Skip to main content
SpringerLink
Log in

Bearing fault diagnosis of wind turbines based on dynamic multi-adversarial adaptive network

  • Original Article
  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Owing to the shortage of available labeled data on wind turbine bearings, a new wind turbine bearing fault diagnosis method based on a dynamic multi-adversarial adaptive network (DMAAN) was proposed. In this new method, a laboratory data were used to obtain fault diagnosis models for wind turbine bearings. The first step was evaluating the interdomain distribution difference and intraclass distribution differences between domains. The second step was setting a dynamic adversarial factor to dynamically measure the relative contribution of the two different distributions. The last step was, reducing the distribution difference through multiple adversarial training, to obtain the diagnosis results. The validity of DMAAN was verified via the transfer experiments of laboratory datasets and wind turbine generator measured datasets. The results showed that DMAAN has a higher diagnostic accuracy and better transmission capability in cross-machine transfer fault diagnosis in compare with the existing methods.

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

Similar content being viewed by others

References

  1. X. L. Wang, X. L. Yan and Y. L. He, Weak fault detection for wind turbine bearing based on ACYCBD and IESB, Journal of Mechanical Science and Technology, 34(4) (2020) 1399–1413.

    Article  Google Scholar 

  2. X. J. Gu and C. Z. Chen, Adaptive parameter-matching method of SR algorithm for fault diagnosis of wind turbine bearing, Journal of Mechanical Science and Technology, 33(3) (2019) 1007–1018.

    Article  MathSciNet  Google Scholar 

  3. F. Natili, A. P. Daga, F. Castellani and L. Garibaldi, Multi-scale wind turbine bearings supervision techniques using industrial SCADA and vibration data, Applied Sciences-Basel, 11(15) (2021) 6785.

    Article  Google Scholar 

  4. X. J. Wan, W. L. Sun, K. Chen and X. D. Zhang, State degradation evaluation and early fault identification of wind turbine bearings, Fuel, 311 (2022) 122348.

    Article  Google Scholar 

  5. A. Khorram, M. Khalooei and M. Rezghi, End-to-end CNN plus LSTM deep learning approach for bearing fault diagnosis, Applied Intelligence, 51(2) (2021) 736–751.

    Article  Google Scholar 

  6. D. Y. Han, J. H. Tian, P. Xue and P. M. Shi, A novel intelligent fault diagnosis method based on dual convolutional neural network with multi-level information fusion, Journal of Mechanical Science and Technology, 35(8) (2021) 3331–3345.

    Article  Google Scholar 

  7. W. Zhang, G. L. Peng, C. H. Li, Y. H. Chen and Z. J. Zhang, A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, Sensors, 17(2) (2017) 425.

    Article  Google Scholar 

  8. A. H. Aljemely, J. P. Xuan, F. K. J. Jawad, O. Al-Azzawi and A. S. Alhumaima, A novel unsupervised learning method for intelligent fault diagnosis of rolling element bearings based on deep functional auto-encoder, Journal of Mechanical Science and Technology, 34(11) (2020) 4367–4381.

    Article  Google Scholar 

  9. X. J. Jia, Y. Han, Y. J. Li, Y. C. Sang and G. L. Zhang, Condition monitoring and performance forecasting of wind turbines based on denoising autoencoder and novel convolutional neural networks, Energy Reports, 7 (2021) 6354–6365.

    Article  Google Scholar 

  10. T. Zhang, S. L. Liu, Y. Wei and H. L. Zhang, A novel feature adaptive extraction method based on deep learning for bearing fault diagnosis, Measurement, 185 (2021) 110030.

    Article  Google Scholar 

  11. K. G. Su, J. H. Liu and H. Xiong, Hierarchical diagnosis of bearing faults using branch convolutional neural network considering noise interference and variable working conditions, Knowledge-Based Systems, 230 (2021) 107386.

    Article  Google Scholar 

  12. S. Emmanuel, Y. Yihun, Z. N. Ahmedabadi and E. Boldsaikhan, Planetary gear train microcrack detection using vibration data and convolutional neural networks, Neural Computing and Applications, 33(24) (2021) 17223–17243.

    Article  Google Scholar 

  13. S. J. Pan and Q. A. Yang, A survey on transfer learning, IEEE Transactions on Knowledge and Data Engineering, 22(10) (2010) 1345–1359.

    Article  Google Scholar 

  14. S. Y. Lee and S. K. Lee, Deep convolutional neural network with new training method and transfer learning for structural fault classification of vehicle instrument panel structure, Journal of Mechanical Science and Technology, 34(11) (2020) 4489–4498.

    Article  Google Scholar 

  15. M. Sun, H. Wang, P. Liu, S. Huang, P. Wang and J. Meng, Stack autoencoder transfer learning algorithm for bearing fault diagnosis based on class separation and domain fusion, IEEE Transactions on Industrial Electronics, 69(3) (2022) 3047–3058.

    Article  Google Scholar 

  16. C. Qian, J. Zhu, Y. Shen, Q. Jiang and Q. Zhang, Deep transfer learning in mechanical intelligent fault diagnosis: application and challenge, Neural Processing Letters, 54(3) (2022) 2509–2531.

