RESEARCH PAPER
A Semi-supervised Fault Diagnosis Method for Rolling Bearing Using Time-Frequency Transform Enhanced Contrastive Learning
1
Department of Mechanical and Manufacturing Engineering, Universiti Kebangsaan Malaysia, Malaysia
2
School of Electromechanical and Transportation, Jiaxing Nanyang Polytechnic Institute, China
Submission date: 2025-03-09
Final revision date: 2025-05-03
Acceptance date: 2025-06-11
Online publication date: 2025-06-19
Publication date: 2025-06-19
Corresponding author
Chen Gao
School of Electromechanical and Transportation, Jiaxing Nanyang Polytechnic Institute, China
School of Electromechanical and Transportation, Jiaxing Nanyang Polytechnic Institute, China
Eksploatacja i Niezawodność – Maintenance and Reliability 2026;28(1):207015
HIGHLIGHTS
- A semi-supervised learning method for bearing fault diagnosis was proposed.
- A STFT enhanced Contrastive Learning is employed to utilize large unlabeled samples.
- The diagnostic accuracy exceeded 99% when using 50 labeled samples per fault type.
KEYWORDS
TOPICS
ABSTRACT
This paper proposes a novel semi-supervised framework, time-frequency Contrastive Learning (CL), to address the challenge of accurate rolling bearing fault diagnosis under industrial small-sample conditions. Raw vibration signals are transformed into discriminative time-frequency images using short-time Fourier transform (STFT). A CL network with a ResNet18 model is pre-trained on a lot of unlabeled samples to learn generalized feature, and the ResNet18 model is fine-tuned using small labeled samples for fault classification. Experimental validation on bearing fault datasets demonstrates that the proposed STFT-CL method achieves above 99% diagnosis accuracy with only 50 labeled samples per fault type, outperforming conventional semi-supervised methods by 6-12%. The proposed method provides a potential solution to the "small sample dilemma" in industrial applications through the synergistic effect of physically driven signal processing and self supervised representation learning.
ACKNOWLEDGEMENTS
We gratefully thank Kumar et al. for their publicly available dataset of bearing faults.
FUNDING
This research was funded by the Science and Technology Plan Project of Jiaxing in China (Grant. 2024AY10010), and the Research Projects of Zhejiang Provincial Department of Education in China (Grant. Y202354102).
REFERENCES (38)
1.
Wang X.B., Yao Y.F., Gao C. Wasserstein Distance- EEMD Enhanced Multi-Head Graph Attention Network for Rolling Bearing Fault Diagnosis Under Different Working Conditions. Eksploatacja i Niezawodność – Maintenance and Reliability 2024, 26(2), 184037.
2.
Xiao, Y.M., Shao, H.D., Yan, S., et al. Domain generalization for rotating machinery fault diagnosis: A survey. Advanced Engineering Informatics, 2025, 64, 103063.
3.
Hei Z.D., Sun W.F., Yang H.Y., et al. Novel Domain-Adaptive Wasserstein Generative Adversarial Networks for Early Bearing Fault Diagnosis under Various Conditions. Reliability Engineering and System Safety, 2025, 257, 110847.
4.
Yan S., Shao H.D., Wang J., et al. LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention. Expert Systems with Applications, 2024, 237, 121338.
5.
Kumar A. Research overview and prospect in condition monitoring of compressors. Expert systems with applications, 2025, 277, 127284.
6.
Li X., Cheng J., Shao H.D., et al. A fusion CWSMM-based framework for rotating machinery fault diagnosis under strong interference and imbalanced case. IEEE Transactions on Industrial Informatics, 2021, 18(8): 5180-5189. https://doi.org/10.1109/TII.20....
7.
Yin, H., Wang, Y., Sun, W., et al. Fault diagnosis of hydraulic system based on D-S evidence theory and SVM. International Journal of Hydromechatronics, 2024, 7(1): 1-15. https://doi.org/10.1504/IJHM.2....
8.
Xiao, Y.M., Shao H.D., Yan, s., et al. Domain generalization for rotating machinery fault diagnosis: A survey. Advanced Engineering Informatics, 2025, 64, 103063.
