Skip to main content
SpringerLink
Log in

Prediction of remaining useful life of metro traction motor bearings based on DCCNN-GRU and multi-information fusion

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

Abstract

A single type of sensor is susceptible to interference and limited degradation information can be extracted. Therefore, a multi-information fusion-based bearing remaining useful life prediction method using the dual-channel convolutional neural network (DCCNN) and the gated recurrent unit (GRU) is proposed. Firstly, vibration sensors are utilized as a basis for signal collection, while acoustic emission sensors are introduced as a complement to obtain more comprehensive degradation information. Secondly, the time domain, frequency domain and time-frequency domain features of the vibration signal and acoustic emission signal were extracted respectively to construct a comprehensive bearing degradation feature set. Third, multiple evaluation indicators are used to comprehensively evaluate the degradation features, and effective degradation features that are highly related to bearing degradation are selected for feature fusion. Subsequently, the DCCNN-GRU model was established, which captures and comprehensively utilizes different degradation feature information in each channel through the DCCNN network structure, and employs GRU to process the time relationships and dependencies in sequence data to solves the vanishing gradient problem. Finally, an experimental bearing test bench was constructed to collect data, and this data was used to experimentally validated the model and compared with other methods to demonstrate its feasibility and effectiveness.

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

Abbreviations

n :

Number of samples

σ :

Sigmoid function

t i :

Time sequence

References

  1. J. H. Zhou, Y. Qin and D. L. Chen, Remaining useful life prediction of bearings by a new reinforced memory GRU network, Advanced Engineering Informatics, 53 (2022) 101682.

    Article  Google Scholar 

  2. Y. Qin, C. C. Li and F. J. Cao, A fault dynamic model of high-speed angular contact ball bearings, Mechanism and Machine Theory, 143 (2020) 103627.

    Article  Google Scholar 

  3. J. Chiachío, M. L. Jalón and M. Chiachío, A Markov chains prognostics framework for complex degradation processes, Reliability Engineering & System Safety, 195 (2020) 106621.

    Article  Google Scholar 

  4. H. D. Shao, M. Xia and G. J. Han, Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images, IEEE Transactions on Industrial Informatics, 17 (5) (2020) 3488–3496.

    Article  Google Scholar 

  5. Y. Wang, H. Ding and X. C. Sun, Residual life prediction of bearings based on SENet-TCN and transfer learning, IEEE Access, 10 (2022) 123007–123019.

    Article  Google Scholar 

  6. T. Zuo, K. Zhang and Q. Zheng, A hybrid attention-based multi-wavelet coefficient fusion method in RUL prognosis of rolling bearings, Reliability Engineering & System Safety, 237 (2023) 109337.

    Article  Google Scholar 

  7. L. Jiang, T. A. Zhang and W. Lei, A new convolutional dualchannel transformer network with time window concatenation for remaining useful life prediction of rolling bearings, Advanced Engineering Informatics, 56 (2023) 101966.

    Article  Google Scholar 

  8. H. M. Zhao, H. D. Liu and Y. Jin, Feature extraction for data-driven remaining useful life prediction of rolling bearings, IEEE Transactions on Instrumentation and Measurement, 70 (2021) 1–10.

    Google Scholar 

  9. Y. G. Lei, N. P. Li and S. Gontarz, A model-based method for remaining useful life prediction of machinery, IEEE Transactions on Reliability, 65 (3) (2016) 1314–1326.

    Article  Google Scholar 

  10. L. L. Cui, X. Wang and H. Q. Wang, Research on remaining useful life prediction of rolling element bearings based on time-varying Kalman filter, IEEE Transactions on Instrumentation and Measurement, 69 (6) (2019) 2858–2867.

    Article  Google Scholar 

  11. Y. N. Qian and R. Q. Yan, Remaining useful life prediction of rolling bearings using an enhanced particle filter, IEEE Transactions on Instrumentation and Measurement, 64 (10) (2015) 2696–2707.

    Article  Google Scholar 

  12. C. P. Lin, M. H. Ling and J. Cabrera, Prognostics for lithiumion batteries using a two-phase gamma degradation process model, Reliability Engineering & System Safety, 214 (2021) 107797.

    Article  Google Scholar 

  13. Y. F. Ding, M. P. Jia and J. C. Zhuang, Deep imbalanced regression using cost-sensitive learning and deep feature transfer for bearing remaining useful life estimation, Applied Soft Computing, 127 (2022) 109271.

    Article  Google Scholar 

  14. S. Subramanian, R. Barbieri and E. N. Brown, Point process temporal structure characterizes electrodermal activity, Proceedings of the National Academy of Sciences, 117 (42) (2020) 26422–26428.

    Article  Google Scholar 

  15. W. N. Yu, W. B. Tu and I. Y. Kim, A nonlinear-drift-driven Wiener process model for remaining useful life estimation considering three sources of variability, Reliability Engineering & System Safety, 212 (2021) 107631.

    Article  Google Scholar 

  16. H. Y. Dui, S. B. Si and M. J. Zuo, Semi-Markov process-based integrated importance measure for multi-state systems, IEEE Transactions on Reliability, 64 (2) (2015) 754–765.

    Article  Google Scholar 

  17. N. N. Zhang, L. F. Wu and Z. H. Wang, Bearing remaining useful life prediction based on naive bayes and weibull distributions, Entropy, 20 (12) (2018) 944.

    Article  Google Scholar 

  18. S. Xiang, Y. Qin and F. Q. Liu, Automatic multi-differential deep learning and its application to machine remaining useful life prediction, Reliability Engineering & System Safety, 223 (2022) 108531.

