Feature Selection Algorithms for Wind Turbine Failure Prediction

It is well known that each year the wind sector has profit losses due to wind turbine failures and operation and maintenance costs. Therefore, operations related to these actions are crucial for wind farm operators and linked companies. One of the key points for failure prediction on wind turbine us...

ver descrição completa

Detalhes bibliográficos
Autores: Marti-Puig, Pere|||0000-0001-6582-4551, Blanco Martínez, Alejandro, Cárdenas Araújo, Juan José, Cusidó Roura, Jordi|||0000-0002-1951-1498, Sole Casals, Jordi
Tipo de documento: artigo
Data de publicação:2019
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/335768
Acesso em linha:https://hdl.handle.net/2117/335768
https://dx.doi.org/10.3390/en12030453
Access Level:Acceso aberto
Palavra-chave:Failure analysis (Engineering)
Wind power plants
Wind turbines
Supervisory control systems
System failures (Engineering)
Machine learning
Feature selection
Failure prediction
Wind energy
Health monitoring
Sensing systems
Wind farms
Condition monitoring
SCADA data
Anàlisi de fallades (Enginyeria)
Parcs eòlics
Aerogeneradors
Avaries
Aprenentatge automatic
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_5943e4b26e435f5e1e482fe57e908ea2
oai_identifier_str oai:upcommons.upc.edu:2117/335768
network_acronym_str ES
network_name_str España
repository_id_str
spelling Feature Selection Algorithms for Wind Turbine Failure PredictionMarti-Puig, Pere|||0000-0001-6582-4551Blanco Martínez, AlejandroCárdenas Araújo, Juan JoséCusidó Roura, Jordi|||0000-0002-1951-1498Sole Casals, JordiFailure analysis (Engineering)Wind power plantsWind turbinesSupervisory control systemsSystem failures (Engineering)Machine learningFeature selectionFailure predictionWind energyHealth monitoringSensing systemsWind farmsCondition monitoringSCADA dataAnàlisi de fallades (Enginyeria)Parcs eòlicsAerogeneradorsAvariesAprenentatge automaticÀrees temàtiques de la UPC::Energies::Energia eòlica::AerogeneradorsÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialIt is well known that each year the wind sector has profit losses due to wind turbine failures and operation and maintenance costs. Therefore, operations related to these actions are crucial for wind farm operators and linked companies. One of the key points for failure prediction on wind turbine using SCADA data is to select the optimal or near optimal set of inputs that can feed the failure prediction (prognosis) algorithm. Due to a high number of possible predictors (from tens to hundreds), the optimal set of inputs obtained by exhaustive-search algorithms is not viable in the majority of cases. In order to tackle this issue, show the viability of prognosis and select the best set of variables from more than 200 analogous variables recorded at intervals of 5 or 10 min by the wind farm’s SCADA, in this paper a thorough study of automatic input selection algorithms for wind turbine failure prediction is presented and an exhaustive-search-based quasi-optimal (QO) algorithm, which has been used as a reference, is proposed. In order to evaluate the performance, a k-NN classification algorithm is used. Results showed that the best automatic feature selection method in our case-study is the conditional mutual information (CMI), while the worst one is the mutual information feature selection (MIFS). Furthermore, the effect of the number of neighbours (k) is tested. Experiments demonstrate that k = 1 is the best option if the number of features is higher than 3. The experiments carried out in this work have been extracted from measures taken along an entire year and corresponding to gearbox and transmission systems of Fuhrländer wind turbines.Research partially funded by Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR) of the Catalan Government (Project reference: 2014-DI-032).Peer Reviewed20192019-01-3120212021-01-21journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/335768https://dx.doi.org/10.3390/en12030453reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3357682026-05-27T15:37:01Z
dc.title.none.fl_str_mv Feature Selection Algorithms for Wind Turbine Failure Prediction
title Feature Selection Algorithms for Wind Turbine Failure Prediction
spellingShingle Feature Selection Algorithms for Wind Turbine Failure Prediction
Marti-Puig, Pere|||0000-0001-6582-4551
Failure analysis (Engineering)
Wind power plants
