Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | spa |
Título da fonte: | Sapienza (Curitiba) |
Texto Completo: | https://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/537 |
Resumo: | The main objective of this research was the detection and classification of electrical faults in an electrical power system using the Wavelet transform and Neural Networks. The methodology consists of two steps; In the first step, the calculation and design process of a radial power system is carried out. The second phase throws the modeling and simulation of fault detection and classification in Matlab/ Simulink. The results obtained indicate that the neural network predicts and classifies the types of faults in the electrical power system. It is concluded that although the neural model with Bayesian regularization and early completion offers relatively low errors, it has the drawback of being a rigid black box, that is, the neural network simply evaluates its inputs and produces its outputs, but it is not known What. For this reason, when a misclassification occurs, there is no way to make changes and the network must be completely retrained, which is not appropriate from a practical point of view. |
id |
SAPIENZA_24aa79a70e4beaea186c219c32ffd4b5 |
---|---|
oai_identifier_str |
oai:ojs2.journals.sapienzaeditorial.com:article/537 |
network_acronym_str |
SAPIENZA |
network_name_str |
Sapienza (Curitiba) |
repository_id_str |
|
spelling |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networksDetección y clasificación de fallas eléctricas en un sistema eléctrico de potencia usando la transformada Wavelet y redes neuronalesDetecção e classificação de falhas elétricas em um sistema elétrico de potência utilizando a transformada wavelet e redes neuraisTransformada Wavelet, técnicas de detecção e detecção de falhas, redes neurais inteligentes.Wavelet transform, fault detection and detection techniques, intelligent neural networksTransformada de Wavelet, Técnicas de detección y detección de falla, redes neuronales inteligentesThe main objective of this research was the detection and classification of electrical faults in an electrical power system using the Wavelet transform and Neural Networks. The methodology consists of two steps; In the first step, the calculation and design process of a radial power system is carried out. The second phase throws the modeling and simulation of fault detection and classification in Matlab/ Simulink. The results obtained indicate that the neural network predicts and classifies the types of faults in the electrical power system. It is concluded that although the neural model with Bayesian regularization and early completion offers relatively low errors, it has the drawback of being a rigid black box, that is, the neural network simply evaluates its inputs and produces its outputs, but it is not known What. For this reason, when a misclassification occurs, there is no way to make changes and the network must be completely retrained, which is not appropriate from a practical point of view.El objetivo principal de esta investigación fue la detección y clasificación de fallas eléctricas en un sistema eléctrico de potencia usando la transformada Wavelet y Redes Neuronales. La metodología consiste en dos pasos; en el primer paso se realiza el proceso de cálculo y diseño de un sistema de potencia radial. La segunda fase arroja la modelación y simulación de detección y clasificación de fallas en Matlab/ Simulink. Los resultados obtenidos indican que la red neuronal predice y clasifica los tipos de fallas en sistema eléctrico de potencia. Se concluye que a pesar de que el modelo neuronal con regularización bayesiana y finalización temprana ofrece errores relativamente bajos, presenta el inconveniente de ser una caja negra rígida, es decir, la red neuronal simplemente evalúa sus entradas y produce sus salidas, pero no se sabe cómo. Por esta razón, cuando ocurre una clasificación errónea, no hay forma de realizar cambios y la red debe volver a entrenarse por completo, lo que no es apropiado desde un punto de vista práctico.O objetivo principal desta pesquisa foi a detecção e classificação de falhas elétricas em um sistema elétrico de potência utilizando a transformada Wavelet e Redes Neurais. A metodologia consiste em duas etapas; Na primeira etapa, é realizado o processo de cálculo e projeto de um sistema de potência radial. A segunda fase lança a modelagem e simulação de detecção e classificação de falhas em Matlab/ Simulink. Os resultados obtidos indicam que a rede neural prevê e classifica os tipos de falhas no sistema elétrico de potência. Conclui-se que embora o modelo neural com regularização Bayesiana e preenchimento antecipado ofereça erros relativamente baixos, ele tem a desvantagem de ser uma caixa preta rígida, ou seja, a rede neural simplesmente avalia suas entradas e produz suas saídas, mas não se sabe O que. Por esse motivo, quando ocorre uma classificação incorreta, não há como fazer alterações e a rede deve ser totalmente retreinada, o que não é adequado do ponto de vista prático.Sapienza Grupo Editorial2022-10-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/53710.51798/sijis.v3i7.537Sapienza: International Journal of Interdisciplinary Studies; Vol. 3 No. 7 (2022): Theoretical and methodological plurality; 228-244Sapienza: International Journal of Interdisciplinary Studies; Vol. 3 Núm. 7 (2022): Pluralidad teórica y metodológica; 228-244Sapienza: International Journal of Interdisciplinary Studies; v. 3 n. 7 (2022): Pluralidade teórica e metodológica; 228-2442675-978010.51798/sijis.v3i7reponame:Sapienza (Curitiba)instname:Sapienza Grupo Editorialinstacron:SAPIENZAspahttps://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/537/370Copyright (c) 2022 Ismael Elías Erazo-Velasco, José Vicencio Bautista-Sánchez, Roberto Iván Rodríguez-Jijón, Luis Adrián González-Quiñonez, Byron Fernando Chere-Quiñónezhttps://creativecommons.org/licenses/by-nc-nd/4.0info:eu-repo/semantics/openAccessErazo-Velasco, Ismael Elías Bautista-Sánchez, José Vicencio Rodríguez-Jijón, Roberto Iván González-Quiñonez, Luis Adrián Chere-Quiñónez, Byron Fernando 2022-11-24T04:33:00Zoai:ojs2.journals.sapienzaeditorial.com:article/537Revistahttps://journals.sapienzaeditorial.com/index.php/SIJISPRIhttps://journals.sapienzaeditorial.com/index.php/SIJIS/oaieditor@sapienzaeditorial.com2675-97802675-9780opendoar:2023-01-12T16:43:03.976442Sapienza (Curitiba) - Sapienza Grupo Editorialfalse |
