To tackle the poor performance of global model owing to the significant distribution discrepancies in harmonic reducers vibration data among users and limited availability of labeled data under certain operating conditions, a federated prototype domain adaptation framework with an adaptive aggregation strategy for fault diagnosis of harmonic reducers (AFPDA) is proposed. First, the user model parameters and class prototypes are considered to be the core interactive information in the federated learning framework. A multiuser prototype collaboration and interaction mechanism is constructed to enable effective knowledge interaction among users in source domain and target domain. Second, a class-prototype-guided local model training strategy is designed to align local data features with class prototypes while ensuring data privacy. Finally, a divergence-aware adaptive model aggregation strategy is proposed to boost the diagnostic capability of the global model. Extensive comparative experiments are conducted on a bearing dataset and a self-collected harmonic reducer dataset. Compared with other federated transfer learning methods, the AFPDA improves diagnostic accuracy on unlabeled target domain users by at least 3.58 and 7.54%, respectively.
WangHQiaoYLeiY, et al. Asymmetric-dot-pattern fusion fault identification of motor-driven belt transmission system in industrial robots. Measurement2025; 251: 117267.
2.
YinTLuNGuoG, et al. Knowledge and data dual-driven transfer network for industrial robot fault diagnosis. Mech Syst Signal Process2023; 182: 109597.
3.
WuZLongZLuoC, et al. DRL-GCNet: a deep reinforcement learning and graph convolutional network for harmonic drive fault diagnosis. IEEE Trans Instrum Meas2025; 74: 1–10.
4.
ZhouXZhouHHeY, et al. Harmonic reducer in-situ fault diagnosis for industrial robots based on deep learning. Sci China Tech Sci2022; 65: 2116–2126.
5.
ZhangGTaoYWangJ, et al. A motor current signal-based fault diagnosis method for harmonic drive of industrial robot under time-varying speed conditions. IEEE Trans Instrum Meas2025; 74: 1–10.
6.
QiJMauricioAGrylliasKC.Comparison of blind diagnostic indicators for condition monitoring of wind turbine gearbox bearings. J Eng Gas Turbines Power2022; 144(4): 041019.
7.
SurucuOGadsdenSAYawneyJ.Condition monitoring using machine learning: a review of theory, applications, and recent advances. Expert Syst Appl2023; 221: 119738.
8.
MaDLiuZGaoQ, et al. Fault diagnosis of multi-step electromagnetic hydraulic valve group based on localized current signal CS-SVM. Measurement2025; 245: 116632.
9.
BingWXiongH.Fault diagnosis technique based on multi-domain features and RelifF-Bayes-KNN in rolling bearing. Nonlinear Dyn2025; 113: 12985–13000.
10.
JiaYLiYXuM, et al. A fault diagnosis scheme for harmonic reducer under practical operating conditions. Measurement2024; 227: 114234.
11.
ZhangLLinJYangZ, et al. Wave-ConvNeXt: an efficient and precise fault diagnosis method for IIoT leveraging tailored ConvNeXt and wavelet transform. IEEE Internet Things J2024; 11(13): 23096–23109.
12.
HeYChenJZhouX, et al. In-situ fault diagnosis for the harmonic reducer of industrial robots via multi-scale mixed convolutional neural networks. J Manuf Syst2023; 66: 233–247.
13.
ChenPZhangRHeC, et al. Progressive contrastive representation learning for defect diagnosis in aluminum disk substrates with a bio-inspired vision sensor. Expert Syst Appl2025; 289: 128305.
14.
LiKYangR GWeiT, et al. Fault diagnosis of the harmonic reducer based on dual-path convolutional network with multi-channel hybrid attention mechanism. Meas Sci Technol2024; 36: 016130.
15.
LiWLiuDLiY, et al. Fault diagnosis using variational autoencoder GAN and focal loss CNN under unbalanced data. Struct Health Monit2025; 24(3): 1859–1872.
16.
WangYHeYKangB, et al. ProbSparse attention-based fault diagnosis for industrial robots under different working conditions. IEEE Trans Instrum Meas2024; 73: 1–12.
17.
ZhaoZSunSWangD, et al. MCVAE-GAN: a novel diagnosis method for solving harmonic reducer fault signal scarcity and sample diversity problem. IEEE Trans Instrum Meas2024; 73: 1–10.
18.
ZouLLamHFHuJ.Adaptive resize-residual deep neural network for fault diagnosis of rotating machinery. Struct Health Monit2023; 22(4): 2193–2213.
19.
QiJChenZKongY, et al. Attention-guided graph isomorphism learning: a multi-task framework for fault diagnosis and remaining useful life prediction. Reliab Eng Syst Saf2025; 263: 111209.
20.
ZhouKDiehlETangJ, et al. Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations. Mech Syst Signal Process2023; 185: 109772.
21.
ZhuZLeiYQiG, et al. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement2023; 206: 112346.
22.
