Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM
To reduce the levelized cost of wind energy, through the reduction in operation and maintenance costs, it is imperative that the wind turbine downtime is reduced through maintenance strategies based on condition monitoring. The standard approach toward this challenge is based on vibration monitoring...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/12/4381 |
_version_ | 1797487813754617856 |
---|---|
author | Christian Tutivén Yolanda Vidal Andres Insuasty Lorena Campoverde-Vilela Wilson Achicanoy |
author_facet | Christian Tutivén Yolanda Vidal Andres Insuasty Lorena Campoverde-Vilela Wilson Achicanoy |
author_sort | Christian Tutivén |
collection | DOAJ |
description | To reduce the levelized cost of wind energy, through the reduction in operation and maintenance costs, it is imperative that the wind turbine downtime is reduced through maintenance strategies based on condition monitoring. The standard approach toward this challenge is based on vibration monitoring, which requires the installation of specific tailored sensors that incur associated added costs. On the other hand, the life expectancy of wind parks built during the 1990s wind power boom is dwindling, and data-driven maintenance strategies issued from already accessible supervisory control and data acquisition (SCADA) data is an auspicious competitive solution because no additional sensors are required. Note that it is a major issue to provide fault diagnosis approaches built only on SCADA data, as these data were not established with the objective of being used for condition monitoring but rather for control capacities. The present study posits an early fault diagnosis strategy based exclusively on SCADA data and supports it with results on a real wind park with 18 wind turbines. The contributed methodology is an anomaly detection model based on a one-class support vector machine classifier; that is, it is a semi-supervised approach that trains a decision function that categorizes fresh data as similar or dissimilar to the training set. Therefore, only healthy (normal operation) data is required to train the model, which greatly expands the possibility of employing this methodology (because there is no need for faulty data from the past, and only normal operation SCADA data is needed). The results obtained from the real wind park show that this is a promising strategy. |
first_indexed | 2024-03-09T23:53:09Z |
format | Article |
id | doaj.art-fe60cdb8ef2341918e5c3b5ec873ab2f |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-09T23:53:09Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-fe60cdb8ef2341918e5c3b5ec873ab2f2023-11-23T16:30:18ZengMDPI AGEnergies1996-10732022-06-011512438110.3390/en15124381Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVMChristian Tutivén0Yolanda Vidal1Andres Insuasty2Lorena Campoverde-Vilela3Wilson Achicanoy4Escuela Superior Politécnica del Litoral (ESPOL), Faculty of Mechanical Engineering and Production Science (FIMCP), Mechatronics Engineering, Campus Gustavo Galindo, Km. 30.5 Vía Perimetral, Guayaquil EC090902, EcuadorControl, Data and Artificial Intelligence (CoDAlab), Department of Mathematics, Escola d’Enginyeria de Barcelona Est (EEBE), Universitat Politècnica de Catalunya (UPC), Campus Diagonal-Besós (CDB), Eduard Maristany 16, 08019 Barcelona, SpainDepartamento de Electrónica, Universidad de Nariño, Clle 18 Cr 50 Ciudadela Universitaria Torobajo, Pasto 52001, ColombiaEscuela Superior Politécnica del Litoral (ESPOL), Faculty of Mechanical Engineering and Production Science (FIMCP), Mechatronics Engineering, Campus Gustavo Galindo, Km. 30.5 Vía Perimetral, Guayaquil EC090902, EcuadorDepartamento de Electrónica, Universidad de Nariño, Clle 18 Cr 50 Ciudadela Universitaria Torobajo, Pasto 52001, ColombiaTo reduce the levelized cost of wind energy, through the reduction in operation and maintenance costs, it is imperative that the wind turbine downtime is reduced through maintenance strategies based on condition monitoring. The standard approach toward this challenge is based on vibration monitoring, which requires the installation of specific tailored sensors that incur associated added costs. On the other hand, the life expectancy of wind parks built during the 1990s wind power boom is dwindling, and data-driven maintenance strategies issued from already accessible supervisory control and data acquisition (SCADA) data is an auspicious competitive solution because no additional sensors are required. Note that it is a major issue to provide fault diagnosis approaches built only on SCADA data, as these data were not established with the objective of being used for condition monitoring but rather for control capacities. The present study posits an early fault diagnosis strategy based exclusively on SCADA data and supports it with results on a real wind park with 18 wind turbines. The contributed methodology is an anomaly detection model based on a one-class support vector machine classifier; that is, it is a semi-supervised approach that trains a decision function that categorizes fresh data as similar or dissimilar to the training set. Therefore, only healthy (normal operation) data is required to train the model, which greatly expands the possibility of employing this methodology (because there is no need for faulty data from the past, and only normal operation SCADA data is needed). The results obtained from the real wind park show that this is a promising strategy.https://www.mdpi.com/1996-1073/15/12/4381anomaly detectioncondition-based maintenancecondition monitoringfault diagnosismain bearingone-class support vector machine |
spellingShingle | Christian Tutivén Yolanda Vidal Andres Insuasty Lorena Campoverde-Vilela Wilson Achicanoy Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM Energies anomaly detection condition-based maintenance condition monitoring fault diagnosis main bearing one-class support vector machine |
title | Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM |
title_full | Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM |
title_fullStr | Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM |
title_full_unstemmed | Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM |
title_short | Early Fault Diagnosis Strategy for WT Main Bearings Based on SCADA Data and One-Class SVM |
title_sort | early fault diagnosis strategy for wt main bearings based on scada data and one class svm |
topic | anomaly detection condition-based maintenance condition monitoring fault diagnosis main bearing one-class support vector machine |
url | https://www.mdpi.com/1996-1073/15/12/4381 |
work_keys_str_mv | AT christiantutiven earlyfaultdiagnosisstrategyforwtmainbearingsbasedonscadadataandoneclasssvm AT yolandavidal earlyfaultdiagnosisstrategyforwtmainbearingsbasedonscadadataandoneclasssvm AT andresinsuasty earlyfaultdiagnosisstrategyforwtmainbearingsbasedonscadadataandoneclasssvm AT lorenacampoverdevilela earlyfaultdiagnosisstrategyforwtmainbearingsbasedonscadadataandoneclasssvm AT wilsonachicanoy earlyfaultdiagnosisstrategyforwtmainbearingsbasedonscadadataandoneclasssvm |