9.
Hei Z.D., Yang H.Y., Sun W.F., et al. Multiscale Conditional Adversarial Networks based domain- adaptive method for rotating machinery fault diagnosis under variable working conditions, ISA Transactions, 2024, 154: 352-370. https://doi.org/10.1016/j.isat....
10.
Jing, C., He, X., Xu, G.C., et al. Finite Element ModelingAssisted Deep Subdomain Adaptation Method for Tool Condition Monitoring. Processes 2025, 13, 545. https://doi.org/10.3390/pr1302....
11.
Xi, C., Yang, J., Liang, X., et al. An improved gated convolutional neural network for rolling bearing fault diagnosis with imbalanced data, International Journal of Hydromechatronics, 2023, 6(2): 108-132.
12.
Kumar A., Kumar R., Xiang J.W., et al. Digital twin-assisted AI framework based on domain adaptation for bearing defect diagnosis in the centrifugal pump. Measurement, 2024, 235, 115013.
13.
Fu Y.D., Zhong M.P., Huang J.F., et al. Denoising diffusion probabilistic model enhanced tool condition monitoring method under imbalanced conditions. Measurement Science and Technology, 2024, 36, https://doi.org/10.1088/1361-6....
14.
Zhang, J., Liu, M., Deng, W., et al. Research on electro-mechanical actuator fault diagnosis based on ensemble learning method. International Journal of Hydromechatronics, 2024, 7(2): 113-131. https://doi.org/10.1504/IJHM.2....
15.
Anil K. Adam G., Hesheng T., et al. Knowledge addition for improving the transfer learning from the laboratory to identify defects of hydraulic machinery. Engineering Applications of Artificial Intelligence, 2023, 126, 106756.
16.
Hei Z.D., Shi Q., Fan X.F., et al. Distance-guided domain adaptation for bearing fault diagnosis under variable operating conditions. Measurement Science and Technology, 2024, 35, https://doi.org/10.1088/1361-6....
17.
Wang S.H., Xiang J.W., Zhong Y, et al. Convolutional neural network-based hidden Markov models for rolling element bearing fault identification. Knowledge-Based Systems, 2018, 144: 65-76. https://doi.org/10.1016/j.knos....
18.
Anil K., Vashishtha G., Gandhi C.P., et al. Novel convolutional neural network (NCNN) for the diagnosis of bearing faults in rotary machinery. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10. https://doi.org/10.1109/TIM.20....
19.
Zhao R., Yan R.Q., Wang J., et al. Learning to monitor machine health with convolutional bi-directional LSTM networks. Sensors, 2017, 17(2): https://doi.org/10.3390/s17020....
20.
Cao X.C., Chen B.Q., Zeng N. A deep domain adaption model with multi-task networks for planetary gearbox fault diagnosis. Neurocomputing, 2020, 409: 173-190. https://doi.org/10.1016/j.neuc....
21.
Zhou Y.Q., Sun B.T., Sun W.F., et al. A tool condition monitoring method based on two-layer angle kernel extreme learning machine and binary differential evolution for milling. Measurement, 2020, 166, 108186.
22.
Wang H.C., Sun W., Sun W.F., et al. A novel tool condition monitoring based on Gramian angular field and comparative learning. International Journal of Hydromechatronics, 2023, 6(2): 93-107. https://doi.org/10.1504/IJHM.2....
23.
Xiao Y.M., Shao H.D., Lin J., et al. BCE-FL: A Secure and Privacy-Preserving Federated Learning System for Device Fault Diagnosis under Non-IID Condition in IIoT. IEEE Internet of Things Journal, 2024, 11(8): https://doi.org/10.1109/JIOT.2....
24.
Zhu Q.S., Sun B.T., Zhou Y.Q., et al. Sample augmentation for intelligent milling tool wear condition monitoring using numerical simulation and generative adversarial network. IEEE Transactions on Instrumentation and Measurement, 2021, 70, https://doi.org/10.1109/TIM.20....
25.
Zhou Y.Q, Zhi G.F., Chen W, et al. A new tool wear condition monitoring method based on deep learning under small samples. Measurement, 2022, 189: 110622.
