SpringerLink
Log in

Vibration-based anomaly pattern mining for remaining useful life (RUL) prediction in bearings

  • Technical Paper
  • Published:
Journal of the Brazilian Society of Mechanical Sciences and Engineering Aims and scope Submit manuscript

Abstract

Predicting the remaining useful life (RUL) of bearings is critical in ensuring rotating machinery’s reliability and maintenance efficiency. Most of the research in this domain focuses on the fault prognosis of bearings without proper investigation of underlying fault feature pattern mining for degradation analysis. This paper investigates the remaining operational lifespan of bearings with an enhanced feature selection strategy and anomaly monitoring of bearing operational data. Specifically, four different models, namely Bi-LSTM, CNN-LSTM, Conv_LSTM, and encoder-decoder LSTM, are utilized to capture complex temporal dependencies and spatial correlations in the bearing sensor data. In the first stage, various feature selection techniques are engaged to select degradation trend monitoring features over time-domain and frequency-domain analysis. Next, anomaly pattern mining techniques are employed to identify abnormal behavior in the data, a crucial input for the subsequent RUL forecasting models. The anomaly patterns are extracted using unsupervised learning methods such as clustering or autoencoders, enabling the detection of early signs of degradation. Subsequently, the RUL forecasting is performed using four deep learning architectures. The performance of the suggested technique is evaluated using a comprehensive dataset of sensor measurements from bearings, which includes the corresponding remaining useful life (RUL) values. The experimental findings demonstrate that the proposed models demonstrate high accuracy in correctly determining the RUL of bearings. This solution offers proactive and cost-effective maintenance procedures by employing advanced deep learning models and anomalous pattern mining techniques, resulting in increased reliability, reduced downtime, and optimized resource allocation.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Germany)

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
Fig. 12

Similar content being viewed by others

References

  1. Unal P et al (2022) Data-driven artificial intelligence and predictive analytics for the maintenance of industrial machinery with hybrid and cognitive digital twins. Technol Appl Big Data Value. https://doi.org/10.1007/978-3-030-78307-5_14

    Article  Google Scholar 

  2. Gawde S, Patil S, Kumar S, Kotecha K (2022) A sco** review on multi-fault diagnosis of industrial rotating machines using multi-sensor data fusion. Artif Intell Rev 2022:1–54. https://doi.org/10.1007/S10462-022-10243-Z

    Article  Google Scholar 

  3. Chen J, Huang R, Chen Z, Mao W, Li W (2023) Transfer learning algorithms for bearing remaining useful life prediction: a comprehensive review from an industrial application perspective. Mech Syst Signal Process 193:110239. https://doi.org/10.1016/J.YMSSP.2023.110239

    Article  Google Scholar 

  4. Wang Y, Wang Y (2023) A denoising semi-supervised deep learning model for remaining useful life prediction of turbofan engine degradation. Appl Intell 53(19):22682–22699. https://doi.org/10.1007/S10489-023-04777-0/METRICS

    Article  Google Scholar 

  5. Gawde S, Patil S, Kumar S, Kamat P, Kotecha K, Abraham A (2023) Multi-fault diagnosis of industrial rotating machines using data-driven approach: a review of two decades of research. Eng Appl Artif Intell 123:106139. https://doi.org/10.1016/J.ENGAPPAI.2023.106139

    Article  Google Scholar 

  6. Akcan E, Kaya Y (2023) A new approach for remaining useful life prediction of bearings using 1D-ternary patterns with LSTM. J Braz Soc Mech Sci Eng 45(7):1–16. https://doi.org/10.1007/S40430-023-04309-4/METRICS

    Article  Google Scholar 

  7. Liu Y, Fan K (2023) Roller bearing fault diagnosis using deep transfer learning and adaptive weighting. J Phys Conf Ser 2467(1):012011. https://doi.org/10.1088/1742-6596/2467/1/012011

    Article  Google Scholar 

  8. Liu Y, **ang H, Jiang Z, **ang J (2023) A domain adaption resnet model to detect faults in roller bearings using vibro-acoustic data. Sensors 23(6):3068. https://doi.org/10.3390/S23063068