dc.title.none.fl_str_mv |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks Detección y clasificación de fallas eléctricas en un sistema eléctrico de potencia usando la transformada Wavelet y redes neuronales Detecção e classificação de falhas elétricas em um sistema elétrico de potência utilizando a transformada wavelet e redes neurais |
title |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
spellingShingle |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks Erazo-Velasco, Ismael Elías Transformada Wavelet, técnicas de detecção e detecção de falhas, redes neurais inteligentes. Wavelet transform, fault detection and detection techniques, intelligent neural networks Transformada de Wavelet, Técnicas de detección y detección de falla, redes neuronales inteligentes |
title_short |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
title_full |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
title_fullStr |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
title_full_unstemmed |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
title_sort |
Detection and classification of electrical faults in an electrical power system using the Wavelet transform and neural networks |
author |
Erazo-Velasco, Ismael Elías |
author_facet |
Erazo-Velasco, Ismael Elías Bautista-Sánchez, José Vicencio Rodríguez-Jijón, Roberto Iván González-Quiñonez, Luis Adrián Chere-Quiñónez, Byron Fernando |
author_role |
author |
author2 |
Bautista-Sánchez, José Vicencio Rodríguez-Jijón, Roberto Iván González-Quiñonez, Luis Adrián Chere-Quiñónez, Byron Fernando |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Erazo-Velasco, Ismael Elías Bautista-Sánchez, José Vicencio Rodríguez-Jijón, Roberto Iván González-Quiñonez, Luis Adrián Chere-Quiñónez, Byron Fernando |
dc.subject.por.fl_str_mv |
Transformada Wavelet, técnicas de detecção e detecção de falhas, redes neurais inteligentes. Wavelet transform, fault detection and detection techniques, intelligent neural networks Transformada de Wavelet, Técnicas de detección y detección de falla, redes neuronales inteligentes |
topic |
Transformada Wavelet, técnicas de detecção e detecção de falhas, redes neurais inteligentes. Wavelet transform, fault detection and detection techniques, intelligent neural networks Transformada de Wavelet, Técnicas de detección y detección de falla, redes neuronales inteligentes |
description |
The main objective of this research was the detection and classification of electrical faults in an electrical power system using the Wavelet transform and Neural Networks. The methodology consists of two steps; In the first step, the calculation and design process of a radial power system is carried out. The second phase throws the modeling and simulation of fault detection and classification in Matlab/ Simulink. The results obtained indicate that the neural network predicts and classifies the types of faults in the electrical power system. It is concluded that although the neural model with Bayesian regularization and early completion offers relatively low errors, it has the drawback of being a rigid black box, that is, the neural network simply evaluates its inputs and produces its outputs, but it is not known What. For this reason, when a misclassification occurs, there is no way to make changes and the network must be completely retrained, which is not appropriate from a practical point of view. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-10-30 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/537 10.51798/sijis.v3i7.537 |
url |
https://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/537 |
identifier_str_mv |
10.51798/sijis.v3i7.537 |
dc.language.iso.fl_str_mv |
spa |
language |
spa |
dc.relation.none.fl_str_mv |
https://journals.sapienzaeditorial.com/index.php/SIJIS/article/view/537/370 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by-nc-nd/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by-nc-nd/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Sapienza Grupo Editorial |
publisher.none.fl_str_mv |
Sapienza Grupo Editorial |
dc.source.none.fl_str_mv |
Sapienza: International Journal of Interdisciplinary Studies; Vol. 3 No. 7 (2022): Theoretical and methodological plurality; 228-244 Sapienza: International Journal of Interdisciplinary Studies; Vol. 3 Núm. 7 (2022): Pluralidad teórica y metodológica; 228-244 Sapienza: International Journal of Interdisciplinary Studies; v. 3 n. 7 (2022): Pluralidade teórica e metodológica; 228-244 2675-9780 10.51798/sijis.v3i7 reponame:Sapienza (Curitiba) instname:Sapienza Grupo Editorial instacron:SAPIENZA |
instname_str |
Sapienza Grupo Editorial |
instacron_str |
SAPIENZA |
institution |
SAPIENZA |
reponame_str |
Sapienza (Curitiba) |
collection |
Sapienza (Curitiba) |
repository.name.fl_str_mv |
Sapienza (Curitiba) - Sapienza Grupo Editorial |
repository.mail.fl_str_mv |
editor@sapienzaeditorial.com |
_version_ |
1797051607049830400 |