An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning

Abstract Dissolved gas analysis is an important technique for the insulation condition assessment and incipient fault diagnosis of power transformers. However, the performance of the traditional ratio methods can be hardly improved due to the overreliance on absolute ratio threshold. In this paper,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lijing Zhang, Gehao Sheng, Huijuan Hou, Nan Zhou, Xiuchen Jiang
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/47e862a5d4f0427cb02abb299cb54ca9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:47e862a5d4f0427cb02abb299cb54ca9
record_format	dspace
spelling	oai:doaj.org-article:47e862a5d4f0427cb02abb299cb54ca92021-11-13T03:16:47ZAn adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning2515-294710.1049/stg2.12044https://doaj.org/article/47e862a5d4f0427cb02abb299cb54ca92021-12-01T00:00:00Zhttps://doi.org/10.1049/stg2.12044https://doaj.org/toc/2515-2947Abstract Dissolved gas analysis is an important technique for the insulation condition assessment and incipient fault diagnosis of power transformers. However, the performance of the traditional ratio methods can be hardly improved due to the overreliance on absolute ratio threshold. In this paper, a novel method combining oversampling and cost‐sensitive learning is proposed to improve the diagnosis accuracy of all fault types of transformers. The radial‐based oversampling (RBO) method is adopted to synthesise samples for the complex fault classes. With the newly generated samples, the deep belief network (DBN) can effectively learn the features of complex fault classes and distinguish them from the other fault classes. Moreover, by integrating a cost matrix into the loss function, the parameters of DBN are adaptively updated so as to ensure the correct classification of the fault class with less samples. Based on the oversampling and cost‐sensitive learning, the proposed method can form suitable classification boundaries amongst thermal, discharge and complex fault classes. The effectiveness and generalisation capability of the proposed method are verified by case studies in a real‐world fault dataset of power transformers with multi‐source samples. The results demonstrate that the proposed method improves the classification accuracies in all fault classes, especially in the complex fault classes. The overall accuracy can be reach over 90% by applying both RBO and cost‐sensitive learning.Lijing ZhangGehao ShengHuijuan HouNan ZhouXiuchen JiangWileyarticleElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIET Smart Grid, Vol 4, Iss 6, Pp 623-635 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electrical engineering. Electronics. Nuclear engineering TK1-9971 Lijing Zhang Gehao Sheng Huijuan Hou Nan Zhou Xiuchen Jiang An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
description	Abstract Dissolved gas analysis is an important technique for the insulation condition assessment and incipient fault diagnosis of power transformers. However, the performance of the traditional ratio methods can be hardly improved due to the overreliance on absolute ratio threshold. In this paper, a novel method combining oversampling and cost‐sensitive learning is proposed to improve the diagnosis accuracy of all fault types of transformers. The radial‐based oversampling (RBO) method is adopted to synthesise samples for the complex fault classes. With the newly generated samples, the deep belief network (DBN) can effectively learn the features of complex fault classes and distinguish them from the other fault classes. Moreover, by integrating a cost matrix into the loss function, the parameters of DBN are adaptively updated so as to ensure the correct classification of the fault class with less samples. Based on the oversampling and cost‐sensitive learning, the proposed method can form suitable classification boundaries amongst thermal, discharge and complex fault classes. The effectiveness and generalisation capability of the proposed method are verified by case studies in a real‐world fault dataset of power transformers with multi‐source samples. The results demonstrate that the proposed method improves the classification accuracies in all fault classes, especially in the complex fault classes. The overall accuracy can be reach over 90% by applying both RBO and cost‐sensitive learning.
format	article
author	Lijing Zhang Gehao Sheng Huijuan Hou Nan Zhou Xiuchen Jiang
author_facet	Lijing Zhang Gehao Sheng Huijuan Hou Nan Zhou Xiuchen Jiang
author_sort	Lijing Zhang
title	An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
title_short	An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
title_full	An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
title_fullStr	An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
title_full_unstemmed	An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
title_sort	adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/47e862a5d4f0427cb02abb299cb54ca9
work_keys_str_mv	AT lijingzhang anadaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT gehaosheng anadaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT huijuanhou anadaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT nanzhou anadaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT xiuchenjiang anadaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT lijingzhang adaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT gehaosheng adaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT huijuanhou adaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT nanzhou adaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning AT xiuchenjiang adaptivefaultdiagnosismethodofpowertransformersbasedoncombiningoversamplingandcostsensitivelearning
_version_	1718430312948563968

An adaptive fault diagnosis method of power transformers based on combining oversampling and cost‐sensitive learning

Ejemplares similares