Estimating the Remaining Useful Life of Bearings Using Weibull Function Fitting on IMF

Document Type : Research Article

Authors

Faculty of Mechanical Engineering, University of Tabriz, Tabriz, Iran

Abstract

This study proposes a robust methodology for accurately estimating the Remaining Useful Life (RUL) of ball bearings in rotary machinery, which are critical components in many industrial systems. The approach utilizes vibration signal analysis, specifically Empirical Mode Decomposition (EMD), to extract meaningful features. Among the decomposed Intrinsic Mode Functions (IMFs), the one with the highest energy is selected to represent the degradation process. The variance of this selected IMF is modeled using a Weibull distribution to reflect the trend of failure progression. Subsequently, a neural network, particularly the Simplified Fuzzy ARTMAP (SFAM), is trained to predict the remaining life based on the fitted Weibull trend. Finally, exponential smoothing is employed to enhance prediction stability. Experimental results validate the method’s effectiveness in tracking degradation and provide accurate RUL estimates under various conditions.

Keywords

Main Subjects

References

[1] C. Ferreira, G. Gonçalves, Remaining Useful Life prediction and challenges: A literature review on the use of Machine Learning Methods, Journal of Manufacturing Systems, 63 (2022) 550-562.
[2] S. Ramezani, A. Moini, M. Riahi, Prognostics and health management in machinery: A review of methodologies for RUL prediction and roadmap, International Journal of Industrial Engineering and Management Science, 6(1) (2019) 38-61.
[3] N. Kumar, R. Satapathy, Bearings in aerospace, application, distress, and life: a review, Journal of Failure Analysis and Prevention, 23(3) (2023) 915-947.
[4] L. Liao, Discovering prognostic features using genetic programming in remaining useful life prediction, IEEE Transactions on Industrial Electronics, 61(5) (2013) 2464-2472.
[5] T. Benkedjouh, K. Medjaher, N. Zerhouni, S. Rechak, Remaining useful life estimation based on nonlinear feature reduction and support vector regression, Engineering Applications of Artificial Intelligence, 26(7) (2013) 1751-1760.
[6] X.-l. Wang, H. Gu, L. Xu, C. Hu, H. Guo, A SVR-based remaining life prediction for rolling element bearings, Journal of Failure Analysis and Prevention, 15(4) (2015) 548-554.
[7] J. Zhang, P. Wang, R. Yan, R.X. Gao, Long short-term memory for machine remaining life prediction, Journal of manufacturing systems, 48 (2018) 78-86.
[8] A.Z. Hinchi, M. Tkiouat, Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network, Procedia Computer Science, 127 (2018) 123-132.
[9] J.B. Ali, B. Chebel-Morello, L. Saidi, S. Malinowski, F. Fnaiech, Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network, Mechanical Systems and Signal Processing, 56 (2015) 150-172.
[10] N. Zhang, L. Wu, Z. Wang, Y. Guan, Bearing remaining useful life prediction based on Naive Bayes and Weibull distributions, Entropy, 20(12) (2018) 944.
[11] N.E. Huang, N.O. Attoh-Okine, The Hilbert-Huang transform in engineering, CRC Press, 2005.
[12] N.E. Huang, S.S. Shen (Eds.), Introduction to the Hilbert-Huang Transform and Its Related Mathematical Problems, World Scientific, Singapore, 2005.
[13] M.Y. Asr, M.M. Ettefagh, R. Hassannejad, S.N. Razavi, Diagnosis of combined faults in rotary machinery by Non-Naive Bayesian approach, Mechanical Systems and Signal Processing, 85 (2017) 56–70.[14] P. Wang, Z. Long, G. Wang, A hybrid prognostics approach for estimating remaining useful life of wind turbine bearings, Energy Reports, 6 (2020) 173-182.
[15] B. Wang, Y. Lei, N. Li, N. Li, A hybrid prognostics approach for estimating remaining useful life of rolling element bearings, IEEE Transactions on Reliability, 69(1) (2018) 401-412.
[16] P. Banker, Simplified Fuzzy ARTMAP, Proceedings of the International Conference on Artificial Intelligence and Machine Learning, 2021, pp. 123–130.
Amirkabir Journal of Mechanical Engineering
Volume 57, Issue 1
2025
Pages 105-122

Files

Share

How to cite

Statistics