Skip to main content
SpringerLink
Log in

Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications

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

Abstract

Research studies on data-driven approaches to rotating components and rolling element bearing (REB) prognostics have recently witnessed a rapid increase. These data-driven methods rely on sensor data for condition monitoring and degradation assessments; however, the problem of mining features from these sophisticated data using appropriate intelligent methods and choosing a practically reliable predictive model(s) has become a global concern. Vibration monitoring for REBs have over the years shown great effectiveness. Although monotonic statistical features serve as reliable health indicators (HIs), relying on a single feature for optimal bearing degradation assessment is inefficient. By fusing highly monotonic features using appropriate methods, a more reliable HI can be constructed and from this, various degradation states/stages and time to start prediction (TSP) can be identified by mapping known failure modes/degradation states to cluster points from clustering algorithms. Emphatically, the choice of regression algorithms for prognostics poses more concern as engineers and data scientists are faced with choosing between Bayessian machine learning (ML) and deep learning (DL) methods. This study presents a methodology for constructing a reliable HI for bearing prognostics, choosing a reliable TSP, and provides a comparison between ML and DL methods for bearing prognostics. As representatives of both domains, the Gaussian process regression (GPR) and the deep belief network (DBN) are introduced and compared. The results provide a reliable paradigm for prognosible feature representation for REBs and for choosing between both domains while considering their dependencies, efficiencies, and deficiencies.

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. C. Huang, H. Huang, W. Peng and T. Huang, Improved trajectory similarity-based approach for turbofan engine prognostics, J. Mech. Sci. Technol., 33 (2019) 4877–4890.

    Article  Google Scholar 

  2. J. Markoff, Giant steps in teaching computers to think like us: ‘neural nets’ mimic the ways human minds listen, see and execute, International Herald Tribune, 24–5 (2012) 1–8.

    Google Scholar 

  3. Y. Gu, X. Zhou, D. Yu and Y. Shen, Fault diagnosis method of rolling bearing using principal component analysis and support vector machine, J. Mech. Sci. Technol., 32 (2018) 5079–5088.

    Article  Google Scholar 

  4. D. An, N. H. Kim and J. Choi, Statistical aspects in neural network for the purpose of prognostics, J. Mech. Sci. Technol., 29 (2015) 1369–1375.

    Article  Google Scholar 

  5. W. Sun, S. Shao and R. Zhao, A sparse auto-encoder-based deep neural network approach for induction motor faults classification, Measurement, 89 (2016) 171–178.

    Article  Google Scholar 

  6. J. W. Hur and U. E. Akpudo, A deep learning approach to prognostics of rolling element bearings, International Journal of Integrated Engineering, 12(3) (2020) 178–186.

    Google Scholar 

  7. J. B. Yu, Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models, Mech. Syst. Signal Process., 25 (2011) 2573–2588.

    Article  Google Scholar 

  8. K. McKee, G. Forbes, I. Mazhar, R. Entwistle and I. Howard, A review of major centrifugal pump failure modes with application to the water supply and sewerage industries, Asset Management Council (ed), ICOMS Asset Management Conference (2011).

  9. M. Hamadache et al., A comprehensive review of artificial intelligence-based approaches for rolling element bearing PHM: shallow and deep learning, Journal of Mechanical Science and Technology Adv., 1 (2019) 125–151.

    Google Scholar 

  10. C. Zhang, P. Lim, A. K. Qin and K. C. Tan, Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics, IEEE Transactions on Neural Networks and Learning Systems, 28(10) (2017) 2306–2318.

    Article  Google Scholar 

  11. D. Zhang, X. Han and C. Deng, Review on the research and practice of deep learning and reinforcement learning in smart grids, CSEE Journal of Power and Energy Systems, 4(3) (2018) 362–370.

    Article  Google Scholar 

  12. H. B. Mann, Nonparametric tests against trend, Econometrica: Journal of the Econometric Society (1945) 245–259.

  13. L. Duan, F. Zhao, J. Wang, N. Wang and J. Zhang, An integrated cumulative transformation and feature fusion approach for bearing degradation prognostics, Shock and Vibration (2018).

  14. U. E. Akpudo and J. W. Hur, A feature fusion-based prognostics approach for rolling element bearings, Journal of Mechanical Science and Technology, 34 (10) (2020).

  15. A. Klausen, H. Van Khang and K. G. Robbersmyr, Novel threshold calculations for remaining useful lifetime estimation of rolling element bearings, 2018 XIII International Conference on Electrical Machines (ICEM), Alexandroupoli (2018) 1912–1918.