    Article  Google Scholar 

  9. Sayyad S, Kumar S, Bongale A, Kamat P, Patil S, Kotecha K (2021) Data-driven remaining useful life estimation for milling process: sensors, algorithms, datasets, and future directions. IEEE Access 9:110255–110286. https://doi.org/10.1109/ACCESS.2021.3101284

    Article  Google Scholar 

  10. Zhang Y, Sun J, Zhang J, Shen H, She Y, Chang Y (2023) Health state assessment of bearing with feature enhancement and prediction error compensation strategy. Mech Syst Signal Process 182:109573. https://doi.org/10.1016/J.YMSSP.2022.109573

    Article  Google Scholar 

  11. He D et al (2023) Remaining useful life prediction for train bearing based on ILSTM network with adaptive hyperparameter optimization. Transp Saf Environ. https://doi.org/10.1093/TSE/TDAD021

    Article  Google Scholar 

  12. Lu W, Wang Y, Zhang M, Gu J (2024) Physics guided neural network: remaining useful life prediction of rolling bearings using long short-term memory network through dynamic weighting of degradation process. Eng Appl Artif Intell 127:107350. https://doi.org/10.1016/J.ENGAPPAI.2023.107350

    Article  Google Scholar 

  13. Lui YH et al (2021) Physics-based prognostics of implantable-grade lithium-ion battery for remaining useful life prediction. J Power Sources 485:229327. https://doi.org/10.1016/J.JPOWSOUR.2020.229327

    Article  Google Scholar 

  14. Karatzinis GD, Apostolikas NA, Boutalis YS, Papakostas GA (2023) Fuzzy cognitive networks in diverse applications using hybrid representative structures. Int J Fuzzy Syst 25(7):2534–2554. https://doi.org/10.1007/S40815-023-01564-4/FIGURES/14

    Article  Google Scholar 

  15. Wang G, **ang J (2021) Remain useful life prediction of rolling bearings based on exponential model optimized by gradient method. Measurement 176:109161. https://doi.org/10.1016/J.MEASUREMENT.2021.109161

    Article  Google Scholar 

  16. Du X, Jia W, Yu P, Shi Y, Gong B (2023) RUL prediction based on GAM–CNN for rotating machinery. J Braz Soc Mech Sci Eng 45(3):1–22. https://doi.org/10.1007/S40430-023-04062-8/METRICS

    Article  Google Scholar 

  17. Lin T, Wang H, Guo X, Wang P, Song L (2023) A novel prediction network for remaining useful life of rotating machinery. Int J Adv Manuf Technol 124(11–12):4009–4018. https://doi.org/10.1007/S00170-021-08351-1/METRICS

    Article  Google Scholar 

  18. Sayyad S, Kumar S, Bongale A, Kotecha K, Selvachandran G, Suganthan PN (2022) Tool wear prediction using long short-term memory variants and hybrid feature selection techniques. Int J Adv Manuf Technol 121(9):6611–6633. https://doi.org/10.1007/S00170-022-09784-Y

    Article  Google Scholar 

  19. Yang X, Zheng Y, Zhang Y, Wong DSH, Yang W (2022) Bearing remaining useful life prediction based on regression shapalet and graph neural network. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2022.3151169

    Article  Google Scholar 

  20. Ren L, Zhao L, Hong S, Zhao S, Wang H, Zhang L (2018) Remaining useful life prediction for lithium-ion battery: a deep learning approach. IEEE Access 6:50587–50598. https://doi.org/10.1109/ACCESS.2018.2858856

    Article  Google Scholar 

  21. Soualhi A, Medjaher K, Zerhouni N (2015) Bearing health monitoring based on hilbert-huang transform, support vector machine, and regression. IEEE Trans Instrum Meas 64(1):52–62. https://doi.org/10.1109/TIM.2014.2330494

    Article  Google Scholar 

  22. Zhu J, Chen N, Shen C (2020) A new data-driven transferable remaining useful life prediction approach for bearing under different working conditions. Mech Syst Signal Process 139:106602. https://doi.org/10.1016/J.YMSSP.2019.106602

    Article  Google Scholar 

  23. Gao T, Li Y, Huang X, Wang C (2021) Data-driven method for predicting remaining useful life of bearing based on bayesian theory. Sensors 21(1):182. https://doi.org/10.3390/S21010182

