In the practical application of wind energy technology, the reliability of wind turbine systems is directly linked to the stable output of renewable electricity. Data imbalance in fault monitoring networks causes classification bias in diagnostic models, which increases the risk of misdiagnosis and ultimately undermines the stability of wind power. In the context of distributed monitoring, this issue is further exacerbated by the geographically dispersed layout of wind farms, which significantly amplifies data imbalance. To address these challenges, a global distribution-aware logits adjustment federated framework is proposed, along with a dynamic estimation mechanism for global fault distribution based on edge node logits. This mechanism accurately captures the global fault feature distribution and enhances attention to minority categories. Additionally, a feature compensation architecture for edge-cloud bidirectional collaboration is developed. By constructing a feature similarity matrix, knowledge distillation is performed at the feature level to transfer global feature knowledge to the edge, enabling local models to learn global common features while preserving the personalized feature extraction capabilities of edge nodes. On-site experiments at Kelmarsh and Xinjiang wind farms demonstrated that the proposed method achieved accuracies of 0.8617 and 0.9891, respectively, showcasing its effectiveness.
GuBZhangHYueS, et al. Fault warning study of gearbox based on SOM-ASTGCN-BiLSTM and mutual diagnosis of same clustered wind turbines. Renew Energy2025; 251: 123442.
2.
ZhouRLiYLinX. A clustered federated learning framework for collaborative fault diagnosis of wind turbines. Appl Energy2025; 377: 124532.
3.
FazliAPoshtanJ. Wind turbine fault prognosis using SCADA measurements, pre-fault labeling, and KNN classifiers robust against data imbalance. Measurement2025; 243: 116202.
4.
JiangGZhaoKLiuX, et al. A federated learning framework for cloud–edge collaborative fault diagnosis of wind turbines. IEEE Internet Things J2024; 11: 23170–23185.
5.
LeiZDengSSuY, et al. Adaptive weighted cost-sensitive learning-driven improved dense convolutional neural network for imbalanced fault diagnosis under limited fault samples. ASCE-ASME J Risk Uncertain Eng Syst A Civ Eng2025; 11: 04025013.
6.
LiuJCaoHDhupiaJS, et al. An adaptive source-free unsupervised domain adaptation method for mechanical fault detection. Mech Syst Signal Process2025; 228: 112475.
7.
YangXLiYZhaoY, et al. Large-scale floating offshore wind turbine anomaly detection and diagnosis system based on spatio-temporal transformation features combining informer and XGBoost. IEEE Trans Ind Inform2025; 21: 6137–6146.
8.
ZhangYKongHHanY, et al. Fed-MWFP: lightweight federated learning with interpretable multiple wavelet fusion network for fault diagnosis under variable operating conditions. Knowl Based Syst2025; 315: 113277.
9.
QianQZhangBLiC, et al. Federated transfer learning for machinery fault diagnosis: a comprehensive review of technique and application. Mech Syst Signal Process2025; 223: 111837.
10.
LiLFanYTseM, et al. A review of applications in federated learning. Computers & Industrial Engineering2020; 149: 106854.
11.
OngunTBoboilaSOpreaA, et al. CELEST: federated learning for globally coordinated threat detection. IEEE Trans Inform Forensics Secur2025; 20: 10434–10448.
12.
YangZYangTLiS, et al. Parameters security strategy formulated by hyperchaos in federal learning. Appl Intell2025; 55: 253.
13.
Rodríguez-BarrosoNStipcichGJiménez-LópezD, et al. Federated learning and differential privacy: software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy. Inform Fusion2020; 64: 270–292.
14.
KakosimosPSaberiANPerettiL. An adaptive ML framework for power converter monitoring via federated transfer learning. IEEE Trans Power Electron2025; 40: 16048–16054.
15.
GuptaVLuqmanAChattopadhyayN, et al. TravellingFL: communication efficient peer-to-peer federated learning. IEEE Trans Veh Technol2024; 73: 5005–5019.
