A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework

Abstract Data-driven approaches demonstrate significant potential in accurately diagnosing faults in wind turbines. To enhance diagnostic performance, we introduce a clustered federated learning framework (CFLF) for wind gear oil diagnosis. Initially, a stepwise multivariate regression (SMR) model i...

Full description

Saved in:
Bibliographic Details
Main Authors: Huihui Han, Ye Zhao, Hao Jiang, Muxin Chen, Song Zhou, Zihan Lin, Xin Wang, Boman Mao, Xinyue Yang, Yuchun Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-06826-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399697607753728
author Huihui Han
Ye Zhao
Hao Jiang
Muxin Chen
Song Zhou
Zihan Lin
Xin Wang
Boman Mao
Xinyue Yang
Yuchun Li
author_facet Huihui Han
Ye Zhao
Hao Jiang
Muxin Chen
Song Zhou
Zihan Lin
Xin Wang
Boman Mao
Xinyue Yang
Yuchun Li
author_sort Huihui Han
collection DOAJ
description Abstract Data-driven approaches demonstrate significant potential in accurately diagnosing faults in wind turbines. To enhance diagnostic performance, we introduce a clustered federated learning framework (CFLF) for wind gear oil diagnosis. Initially, a stepwise multivariate regression (SMR) model is introduced and optimized after data processing, which integrates multiscale features and an AIC-diagnosis feature. Subsequently, to tackle data heterogeneity among different indicators, a series of canonical correlation representations are extracted from the SMR models, and a combined model of CFLF method and SMR is proposed to assess the performance of gear oil. Actual data analysis of wind turbine gear oil showcase the superior performance of the proposed model over the single SMR model with higher prediction accuracy of 35.73%. This study provides a new technique for evaluating gear oil in the wind energy sector.
format Article
id doaj-art-9916078af7dc4d0c9dd9c08ad5fa31d2
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9916078af7dc4d0c9dd9c08ad5fa31d22025-08-20T03:38:16ZengNature PortfolioScientific Reports2045-23222025-07-0115111010.1038/s41598-025-06826-9A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning frameworkHuihui Han0Ye Zhao1Hao Jiang2Muxin Chen3Song Zhou4Zihan Lin5Xin Wang6Boman Mao7Xinyue Yang8Yuchun Li9East China Electric Power Test and Research Institute, China Datang Corporation Science and Technology Research Institute Co., LtdEast China Electric Power Test and Research Institute, China Datang Corporation Science and Technology Research Institute Co., LtdDatang Guoxin Binhai Offshore Wind Power Co., Ltd.East China Electric Power Test and Research Institute, China Datang Corporation Science and Technology Research Institute Co., LtdDatang Guoxin Binhai Offshore Wind Power Co., Ltd.School of Chemistry and Pharmaceutical Engineering, Changsha University of Science and TechnologyEast China Electric Power Test and Research Institute, China Datang Corporation Science and Technology Research Institute Co., LtdSchool of Computer Science and Technology, Changsha University of Science and TechnologySchool of Computer Science and Technology, Changsha University of Science and TechnologySchool of Chemistry and Pharmaceutical Engineering, Changsha University of Science and TechnologyAbstract Data-driven approaches demonstrate significant potential in accurately diagnosing faults in wind turbines. To enhance diagnostic performance, we introduce a clustered federated learning framework (CFLF) for wind gear oil diagnosis. Initially, a stepwise multivariate regression (SMR) model is introduced and optimized after data processing, which integrates multiscale features and an AIC-diagnosis feature. Subsequently, to tackle data heterogeneity among different indicators, a series of canonical correlation representations are extracted from the SMR models, and a combined model of CFLF method and SMR is proposed to assess the performance of gear oil. Actual data analysis of wind turbine gear oil showcase the superior performance of the proposed model over the single SMR model with higher prediction accuracy of 35.73%. This study provides a new technique for evaluating gear oil in the wind energy sector.https://doi.org/10.1038/s41598-025-06826-9Stepwise multivariate regressionGear oil evaluationClustered federated learning frameworkWind turbines
spellingShingle Huihui Han
Ye Zhao
Hao Jiang
Muxin Chen
Song Zhou
Zihan Lin
Xin Wang
Boman Mao
Xinyue Yang
Yuchun Li
A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
Scientific Reports
Stepwise multivariate regression
Gear oil evaluation
Clustered federated learning framework
Wind turbines
title A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
title_full A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
title_fullStr A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
title_full_unstemmed A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
title_short A novel diagnosis methodology of gear oil for wind turbine combining Stepwise multivariate regression and clustered federated learning framework
title_sort novel diagnosis methodology of gear oil for wind turbine combining stepwise multivariate regression and clustered federated learning framework
topic Stepwise multivariate regression
Gear oil evaluation
Clustered federated learning framework
Wind turbines
url https://doi.org/10.1038/s41598-025-06826-9
work_keys_str_mv AT huihuihan anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT yezhao anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT haojiang anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT muxinchen anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT songzhou anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT zihanlin anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT xinwang anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT bomanmao anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT xinyueyang anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT yuchunli anoveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT huihuihan noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT yezhao noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT haojiang noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT muxinchen noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT songzhou noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT zihanlin noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT xinwang noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT bomanmao noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT xinyueyang noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework
AT yuchunli noveldiagnosismethodologyofgearoilforwindturbinecombiningstepwisemultivariateregressionandclusteredfederatedlearningframework