26.
He X., Zhong M.P., He C., et al. A Novel Tool Wear Identification Method Based on a Semi-Supervised LSTM. Lubricants 2025, 13, 72. https://doi.org/10.3390/lubric....
27.
Zhou Y.Q., Wang H.C., Wang G.H., et al. Semi-Supervised Multiscale Permutation Entropy- Enhanced Contrastive Learning for Fault Diagnosis of Rotating Machinery. IEEE Transactions on Instrumentation and Measurement, 2023, 72, https://doi.org/10.1109/TIM.20....
28.
Hadsell R., Chopra S., LeCun Y. Dimensionality reduction by learning an invariant mapping [C] // 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06). IEEE, 2006, 2: 1735-1742. https://doi.org/10.1109/CVPR.2....
29.
Chen T., Kornblith S., Norouzi M., et al. A simple framework for contrastive learning of visual representations [C] // International conference on machine learning. PMLR, 2020: 1597-1607.
30.
Xia X., Yin H., Yu J., et al. Self-supervised hypergraph convolutional networks for session-based recommendation[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(5): 4503-4511. https://doi.org/10.1609/aaai.v....
31.
Wu Z., Wang S., Gu J., et al. Clear: Contrastive learning for sentence representation. arXiv preprint arXiv, 2020, 2012.15466.
32.
Zhang D., Nan F., Wei X., et al. Supporting clustering with contrastive learning. arXiv preprint arXiv, 2021, 2103.12953.
33.
Chen X., He K. Exploring simple siamese representation learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 15750-15758. https://doi.org/10.1109/CVPR46....
34.
Aafaq N., Akhtar N., Liu W., et al. Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 12487-12496. https://doi.org/10.1109/CVPR.2....
35.
Chin C.H., Abdullah S., Singh S.S.K., et al. Strain generation for fatigue-durability predictions considering load sequence effect of random vibration loading. International Journal of Fatigue, 2023, 166, 107242.
36.
Hamzi N.M., Singh S.S.K., Abdullah S., et al. Characterising Multiaxial Fatigue Random Strain Time Domain in Assessing the Durability of a Suspension Coil Spring. Experimental Techniques, 2023, 47(3): 655-667. https://doi.org/10.1007/s40799....
37.
Firdous A.S., Waseem Z.L., Azhar Y.T. Short-time quadratic-phase Fourier transform. Optik, 2021, 245, 167689.
38.
Kumar A., Zhou Y.Q., Gandhi C.P., et al. Bearing fault size assessment using wavelet transform based Deep Convolutional Neural Network (DCNN). Alexandria Engineering Journal, 2020, 59(2): 999-1012. https://doi.org/10.1016/j.aej.....
CITATIONS (3):
1.
A novel graph representation framework for bearing fault diagnosis via wavelet packet decomposition and Gramian angular field weighting
Jicai Wang, Shahrum Abdullah, Xingbing Wang, Azli Arifin, Salvinder Singh Karam Singh, Chen Gao
Nondestructive Testing and Evaluation
Jicai Wang, Shahrum Abdullah, Xingbing Wang, Azli Arifin, Salvinder Singh Karam Singh, Chen Gao
Nondestructive Testing and Evaluation
2.
Symmetrized dot pattern enhanced cross-attention DDPM method for tool condition monitoring
Xiaoqin Chen, Huan Zhang, Yuandie Fu, Qiusheng Song, Hai Zhang, Jiyan Yi, Yuqing Zhou
AIP Advances
Xiaoqin Chen, Huan Zhang, Yuandie Fu, Qiusheng Song, Hai Zhang, Jiyan Yi, Yuqing Zhou
AIP Advances
3.
Tool Wear Condition Monitoring Based on Improved Symmetrized Dot Pattern Enhanced Resnet18 Under Small Samples
Xiaoqin Chen, Gonghai Wang, Yuandie Fu, Huan Zhang, Chen Gao
Lubricants
Xiaoqin Chen, Gonghai Wang, Yuandie Fu, Huan Zhang, Chen Gao
Lubricants
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
