. Secondly, the time–domain signals acquired through the oscillating wave method are transformed into a time–frequency domain image, from which colour and texture features are extracted. Next, single features from different dimensions are integrated into multiple composite features by employing a feature fusion technique. Then optimal multifeatures are selected using the standardised cluster-centre parameter. Based on the multifeatures, the intelligent algorithm completes the classification. Finally, simulation results demonstrate that the multifeature fusion method, which incorporates colour and texture features, can accurately identify fault types, degrees and locations. This approach offers crucial technical support for the automated analysis of oscillating wave signals.

Abstract Image

基于多维振荡波信号特征融合的电力变压器绕组故障诊断
振荡波法是一种高效的测试方法,通过一次连接完成多次变压器测试,对绕组故障具有很高的灵敏度。现有的方法直接从检测信号中提取独立的特征,仅仅将它们组合在一起,而不考虑这些特征之间的相关性和互补性。这种疏忽导致对故障信息的描述不足,从而降低了诊断的准确性。为此,提出了一种高相关特征筛选与组合方法来处理振荡波信号。首先,提出了振荡波信号的多维变换方法。其次,将振荡波法获取的时域信号变换为时频域图像,提取时域图像的颜色和纹理特征;其次,采用特征融合技术将不同维度的单个特征集成为多个复合特征;然后利用标准化聚类中心参数选择最优多特征。基于多特征,智能算法完成分类。仿真结果表明,结合颜色特征和纹理特征的多特征融合方法能够准确识别故障类型、程度和位置。这种方法为振荡波信号的自动分析提供了关键的技术支持。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Iet Electric Power Applications
Iet Electric Power Applications 工程技术-工程:电子与电气
CiteScore
4.80
自引率
5.90%
发文量
104
审稿时长
3 months
期刊介绍: IET Electric Power Applications publishes papers of a high technical standard with a suitable balance of practice and theory. The scope covers a wide range of applications and apparatus in the power field. In addition to papers focussing on the design and development of electrical equipment, papers relying on analysis are also sought, provided that the arguments are conveyed succinctly and the conclusions are clear. The scope of the journal includes the following: The design and analysis of motors and generators of all sizes Rotating electrical machines Linear machines Actuators Power transformers Railway traction machines and drives Variable speed drives Machines and drives for electrically powered vehicles Industrial and non-industrial applications and processes Current Special Issue. Call for papers: Progress in Electric Machines, Power Converters and their Control for Wave Energy Generation - https://digital-library.theiet.org/files/IET_EPA_CFP_PEMPCCWEG.pdf
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信