    Article  Google Scholar 

  17. R. Zhang and Y. Gu, A transfer learning framework with a one-dimensional deep subdomain adaptation network for bearing fault diagnosis under different working conditions, Sensors, 22(4) (2022) 1624.

    Article  Google Scholar 

  18. R. Hu, M. Zhang, Z. Xiang and J. Mo, Guided deep subdomain adaptation network for fault diagnosis of different types of rolling bearings, Journal of Intelligent Manufacturing (2022).

  19. Y. Jiang, T. Xia, D. Wang, K. Zhang and L. Xi, Joint adaptive transfer learning network for cross-domain fault diagnosis based on multi-layer feature fusion, Neurocomputing, 487 (2022) 228–242.

    Article  Google Scholar 

  20. C. Qian, Q. Jiang, Y. Shen, C. Huo and Q. Zhang, An intelligent fault diagnosis method for rolling bearings based on feature transfer with improved DenseNet and joint distribution adaptation, Measurement Science and Technology, 33(2) (2022) 025101.

    Article  Google Scholar 

  21. X. C. Cao, Y. Wang, B. Q. Chen and N. Y. Zeng, Domain-adaptive intelligence for fault diagnosis based on deep transfer learning from scientific test rigs to industrial applications, Neural Computing and Applications, 33(9) (2021) 4483–4499.

    Article  Google Scholar 

  22. B. Wang, B. Wang and Y. Ning, A novel transfer learning fault diagnosis method for rolling bearing based on feature correlation matching, Measurement Science and Technology, 33(12) (2022) 125006.

    Article  Google Scholar 

  23. Z. Chen, J. Wu, C. Deng, C. Wang and Y. Wang, Residual deep subdomain adaptation network: a new method for intelligent fault diagnosis of bearings across multiple domains, Mechanism and Machine Theory, 169 (2022) 104635.

    Article  Google Scholar 

  24. T. Wang, T. Li, P. Jiang, Y. Cheng and T. Tang, A fault diagnosis method for rolling bearings based on inter-class repulsive force discriminant transfer learning, Measurement Science and Technology, 33(1) (2022) 015011.

    Article  Google Scholar 

  25. T. Han, C. Liu, W. G. Yang and D. X. Jiang, Deep transfer network with joint distribution adaptation: a new intelligent fault diagnosis framework for industry application, ISA Transactions, 97 (2020) 269–281.

    Article  Google Scholar 

  26. M. Z. Lv, S. X. Liu, X. M. Su and C. Z. Chen, Deep transfer network with multi-kernel dynamic distribution adaptation for cross-machine fault diagnosis, IEEE Access, 9 (2021) 16392–16409.

    Article  Google Scholar 

  27. Y. Z. Liu, K. M. Shi, Z. X. Li, G. F. Ding and Y. S. Zou, Transfer learning method for bearing fault diagnosis based on fully convolutional conditional wasserstein adversarial networks, Measurement, 180 (2021) 109553.

    Article  Google Scholar 

  28. Y. S. Zou, Y. Z. Liu, J. L. Deng, Y. L. Jiang and W. H. Zhang, A novel transfer learning method for bearing fault diagnosis under different working conditions, Measurement, 171 (2021) 108767.

    Article  Google Scholar 

  29. X. Pei, S. Su, L. Jiang, C. Chu, L. Gong and Y. Yuan, Research on rolling bearing fault diagnosis method based on generative adversarial and transfer learning, Processes, 10(8) (2022) 1443.

    Article  Google Scholar 

  30. C. Hao, J. Du and H. Liang, Imbalanced fault diagnosis of rolling bearing using data synthesis based on multi-resolution fusion generative adversarial networks, Machines, 10(5) (2022) 295.

    Article  Google Scholar 

  31. S. W. Liu, H. K. Jiang, Z. H. Wu and X. Q. Li, Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis, Mechanical Systems and Signal Processing, 163 (2021) 108139.

    Article  Google Scholar 

  32. Y. S. Li, P. Y. Che, C. L. Liu, D. F. Wu and Y. C. Du, Cross-scene pavement distress detection by a novel transfer learning framework, Computer-Aided Civil and Infrastructure Engineering, 36(11) (2021) 1398–1415.

    Article  Google Scholar 

  33. J. He, M. Ouyang, Z. Chen, D. Chen and S. Liu, A deep transfer learning fault diagnosis method based on WGAN and minimum singular value for non-homologous bearing, IEEE Transactions on Instrumentation and Measurement, 71 (2022) 1–9.

    Google Scholar 

  34. C. Cheng, B. T. Zhou, G. J. Ma, D. R. Wu and Y. Yuan, Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data, Neurocomputing, 409 (2020) 35–45.

    Article  Google Scholar 

  35. J. Li, Y. B Liu and Q. J. Li, Generative adversarial network and transfer-learning-based fault detection for rotating machinery with imbalanced data condition, Measurement Science and Technology, 33(4) (2022) 045103.

