Skip to main content
SpringerLink
Log in

Deep Transfer Learning for Bearing Fault Diagnosis using CWT Time–Frequency Images and Convolutional Neural Networks

  • Technical Article---Peer-Reviewed
  • Published:
Journal of Failure Analysis and Prevention Aims and scope Submit manuscript

Abstract

Deep transfer learning has evolved into a powerful method for defect identification, particularly in mechanical systems that lack sufficient training data. Nonetheless, domain divergence and absence of overlap between the source and target domains might result in negative transfer. This study examines the partial knowledge transfer, for bearing fault diagnosis, by freezing layers in varying proportions to take advantage of both freezing and fine-tuning strategies. To assess the proposed strategy, three distinct pre-trained models are used, namely ResNet-50, GoogLeNet, and SqueezeNet. Each network is trained using three different optimizers: root mean square propagation, adaptive moment estimation, and stochastic gradient descent with momentum. The suggested technique performance is evaluated in terms of fault classification accuracy, specificity, precision, and training time. The classification results obtained using the CWRU datasets show that the proposed technique reduces training time while enhancing diagnostic accuracy, hence improving bearing defect diagnosis performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. S. Devendiran, K. Manivannan, Vibration based condition monitoring and fault diagnosis technologies for bearing and gear components-a review. Int. J. Appl. Eng. Res. 11, 3966–3975 (2016)

    Google Scholar 

  2. Z. Liu, Y.S. Zou, Y.L. Jiang, H. Yu, G.F. Ding, A novel method for diagnosis of bearing fault using hierarchical multitasks convolutional neural networks. Shock. Vib. 2020, 1–4 (2020)

    CAS  Google Scholar 

  3. S. Fu, K. Liu, Y. Xu, Y. Liu, rolling bearing diagnosing method based on time domain analysis and adaptive fuzzy-means clustering. Shock. Vib. 2016, 1362 (2016)

    Google Scholar 

  4. S. Djaballah, K. Meftah, Detection and diagnosis of fault bearing using wavelet packet transform and neural network. Frat. ed Integ. Strut. 13(49), 291–301 (2019)

    Article  Google Scholar 

  5. F. Al-Badour, M. Sunar, L. Cheded, Vibration analysis of rotating machinery using time–frequency analysis and wavelet techniques. Mech. Syst. Signal Process. 25(6), 2083–2101 (2011)

    Article  Google Scholar 

  6. D. Zhong, W. Guo, D. He, An intelligent fault diagnosis method based on stft and convolutional neural network for bearings under variable working conditions (China). Prognost. Syst. Health Manage. Conf. 2, 1–6 (2019)

    Google Scholar 

  7. D. Verstraete, A. Ferrada, E. Droguett, V. Meruane, M. Modarres, Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings. Shock. Vib. 2017, 137395 (2017)

    Google Scholar 

  8. A. Widodo, B.S. Yang, Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 21(6), 2560–2574 (2007)

    Article  Google Scholar 

  9. E. Song, F. Gao, C. Yao, Y. Ke, Research on rolling bearing fault diagnosis method based on improved LMD and CMWPE. J. Fail. Anal. Preven. 21, 1714–1728 (2021)

    Article  Google Scholar 

  10. L. Eren, A. Karahoca, and M.J. Devaney, Neural network based motor bearing fault detection, in Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference, May 2004 (Italy), pp. 1657–1660

  11. J. Khelil, K. Khelil, M. Ramdani, N. Boutasseta, Discrete wavelet design for bearing fault diagnosis using particle swarm optimization. IIETA. 53(5), 705–713 (2020)

    Google Scholar 

  12. D.T. Hoang, H.J. Kang, rolling element bearing fault diagnosis using convolutional neural network and vibration image. Cogn. Syst. Res. 53(6), 42–50 (2019)

    Article  Google Scholar 

  13. Z. Chen, J. Cen, J. Xiong, Rolling bearing fault diagnosis using time-frequency analysis and deep transfer convolutional neural network. IEEE Access. 8, 150248–150261 (2020)

    Article  Google Scholar 

  14. T. Lu, F. Yu, B. Han, J. Wang, A generic intelligent bearing fault diagnosis system using convolutional neural networks with transfer learning. IEEE Access. 8, 164807–164814 (2020)

    Article  Google Scholar 

  15. G.E. Hinton, S. Osindero, Y. Teh, A fast learning algorithm for deep belief nets. Neural. Comput. 18(7), 1527–1554 (2006)

    Article  Google Scholar 

  16. J. Gehring, Y. Miao, F. Metze, and A. Waibel, Extracting deep bottleneck features using stacked auto-encoders, in IEEE International Conference Acoust, Speech Signal Process, 26–31May 2013 (Canada), pp. 3377–3381

  17. T. Zan, H. Wang, M. Wang, Z. Liu, X. Gao, Application of multi-dimension input convolutional neural network in fault diagnosis of rolling bearings. Appl. Sci. 9(13), 2690 (2019)

    Article  Google Scholar 

  18. T. Ince, S. Kiranyaz, L. Eren, Real-time motor fault detection by 1-d convolutional neural networks. IEEE T. Ind. Electron. 63(11), 7067–7075 (2016)