LuSGaoZXuQ, et al. Class-imbalance privacy-preserving federated learning for decentralized fault diagnosis with biometric authentication. IEEE Trans Ind Inform2022; 18: 9101–9111.
23.
McMahanHMooreERamageD, et al. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th international conference on artificial intelligence and statistics, 2017, pp. 1273–1282.
24.
ZhangJDuanLLiK, et al. Improved lightweight federated learning network for fault feature extraction of reciprocating machinery. Meas Sci Technol2024; 35: 045115.
25.
KangSZhangWWangY, et al. A fault diagnosis method for harmonic reducers under different operating conditions based on information fusion subdomain adaptation. Chin J Sci Instrum2024; 45: 60–71.
26.
YangBLeiYLiX, et al. Targeted transfer learning through distribution barycenter medium for intelligent fault diagnosis of machines with data decentralization. Expert Syst Appl2024; 244: 122997.
27.
WangYZhangZXueC, et al. Progressive transfer learning: an intelligent fault diagnosis method for unlabeled rotating machinery with small samples. IEEE Trans Instrum Meas2025; 74: 1–12.
28.
TangSMaJYanZ, et al. Deep transfer learning strategy in intelligent fault diagnosis of rotating machinery. Eng Appl Artif Intell2024; 134: 108678.
29.
YangDZhangWJiangY.Mechanical fault diagnosis based on deep transfer learning: a review. Meas Sci Technol2023; 34: 112001.
30.
LiuYZouSGantiV T, et al. A domain-adaptive deep learning-empowered integrative framework for condition monitoring of the underwater mooring system under unseen wave conditions. Ocean Eng2026; 344: 123664.
31.
DingYZhuangJCaoY, et al. Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions. Reliab Eng Syst Saf2023; 230: 108890.
32.
JiangFKuangYLiT, et al. Towards enhanced interpretability: a mechanism-driven domain adaptation model for bearing fault diagnosis across operating conditions. Mech Syst Signal Process2025; 225: 112244.
33.
QianQZhangBLiC, et al. Federated transfer learning for machinery fault diagnosis: a comprehensive review of technique and application. Mech Syst Signal Process2025; 223: 111837.
34.
WangRHuangWLuY, et al. Cloud-edge collaborative transfer fault diagnosis of rotating machinery via federated fine-tuning and target self-adaptation. Expert Syst Appl2024; 250: 123859.
35.
WangRYanFYuL, et al. A federated transfer learning method with low-quality knowledge filtering and dynamic model aggregation for rolling bearing fault diagnosis. Mech Syst Signal Process2023; 198: 110413.
36.
LiXZhangCLiX, et al. Federated transfer learning in fault diagnosis under data privacy with target self-adaptation. J Manuf Syst2023; 68: 523–535.
37.
ZhaoKHuJShaoH, et al. Federated multi-source domain adversarial adaptation framework for machinery fault diagnosis with data privacy. Reliab Eng Syst Saf2023; 236: 109246.
38.
XueXZhaoXZhangY, et al. Federated transfer learning with consensus knowledge distillation for intelligent fault diagnosis under data privacy preserving. Meas Sci Technol2023; 35: 015108.
39.
SunYKangSWangY, et al. Fault diagnosis method for harmonic reducer based on personalized federated aggregation strategy with skip cycle weight. Measurement2025; 242: 116275.
40.
XiaPHuangYLiuC, et al. Learn to supervise: deep reinforcement learning-based prototype refinement for few-shot motor fault diagnosis. IEEE Trans Neural Netw Learn Syst2025; 36: 11428–11442.
41.
LiYMenZBaiX, et al. A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism. Struct Health Monit2024; 24(2): 830–852.
42.
JianCPengYMoG, et al. Imbalanced multidomain generalization fault diagnosis based on prototype-guided supervised contrastive learning with dynamic temperature modulation. Struct Health Monit2025; 0(0): 1–22
43.
WangQLiMWeiJ, et al. Category-aware trajectory domain adaptation network for cross-machine fault diagnosis. Struct Health Monit2025; 0(0): 1–20.
44.
CuturiM.Sinkhorn distances: lightspeed computation of optimal transport. Advances in Neural Information Processing Systems 26, Nevada, USA, 2013, pp. 2292–2300. Curran Associates, Inc.
45.
LessmeierCKimothoJKZimmerD, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. Proc Eur Conf Progn Health Manag Soc2016; 3: 1–17.
46.
WuXLiuXNiuJ, et al. Bold but cautious: unlocking the potential of personalized federated learning through cautiously aggressive collaboration. In: Proceedings of the IEEE/CVF international conference on computer vision, Paris, France, 1–6 October 2023, pp. 19375–19384. IEEE.
47.
GuoYGuoKCaoX, et al. Out-of-distribution generalization of federated learning via implicit invariant relationships. In: Proceedings of the 40th international conference on machine learning, Honolulu, Hawaii, USA, 2023, pp. 11905–11933. PMLR.
48.
McInnesLHealyJMelvilleJ.UMAP: uniform manifold approximation and projection for dimension reduction. 2020.
