The demand for advanced monitoring and fault diagnosis technologies for critical mechanical components is growing rapidly. Early detection of rolling bearing faults is essential for preventing performance degradation, unplanned downtime, and safety risks. This article presents a novel fault diagnosis method that leverages digital twin technology and transfer learning to address the limitations of existing approaches in terms of data dependency and cross-domain effectiveness. Initially, a precise digital twin model is developed using finite element analysis to accurately simulate bearing dynamics under various operating conditions, generating extensive simulation data. These data compensate for the scarcity of fault data and are valuable for training diagnostic models. To reduce the noise level in real-world data, the snow ablation optimizer algorithm is employed to optimize variational mode decomposition for noise reduction. Subsequently, transfer learning techniques are utilized to treat the simulation data as the source domain and the actual vibration signals as the target domain, enabling domain-adaptive transfer learning. This approach facilitates cross-domain feature alignment and knowledge transfer, further optimized through adversarial loss and the maximum kernel mean discrepancy metric. Moreover, a deep learning model that combines residual convolutional neural networks with a Transformer is developed, significantly enhancing feature extraction and classification accuracy. Experimental validation conducted on the XJTU-SY dataset demonstrates that the proposed diagnostic method exhibits superior diagnostic performance under small sample conditions, outperforming existing diagnostic methods.
TkaczEKozaneckiZKozaneckaD, et al. A self-acting gas journal bearing with a flexibly supported foil—Numerical model of bearing dynamics. Int J Struct Stab Dyn2017; 17(5): 1740012.
2.
TkaczEKozaneckiZKozaneckaD, Numerical methods for theoretical analysis of foil bearing dynamics. Mech Res Commun2017; 82: 9–13.
3.
Özşahin BudakEÖzgüvenHN.Identification of bearing dynamics under operational conditions for chatter stability prediction in high speed machining operations. Precis Eng J Int Soc Precis Eng Nanotechnol2015; 42: 53–65.
4.
ChenXHYangRXueYH, et al. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Meas2023; 72: 1–21.
5.
ShaoHDJiangHKZhangHZ, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network. IEEE Trans Ind Electron2018; 65(3): 2727–2736.
6.
HoangDTKangHJA motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Trans Instrum Meas2020; 69(6): 3325–3333.
7.
SarangiSBiswalCSahuBK, et al. Fault detection technique using time-varying filter-EMD and differential-CUSUM for LVDC microgrid system. Electr Power Syst Res2023; 219: 109254.
8.
QiaoZJChenSLaiZH, et al. Harmonic-Gaussian double-well potential stochastic resonance with its application to enhance weak fault characteristics of machinery. Nonlinear Dyn2023; 111(8): 7293–7307.
9.
QiaoZJHeYBLiaoCR, et al. Noise-boosted weak signal detection in fractional nonlinear systems enhanced by increasing potential-well width and its application to mechanical fault diagnosis. Chaos Solitons Fractals2023; 175: 113960.
10.
YangYLiuHHanL, et al. A feature extraction method using VMD and improved envelope spectrum entropy for rolling bearing fault diagnosis. IEEE Sens J2023; 23(4): 3848–3858.
11.
BessousNSbaaSMegherbiAC.Mechanical fault detection in rotating electrical machines using MCSA-FFT and MCSA-DWT techniques. B Pol Acad Sci Tech2019; 67(3): 571–582.
12.
XiangJWZhongYT.A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Appl Sci2016; 6(12): 414–414.
13.
LuQBShenXQWangXJ, et al. Fault diagnosis of rolling bearing based on improved VMD and KNN. Math Probl Eng2021; 2021: 1–11.
14.
ZhaoKCXiaoJQLiC, et al. Fault diagnosis of rolling bearing using CNN and PCA fractal based feature extraction. Measurement2023; 223: 13754.
15.
AnYYZhangKLiuQ, et al. Rolling bearing fault diagnosis method base on periodic sparse attention and LSTM. IEEE Sens J2022; 22(12): 12044–12053.
16.
YuPFZhangJJZhangBB, et al. Research on small sample rolling bearing fault diagnosis method based on mixed signal processing technology. Symmetry2024; 16(9): 1178.
17.
XuYDFengKYanXA, et al. Cross-modal fusion convolutional neural networks with online soft-label training strategy for mechanical fault diagnosis. IEEE Trans Ind Inf2024; 20(1): 73–84.
18.
QuJQSunQQianZ, et al. Fault diagnosis for PV arrays considering dust impact based on transformed graphical features of characteristic curves and convolutional neural network with CBAM modules. Appl Energy2024; 355: 122252.
19.
ZhangJXChenXYWeiHK, et al. A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation. Appl Energy2024; 355: 122184.
20.
