Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults

Both wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated c...

Descripción completa

Detalles Bibliográficos
Autores: Maestro Prieto, José Alberto, Ramírez Sanz, José Miguel, Bustillo Iglesias, Andrés, Rodríguez Diez, Juan José
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universidad de Burgos (UBU)
Repositorio:Repositorio Institucional de la Universidad de Burgos (RIUBU)
OAI Identifier:oai:riubu.ubu.es:10259/9983
Acceso en línea:http://hdl.handle.net/10259/9983
Access Level:acceso abierto
Palabra clave:Wind turbine
Powertrain failures
Bearing failures
Semi-supervised learning
Fault detection and diagnosis
Informática
Bioinformática
Computer science
Bioinformatics
id ES_5787bcedee413d8f74fe8cf191cc94e3
oai_identifier_str oai:riubu.ubu.es:10259/9983
network_acronym_str ES
network_name_str España
repository_id_str
spelling Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faultsMaestro Prieto, José AlbertoRamírez Sanz, José MiguelBustillo Iglesias, AndrésRodríguez Diez, Juan JoséWind turbinePowertrain failuresBearing failuresSemi-supervised learningFault detection and diagnosisInformáticaBioinformáticaComputer scienceBioinformaticsBoth wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated containing both normal operating patterns and seven different failure classes of the two aforementioned failure modes that vary in intensity. Several datasets are then generated, maintaining different numbers of labeled instances and unlabeling the others, in order to evaluate the number of labeled instances needed for the desired accuracy level. Subsequently, different types of SSL algorithms and combinations of algorithms are trained and then evaluated with the test data. The results showed that an SSL approach could improve the accuracy of trained classifiers when a small number of labeled instances were used together with many unlabeled instances to train a Co-Training algorithm or combinations of such algorithms. When a few labeled instances (fewer than 10% or 327 instances, in this case) were used together with unlabeled instances, the SSL algorithms outperformed the result obtained with the Supervised Learning (SL) techniques used as a benchmark. When the number of labeled instances was sufficient, the SL algorithm (using only labeled instances) performed better than the SSL algorithms (accuracy levels of 87.04% vs. 86.45%, when labeling 10% of instances). A competitive accuracy of 97.73% was achieved with the SL algorithm processing a subset of 40% of the labeled instances.Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.Springer202520252024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10259/9983reponame:Repositorio Institucional de la Universidad de Burgos (RIUBU)instname:Universidad de Burgos (UBU)InglésApplied Intelligence. 2024, V. 54, n. 6, p. 4525-4544https://doi.org/10.1007/s10489-024-05373-6Atribución 4.0 Internacionalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:riubu.ubu.es:10259/99832026-05-28T07:56:11Z
dc.title.none.fl_str_mv Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
title Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
spellingShingle Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
Maestro Prieto, José Alberto
Wind turbine
Powertrain failures
Bearing failures
Semi-supervised learning
Fault detection and diagnosis
Informática
Bioinformática
Computer science
Bioinformatics
title_short Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
title_full Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
title_fullStr Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
title_full_unstemmed Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
title_sort Semi-supervised diagnosis of wind-turbine gearbox misalignment and imbalance faults
dc.creator.none.fl_str_mv Maestro Prieto, José Alberto
Ramírez Sanz, José Miguel
Bustillo Iglesias, Andrés
Rodríguez Diez, Juan José
author Maestro Prieto, José Alberto
author_facet Maestro Prieto, José Alberto
Ramírez Sanz, José Miguel
Bustillo Iglesias, Andrés
Rodríguez Diez, Juan José
author_role author
author2 Ramírez Sanz, José Miguel
Bustillo Iglesias, Andrés
Rodríguez Diez, Juan José
author2_role author
author
author
dc.subject.none.fl_str_mv Wind turbine
Powertrain failures
Bearing failures
Semi-supervised learning
Fault detection and diagnosis
Informática
Bioinformática
Computer science
Bioinformatics
topic Wind turbine
Powertrain failures
Bearing failures
Semi-supervised learning
Fault detection and diagnosis
Informática
Bioinformática
Computer science
Bioinformatics
description Both wear-induced bearing failure and misalignment of the powertrain between the rotor and the electrical generator are common failure modes in wind-turbine motors. In this study, Semi-Supervised Learning (SSL) is applied to a fault detection and diagnosis solution. Firstly, a dataset is generated containing both normal operating patterns and seven different failure classes of the two aforementioned failure modes that vary in intensity. Several datasets are then generated, maintaining different numbers of labeled instances and unlabeling the others, in order to evaluate the number of labeled instances needed for the desired accuracy level. Subsequently, different types of SSL algorithms and combinations of algorithms are trained and then evaluated with the test data. The results showed that an SSL approach could improve the accuracy of trained classifiers when a small number of labeled instances were used together with many unlabeled instances to train a Co-Training algorithm or combinations of such algorithms. When a few labeled instances (fewer than 10% or 327 instances, in this case) were used together with unlabeled instances, the SSL algorithms outperformed the result obtained with the Supervised Learning (SL) techniques used as a benchmark. When the number of labeled instances was sufficient, the SL algorithm (using only labeled instances) performed better than the SSL algorithms (accuracy levels of 87.04% vs. 86.45%, when labeling 10% of instances). A competitive accuracy of 97.73% was achieved with the SL algorithm processing a subset of 40% of the labeled instances.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10259/9983
url http://hdl.handle.net/10259/9983
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Applied Intelligence. 2024, V. 54, n. 6, p. 4525-4544
https://doi.org/10.1007/s10489-024-05373-6
dc.rights.none.fl_str_mv Atribución 4.0 Internacional
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Atribución 4.0 Internacional
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Repositorio Institucional de la Universidad de Burgos (RIUBU)
instname:Universidad de Burgos (UBU)
instname_str Universidad de Burgos (UBU)
reponame_str Repositorio Institucional de la Universidad de Burgos (RIUBU)
collection Repositorio Institucional de la Universidad de Burgos (RIUBU)
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408458556571648
score 15,811543

Similares en LA Referencia