Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes

Autores
Cosa Rodríguez, Pablo; Martí Puig, Pere; Caiafa, César Federico; Serra Serra, Moises; Cusidó, Jordi; Solé Casals, Jordi
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Product maintenance costs throughout the product’s lifetime can account for between 30–60% of total operating costs, making it necessary to implement maintenance strategies. This problem not only affects the economy but is also related to the impact on the environment, since breakdowns are also responsible for the delivery of greenhouse gases. Industrial maintenance is a set of measures of a technical-organizational nature whose purpose is to sustain the functionality of theequipment and guarantee an optimal state of the machines over time, with the aim of saving costs, extending the useful life of the machines, saving energy, maximising production and availability, ensuring the quality of the product obtained, providing job security for technicians, preserving the environment, and reducing emissions as much as possible. Machine learning techniques can be used to detect or predict faults in wind turbines. However, labelled data suffers from many problems in this application because alarms are usually not clearly associated with a specific fault, some labelsare wrongly associated with a problem, and the imbalance between labels is evident. To avoid using labelled data, we investigate here the use of the clustering technique, more specifically K-means, and boxplot representations of the variables for a set of six different tests. Experimental results show that in some cases, the clustering and boxplot techniques allow us to determine outliers or identify erroneous behaviours of the wind turbines. These cases can then be investigated in detail by a specialist so that more efficient predictive maintenance can be carried out.
Fil: Cosa Rodríguez, Pablo. Open University of Catalonia. Faculty of Computer Science, Multimedia and Telecommunications.; España
Fil: Martí Puig, Pere. University of Vic-Central. Data and Signal Processing Group; España
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Serra Serra, Moises. University of Vic-Central. Data and Signal Processing Group; España
Fil: Cusidó, Jordi. University of Vic-Central. Data and Signal Processing Group; España
Fil: Solé Casals, Jordi. University of Vic-Central. Data and Signal Processing Group; España
Materia
predictive maintenance
prognosis
machine learning
K-means
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/218002
Acceder
id CONICETDig_e48a280fba660d12386205d687fc0afb
oai_identifier_str oai:ri.conicet.gov.ar:11336/218002
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance PurposesCosa Rodríguez, PabloMartí Puig, PereCaiafa, César FedericoSerra Serra, MoisesCusidó, JordiSolé Casals, Jordipredictive maintenanceprognosismachine learningK-meanshttps://purl.org/becyt/ford/2.7https://purl.org/becyt/ford/2Product maintenance costs throughout the product’s lifetime can account for between 30–60% of total operating costs, making it necessary to implement maintenance strategies. This problem not only affects the economy but is also related to the impact on the environment, since breakdowns are also responsible for the delivery of greenhouse gases. Industrial maintenance is a set of measures of a technical-organizational nature whose purpose is to sustain the functionality of theequipment and guarantee an optimal state of the machines over time, with the aim of saving costs, extending the useful life of the machines, saving energy, maximising production and availability, ensuring the quality of the product obtained, providing job security for technicians, preserving the environment, and reducing emissions as much as possible. Machine learning techniques can be used to detect or predict faults in wind turbines. However, labelled data suffers from many problems in this application because alarms are usually not clearly associated with a specific fault, some labelsare wrongly associated with a problem, and the imbalance between labels is evident. To avoid using labelled data, we investigate here the use of the clustering technique, more specifically K-means, and boxplot representations of the variables for a set of six different tests. Experimental results show that in some cases, the clustering and boxplot techniques allow us to determine outliers or identify erroneous behaviours of the wind turbines. These cases can then be investigated in detail by a specialist so that more efficient predictive maintenance can be carried out.Fil: Cosa Rodríguez, Pablo. Open University of Catalonia. Faculty of Computer Science, Multimedia and Telecommunications.; EspañaFil: Martí Puig, Pere. University of Vic-Central. Data and Signal Processing Group; EspañaFil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Serra Serra, Moises. University of Vic-Central. Data and Signal Processing Group; EspañaFil: Cusidó, Jordi. University of Vic-Central. Data and Signal Processing Group; EspañaFil: Solé Casals, Jordi. University of Vic-Central. Data and Signal Processing Group; EspañaMDPI2023-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/218002Cosa Rodríguez, Pablo; Martí Puig, Pere; Caiafa, César Federico; Serra Serra, Moises; Cusidó, Jordi; et al.; Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes; MDPI; Machines; 11; 2; 2-2023; 1-152075-1702CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2075-1702/11/2/270/htminfo:eu-repo/semantics/altIdentifier/doi/10.3390/machines11020270info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:18:21Zoai:ri.conicet.gov.ar:11336/218002instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:18:21.514CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
title Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
spellingShingle Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
