A combined technique for power transformer fault diagnosis based on k-means clustering and support vector machine

IF 3.8 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Arnaud Nanfak, Abdelmoumene Hechifa, Samuel Eke, Abdelaziz Lakehal, Charles Hubert Kom, Sherif S. M. Ghoneim
{"title":"A combined technique for power transformer fault diagnosis based on k-means clustering and support vector machine","authors":"Arnaud Nanfak,&nbsp;Abdelmoumene Hechifa,&nbsp;Samuel Eke,&nbsp;Abdelaziz Lakehal,&nbsp;Charles Hubert Kom,&nbsp;Sherif S. M. Ghoneim","doi":"10.1049/nde2.12088","DOIUrl":null,"url":null,"abstract":"<p>This contribution presents a two-step hybrid diagnostic approach, combining <i>k</i>-means clustering for subset formation, followed by subset analysis conducted by human experts. As the feature input vector has a significant influence on the performance of unsupervised machine learning algorithms, seven feature input vectors derived from traditional methods, including Duval pentagon method, Rogers ratio method, three ratios technique, Denkyoken method, ensemble gas characteristics method, Duval triangle method, and Gouda triangle method were explored for the subset formation stage. The seven proposed individual methods, corresponding to the seven feature input vectors, were implemented using a dataset of 595 DGA samples and tested on an additional 254 DGA samples. Furthermore, a combined technique based on a support vector machine was introduced, utilising the diagnostic results of the individual methods as input features. From training and testing, with diagnostic outcomes of 91.09% and 90.94%, the combined technique demonstrated the highest overall diagnostic accuracies. Using the IEC TC10 database, the diagnosis accuracies of the proposed diagnostic methods were compared to existing methods of literature. From the results obtained, the combined technique outperformed the proposed individual methods and existing methods used for comparison.</p>","PeriodicalId":36855,"journal":{"name":"IET Nanodielectrics","volume":"7 3","pages":"175-187"},"PeriodicalIF":3.8000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/nde2.12088","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Nanodielectrics","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/nde2.12088","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

This contribution presents a two-step hybrid diagnostic approach, combining k-means clustering for subset formation, followed by subset analysis conducted by human experts. As the feature input vector has a significant influence on the performance of unsupervised machine learning algorithms, seven feature input vectors derived from traditional methods, including Duval pentagon method, Rogers ratio method, three ratios technique, Denkyoken method, ensemble gas characteristics method, Duval triangle method, and Gouda triangle method were explored for the subset formation stage. The seven proposed individual methods, corresponding to the seven feature input vectors, were implemented using a dataset of 595 DGA samples and tested on an additional 254 DGA samples. Furthermore, a combined technique based on a support vector machine was introduced, utilising the diagnostic results of the individual methods as input features. From training and testing, with diagnostic outcomes of 91.09% and 90.94%, the combined technique demonstrated the highest overall diagnostic accuracies. Using the IEC TC10 database, the diagnosis accuracies of the proposed diagnostic methods were compared to existing methods of literature. From the results obtained, the combined technique outperformed the proposed individual methods and existing methods used for comparison.

Abstract Image

基于均值聚类和支持向量机的电力变压器故障诊断组合技术
本文提出了一种两步混合诊断方法,结合了用于形成子集的 k-means 聚类,以及由人类专家进行的子集分析。由于特征输入向量对无监督机器学习算法的性能有重要影响,因此在子集形成阶段探讨了从传统方法中衍生出的七个特征输入向量,包括杜瓦尔五边形法、罗杰斯比率法、三比率技术、Denkyoken 法、集合气体特征法、杜瓦尔三角形法和高达三角形法。使用 595 个 DGA 样本数据集实现了与七个特征输入向量相对应的七种拟议的单独方法,并在另外 254 个 DGA 样本上进行了测试。此外,还引入了一种基于支持向量机的组合技术,利用单个方法的诊断结果作为输入特征。通过训练和测试,综合技术的诊断结果分别为 91.09% 和 90.94%,总体诊断准确率最高。利用 IEC TC10 数据库,将所提出的诊断方法的诊断准确率与现有的文献方法进行了比较。从获得的结果来看,组合技术优于所建议的单个方法和用于比较的现有方法。
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 Nanodielectrics
IET Nanodielectrics Materials Science-Materials Chemistry
CiteScore
5.60
自引率
3.70%
发文量
7
审稿时长
21 weeks
×
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:481959085
Book学术官方微信