Wind turbines
Supervisory control systems
System failures (Engineering)
Machine learning
Feature selection
Failure prediction
Wind energy
Health monitoring
Sensing systems
Wind farms
Condition monitoring
SCADA data
Anàlisi de fallades (Enginyeria)
Parcs eòlics
Aerogeneradors
Avaries
Aprenentatge automatic
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Feature Selection Algorithms for Wind Turbine Failure Prediction
title_full Feature Selection Algorithms for Wind Turbine Failure Prediction
title_fullStr Feature Selection Algorithms for Wind Turbine Failure Prediction
title_full_unstemmed Feature Selection Algorithms for Wind Turbine Failure Prediction
title_sort Feature Selection Algorithms for Wind Turbine Failure Prediction
dc.creator.none.fl_str_mv Marti-Puig, Pere|||0000-0001-6582-4551
Blanco Martínez, Alejandro
Cárdenas Araújo, Juan José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Sole Casals, Jordi
author Marti-Puig, Pere|||0000-0001-6582-4551
author_facet Marti-Puig, Pere|||0000-0001-6582-4551
Blanco Martínez, Alejandro
Cárdenas Araújo, Juan José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Sole Casals, Jordi
author_role author
author2 Blanco Martínez, Alejandro
Cárdenas Araújo, Juan José
Cusidó Roura, Jordi|||0000-0002-1951-1498
Sole Casals, Jordi
author2_role author
author
author
author
dc.subject.none.fl_str_mv Failure analysis (Engineering)
Wind power plants
Wind turbines
Supervisory control systems
System failures (Engineering)
Machine learning
Feature selection
Failure prediction
Wind energy
Health monitoring
Sensing systems
Wind farms
Condition monitoring
SCADA data
Anàlisi de fallades (Enginyeria)
Parcs eòlics
Aerogeneradors
Avaries
Aprenentatge automatic
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Failure analysis (Engineering)
Wind power plants
Wind turbines
Supervisory control systems
System failures (Engineering)
Machine learning
Feature selection
Failure prediction
Wind energy
Health monitoring
Sensing systems
Wind farms
Condition monitoring
SCADA data
Anàlisi de fallades (Enginyeria)
Parcs eòlics
Aerogeneradors
Avaries
Aprenentatge automatic
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description It is well known that each year the wind sector has profit losses due to wind turbine failures and operation and maintenance costs. Therefore, operations related to these actions are crucial for wind farm operators and linked companies. One of the key points for failure prediction on wind turbine using SCADA data is to select the optimal or near optimal set of inputs that can feed the failure prediction (prognosis) algorithm. Due to a high number of possible predictors (from tens to hundreds), the optimal set of inputs obtained by exhaustive-search algorithms is not viable in the majority of cases. In order to tackle this issue, show the viability of prognosis and select the best set of variables from more than 200 analogous variables recorded at intervals of 5 or 10 min by the wind farm’s SCADA, in this paper a thorough study of automatic input selection algorithms for wind turbine failure prediction is presented and an exhaustive-search-based quasi-optimal (QO) algorithm, which has been used as a reference, is proposed. In order to evaluate the performance, a k-NN classification algorithm is used. Results showed that the best automatic feature selection method in our case-study is the conditional mutual information (CMI), while the worst one is the mutual information feature selection (MIFS). Furthermore, the effect of the number of neighbours (k) is tested. Experiments demonstrate that k = 1 is the best option if the number of features is higher than 3. The experiments carried out in this work have been extracted from measures taken along an entire year and corresponding to gearbox and transmission systems of Fuhrländer wind turbines.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-01-31
2021
2021-01-21
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/2117/335768
https://dx.doi.org/10.3390/en12030453
url https://hdl.handle.net/2117/335768
https://dx.doi.org/10.3390/en12030453
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 4.0
http://creativecommons.org/licenses/by/4.0/
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 4.0
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
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_ 1869408601336971264
score 15.301603

Registros relacionados