New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/TII.2023.3240590 http://hdl.handle.net/11449/249039 |
Resumo: | Industry and science have been growing attention to developing systems that ensure the integrity of high voltage devices like power transformers. The goal is to avoid unexpected stoppages by detecting incipient failures before they become a major problem. In this context, the detection of discharge activity is an effective way to assess the condition operation of power transformers since this type of flaw can lead the transformer to total failure. The effectiveness of the fault diagnosis systems is related to their capability to distinguish the types of discharges since different flaws require different maintenance planning. This article proposes a new data analysis which combined the frequency spectrum of the signals with the Karhunen-Loève Transform to perform self-organization maps. The effectiveness of this analysis was validated by comparing it with the Fundamental Signals Properties Classification Technique, which is widely applied for pattern recognition.Two types of sensing techniques were assessed in order to enhance the capability of the new approach. Results indicated that the new methodology presented lower standard deviation for data classification, being a promising tool to monitoring systems. |
id |
UNSP_ae8a9387d48f5b3f730939a143d0f0df |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/249039 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève TransformAcoustic emissionDischargeDischarges (electric)Discrete Fourier transformsHall effectInsulationInsulatorsPattern recognitionPower transformer insulationSensorsTransformers fault diagnosisWindingsIndustry and science have been growing attention to developing systems that ensure the integrity of high voltage devices like power transformers. The goal is to avoid unexpected stoppages by detecting incipient failures before they become a major problem. In this context, the detection of discharge activity is an effective way to assess the condition operation of power transformers since this type of flaw can lead the transformer to total failure. The effectiveness of the fault diagnosis systems is related to their capability to distinguish the types of discharges since different flaws require different maintenance planning. This article proposes a new data analysis which combined the frequency spectrum of the signals with the Karhunen-Loève Transform to perform self-organization maps. The effectiveness of this analysis was validated by comparing it with the Fundamental Signals Properties Classification Technique, which is widely applied for pattern recognition.Two types of sensing techniques were assessed in order to enhance the capability of the new approach. Results indicated that the new methodology presented lower standard deviation for data classification, being a promising tool to monitoring systems.Universidade Estadual Paulista, Sao Paulo, BrazilElectrical Engineering, Universidad Tecnica Federico santa Maria, Santiago de Chile, ChileR&D, IPEC Ltd, Manchester, UKElectrical Engineering, São Paulo State University, Bauru, BrazilUniversidade Estadual Paulista (UNESP)Castro, Bruno Albuquerque deBinotto, AmandaArdila-Rey, Jorge AlfredoFraga, Jose Renato Castro PompeiaSmith, ColinAndreoli, Andre Luiz2023-07-29T14:00:48Z2023-07-29T14:00:48Z2023-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1109/TII.2023.3240590IEEE Transactions on Industrial Informatics.1941-00501551-3203http://hdl.handle.net/11449/24903910.1109/TII.2023.32405902-s2.0-85148454215Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIEEE Transactions on Industrial Informaticsinfo:eu-repo/semantics/openAccess2023-07-29T14:00:48Zoai:repositorio.unesp.br:11449/249039Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-07-29T14:00:48Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
title |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
spellingShingle |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform Castro, Bruno Albuquerque de Acoustic emission Discharge Discharges (electric) Discrete Fourier transforms Hall effect Insulation Insulators Pattern recognition Power transformer insulation Sensors Transformers fault diagnosis Windings |
title_short |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
title_full |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
title_fullStr |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
title_full_unstemmed |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
title_sort |
New Algorithm Applied to Transformers’ Failures Detection Based on Karhunen-Loève Transform |
author |
Castro, Bruno Albuquerque de |
author_facet |
Castro, Bruno Albuquerque de Binotto, Amanda Ardila-Rey, Jorge Alfredo Fraga, Jose Renato Castro Pompeia Smith, Colin Andreoli, Andre Luiz |
author_role |
author |
author2 |
Binotto, Amanda Ardila-Rey, Jorge Alfredo Fraga, Jose Renato Castro Pompeia Smith, Colin Andreoli, Andre Luiz |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Castro, Bruno Albuquerque de Binotto, Amanda Ardila-Rey, Jorge Alfredo Fraga, Jose Renato Castro Pompeia Smith, Colin Andreoli, Andre Luiz |
dc.subject.por.fl_str_mv |
Acoustic emission Discharge Discharges (electric) Discrete Fourier transforms Hall effect Insulation Insulators Pattern recognition Power transformer insulation Sensors Transformers fault diagnosis Windings |
topic |
Acoustic emission Discharge Discharges (electric) Discrete Fourier transforms Hall effect Insulation Insulators Pattern recognition Power transformer insulation Sensors Transformers fault diagnosis Windings |
description |
Industry and science have been growing attention to developing systems that ensure the integrity of high voltage devices like power transformers. The goal is to avoid unexpected stoppages by detecting incipient failures before they become a major problem. In this context, the detection of discharge activity is an effective way to assess the condition operation of power transformers since this type of flaw can lead the transformer to total failure. The effectiveness of the fault diagnosis systems is related to their capability to distinguish the types of discharges since different flaws require different maintenance planning. This article proposes a new data analysis which combined the frequency spectrum of the signals with the Karhunen-Loève Transform to perform self-organization maps. The effectiveness of this analysis was validated by comparing it with the Fundamental Signals Properties Classification Technique, which is widely applied for pattern recognition.Two types of sensing techniques were assessed in order to enhance the capability of the new approach. Results indicated that the new methodology presented lower standard deviation for data classification, being a promising tool to monitoring systems. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T14:00:48Z 2023-07-29T14:00:48Z 2023-01-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/TII.2023.3240590 IEEE Transactions on Industrial Informatics. 1941-0050 1551-3203 http://hdl.handle.net/11449/249039 10.1109/TII.2023.3240590 2-s2.0-85148454215 |
url |
http://dx.doi.org/10.1109/TII.2023.3240590 http://hdl.handle.net/11449/249039 |
identifier_str_mv |
IEEE Transactions on Industrial Informatics. 1941-0050 1551-3203 10.1109/TII.2023.3240590 2-s2.0-85148454215 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
IEEE Transactions on Industrial Informatics |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803046404371775488 |