    Article  Google Scholar 

  24. Vos K, Peng Z, Jenkins C, Shahriar MR, Borghesani P, Wang W (2022) Vibration-based anomaly detection using LSTM/SVM approaches. Mech Syst Signal Process 169:108752. https://doi.org/10.1016/J.YMSSP.2021.108752

    Article  Google Scholar 

  25. Mao W, Shi H, Wang G, Liang X (2022) Unsupervised deep multitask anomaly detection with robust alarm strategy for online evaluation of bearing early fault occurrence. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2022.3200092

    Article  Google Scholar 

  26. Liu Y et al (2022) The detection of generator bearing failures on wind turbines using machine learning based anomaly detection A direction of arrival estimation method based on deep learning The Science of Making Torque from Wind ( The detection of generator bearing failures on wind turbines using machine learning based anomaly detection. J Phy Conf Series 2265:32066. https://doi.org/10.1088/1742-6596/2265/3/032066

    Article  Google Scholar 

  27. Lei Y, Li C, Gao H, Guo L, Liang J, He J (2022) Research on quantitative monitoring method of milling tool wear condition based on multi-source data feature learning and extraction. Global Reliab Progn Health Manag Conf PHM-Yantai. https://doi.org/10.1109/PHM-YANTAI55411.2022.9942215

    Article  Google Scholar 

  28. P Nectoux et al. 2012 PRONOSTIA: An experimental platform for bearings accelerated degradation tests. IEEE International Conference on Prognostics and Health Management, PHM’12 Denver Col- orado United States 1–8

  29. He K, Su Z, Tian X, Yu H, Luo M (2022) RUL prediction of wind turbine gearbox bearings based on self-calibration temporal convolutional network. IEEE Trans Instrum Meas. https://doi.org/10.1109/TIM.2022.3143881

    Article  Google Scholar 

  30. **a J, Feng Y, Lu C, Fei C, Xue X (2021) LSTM-based multi-layer self-attention method for remaining useful life estimation of mechanical systems. Eng Fail Anal 125:105385. https://doi.org/10.1016/J.ENGFAILANAL.2021.105385

    Article  Google Scholar 

  31. QRS Fitni, K Ramli, 2020 Implementation of ensemble learning and feature selection for performance improvements in anomaly-based intrusion detection systems. In: Proceedings—2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 118–124 doi: https://doi.org/10.1109/IAICT50021.2020.9172014

  32. Jebadurai IJ, Paulraj GJL, Jebadurai J, Silas S (2022) Experimental analysis of filtering-based feature selection techniques for fetal health classification. Serb J Electr Eng 19(2):207–224. https://doi.org/10.2298/SJEE2202207J

    Article  Google Scholar 

  33. Luo M et al (2021) Combination of feature selection and CatBoost for prediction: the first application to the estimation of aboveground biomass. Forests 12(2):216. https://doi.org/10.3390/F12020216

    Article  Google Scholar 

  34. Elsayed MS, Le-Khac NA, Dev S, Jurcut AD, 2020 Network anomaly detection using LSTM Based autoencoder. Q2SWinet 2020—In: Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks 37–45 doi: https://doi.org/10.1145/3416013.3426457

  35. Yin C, Zhang S, Wang J, **ong NN (2022) Anomaly detection based on convolutional recurrent autoencoder for IoT time series. IEEE Trans Syst Man Cybern Syst 52(1):112–122. https://doi.org/10.1109/TSMC.2020.2968516

    Article  Google Scholar 

  36. Cao Y, Ding Y, Jia M, Tian R (2021) A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings. Reliab Eng Syst Saf 215:107813. https://doi.org/10.1016/J.RESS.2021.107813

    Article  Google Scholar 

  37. Heimes FO (2008) Recurrent neural networks for remaining useful life estimation. Int Conf Progn Health Manag. https://doi.org/10.1109/PHM.2008.4711422

    Article  Google Scholar 

  38. Kong Z, ** X, Xu Z, Chen Z (2023) A contrastive learning framework enhanced by unlabeled samples for remaining useful life prediction. Reliab Eng Syst Saf 234:109163. https://doi.org/10.1016/J.RESS.2023.109163