    Article  Google Scholar 

  19. L. Wen, X. Li, L. Gao, Y. Zhang, A new convolutional neural network-based data-driven fault diagnosis method. IEEE Trans. Ind. Electron. 65(7), 5990–5998 (2018)

    Article  Google Scholar 

  20. K. Weiss, T.M. Khoshgoftaar, D. Wang, A survey of transfer learning. J. Big Data. 3(9), 365 (2016)

    Google Scholar 

  21. C. Grover, N. Turk, A novel fault diagnostic system for rolling element bearings using deep transfer learning on bispectrum contour maps. Eng. Sci. Technol. Int. 31, 1245 (2021)

    Google Scholar 

  22. Y. Liu, J. Li, Q. Li, Q. Wang, Transfer learning with inception resnet-based model for rolling bearing fault diagnosis. J. Adv. Mech. Des. Syst. Manuf. 16(2), JAMDSM0023 (2022)

    Article  Google Scholar 

  23. F. Hlawatsch, G.F. Boudreaux-Bartels, Linear and quadratic time frequency signal representations. IEEE Signal Process. Mag. 9(2), 21–67 (1992)

    Article  Google Scholar 

  24. S. Sivakumar, D. Nedumaran, Discrete time-frequency signal analysis and processing techniques for non-stationary signals. J. Appl. Math. Phys. 6(9), 1916–1927 (2018)

    Article  Google Scholar 

  25. K. Khelil, F. Berrezzek, T. Bouadjila, GA-based design of optimal discrete wavelet filters for efficient wind speed forecasting. Neural Comput. App. 32(16), 4373–4386 (2021)

    Article  Google Scholar 

  26. J. Kumar, M. Rashid, R.M. Musa, M.A. Razman, N. Sulaiman, R. Jailani, The classification of EEG-based wink signals: a CWT-transfer learning pipeline. ICT Exp. 7(4), 421–425 (2021)

    Article  Google Scholar 

  27. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE. 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  28. M.S. Rathore, S.P. Harsha, Roller bearing failure analysis using gaussian mixture models and convolutional neural networks. J Fail. Anal. Preven. 22, 1853–1871 (2022)

    Article  Google Scholar 

  29. C. Cui, Intelligent analysis of exercise health big data based on deep convolutional neural network. Comput. Intell. Neurosci. 325, 5020150 (2022)

    Google Scholar 

  30. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in IEEE Conference on Computer Vision and Pattern Recognition, 27–30 June 2016 (USA), pp. 770–778

  31. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, and D. Erhan, Going deeper with convolutions. in The IEEE Conference on Computer Vision and Pattern Recognition, 7–12 June 2015(USA), pp. 1–9

  32. F.N. Iandola, S. Han, M.W. Moskewicz, K. Ashraf, W.J. Dally, and K. Keutzer, SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and < 0.5 MB model size, pp. 12–25 (2016)

  33. Y.N. Dauphin, H. de Vries, J. Chung, Y. Bengio, Rmsprop and equilibrated adaptive learning rates for non-convex optimization. Adv. Neural Inf. Process. Syst. 28, 1504–1512 (2015)

    Google Scholar 

  34. D. P. Kingma, J. Ba. Adam: a method for stochastic optimization, in 3rd International Conference on Learning Representations. ICLR 2015 May (USA), pp. 7–9

  35. R. Jie, J. Gao, A. Vasnev et al., Adaptive hierarchical hyper-gradient descent. Int. J. Mach. Learn. Cyber. 13, 3785–3805 (2022)

    Article  Google Scholar 

  36. S. Ruder. An overview of gradient descent optimization algorithms. arXiv:1609.04747 (2016)

  37. R. Yan, F. Shen, C. Sun, X. Chen, Knowledge transfer for rotary machine fault diagnosis. IEEE Sens. J. 20(15), 8374–8393 (2020)

    Article  Google Scholar 

  38. O. Russakovsky, J. Deng, H. Su et al., ImageNet large scale visual recognition challenge. Int. Jour. of Comp. Vis. 115(3), 211–252 (2015)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. LGEM Laboratory, University of Biskra, Biskra, Algeria

    Said Djaballah & Kamel Meftah

  2. Faculty of Technology, University of Batna 2, Batna, Algeria

    Kamel Meftah

  3. LEER Laboratory, Faculty of Science and Technology, University of Souk Ahras, Souk Ahras, Algeria

    Khaled Khelil

  4. SIME Laboratory, University of Tunis, ENSIT, Tunis, Tunisia

    Mounir Sayadi

Authors
  1. Said Djaballah
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kamel Meftah
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Khaled Khelil
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mounir Sayadi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Said Djaballah.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Djaballah, S., Meftah, K., Khelil, K. et al. Deep Transfer Learning for Bearing Fault Diagnosis using CWT Time–Frequency Images and Convolutional Neural Networks. J Fail. Anal. and Preven. 23, 1046–1058 (2023). https://doi.org/10.1007/s11668-023-01645-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11668-023-01645-4

Keywords

Search

Navigation