  16. D. Wu, Q. Yang, F. Tian and D. X. Zhang, Fault diagnosis based on K-means clustering and PNN, 2010 Third International Conference on Intelligent Networks and Intelligent Systems, Shenyang (2010) 173–176.

  17. J. Shi, Q. He and Z. Wang, GMM clustering-based decision trees considering fault rate and cluster validity for analog circuit fault diagnosis, IEEE Access, 7 (2019) 140637–140650.

    Article  Google Scholar 

  18. P. Navaseelan and N. S. Bhuvaneswari, Fuzzy based fault detection and isolation of super heater faults in industrial boiler, 2017 IEEE International Conference on Technological Innovations in Communication, Control and Automation (TICCA), Chennai (2017) 25–30.

  19. C. Rasmussen, Gaussian processes in machine learning, Advanced Lectures on Machine Learning (2004) 63–71.

  20. P. L. T. Duong and N. Raghavan, Prognostic health management for LED with missing data: multi-task Gaussian process regression approach, 2018 Prognostics and System Health Management Conference (PHM-Chongqing), Chongqing (2018) 1182–1187.

  21. Y. Zhang, X. Peng, Y. Peng, J. Pang and D. Liu, Weighted bagging Gaussian process regression to predict remaining useful life of electro-mechanical actuator, 2016 Prognostics and System Health Management Conference (PHM-Chengdu), Chengdu (2016) 1–6.

  22. J. Liu and Z. Chen, Remaining useful life prediction of lithiumion batteries based on health indicator and Gaussian process regression model, IEEE Access, 7 (2019) 39474–39484.

    Article  Google Scholar 

  23. S. Hong and Z. Zhou, Application of Gaussian process regression for bearing degradation assessment, 2012 6th International Conference on New Trends in Information Science, Service Science and Data Mining (ISSDM2012), Taipei (2012) 644–648.

  24. C.-S. Lin, Y.-C. Huang, S.-H. Chen, Y.-L. Hsu and Y.-C. Lin, The application of deep learning and image processing technology in laser positioning, Appl. Sci., 8(9) (2018) 1542.

    Article  Google Scholar 

  25. P. Dhakal, P. Damacharla, A. Y. Javaid and V. Devabhaktuni, A near real-time automatic speaker recognition architecture for voice-based user interface, Mach. Learn. Knowl. Extr. (2019) 504–520.

  26. Z. Zhao, P. Zheng, S. Xu and X. Wu, Object detection with deep learning: a review, IEEE Transactions on Neural Networks and Learning Systems, 30(11) (2019) 3212–3232.

    Article  Google Scholar 

  27. Ö. Yildirim, P. Ptawiak, R. Tan and U. Acharya, Arrhythmia detection using deep convolutional neural network with long duration ECG signals, Computers in Biology and Medicine, 102 (2018) 411–420.

    Article  Google Scholar 

  28. W. Bao, J. Yue and Y. Rao, A deep learning framework for financial time series using stacked autoencoders and longshort term memory, PLoS ONE, 12 (2017).

  29. G. Salman, Y. Heryadi, E. Abdurahman and W. S. Uyili, Weather forecasting using merged long short-term memory model, Bulletin of Electrical Engineering and Informatics, 7(3) (2018) 377–385.

    Article  Google Scholar 

  30. G. Martínez-Arellano, G. Terrazas and S. Ratchev, Tool wear classification using time series imaging and deep learning, The International Journal of Advanced Manufacturing Technology, 104 (2019) 3647–3662.

    Article  Google Scholar 

  31. X. Wu, Y. Liu, X. Zhou and A. Mou, Automatic identification of tool wear based on convolutional neural network in face milling process, Sensors (Basel, Switzerland), 19(18) (2019) 3817.

    Article  Google Scholar 

  32. D. Ciobanu and M. Vasilescu, Advantages and disadvantages of using neural networks for predictions, Ovidius University Annals, Economic Sciences Series, 1 (2013) 444–449.

    Google Scholar 

  33. G. Zhao, X. Liu, B. Zhang, Y. Liu, G. Niu and C. Hu, A novel approach for analog circuit fault diagnosis based on deep belief network, Measurement, 121 (2018) 170–178.

    Article  Google Scholar 

  34. G. Salman, Y. Heryadi, E. Abdurahman and W. S. Uyili, Weather forecasting using merged long short-term memory model (LSTM) and autoregressive integrated moving average (ARIMA) model, Journal of Computer Science, 14(7) (2018) 930–938.