    Article  Google Scholar 

  39. F Rayhan et al. 2023 A bi-directional temporal sequence approach for condition monitoring of broken rotor bar in three-phase induction motors. 3rd International Conference on Electrical, Computer and Communication Engineering doi: https://doi.org/10.1109/ECCE57851.2023.10101518

  40. Zhu C et al (2023) State of health prediction for li-ion batteries with end-to-end deep learning. J Energy Storage 65:107218. https://doi.org/10.1016/J.EST.2023.107218

    Article  Google Scholar 

  41. Peng Y, Chen T, **ao F, Zhang S (2023) Remaining useful lifetime prediction methods of proton exchange membrane fuel cell based on convolutional neural network-long short-term memory and convolutional neural network-bidirectional long short-term memory. Fuel Cells 23(1):75–87. https://doi.org/10.1002/FUCE.202200106

    Article  Google Scholar 

  42. Zhang C, Chen P, Jiang F, **e J, Yu T (2023) Fault diagnosis of nuclear power plant based on sparrow search algorithm optimized CNN-LSTM neural network. Energies 16(6):2934. https://doi.org/10.3390/EN16062934

    Article  Google Scholar 

  43. Szarek D, Jabłoński I, Zimroz R, Wyłomańska A (2023) Non-Gaussian feature distribution forecasting based on ConvLSTM neural network and its application to robust machine condition prognosis. Expert Syst Appl 230:120588. https://doi.org/10.1016/J.ESWA.2023.120588

    Article  Google Scholar 

  44. Zhu G, Zhu Z, **ang L, Hu A, Xu Y (2023) Prediction of bearing remaining useful life based on DACN-ConvLSTM model. Measurement 211:112600. https://doi.org/10.1016/J.MEASUREMENT.2023.112600

    Article  Google Scholar 

  45. Zuo T et al (2023) A hybrid attention-based multi-wavelet coefficient fusion method in RUL prognosis of rolling bearings. Reliab Eng Syst Saf 237:109337. https://doi.org/10.1016/J.RESS.2023.109337

    Article  Google Scholar 

  46. Liu Y, Young R, Jafarpour B (2023) Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes. J Process Control 124:166–178. https://doi.org/10.1016/J.JPROCONT.2023.01.015

    Article  Google Scholar 

  47. Dang W et al (2023) An encoder-decoder fusion battery life prediction method based on Gaussian process regression and improvement. J Energy Storage 59:106469. https://doi.org/10.1016/J.EST.2022.106469

    Article  Google Scholar 

  48. ** X, Sun Y, Que Z, Wang Y, Chow TWS (2016) Anomaly detection and fault prognosis for bearings. IEEE Trans Instrum Meas 65(9):2046–2054. https://doi.org/10.1109/TIM.2016.2570398

    Article  Google Scholar 

  49. Li X, Zhang W, Ding Q (2019) Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction. Reliab Eng Syst Saf 182:208–218. https://doi.org/10.1016/J.RESS.2018.11.011

    Article  Google Scholar 

Download references

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115, India

    Pooja Kamat & Satish Kumar

  2. Symbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University), Pune, 412115, India

    Satish Kumar

  3. School of Computing, MIT Art, Design and Technology University, Pune, India

    Rekha Sugandhi

Authors
  1. Pooja Kamat
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Satish Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rekha Sugandhi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by Pooja Kamat, Satish Kumar, and Rekha Sugandhi. The first draft of the manuscript was written by Pooja Kamat, Satish Kumar, and Rekha Sugandhi, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Pooja Kamat.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Consent for publication

This manuscript is the authors’ original work and has not been published elsewhere. All authors have checked the manuscript and have agreed to this submission.

Additional information

Technical Editor: Jarir Mahfoud.

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

Kamat, P., Kumar, S. & Sugandhi, R. Vibration-based anomaly pattern mining for remaining useful life (RUL) prediction in bearings. J Braz. Soc. Mech. Sci. Eng. 46, 290 (2024). https://doi.org/10.1007/s40430-024-04872-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s40430-024-04872-4

Keywords

Search

Navigation