An ensemble learning solution for predicitive manintenance of wind turbines main bearing

A novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised...

Descripción completa

Detalles Bibliográficos
Autores: Beretta, Mattia|||0000-0002-9690-4359, Julian, Anatole Alexandre, Sepúlveda, José, Cusidó Roura, Jordi|||0000-0002-1951-1498, Porro Martorell, Olga
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/340787
Acceso en línea:https://hdl.handle.net/2117/340787
https://dx.doi.org/10.3390/s21041512
Access Level:acceso abierto
Palabra clave:Wind turbines--Maintenance and repair
Main bearing
Wind turbine
Failures
Predictive maintenance
Ensemble learning
Unsupervised
Interpretable
Scalable
SCADA
Aerogeneradors -- Manteniment i reparació
Àrees temàtiques de la UPC::Enginyeria civil::Materials i estructures
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
id ES_901121e997fd4c64fb7f4e4e519e919f
oai_identifier_str oai:upcommons.upc.edu:2117/340787
network_acronym_str ES
network_name_str España
repository_id_str
spelling An ensemble learning solution for predicitive manintenance of wind turbines main bearingBeretta, Mattia|||0000-0002-9690-4359Julian, Anatole AlexandreSepúlveda, JoséCusidó Roura, Jordi|||0000-0002-1951-1498Porro Martorell, OlgaWind turbines--Maintenance and repairMain bearingWind turbineFailuresPredictive maintenanceEnsemble learningUnsupervisedInterpretableScalableSCADAAerogeneradors -- Manteniment i reparacióÀrees temàtiques de la UPC::Enginyeria civil::Materials i estructuresÀrees temàtiques de la UPC::Energies::Energia eòlica::AerogeneradorsA novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised as it does not require the labeling of data through work orders logs. Results of interpretable algorithms, which are tailored to capture specific aspects of main bearing failures, are merged into a combined health status indicator making use of Ensemble Learning principles. Based on multiple specialized indicators, the interpretability of the results is greater compared to black-box solutions that try to address the problem with a single complex algorithm. The proposed methodology has been tested on a dataset covering more than two year of operations from two onshore wind farms, counting a total of 84 turbines. All four main bearing failures are anticipated at least one month of time in advance. Combining individual indicators into a composed one proved effective with regard to all the tracked metrics. Accuracy of 95.1%, precision of 24.5% and F1 score of 38.5% are obtained averaging the values across the two windfarms. The encouraging results, the unsupervised nature and the flexibility and scalability of the proposed solution are appealing, making it particularly attractive for any online monitoring system used on single wind farms as well as entire wind turbine fleets.This research was funded by Centro para el Desarollo Tecnológico Industrial, grant number CDTI-IDI 20191294 and Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR), grant number DOCTORADO AGAUR-2017-DI 004.Peer ReviewedObjectius de Desenvolupament Sostenible::7 - Energia Assequible i No ContaminantMultidisciplinary Digital Publishing Institute (MDPI)20212021-02-0120212021-03-02journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/340787https://dx.doi.org/10.3390/s21041512reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 3.0 Spainhttp://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3407872026-05-27T15:37:01Z
dc.title.none.fl_str_mv An ensemble learning solution for predicitive manintenance of wind turbines main bearing
title An ensemble learning solution for predicitive manintenance of wind turbines main bearing
spellingShingle An ensemble learning solution for predicitive manintenance of wind turbines main bearing
Beretta, Mattia|||0000-0002-9690-4359
Wind turbines--Maintenance and repair
Main bearing
Wind turbine
Failures
Predictive maintenance
Ensemble learning
Unsupervised
Interpretable
Scalable
SCADA
Aerogeneradors -- Manteniment i reparació
Àrees temàtiques de la UPC::Enginyeria civil::Materials i estructures
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
title_short An ensemble learning solution for predicitive manintenance of wind turbines main bearing
title_full An ensemble learning solution for predicitive manintenance of wind turbines main bearing
title_fullStr An ensemble learning solution for predicitive manintenance of wind turbines main bearing
title_full_unstemmed An ensemble learning solution for predicitive manintenance of wind turbines main bearing
title_sort An ensemble learning solution for predicitive manintenance of wind turbines main bearing
dc.creator.none.fl_str_mv Beretta, Mattia|||0000-0002-9690-4359
Julian, Anatole Alexandre
Sepúlveda, José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Porro Martorell, Olga
author Beretta, Mattia|||0000-0002-9690-4359
author_facet Beretta, Mattia|||0000-0002-9690-4359
Julian, Anatole Alexandre
Sepúlveda, José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Porro Martorell, Olga
author_role author
author2 Julian, Anatole Alexandre
Sepúlveda, José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Porro Martorell, Olga
author2_role author
author
author
author
dc.subject.none.fl_str_mv Wind turbines--Maintenance and repair
Main bearing
Wind turbine
Failures
Predictive maintenance
Ensemble learning
Unsupervised
Interpretable
Scalable
SCADA
Aerogeneradors -- Manteniment i reparació
Àrees temàtiques de la UPC::Enginyeria civil::Materials i estructures
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
topic Wind turbines--Maintenance and repair
Main bearing
Wind turbine
Failures
Predictive maintenance
Ensemble learning
Unsupervised
Interpretable
Scalable
SCADA
Aerogeneradors -- Manteniment i reparació
Àrees temàtiques de la UPC::Enginyeria civil::Materials i estructures
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
description A novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised as it does not require the labeling of data through work orders logs. Results of interpretable algorithms, which are tailored to capture specific aspects of main bearing failures, are merged into a combined health status indicator making use of Ensemble Learning principles. Based on multiple specialized indicators, the interpretability of the results is greater compared to black-box solutions that try to address the problem with a single complex algorithm. The proposed methodology has been tested on a dataset covering more than two year of operations from two onshore wind farms, counting a total of 84 turbines. All four main bearing failures are anticipated at least one month of time in advance. Combining individual indicators into a composed one proved effective with regard to all the tracked metrics. Accuracy of 95.1%, precision of 24.5% and F1 score of 38.5% are obtained averaging the values across the two windfarms. The encouraging results, the unsupervised nature and the flexibility and scalability of the proposed solution are appealing, making it particularly attractive for any online monitoring system used on single wind farms as well as entire wind turbine fleets.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-02-01
2021
2021-03-02
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/340787
https://dx.doi.org/10.3390/s21041512
url https://hdl.handle.net/2117/340787
https://dx.doi.org/10.3390/s21041512
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 3.0 Spain
http://creativecommons.org/licenses/by/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 3.0 Spain
http://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869413263820718080
score 15,300724

Similares en LA Referencia