MuGQLiuCLChenJH.Integrating physical knowledge for generative-based zero-shot learning models in process fault diagnosis. Reliab Eng Syst Saf2025; 258: 110852.
21.
GuoYLiXYZhangJD, et al. SDCGAN: a CycleGAN-based single-domain generalization method for mechanical fault diagnosis. Reliab Eng Syst Saf2025; 258: 110854.
22.
HeiZDSunWFYangHY, et al. Novel domain-adaptive wasserstein generative adversarial networks for early bearing fault diagnosis under various conditions. Reliab Eng Syst Saf2025; 257: 110847.
23.
LiZNJiangHKWangX. A novel reinforcement learning agent for rotating machinery fault diagnosis with data augmentation. Reliab Eng Syst Saf2025; 253: 110570.
24.
JiangZCLiuDDCuiLL.A temporal-spatial multi-order weighted graph convolution network with refined feature topology graph for imbalance fault diagnosis of rotating machinery. Reliab Eng Syst Saf2025; 257: 110830.
25.
HuangMShengCXRaoX.Conditional variational autoencoder and generative adversarial network-based approach for long-tailed fault diagnosis for the motor system. Measurement2025; 242: 116116.
26.
MaDLiuZHGaoQH, et al. Few-shot fault diagnosis of EHA based on MTF-ResNet-MA and dual-attribute adaptive decision-level fusion. Measurement2025; 247: 116787.
27.
GaoYLiuXYXiangJW.Fault detection in gears using fault samples enlarged by a combination of numerical simulation and a generative adversarial network. IEEE/ASME Trans. Mechatron2022; 27(5): 3798–3805.
28.
LouYXKumarAXiangJW.Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. IEEE Trans Instrum Meas2022; 71: 1–9.
29.
QinYWuXLuoJ.Data-model combined driven digital twin of life-cycle rolling bearing. IEEE Trans. Ind. Inf2022; 18(3): 1530–1540.
30.
TaoFZhangHLiuA, et al. Digital twin in industry: state-of-the-art. IEEE Trans. Ind. Inf2019; 15(4): 2405–2415.
31.
FullerAFanZDayC, et al. Digital twin: enabling technologies, challenges and open research. IEEE Access2020; 8: 108952–108971.
32.
LiZXDingXXSongZZ, et al. Digital twin-assisted dual transfer: A novel information-model adaptation method for rolling bearing fault diagnosis. Inf Fusion2024; 106: 102271.
33.
QinYLiuHYWangY, et al. Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samples. Knowl Based Syst2024; 292: 111641.
34.
XuYDJiangQBLiS, et al. Digital twin-driven discriminative graph learning networks for cross-domain bearing fault recognition. Comput Ind Eng2024; 193: 110292.
35.
Montes-RomeroJHeinzleNLiveraA, et al. Novel data-driven health-state architecture for photovoltaic system failure diagnosis. Sol Energy2024; 279, 112820.
36.
YaoHZhangXGuoQ, et al. Fault diagnosis method for oil-immersed transformers integrated digital twin model. Sci Rep2024; 14(1): 20355.
37.
AzariMSSantiniSEdrisiF, et al. Self-adaptive fault diagnosis for unseen working conditions based on digital twins and domain generalization. Reliab Eng Syst Saf2025; 254: 110560.
38.
JiaSXSunDYNomanK, et al. Lifting wavelet-informed hierarchical domain adaptation network: an interpretable digital twin-driven gearbox fault diagnosis method. Reliab Eng Syst Saf2025; 254: 110660.
39.
XiaJYHuangRYChenZY, et al. A novel digital twin-driven approach based on physical-virtual data fusion for gearbox fault diagnosis. Reliab Eng Syst Saf2023; 240: 109542.
40.
ZhouZYChenWH.Cross-domain bearing fault diagnosis under missing labels with uncertainty modeling and digital twin correction. Measurement2025; 247: 116869.
41.
HabboucheHAmiratYBenkedjouhT, et al. Digital twin-based gearbox fault diagnosis using variational mode decomposition and dynamic vibration modeling. Measurement2025; 246: 116669.
42.
KumarAKumarRXiangJW, et al. Digital twin-assisted AI framework based on domain adaptation for bearing defect diagnosis in the centrifugal pump. Measurement2024; 235: 115013.
43.
WangJJYeLKGaoRX, et al. Digital twin for rotating machinery fault diagnosis in smart manufacturing. Int J Prod Res2018; 57(12): 3920–3934.
44.
LiTShiHTBaiXT, et al. A digital twin model of life-cycle rolling bearing with multiscale fault evolution combined with different scale local fault extension mechanism. IEEE Trans Instrum Meas2023; 72: 3507211.
45.
YuXWangYJLiangZT, An adaptive domain adaptation method for rolling bearings’ fault diagnosis fusing deep convolution and self-attention networks. IEEE Trans Instrum Meas2023; 72: 1–14.
