Bearings, being essential to modern industry, demand reliable cross-domain diagnostic methods. We propose a transfer learning method for bearing fault diagnosis based on a multi-channel Transformer model with shift windows. The relationship between segmented patch sequences was modeled through self-attention calculation using non-overlapping shift windows. A new partitioning strategy is employed that shifts windows and alternates between two distinct methods to create cross-window connections. To capture basic signal features while preserving positional details, several convolutional layers are introduced prior to the Transformer block. We propose a multi-channel calibration module to ensure stable optimization of the model. Additionally, we introduce a joint maximum mean discrepancy method to measure the distance between the source and target domains. Experimental results demonstrate that the proposed approach achieves superior diagnostic accuracy and offers reliable support for monitoring and predicting the state of rotating machinery.
GangsarPBajpeiARPorwalR.A review on deep learning based condition monitoring and fault diagnosis of rotating machinery. Noise Vibr Worldwide2022; 53(11): 550–578.
2.
DongWWuXZhangS, et al. An early fault warning and diagnosis model based on a two-step analysis strategy for wind turbine bearings. Struct Health Monit2024.
3.
YanGChenJBaiY, et al. A survey on fault diagnosis approaches for rolling bearings of railway vehicles. Processes2022; 10(4): 724.
4.
ChenFTianWZhangL, et al. Fault diagnosis of power transformer based on time-shift multiscale bubble entropy and stochastic configuration network. Entropy2022; 24(8): 1135.
5.
YapJSLimMSalmanLM.Improved versatility and robustness of bearing fault detection and diagnostic method for nuclear power plant. Nuclear Eng Des2024; 428: 113474.
6.
ZhiSShenHWangT.Gearbox localized fault detection based on meshing frequency modulation analysis. Appl Acoust2024; 219: 109943.
7.
PapaeliasMAminiAHuangZ, et al. Online condition monitoring of rolling stock wheels and axle bearings. Proc IMechE, Part F: J Rail Rapid Transit2016; 230(3): 709–723.
8.
JiaFLeiYGuoL, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing2018; 272: 619–628.
9.
LiXYuTZhangF, et al. Mixed style network based: A novel rotating machinery fault diagnosis method through batch spectral penalization. Reliab Eng Syst Safety2025; 255: 110667.
10.
LiXLiJZhaoC, et al. Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection. Mech Syst Signal Process2020; 142: 106740.
11.
ChenZChenJLiuS, et al. Multi-channel Calibrated Transformer with Shifted Windows for few-shot fault diagnosis under sharp speed variation. ISA Trans2022; 131: 501–515.
12.
WangHLiuZPengD, et al. Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising. ISA Trans2022; 128: 470–484.
13.
RenHLiuSWeiF, et al. A novel two-stream multi-head self-attention convolutional neural network for bearing fault diagnosis. Proc IMechE, Part C: J Mech Eng Sci2024; 238(11): 5393–5405.
14.
LiXKaiyuSuQiushiHe, et al. Research on fault diagnosis of highway bi-LSTM based on attention mechanism. Eksploatacja i Niezawodność– Maintenance Reliab2023; 25(2): 71–79.
15.
YueKLiJChenJ, et alIntelligent cross-domain fault diagnosis for rotating machinery using multiscale adversarial convolutional neural network. In: 2022 IEEE international instrumentation and measurement technology conference (I2MTC), Ottawa, ON, Canada, 2022, pp. 1–6. IEEE.
16.
ChenZHuangH-ZDengZ, et al. Shrinkage mamba relation network with out-of-distribution data augmentation for rotating machinery fault detection and localization under zero-faulty data. Mech Syst Signal Process2025; 224: 112145.
17.
KumarSKumarVSarangiS, et al. Gearbox fault diagnosis: a higher order moments approach. Measurement2023: 210: 112489.
18.
ChenYXuXLiuC.Few-shot meta transfer learning-based damage detection of composite structures. Smart Mater Struct2024; 33(2): 025027.
19.
YangBLeiYJiaF, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process2019; 122: 692–706.
20.
LiuCChenYXuX, et al. Domain generalization-based damage detection of composite structures powered by structural digital twin. Compos Sci Technol2024; 258: 110908.
21.
YinTLuNGuoG, et al. Knowledge and data dual-driven transfer network for industrial robot fault diagnosis. Mech Syst Signal Process2023; 182: 109597.
22.
HuangRXiaJZhangB, et al. Compound fault diagnosis for rotating machinery: state-of-the-art, challenges, and opportunities. J Dyn Monit Diagn2023; 2(1): 13–29.
23.
GulatiAQinJChiuC-C, et al. Conformer: convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100, 2020.
24.
VaswaniAShazeerNParmarN, et al. Attention is all you need. Adv Neural Inform Process Syst2017; 30, 2017.
25.
WangRDongEChengZ, et al. Transformer-based intelligent fault diagnosis methods of mechanical equipment: a survey. Open Phys2024; 22(1): 20240015.
26.
WangJCaoJFuJ, et al. Missing well logs prediction using deep learning integrated neural network with the self-attention mechanism. Energy2022; 261: 125270.
27.
XiaoXZhangDHuG, et al. CNN–MHSA: a convolutional neural network and multi-head self-attention combined approach for detecting phishing websites. Neural Netw2020; 125: 303–312.
28.
HuHZhangZXieZ, et al. Local relation networks for image recognition. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea (South), 2019, pp. 3464–3473.
29.
SinghBDavisLS. An analysis of scale invariance in object detection snip. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, 2018, pp. 3578–3587.
30.
XuTChenWWangP, et al. CDTrans: cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165, 2021.
31.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
32.
LiuZLinYCaoY, et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 2021, pp. 10012–10022.
33.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, 2016, pp. 770–778.
34.
LiXSuKLiD, et al. Transfer learning for bearing fault diagnosis: adaptive batch normalization and combined optimization method. Meas Sci Technol2024; 35(4): 046106.
35.
GaoYLiX.Fault diagnosis of centrifugal fan bearings based on I-CNN and JMMD in the context of sample imbalance. Eksploatacja I Niezawodnosc-Maintenance Reliab2024; 26(4): 191459.
36.
LiKSuLWuJ, et al. A rolling bearing fault diagnosis method based on variational mode decomposition and an improved kernel extreme learning machine. Appl Sci2017; 7(10): 1004.
37.
WeiLLiK.Intelligent diagnosis method for rotating machinery based on feature extraction and particle swarm optimization. J Simulation2016; 4(2): 60.
38.
WangXGirshickRGuptaA, et al. Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, 2018, pp. 7794–7803.
39.
HanSShaoHChengJ, et al. Convformer-NSE: a novel end-to-end gearbox fault diagnosis framework under heavy noise using joint global and local information. IEEE/ASME Trans Mech2022; 28(1): 340–349.
40.
LiYZhangKCaoJ, et al. Localvit: bringing locality to vision transformers. arXiv preprint arXiv:2104.05707, 2021.
41.
ChenCFRFanQPandaR. Crossvit: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 2021, pp. 357–366.
