Authors : Innocent Mpia; Christian Lefi; Rodrick Kanku; Joseph Cimbela

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/48pef3us

Scribd : https://tinyurl.com/9wdmf353

DOI : https://doi.org/10.38124/ijisrt/26mar1181

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Many RUL estimation single models still have problems of low prediction accuracy while dealing with some nonstationary multivariate time series data, such as vibration signal from bearings degradation process. This paper aims to enhancing the prediction accuracy of the bearings remaining useful life from real vibration signals using LSTM model, by inserting SSA as preprocessing technique step in the predictive process of bearing RUL. The results of the study with femto Pronostia bearing dataset show a significant accuracy outperformance, through reduction of root mean square error (RMSE) and mean absolute error (MAE) performance metrics in majority of test data; up to 24.5% reduction with bearing1_3. The most interesting value reached is 74,7 % reduction, case of bearing 2_7. However, the model suffer from generalization over a certain number of data; case of bearing1_5. Thus several ways to leverage the prognosis model must be considered.

Keywords : SSA, REBs Prognosis, LSTM, RUL Estimation, Time Series, Feature Enhancement.

References :

1. T. Han, J. Pang, A.C.C. Tan, Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network, J. Manuf. Syst.  (2021).
2. Cheng C., Guijun M, Yong Z., Mingyang S., Fei Teng, Han D., and Ye Yuan. A deep learning-based remaining useful life prediction approach for bearings. August 2022
3. Bono F. M, Cinquemani S, Chatterton S, and Pennacchi P. A deep learning-based remaining useful life prediction approach for bearings. Jun 2022.
4. Junchuan Shi, Tianyu Yu, Kai Goebel, Dazhong Wu. Remaining Useful Life Prediction of       Bearings Using Ensemble Learning: The Impact of Diversity in Base Learners and   Features.Octobre 2020. Journal of Computing and Information Science in Engineering.
5. Tran Van Tung and Bo-Suk Yang. Machine Fault Diagnosis and Prognosis: The State of The Art. January 2009.
6. W. Ahmad, S. Ali Khan, M M Manjurul Islam, and Jong-Myon Kim1. A Reliable Technique for Remaining Useful Life (RUL) Estimation of Rolling Element Bearings using Dynamic Regression Models. 2017.
7. Aras Fırat Unal, Ali Yuce Kaleli,Emre Ummak, et Ozlem Albayrak. A Comparison of State-of-the-Art   Machine Learning Algorithms on Fault Indication and Remaining Useful Life Determination by Telemetry Data.2021. International Conference on Future Internet of Things and Cloud
8. R. V. Bhandare, S.P Mogal,V.M Phalle,P.B Kushare.  Fault Diagnosis and Prediction of Remaining Useful Life (RUL) of Rolling Element Bearing: A review state of art .2024
9. Ahmed Ayman, Ahmed Onsy, Omneya Attallah, Hadley Brooks, Iman Morsi. Feature learning for bearing prognostics: A comprehensive review of machine/deep learning methods, challenges, and opportunities. December 2024
10. Li, X.; Ding, Q., Sun, J.Q. Remaining useful life estimation in prognostics using deep convolution neuralnetworks. Reliability Engineering & System Safety. 2018.
11. Ma, J.; Su, H. Zhao, W.L. Liu, B. Predicting the remaining useful life of an aircraft engine using astacked sparse autoencoder with multilayer self-learning. Complexity. 2018.
12. Wu, Y.; Yuan, M.; Dong, S. Lin, L. Liu, Y. Remaininguseful life estimation of engineered systems using vanilla LSTM neural networks. Neurocomputing. 2018.
13. Miao Jiang, Yang Xiang, Longkui Zheng, Renjie Zhu. MULTI-FEATURE BASED LSTM ROLLING BEARING REMAINING USEFUL LIFE PREDICTION (2022)
14. Abdel Wahhab Lourari, Tarak Benkedjouh, Bilal El Yousfi. Advanced Pronostic Models for Bearing Heath: a Comparative Analysis of BiLSTM and ANFIS (2024)
15. Zhuo Li, Funa Zhou, Jiechen Sun. Missing Data Rolling Bearing Remaining Useful Life Prediction Fusion Autocorrélation and CrossCorrelation. Décembre 2023.
16. S. Dong, J. Xiao, X. Hu, N. Fang, L. Liu, J.Yao. Deep transfer learning based on Bi-LSTM and attention for remaining useful life prediction of rolling bearing. China 2023.
17. J. Li, Z. Wang, X. Liu and Z. Feng. Remaining Useful Life Prediction of Rolling Bearings Using GRU-DeepAR with Adaptive Failure Threshold. Janvier 2023. Applied sciences
18. Tian Han, Jiachen Pang, Andy C.C. Tan. Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network. https://doi.org/10.1016/j.jmsy.2021.10.011
19. Eyyup Akcan and Yilmaz Kaya (2023). A new approach for remaining useful life prediction of bearings using 1D-ternary patterns with LSTM
20. Salem, Fathi M. "Gated RNN: The Long Short-Term Memory (LSTM) RNN." In Recurrent Neural Networks, 71–82. Springer International
21. Rui Zhu, Mingxin Wang, Siyu Xu, Kai li, Qingpeng Han, Xin Tong and Keyuan He. Fault diagnosis of rolling bearing based on singular spectrum analysis and wide convolution kernel neural network.2022
22. Haobin Wen, Long Zhang and Jyoti K. Sinha. From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty. November 2024.
23. Nectoux, P.; Gouriveau, R.; Medjaher, K.; Ramasso, E.; Chebel-Morello, B.; Zerhouni, N. Varnier, C. PRONOSTIA: An experimental platform for bearings accelerated degradation tests. 2012.
24. Kilundu, B. Détection et diagnostic vibratoire de dégradations mécaniques : apport du data Mining. Faculté Polytechnique de Mons. 2008.
25. Kilundu, B. et Dehombreux, P. Analyse   Spectrale   Singulière   des   signaux   vibratoires   et Machine Learning pour la surveillance d’usure d’outils. Mons 2007.
26. B. Kilundu, X. Chiementin, P.Dehombreux. Singular Spectrum Analysis for Bearing Defect Detection. OCTOBER 2011, Vol. 133. DOI : 10.1115/1.4003938
27. W.Mao, J. He, J.Tang and Y.Li. Predicting remaining useful life of rolling bearings based on      deep feature representation and long short-term memory neural network. November 2018.
28. J. Zhanga, P. Wanga, R. Yanb, R. X. Gaoa. Long short-term memory for machine remaining life prediction. 2018
29. https://colah.github.io/posts/2015-08-Understanding-LSTMs/img/LSTM3-Single RNN.pgn.
30. Wei Hao, Zhixuan Li, Guohao Qin, Kun Ding, Xuwei Lai and Kai Zhang. A Novel Prediction Method Based on Bi-Channel Hierarchical Vision Transformer for Rolling Bearings’ Remaining Useful Life. Avril 2023.