    Article  Google Scholar 

  36. H. Cao, H. Shao, B. Liu, B. Cai and J. Cheng, Clustering-guided novel unsupervised domain adversarial network for partial transfer fault diagnosis of rotating machinery, IEEE Sensors Journal, 22(14) (2022) 14387–14396.

    Article  Google Scholar 

  37. F. Li, T. J. Tang, B. P. Tang and Q. Y. He, Deep convolution domain-adversarial transfer learning for fault diagnosis of rolling bearings, Measurement, 169 (2021) 108339.

    Article  Google Scholar 

  38. W. Wang and L. Q. Zhu, Structured feature sparsity training for convolutional neural network compression, Journal of Visual Communication and Image Representation, 71 (2020) 102867.

    Article  Google Scholar 

  39. J. D. Sun, J. T. Wen, C. Y. Yuan, Z. Liu and Q. Y. Xiao, Bearing fault diagnosis based on multiple transformation domain fusion and improved residual dense networks, IEEE Sensors Journal, 22(2) (2022) 1541–1551.

    Article  Google Scholar 

  40. R. J. Xu, G. B. Li, J. Yang and L. Lin, Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation, 2019 IEEE/CVF International Conference on Computer Vision (ICCV) IEEE (2020) 1426–1435.

  41. S. J. Pan, I. W. Tsang, J. T. Kwok and Q. A. Yang, Domain adaptation via transfer component analysis, IEEE Transactions on Neural Networks, 22(2) (2011) 199–210.

    Article  Google Scholar 

  42. J. D. Wang, Y. Q. Chen, S. J. Hao, W. J. Feng and Z. Q. Shen, Balanced distribution adaptation for transfer learning, 2017 IEEE International Conference on Data Mining (ICDM) (2017) 1129–1134.

  43. Y. Ganin and V. Lempitsky, Unsupervised domain adaptation by backpropagation, International Conference on Machine Learning PMLR (2015) 1180–1189.

  44. C. H. Yu, J. D. Wang, Y. Q. Chen and M. Y. Huang, Transfer learning with dynamic adversarial adaptation network, 2019 IEEE International Conference on Data Mining (ICDM) (2019) 778–786.

  45. S. Y. Jia, Y. F. Deng, J. Lv, S. C. Du and Z. Y. Xie, Joint distribution adaptation with diverse feature aggregation: A new transfer learning framework for bearing diagnosis across different machines, Measurement, 187 (2022) 110332.

    Article  Google Scholar 

Download references

Acknowledgments

This work is supported by the National Natural Science Foundation of China (grant numbers 51675350, 51575361).

Author information

Authors and Affiliations

  1. School of Mechanical Engineering, Shenyang University of Technology, Shenyang, 110870, China

    Miao Tian, Xiaoming Su & Changzheng Chen

  2. School of Environmental and Chemical Engineering, Shenyang University of Technology, Shenyang, 110870, China

    Yuanqing Luo

  3. Ningbo Kunbo Measurement and Control Technology Co., Ltd., Ningbo, 315000, China

    Xianming Sun

Authors
  1. Miao Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoming Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Changzheng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuanqing Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xianming Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoming Su.

Additional information

Miao Tian received her M.S. degree in Operations Research and Cybernetics from Liaoning Normal University, China, in 2019. She is currently a Ph.D. student at the School of Mechanical Engineering, Shenyang University of Technology, China. Her research interests are wind turbine condition monitoring, fault diagnosis, and remaining useful life prediction.

Xiaoming Su received his Ph.D. degree from the School of Information Science and Engineering, Northeastern University, Shenyang, China. He is currently a Professor and a Ph.D. Supervisor in the School of Mechanical Engineering, Shenyang University of Technology, China. His current research interests include mathematics, automatic control, and industrial engineering. He is also the Vice Chairman of the Liaoning Provincial Mathematical Society.

Changzheng Chen received his Ph.D. degree from School of Mechanical Engineering, Northeastern University, Shenyang, China. He is currently the Executive Director of the Fault Diagnosis Professional Committee of the Chinese Vibration Engineering Society, the consultant of the Fault Diagnosis Center of the Chinese Mechanical Engineering Society, the executive director of the Liaoning Vibration Engineering Society, the director of the Noise and Vibration Control Professional Committee, the noise control expert of the Shenyang Environmental Protection Bureau, and a Shenyang Environmental Protection Industry Council member. He is currently a Professor and a Ph.D. Supervisor at the School of Mechanical Engineering, Shenyang University of Technology, China. His current research interests include vibration, noise, and fault diagnosis.

Yuanqing Luo received his M.S. degree in Mechanical Engineering from Shenyang University of Technology, China, in 2016. He is currently a Ph.D. student at the School of Mechanical Engineering, Shenyang University of Technology, China. His research interests are wind turbine condition monitoring and fault diagnosis.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, M., Su, X., Chen, C. et al. Bearing fault diagnosis of wind turbines based on dynamic multi-adversarial adaptive network. J Mech Sci Technol 37, 1637–1651 (2023). https://doi.org/10.1007/s12206-023-0306-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-023-0306-z

Keywords

Search

Navigation