Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy

ABSTRACT In order to reduce curative interventions in wind energy, maintenance approaches based on real‐time monitoring of component health have been widely studied. These condition‐based maintenance processes generally rely on data‐driven residual indicators, measuring the difference between a meas...

Full description

Saved in:
Bibliographic Details
Main Authors: Théodore Raymond, Sylvie Charbonnier, Christophe Bérenguer, Alexis Lebranchu
Format: Article
Language:English
Published: Wiley 2025-09-01
Series:Wind Energy
Subjects:
Online Access:https://doi.org/10.1002/we.70050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233501733257216
author Théodore Raymond
Sylvie Charbonnier
Christophe Bérenguer
Alexis Lebranchu
author_facet Théodore Raymond
Sylvie Charbonnier
Christophe Bérenguer
Alexis Lebranchu
author_sort Théodore Raymond
collection DOAJ
description ABSTRACT In order to reduce curative interventions in wind energy, maintenance approaches based on real‐time monitoring of component health have been widely studied. These condition‐based maintenance processes generally rely on data‐driven residual indicators, measuring the difference between a measured value and an estimation made by a normal behavior model. These solutions face limitations that prevent their applicability to an industrial context. First, models, which are mostly built using artificial neural networks, can be very accurate but remain difficult to interpret by a wind turbine operator and present implementation constraints due to the large number of inputs variables. Moreover, existing condition monitoring processes proposed for wind turbines are defined for a scope reduced to a single manufacturer and to a set of components that does not include all the critical ones, which does not guarantee their possible deployment across a fleet. In this paper, a data‐driven automatic model generation method for fault detection, applicable to an entire fleet of wind turbines, is presented. The models obtained are simple, physically coherent, and valid for all the wind turbines of a farm. Multiturbine residual indicators, robust to environmental variations, are then built and analyzed to perform fault detection. The fault detection ability of these indicators is evaluated on four faults impacting four components from different wind farms and manufacturers, using receiver operating characteristic curves. Finally, the fault detection performances of the proposed models are evaluated on wind farms with turbines of various technologies, whose data have not been used to learn the models. The good results obtained show that the implemented process is suitable for industrial deployment, and is of interest to companies wishing to optimize the profitability of their fleet.
format Article
id doaj-art-c4dc413be5a4492ebf44c2bb2c677759
institution Kabale University
issn 1095-4244
1099-1824
language English
publishDate 2025-09-01
publisher Wiley
record_format Article
series Wind Energy
spelling doaj-art-c4dc413be5a4492ebf44c2bb2c6777592025-08-20T05:18:42ZengWileyWind Energy1095-42441099-18242025-09-01289n/an/a10.1002/we.70050Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind EnergyThéodore Raymond0Sylvie Charbonnier1Christophe Bérenguer2Alexis Lebranchu3Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA‐Lab Grenoble FranceUniv. Grenoble Alpes, CNRS, Grenoble INP, GIPSA‐Lab Grenoble FranceUniv. Grenoble Alpes, CNRS, Grenoble INP, GIPSA‐Lab Grenoble FranceEngineering Department Valemo Bégles FranceABSTRACT In order to reduce curative interventions in wind energy, maintenance approaches based on real‐time monitoring of component health have been widely studied. These condition‐based maintenance processes generally rely on data‐driven residual indicators, measuring the difference between a measured value and an estimation made by a normal behavior model. These solutions face limitations that prevent their applicability to an industrial context. First, models, which are mostly built using artificial neural networks, can be very accurate but remain difficult to interpret by a wind turbine operator and present implementation constraints due to the large number of inputs variables. Moreover, existing condition monitoring processes proposed for wind turbines are defined for a scope reduced to a single manufacturer and to a set of components that does not include all the critical ones, which does not guarantee their possible deployment across a fleet. In this paper, a data‐driven automatic model generation method for fault detection, applicable to an entire fleet of wind turbines, is presented. The models obtained are simple, physically coherent, and valid for all the wind turbines of a farm. Multiturbine residual indicators, robust to environmental variations, are then built and analyzed to perform fault detection. The fault detection ability of these indicators is evaluated on four faults impacting four components from different wind farms and manufacturers, using receiver operating characteristic curves. Finally, the fault detection performances of the proposed models are evaluated on wind farms with turbines of various technologies, whose data have not been used to learn the models. The good results obtained show that the implemented process is suitable for industrial deployment, and is of interest to companies wishing to optimize the profitability of their fleet.https://doi.org/10.1002/we.70050health monitoringindustrial applicationintelligent variable selectionlinear multivariable modelsresidual‐based fault detectionwind energy
spellingShingle Théodore Raymond
Sylvie Charbonnier
Christophe Bérenguer
Alexis Lebranchu
Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
Wind Energy
health monitoring
industrial application
intelligent variable selection
linear multivariable models
residual‐based fault detection
wind energy
title Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
title_full Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
title_fullStr Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
title_full_unstemmed Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
title_short Fleet‐Wide Data‐Driven Model Generation Process for Residual‐Based Fault Detection in Wind Energy
title_sort fleet wide data driven model generation process for residual based fault detection in wind energy
topic health monitoring
industrial application
intelligent variable selection
linear multivariable models
residual‐based fault detection
wind energy
url https://doi.org/10.1002/we.70050
work_keys_str_mv AT theodoreraymond fleetwidedatadrivenmodelgenerationprocessforresidualbasedfaultdetectioninwindenergy
AT sylviecharbonnier fleetwidedatadrivenmodelgenerationprocessforresidualbasedfaultdetectioninwindenergy
AT christopheberenguer fleetwidedatadrivenmodelgenerationprocessforresidualbasedfaultdetectioninwindenergy
AT alexislebranchu fleetwidedatadrivenmodelgenerationprocessforresidualbasedfaultdetectioninwindenergy