A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes

Gearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect...

Full description

Saved in:
Bibliographic Details
Main Authors: Liqiang Wang, Shixian Dai, Zijian Kang, Shuang Han, Guozhen Zhang, Yongqian Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/14/3696
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246378765582336
author Liqiang Wang
Shixian Dai
Zijian Kang
Shuang Han
Guozhen Zhang
Yongqian Liu
author_facet Liqiang Wang
Shixian Dai
Zijian Kang
Shuang Han
Guozhen Zhang
Yongqian Liu
author_sort Liqiang Wang
collection DOAJ
description Gearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect the impact of class imbalance, thereby limiting diagnostic accuracy. To address these challenges, this paper proposes a fault diagnosis model for wind turbine gearboxes based on CNN-SA-GRU and Focal Loss. Specifically, a CNN-SA-GRU network is constructed to extract both spatial and temporal features, in which CNN is employed to extract local spatial features from SCADA data, Shuffle Attention is integrated to efficiently fuse channel and spatial information and enhance spatial representation, and GRU is utilized to capture long-term spatiotemporal dependencies. To mitigate the adverse effects of class imbalance, the conventional cross-entropy loss is replaced with Focal Loss, which assigns higher weights to hard-to-classify fault samples. Finally, the model is validated using real wind farm data. The results show that, compared with the cross-entropy loss, using Focal Loss improves the accuracy and F1 score by an average of 0.24% and 1.03%, respectively. Furthermore, the proposed model outperforms other baseline models with average gains of 0.703% in accuracy and 4.65% in F1 score.
format Article
id doaj-art-06ba614234f948c6a6ca1af1ce067371
institution Kabale University
issn 1996-1073
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-06ba614234f948c6a6ca1af1ce0673712025-08-20T03:58:31ZengMDPI AGEnergies1996-10732025-07-011814369610.3390/en18143696A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine GearboxesLiqiang Wang0Shixian Dai1Zijian Kang2Shuang Han3Guozhen Zhang4Yongqian Liu5Longyuan Power Group Co., Ltd., Beijing 100034, ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of New Energy, North China Electric Power University, Beijing 102206, ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of New Energy, North China Electric Power University, Beijing 102206, ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of New Energy, North China Electric Power University, Beijing 102206, ChinaLongyuan Power Group Co., Ltd., Beijing 100034, ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of New Energy, North China Electric Power University, Beijing 102206, ChinaGearbox failures are a major cause of unplanned downtime and increased maintenance costs, making accurate diagnosis crucial in ensuring wind turbine reliability and cost-efficiency. However, most existing diagnostic methods fail to fully extract the spatiotemporal features in SCADA data and neglect the impact of class imbalance, thereby limiting diagnostic accuracy. To address these challenges, this paper proposes a fault diagnosis model for wind turbine gearboxes based on CNN-SA-GRU and Focal Loss. Specifically, a CNN-SA-GRU network is constructed to extract both spatial and temporal features, in which CNN is employed to extract local spatial features from SCADA data, Shuffle Attention is integrated to efficiently fuse channel and spatial information and enhance spatial representation, and GRU is utilized to capture long-term spatiotemporal dependencies. To mitigate the adverse effects of class imbalance, the conventional cross-entropy loss is replaced with Focal Loss, which assigns higher weights to hard-to-classify fault samples. Finally, the model is validated using real wind farm data. The results show that, compared with the cross-entropy loss, using Focal Loss improves the accuracy and F1 score by an average of 0.24% and 1.03%, respectively. Furthermore, the proposed model outperforms other baseline models with average gains of 0.703% in accuracy and 4.65% in F1 score.https://www.mdpi.com/1996-1073/18/14/3696wind turbineCNNShuffle AttentionGRUFocal Lossfault diagnosis
spellingShingle Liqiang Wang
Shixian Dai
Zijian Kang
Shuang Han
Guozhen Zhang
Yongqian Liu
A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
Energies
wind turbine
CNN
Shuffle Attention
GRU
Focal Loss
fault diagnosis
title A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
title_full A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
title_fullStr A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
title_full_unstemmed A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
title_short A CNN-SA-GRU Model with Focal Loss for Fault Diagnosis of Wind Turbine Gearboxes
title_sort cnn sa gru model with focal loss for fault diagnosis of wind turbine gearboxes
topic wind turbine
CNN
Shuffle Attention
GRU
Focal Loss
fault diagnosis
url https://www.mdpi.com/1996-1073/18/14/3696
work_keys_str_mv AT liqiangwang acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT shixiandai acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT zijiankang acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT shuanghan acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT guozhenzhang acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT yongqianliu acnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT liqiangwang cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT shixiandai cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT zijiankang cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT shuanghan cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT guozhenzhang cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes
AT yongqianliu cnnsagrumodelwithfocallossforfaultdiagnosisofwindturbinegearboxes