16.
SrinivaasASakthivelNRNairBB. Cross domain fault diagnosis in internal combustion engines using multisensor data with transfer federated and transformer based federated transfer learning. Scientific Reports2025; 15: 36775.
17.
HasanMNJanSUKooI. Federated learning-based sensor fault classification in label-scarce sensor networks. IEEE Sens J2025; 25: 33245–33264.
18.
LiuHZhangZ. A bi-party engaged modeling framework for renewable power predictions with privacy-preserving. IEEE Trans Power Syst2023; 38: 5794–5805.
19.
LiuHZhangZ. Probabilistic forecasting of multiple plant day-ahead renewable power generation sequences with data privacy preserving. Energy AI2025; 19: 100463.
20.
GrataloupAJonasSMeyerA. Wind turbine condition monitoring based on intra- and inter-farm federated learning. IEEE Access2025; 13: 146617–146629.
21.
YinHZhouKChenZ, et al. Toward non-I.I.D. in load disaggregation: an unsupervised domain adaptation framework for heterogeneous energy consumption sectors. IEEE Trans Ind Inform2025; 21: 663–672.
22.
ChatterjeeSGhoshKBhattacharjeeS, et al. FedAR: federated artificial resampling for imbalanced facial emotion recognition. IEEE Trans Affect Comput2025; 16: 1461–1472.
23.
KhanIAPiDKamalS, et al. Federated-boosting: a distributed and dynamic boosting-powered cyber-attack detection scheme for security and privacy of consumer IoT. IEEE Trans Consum Electron2025; 71: 6340–6347.
24.
SchwanckFMLeipnitzMTCarboneraJL, et al. A framework for testing federated learning algorithms using an edge-like environment. Future Generation Computer Systems2025; 166: 107626.
25.
WangLFanWJiangG, et al. An efficient federated transfer learning framework for collaborative monitoring of wind turbines in IoE-enabled wind farms. Energy2023; 284: 128518.
26.
ZhuQLiuHBaoC, et al. Decoupled interpretable robust domain generalization networks: A fault diagnosis approach across bearings, working conditions, and artificial-to-real scenarios. Adv Eng Inform2024; 61: 102445.
27.
LiXSunSLiuM, et al. FedCRAC: improving federated classification performance on long-tailed data via classifier representation adjustment and calibration. IEEE Trans Mobile Comput2025; 24: 482–499.
28.
QinJHongD. A survey of long-tail item recommendation methods. Wirel Commun Mob Comput2021; 2021: 14.
29.
ZhaoLTengYWangL. Logit normalization for long-tail object detection. Int J Comput Vis2024; 132: 2114–2134.
30.
HanJ-yLiuJ-wXuJ-d. Dual-branch network with hypergraph feature augmentation and adaptive logits adjustment for long-tailed visual recognition. Appl Soft Comput2024; 167: 112400.
31.
ZhouHLuoTHeY. Dynamic collaborative learning with heterogeneous knowledge transfer for long-tailed visual recognition. Inf Fusion2025; 115: 102734.
McMahanBMooreERamageD, et al. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th international conference on artificial intelligence and statistics, Ft. Lauderdale, FL, USA, 20–22 April 2017, pp. 1273–1282. PMLR.
34.
LiTSahuAKZaheerM, et al. Federated optimization in heterogeneous networks. Proc Mach Learn Res2020; 2: 429–450.
35.
LiQHeBSongD. Model-contrastive federated learning. In: 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2021, pp. 10708–10717.
36.
WangHYurochkinMSunY, et al. Federated learning with matched averaging. In: International conference on learning representations (ICLR), Addis Ababa, Ethiopia, 30 April 2020.
37.
WangJLiuQLiangH, et al. A novel framework for the analysis and design of heterogeneous federated learning. IEEE Trans Signal Process2021; 69: 5234–5249.
