An Ensemble Learning Solution for Predictive Maintenance 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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/4/1512 |
| _version_ | 1797395657391079424 |
|---|---|
| author | Mattia Beretta Anatole Julian Jose Sepulveda Jordi Cusidó Olga Porro |
| author_facet | Mattia Beretta Anatole Julian Jose Sepulveda Jordi Cusidó Olga Porro |
| author_sort | Mattia Beretta |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T00:38:40Z |
| format | Article |
| id | doaj.art-9e8412ce6cbd489b8d864331354a65fb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T00:38:40Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9e8412ce6cbd489b8d864331354a65fb2023-12-11T17:58:44ZengMDPI AGSensors1424-82202021-02-01214151210.3390/s21041512An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main BearingMattia Beretta0Anatole Julian1Jose Sepulveda2Jordi Cusidó3Olga Porro4Unitat Transversal de Gestió de l’Àmbit de Camins UTGAC, Universitat Politécnica de Catalunya, 08034 Barcelona, SpainSMARTIVE S.L., 08204 Sabadell, SpainSMARTIVE S.L., 08204 Sabadell, SpainSMARTIVE S.L., 08204 Sabadell, SpainSMARTIVE S.L., 08204 Sabadell, SpainA 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.https://www.mdpi.com/1424-8220/21/4/1512main bearingwind turbinefailurespredictive maintenanceensemble learningunsupervised |
| spellingShingle | Mattia Beretta Anatole Julian Jose Sepulveda Jordi Cusidó Olga Porro An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing Sensors main bearing wind turbine failures predictive maintenance ensemble learning unsupervised |
| title | An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing |
| title_full | An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing |
| title_fullStr | An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing |
| title_full_unstemmed | An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing |
| title_short | An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing |
| title_sort | ensemble learning solution for predictive maintenance of wind turbines main bearing |
| topic | main bearing wind turbine failures predictive maintenance ensemble learning unsupervised |
| url | https://www.mdpi.com/1424-8220/21/4/1512 |
| work_keys_str_mv | AT mattiaberetta anensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT anatolejulian anensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT josesepulveda anensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT jordicusido anensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT olgaporro anensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT mattiaberetta ensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT anatolejulian ensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT josesepulveda ensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT jordicusido ensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing AT olgaporro ensemblelearningsolutionforpredictivemaintenanceofwindturbinesmainbearing |