46.
LiXYYuanPSuKY, et al. Innovative integration of multi-scale residual networks and MK-MMD for enhanced feature representation in fault diagnosis. Meas Sci Technol2024; 35(8): 086108.
47.
LiJMYeZDGaoJ, et al. Fault transfer diagnosis of rolling bearings across different devices via multi-domain information fusion and multi-kernel maximum mean discrepancy. Appl Soft Comput2024; 159: 111620.
48.
XiaoYZhouXYZhouHY, et al. Multi-label deep transfer learning method for coupling fault diagnosis. Mech Syst Signal Process2024; 212: 111327.
49.
ZhengBHuangJMaX, et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis. Mech Syst Signal Process2024; 208: 111047.
50.
WangTXuXPanHX.Anti-noise transfer adversarial convolutions with adaptive threshold for rotating machine fault diagnosis. ISA Trans2024; 146: 175–185.
51.
GaoTYYangJLTangQ.A multi-source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions. Inf Fusion2024; 106: 102278.
52.
WangCWangZDLiuQY, et al. Support-sample-assisted domain generalization via attacks and defenses: concepts, algorithms, and applications to pipeline fault diagnosis. IEEE Trans Ind Inf2024; 20(4): 6413–6423.
53.
LiZRMaJWuJD, et al. A gated recurrent generative transfer learning network for fault diagnostics considering imbalanced data and variable working conditions. IEEE Trans Neural Netw Learn Syst2024: 1–12.
54.
ZhangYTZhangHLChenB, et al. Integrating intrinsic information: a novel open set domain adaptation network for cross-domain fault diagnosis with multiple unknown faults. Knowl Based Syst2024; 299: 112100.
55.
GuoWLiXShenZQ.A lightweight residual network based on improved knowledge transfer and quantized distillation for cross-domain fault diagnosis of rolling bearings. Expert Syst Appl2024; 245: 123083.
56.
YanZHXuZFZhangYX, et al. FTSDC: a novel federated transfer learning strategy for bearing cross-machine fault diagnosis based on dual-correction training. Adv Eng Inform2024; 61: 102499.
57.
WuZHJiangHKLiuSW, et al. Conditional distribution-guided adversarial transfer learning network with multi-source domains for rolling bearing fault diagnosis. Adv Eng Inform2023; 56: 101993.
58.
LiJPHuangRYChenZY, et al. Deep continual transfer learning with dynamic weight aggregation for fault diagnosis of industrial streaming data under varying working conditions. Adv Eng Inform2023; 55: 101883.
59.
ZhangWWangZWLiX.Blockchain-based decentralized federated transfer learning methodology for collaborative machinery fault diagnosis. Reliab Eng Syst Saf2023; 229: 108885.
60.
DingYFJiaMPZhuangJC, et al. Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions. Reliab Eng Syst Saf2023; 230: 108890.
61.
WangBLeiYLiN, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Trans Rel2018; 69(1): 401–412.
62.
DragomiretskiyKZossoD.Variational mode decomposition. IEEE Trans Signal Process2014; 62(3): 531–544.
63.
BoydS, Distributed optimization and statistical learning via the alternating direction method of multipliers. FNT Mach. Learn2010; 3(1): 1–122.
64.
DengLYLiuSY.Snow ablation optimizer: a novel metaheuristic technique for numerical optimization and engineering design. Expert Syst Appl2023; 225: 120069.
65.
KennedyJEberhartR. Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks 1995, 2011, vol. 4, no. 8, pp. 1942–1948.
66.
MirjaliliSMirjaliliSMLewisA.Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
MenZHLiYHTangWC, et al. A new multi-modal time series transformation method and multi-scale convolutional attention network for railway wagon bearing fault diagnosis. J Vib Control2024; 0: 1–24.
70.
LiYHWangDLZhaoX, et al. Research on rolling bearing fault diagnosis method based on simulation and experiment fusion drive. Rev Sci Instrum2024; 95(6): 065107.
71.
WangYPGaoSDWangXS, et al. Composite fault diagnosis of rolling bearings across operating conditions with MAAN and MK-MMD in multi-source domains. J Vib Eng2024: 1–12.
72.
MenZHHuCQLiYH, et al. A hybrid intelligent gearbox fault diagnosis method based on EWCEEMD and whale optimization algorithm-optimized SVM. Int J Struct Integr2023; 14(2): 322–336.
73.
DengFYDongSFGuXH.Research on fault diagnosis of high-speed train axlebox bearing based on ITR-net multi-source domain transfer learning. Adv Eng Sci2024; 14: 8666.
74.
HuCQLiYHChenZ, et al. Research on fault diagnosis of rolling bearing based on multi-sensor bi-layer information fusion under small samples. Rev Sci Instrum2023; 94(11): 115106.