    Article  Google Scholar 

  35. I. Medennikov and B. Anna, LSTM-based language models for spontaneous speech recognition, International Conference on Speech and Computer (2016) 469–475.

  36. K. L. Tsui, N. Chen, Q. Zhou, Y. Hai and W. Wang, Prognostics and health management: a review on data driven approaches, Mathematical Problems in Engineering (2015) Article ID 79316.

  37. G. Zhao, X. Liu, B. Zhang, G. Zhang, G. Niu and C. Hu, Bearing health condition prediction using deep belief network, Annual Conference of the Prognostics and Health Management Society (2017).

  38. H. Jiang, H. Shao, X. Chen and J. Huang, Aircraft fault diagnosis based on deep belief network, 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), Shanghai (2017) 123–127.

  39. J. Deutsch and D. He, Using deep learning-based approach to predict remaining useful life of rotating components, IEEE Transactions on Systems, Man, and Cybernetics: Systems (2017) 1–10.

  40. G. Niu, B. Zhang, P. Ziehl, F. Ferrese and M. Golda, Rolling element bearing fault diagnosis based on deep belief network and principal component analysis, Proceedings of the Annual Conference of the PHM Society, 11 (1) (2019).

  41. Q. Sun, Y. Wang, Y. Jiang, L. Shao and D. Chen, Fault diagnosis diagnosis of SEPIC converters based on PSO-DBN and wavelet packet energy spectrum, 2017 Prognostics and System Health Management Conference (PHM-Harbin), Harbin (2017) 1–7.

  42. Z. Chiba, N. Abghour, K. Moussaid, A. E. Omri and M. Rida, A clever approach to develop an efficient deep neural network based IDS for cloud environments using a self-adaptive genetic algorithm, 2019 International Conference on Advanced Communication Technologies and Networking (CommNet), Rabat, Morocco (2019) 1–9.

  43. A. Saxena et al., Metrics for evaluating performance of prognostic techniques, 2008 International Conference on Prognostics and Health Management, Denver, CO (2008) 1–17.

  44. H. Qiu, J. Lee and J. Lin, Wavelet filter-based weak signature detection method and its application on roller bearing prognostics, Journal of Sound and Vibration, 289 (2006) 1066–1090.

    Article  Google Scholar 

  45. J. Lee, H. Qiu, G. Yu and J. Lin, Rexnord technical services, IMS, University of Cincinnati, Bearing Data Set, NASA Ames Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA (2007).

    Google Scholar 

Download references

Acknowledgments

This article is based on the results of a study conducted with the support of the Agency for Defense Development (RAM specialized laboratory, UD180018AD).

Author information

Authors and Affiliations

  1. Department of Mechanical Systems Engineering, Kumoh National Institute of Technology, 61 Daehak-ro (yangho-dong), Gumi, Gyeongbuk, 39177, Korea

    Ugochukwu Ejike Akpudo & Jang-Wook Hur

Authors
  1. Ugochukwu Ejike Akpudo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jang-Wook Hur
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jang-Wook Hur.

Additional information

Ugochukwu Ejike Akpudo received his B.Eng. degree in Mechanical and Production Engineering at Enugu State University of Science and Technology, Nigeria in 2012. While working at Maclisle Complex Limited, Enugu, Nigeria from 2015 to 2019, he familiarized himself with a wide variety of efficient and effective ways of mechanical systems maintainability, general safety engineering, reliability engineering, and loss prevention. Currently he is a graduate student and full-time researcher at Defence Reliability Laboratory, Mechanical Systems Engineering at Kumoh National Institute of Technology Gumi, South Korea. His research interests include but not limited to prognostics and health management and reliability engineering.

Jang-Wook Hur received his Ph.D. degree in Mechanical Engineering from Tokyo Institute of Technology, Japan, in 1995. While serving in the Republic of Korea National Military, he, in 2011 ranked a Colonel and took part in various projects funded by the Korean Government like the DAPA KHP Project. From 2015 to 2020, he led the project team in the RAM program aimed at optimizing Reliability, Availability, and Maintainability in the Korean Defense Systems. He is currently the H.O.D. Mechanical Systems Engineering and the Director of Defense Reliability Laboratory (an Advanced Research Center supported by the Korean Government) at Kumoh National University of Science and Technology. He is currently the Vice President of the Korean Society for Prognostics and Health Management (KSPHM). His research interests are prognostics and health management and reliability engineering.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Akpudo, U.E., Hur, JW. Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications. J Mech Sci Technol 34, 4161–4172 (2020). https://doi.org/10.1007/s12206-020-0908-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-020-0908-7

Keywords

Search

Navigation