Cosa Rodríguez, Pablo
predictive maintenance
prognosis
machine learning
K-means
title_short Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
title_full Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
title_fullStr Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
title_full_unstemmed Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
title_sort Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes
dc.creator.none.fl_str_mv Cosa Rodríguez, Pablo
Martí Puig, Pere
Caiafa, César Federico
Serra Serra, Moises
Cusidó, Jordi
Solé Casals, Jordi
author Cosa Rodríguez, Pablo
author_facet Cosa Rodríguez, Pablo
Martí Puig, Pere
Caiafa, César Federico
Serra Serra, Moises
Cusidó, Jordi
Solé Casals, Jordi
author_role author
author2 Martí Puig, Pere
Caiafa, César Federico
Serra Serra, Moises
Cusidó, Jordi
Solé Casals, Jordi
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv predictive maintenance
prognosis
machine learning
K-means
topic predictive maintenance
prognosis
machine learning
K-means
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.7
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv Product maintenance costs throughout the product’s lifetime can account for between 30–60% of total operating costs, making it necessary to implement maintenance strategies. This problem not only affects the economy but is also related to the impact on the environment, since breakdowns are also responsible for the delivery of greenhouse gases. Industrial maintenance is a set of measures of a technical-organizational nature whose purpose is to sustain the functionality of theequipment and guarantee an optimal state of the machines over time, with the aim of saving costs, extending the useful life of the machines, saving energy, maximising production and availability, ensuring the quality of the product obtained, providing job security for technicians, preserving the environment, and reducing emissions as much as possible. Machine learning techniques can be used to detect or predict faults in wind turbines. However, labelled data suffers from many problems in this application because alarms are usually not clearly associated with a specific fault, some labelsare wrongly associated with a problem, and the imbalance between labels is evident. To avoid using labelled data, we investigate here the use of the clustering technique, more specifically K-means, and boxplot representations of the variables for a set of six different tests. Experimental results show that in some cases, the clustering and boxplot techniques allow us to determine outliers or identify erroneous behaviours of the wind turbines. These cases can then be investigated in detail by a specialist so that more efficient predictive maintenance can be carried out.
Fil: Cosa Rodríguez, Pablo. Open University of Catalonia. Faculty of Computer Science, Multimedia and Telecommunications.; España
Fil: Martí Puig, Pere. University of Vic-Central. Data and Signal Processing Group; España
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Serra Serra, Moises. University of Vic-Central. Data and Signal Processing Group; España
Fil: Cusidó, Jordi. University of Vic-Central. Data and Signal Processing Group; España
Fil: Solé Casals, Jordi. University of Vic-Central. Data and Signal Processing Group; España
description Product maintenance costs throughout the product’s lifetime can account for between 30–60% of total operating costs, making it necessary to implement maintenance strategies. This problem not only affects the economy but is also related to the impact on the environment, since breakdowns are also responsible for the delivery of greenhouse gases. Industrial maintenance is a set of measures of a technical-organizational nature whose purpose is to sustain the functionality of theequipment and guarantee an optimal state of the machines over time, with the aim of saving costs, extending the useful life of the machines, saving energy, maximising production and availability, ensuring the quality of the product obtained, providing job security for technicians, preserving the environment, and reducing emissions as much as possible. Machine learning techniques can be used to detect or predict faults in wind turbines. However, labelled data suffers from many problems in this application because alarms are usually not clearly associated with a specific fault, some labelsare wrongly associated with a problem, and the imbalance between labels is evident. To avoid using labelled data, we investigate here the use of the clustering technique, more specifically K-means, and boxplot representations of the variables for a set of six different tests. Experimental results show that in some cases, the clustering and boxplot techniques allow us to determine outliers or identify erroneous behaviours of the wind turbines. These cases can then be investigated in detail by a specialist so that more efficient predictive maintenance can be carried out.
publishDate 2023
dc.date.none.fl_str_mv 2023-02
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/218002
Cosa Rodríguez, Pablo; Martí Puig, Pere; Caiafa, César Federico; Serra Serra, Moises; Cusidó, Jordi; et al.; Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes; MDPI; Machines; 11; 2; 2-2023; 1-15
2075-1702
CONICET Digital
CONICET
url http://hdl.handle.net/11336/218002
identifier_str_mv Cosa Rodríguez, Pablo; Martí Puig, Pere; Caiafa, César Federico; Serra Serra, Moises; Cusidó, Jordi; et al.; Exploratory Analysis of SCADA Data from Wind Turbines Using the K-Means Clustering Algorithm for Predictive Maintenance Purposes; MDPI; Machines; 11; 2; 2-2023; 1-15
2075-1702
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2075-1702/11/2/270/htm
info:eu-repo/semantics/altIdentifier/doi/10.3390/machines11020270
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614144315097088
score 13.070432

Publicaciones similares