Train traction motor bearings (TTMBs) are critical for ensuring stable and safe train operation. However, most intelligent fault diagnosis methods face significant challenges due to the complexity and variability of TTMB fault data, as well as the high cost of obtaining labeled data. Accordingly, this paper introduces a self-supervised learning model that leverages time–frequency dual domain prediction (TFDDP). First, a data augmentation module is designed to generate diverse training data, thereby enhancing the model’s robustness and generalization ability under different conditions. Secondly, an encoder combining multiple attention mechanisms and residual networks is proposed to extract critical time–frequency features efficiently and improve fault mode recognition capabilities. A cross-correlation smoothing matrix loss function is then designed, employing a smoothing matrix to effectively regulate the interplay between frequency-domain predictions and time-domain features, thereby strengthening the alignment between related features. Additionally, by introducing adaptive moment estimation with a weight-decay optimizer and the one-cycle learning rate scheduler, the model’s risk of overfitting is reduced, and convergence speed is accelerated. Finally, comparisons with existing optimal models indicate that TFDDP achieves competitive diagnostic performance across various conditions and performs excellently in TTMB fault classification even with limited labeled samples.
JinZHeDWeiZ.Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBN. Eng Appl Artif Intell2022; 110: 104713.
2.
HeDLiuCJinZ, et al. Fault diagnosis of flywheel bearing based on parameter optimization variational mode decomposition energy entropy and deep learning. Energy2022; 239: 122108.
3.
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.
4.
LiYMenZBaiX, et al. A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism. Struct Health Monit2025; 24(2): 830–852.
5.
JinZHeDMaR, et al. Fault diagnosis of train rotating parts based on multi-objective VMD optimization and ensemble learning. Digit Signal Process2022; 121: 103312.
6.
WeiZHeDJinZ, et al. Density-based affinity propagation tensor clustering for intelligent fault diagnosis of train bogie bearing. IEEE Trans Intell Transp Syst2023; 24(6): 6053–6064.
7.
HeDXuYJinZ, et al. A zero-shot model for diagnosing unknown composite faults in train bearings based on label feature vector generated fault features. Appl Acoust2025; 232: 110563.
8.
HeDDaiCWuJ, et al. Advances in digital twinning for bearing fault diagnosis: a literature review. Meas Sci Technol2025; 36(9): 92001.
9.
ZhouHLiuRLiY, et al. A rolling bearing fault diagnosis method based on a convolutional neural network with frequency attention mechanism. Struct Health Monit2024; 23(4): 2475–10.
10.
RaoMESimonJMollJ, et al. Real-time onboard propeller fault diagnosis of autonomous delivery drones through vibration analysis. Struct Health Monit2025: 14759217251327224.
11.
ZhangXZhaoBLinY.Machine learning based bearing fault diagnosis using the case western reserve university data: a review. IEEE Access2021; 9: 155598–155608.
12.
DongWWuXZhangS, et al. An early fault warning and diagnosis model based on a two-step analysis strategy for wind turbine bearings. Struct Health Monit2024; 24(6): 3637–3656.
13.
XieSWangJLiY, et al. Bearing fault diagnosis method based on improved meta-ResNet and sample weighting under noise label. Struct Health Monit2024; 24(6): 3707–3727.
14.
LiYChengGMaS, et al. Bearing fault diagnosis method based on complete center frequency distribution feature. Struct Health Monit2023; 22(6): 4100–4116.
15.
LaoZHeDJinZ, et al. Few-shot fault diagnosis of turnout switch machine based on semi-supervised weighted prototypical network. Knowl Based Syst2023; 274: 110634.
16.
KumarPRaoufISongJ, et al. Multi-size wide kernel convolutional neural network for bearing fault diagnosis. Adv Eng Softw2024; 198: 103799.
17.
YaoRZhaoHZhaoZ, et al. Parallel convolutional transfer network for bearing fault diagnosis under varying operation states. IEEE Trans Instrum Meas2024; 73: 1–13.
18.
ZhangYRenZZhouS, et al. Supervised contrastive learning-based domain adaptation network for intelligent unsupervised fault diagnosis of rolling bearing. IEEE/ASME Trans Mechatronics2022; 27(6): 5371–5380.
19.
HeYHeDLaoZ, et al. Few-shot fault diagnosis of turnout switch machine based on flexible semi-supervised meta-learning network. Knowl Based Syst2024; 294: 111746.
20.
YuKMaHLinTR, et al. A consistency regularization based semi-supervised learning approach for intelligent fault diagnosis of rolling bearing. Measurement2020; 165: 107987.
21.
YuKLinTRMaH, et al. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning. Mech Syst Signal Process2021; 146: 107043.
22.
HanTLiuCWuR, et al. Deep transfer learning with limited data for machinery fault diagnosis. Appl Soft Comput2021; 103: 107150.
23.
ShaoSMcAleerSYanR, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform2018; 15(4): 2446–2455.
24.
CenJYangZWuY, et al. A mask self-supervised learning-based transformer for bearing fault diagnosis with limited labeled samples. IEEE Sens Journal2023; 23(10): 10359–10369.
25.
HeDXuYSunH, et al. Self-supervised learning for vehicle bearing fault diagnosis based on time–frequency dual-domain contrast and fusion. Nonlinear Dyn2025; 113(14): 17385–17412.
26.
WanWChenJZhouZ, et al. Self-supervised simple siamese framework for fault diagnosis of rotating machinery with unlabeled samples. IEEE Trans Neural Netw Learn Syst2022; 35(5): 6380–6392.
27.
WuKNieYWuJ, et al. Prior knowledge-based self-supervised learning for intelligent bearing fault diagnosis with few fault samples. Meas Sci Technol2023; 34(10): 105104.
28.
GrillJBStrubFAltchéF, et al. Bootstrap your own latent-a new approach to self-supervised learning. Adv Neural Inform Process Syst2020; 33: 21271–21284.
29.
HuCWuJSunC, et al. Interinstance and intratemporal self-supervised learning with few labeled data for fault diagnosis. IEEE Trans Ind Inform2022; 19(5): 6502–6512.
30.
ChenXYangRXueY, et al. TFPred: learning discriminative representations from unlabeled data for few-label rotating machinery fault diagnosis. Control Eng Pract2024; 146: 105900.
31.
WangWLiCLiA, et al. One-stage self-supervised momentum contrastive learning network for open-set cross-domain fault diagnosis. Knowl Based Syst2023; 275: 110692.
32.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Seattle, WA, 2016, pp. 770–778.
33.
ZbontarJJingLMisraI, et al. Barlow twins: self-supervised learning via redundancy reduction. In: International conference on machine learning, PMLR, Eeectr Network, Vol. 139, 2021, pp. 12310–12320.
34.
FuDLiuJZhongH, et al. A novel self-supervised representation learning framework based on time-frequency alignment and interaction for mechanical fault diagnosis. Knowl Based Syst2024; 295: 111846.
35.
QianQQinYLuoJ, et al. Deep discriminative transfer learning network for cross-machine fault diagnosis. Mech Syst Signal Process2023; 186: 109884.
36.
FengYChenJZhangT, et al. Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis. ISA Trans2022; 120: 383–401.
37.
LinJShaoHMinZ, et al. Cross-domain fault diagnosis of bearing using improved semi-supervised meta-learning towards interference of out-of-distribution samples. Knowl Based Syst2022; 252: 109493.
