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, Xiang Wu, Rui Sun, Wenping Cao, 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.
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