    Article  Google Scholar 

  19. H. Su, L. Xiang and A. Hu, A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions, Mechanical Systems and Signal Processing, 169 (2022) 108765.

    Article  Google Scholar 

  20. G. Hinton, L. Deng and D. Yu, Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, IEEE Signal Processing Magazine, 29 (6) (2012) 82–97.

    Article  Google Scholar 

  21. M. Ma, C. Sun and X. F. Chen, Discriminative deep belief networks with ant colony optimization for health status assessment of machine, IEEE Transactions on Instrumentation and Measurement, 66 (12) (2017) 3115–3125.

    Article  Google Scholar 

  22. B. Rezaeianjouybari and Y. Shang, Deep learning for prognostics and health management: state of the art, challenges, and opportunities, Measurement, 163 (2020) 107929.

    Article  Google Scholar 

  23. Q. B. Wang, K. Xu and X. G. Kong, A linear mapping method for predicting accurately the RUL of rolling bearing, Measurement, 176 (2021) 109127.

    Article  Google Scholar 

  24. H. Ding, L. L. Yang and Z. Y. Cheng, A remaining useful life prediction method for bearing based on deep neural networks, Measurement, 172 (2021) 108878.

    Article  Google Scholar 

  25. S. Zhao, Y. Zhang and S. Wang, A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method, Measurement, 146 (2019) 279–288.

    Article  Google Scholar 

  26. K. X. Peng, R. H. Jiao and J. Dong, A deep belief network based health indicator construction and remaining useful life prediction using improved particle filter, Neurocomputing, 361 (2019) 19–28.

    Article  Google Scholar 

  27. C. W. Guo, Y. H. Deng and C. F. Zhang, Remaining useful life prediction of bearing based on autoencoder-LSTM, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation: SPIE (2021) 138–145.

  28. Y. J. Shang, X. L. Tang and G. Q. Zhao, A remaining life prediction of rolling element bearings based on a bidirectional gate recurrent unit and convolution neural network, Measurement, 202 (2022) 111893.

    Article  Google Scholar 

  29. L. Guo, N. P. Li and F. Jia, A recurrent neural network based health indicator for remaining useful life prediction of bearings, Neurocomputing, 240 (2017) 98–109.

    Article  Google Scholar 

  30. S. J. Dong, J. F. Xiao and X. L. Hu, Deep transfer learning based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing, Reliability Engineering & System Safety, 230 (2023) 108914.

    Article  Google Scholar 

  31. L. Wang, H. R. Cao and Z. S. Ye, Bayesian large-kernel attention network for bearing remaining useful life prediction and uncertainty quantification, Reliability Engineering & System Safety, 238 (2023) 109421.

    Article  Google Scholar 

  32. Y. K. Gu, L. Zeng and G. Q. Qiu, Bearing fault diagnosis with varying conditions using angular domain resampling technology, SDP and DCNN, Measurement, 156 (2020) 107616.

    Article  Google Scholar 

  33. S. Gai and Z. Y. Bao, New image denoising algorithm via improved deep convolutional neural network with perceptive loss, Expert Systems with Applications, 138 (2019) 112815.

    Article  Google Scholar 

  34. B. Zhang, S. H. Zhang and W. H. Li, Bearing performance degradation assessment using long short-term memory recurrent network, Computers in Industry, 106 (2019) 14–29.

    Article  Google Scholar 

  35. E. Mollasalehi, D. Wood and Q. Sun, Indicative fault diagnosis of wind turbine generator bearings using tower sound and vibration, Energies, 10 (11) (2017) 1853.

    Article  Google Scholar 

  36. Y. G. Lei, N. P. Li and L. Guo, Machinery health prognostics: A systematic review from data acquisition to RUL prediction, Mechanical Systems and Signal Processing, 104 (2018) 799–834.

    Article  Google Scholar 

  37. J. Tang, G. Zheng and D. He, Rolling bearing remaining useful life prediction via weight tracking relevance vector machine, Measurement Science and Technology, 32 (2) (2020) 024006.

    Article  Google Scholar 

  38. C. Luo, M. Jia and Y. Wen, The diagnosis approach for rolling bearing fault based on Kurtosis criterion EMD and Hilbert envelope spectrum, 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China (2017) 692–696.

Download references

Acknowledgments

This research was funded by the National Natural Science Foundation of China (grant number:51805151) and the Key Scientific Research Project of the University of Henan Province of China (grant number: 21B460004).

Author information

Authors and Affiliations

  1. School of Mechatronics Engineering, Hennan University of Science and Technology, Luoyang, 471003, China

    Yongshuai Zhu, Yanwei Xu, Shengbo Cao, Mengke Zhang, Junhua Wang, Tancheng Xie & Haichao Cai

  2. Intelligent Numerical Control Equipment Engineering Laboratory of Henan Province, Luoyang, 471003, China

    Yongshuai Zhu, Yanwei Xu, Shengbo Cao, Mengke Zhang & Tancheng Xie

Authors
  1. Yongshuai Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanwei Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shengbo Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mengke Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junhua Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tancheng Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Haichao Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yanwei Xu.

Additional information

Yanwei Xu received his Ph.D. degree from Tianjin University in 2010. He has been a Professor and an M.S. Supervisor with Henan University of Science and Technology. He is mainly engaged in research on bearing life prediction and fault diagnosis.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhu, Y., Xu, Y., Cao, S. et al. Prediction of remaining useful life of metro traction motor bearings based on DCCNN-GRU and multi-information fusion. J Mech Sci Technol 38, 2247–2264 (2024). https://doi.org/10.1007/s12206-024-0407-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-024-0407-3

Keywords

Search

Navigation