Abstract
Fault in rolling element bearings is a very common fault in mechanical systems. It may lead to abnormal operation of equipment, even to serious accidents or significant losses. Periodical monitoring of bearings plays a vital role in reducing unplanned maintenance and improving the reliability of machines. However, the existing methods for determining faults in rolling element bearings introduce too many artificial factors, and the results are often subjective. In order to solve this problem, the present paper proposes a hybrid real-time method for determining the starting time of a fault in a rolling element bearing. Based on the dynamic 3σ interval and voting mechanism, our method can adaptively predict the starting time. Firstly, the long short-term memory (LSTM) neural network is used to predict the trend of the future operation of the bearing. Then, an exponential model is used to estimate its remaining useful life (RUL). The obtained experimental results show that the proposed approach can significantly reduce artificial interference, adaptively divide the state of rolling element bearings, and accurately predict RUL.
Similar content being viewed by others
References
Tian Z (2012) An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring [J]. J Intell Manuf 23(2):227–237
Malhi A, Yan R, Gao RX (2011) Prognosis of defect propagation based on recurrent neural networks [J]. IEEE Trans Instrum Meas 60(3):703–711
Liao H, Tian Z (2013) A framework for predicting the remaining useful life of a single unit under time-varying operating conditions [J]. IIE Trans 45(9):964–980
Li N, Lei Y, Lin J et al (2015) An improved exponential model for predicting remaining useful life of rolling element bearings [J]. IEEE Trans Industr Electron 62(12):7762–7773
Qian Y, Yan R (2014) Bearing degradation evaluation using recurrence quantification analysis and Kalman filter [J]. IEEE Trans Instrum Meas 63(11):2599–2610
Shao H, Jiang H, Li X et al (2018) Rolling bearing fault detection using continuous deep belief network with locally linear embedding [J]. Comput Ind 96:27–39
Ahmad W, Khan SA, Islam MM et al (2019) A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models [J], vol 184. Reliability Engineering & System Safety, pp 67–76
Heng A, Zhang S, Tan AC et al (2009) Rotating machinery prognostics: state of the art, challenges and opportunities [J]. Mech Syst Signal Process 23(3):724–739
Tian Z, Liao H (2011) Condition based maintenance optimization for multi-component systems using proportional hazards model [J]. Reliab Eng Syst Saf 96(5):581–589
Liao L (2013) Discovering prognostic features using genetic programming in remaining useful life prediction [J]. IEEE Trans Ind Electron 61(5):2464–72
Gebraeel NZ, Lawley MA, Li R et al (2005) Residual-life distributions from component degradation signals: a bayesian approach [J]. IIE Trans 37(6):543–557
Shao Y, Nezu K (2000) Prognosis of remaining bearing life using neural networks [J]. Proc Inst Mech Eng Part I J Syst Control Eng 214(3):217–30
Moghaddass R, Zuo MJ (2012) A parameter estimation method for a condition-monitored device under multi-state deterioration [J]. Reliab Eng Syst Saf 106:94–103
Lee J (1996) Measurement of machine performance degradation using a neural network model [J]. Comput Ind 30(3):193–209
Gebraeel N, Lawley M, Liu R et al (2004) Residual life predictions from vibration-based degradation signals: a neural network approach [J]. IEEE Trans Industr Electron 51(3):694–700
Javed K, Gauriveau R, Zerhouni N et al (2014) Enabling health monitoring approach based on vibration data for accurate prognostics [J]. IEEE Trans Industr Electron 62(1):647–656
Sikorska JZ, Hodkiewicz M (2011) Prognostic modelling options for remaining useful life estimation by industry [J]. Mech Syst Signal Process 25(5):1803–1836
Elsheikh A, Yacout S, Ouali M-S (2019) Bidirectional handshaking LSTM for remaining useful life prediction [J]. Neurocomputing 323:148–156
Hochreiter S, Schmidhuber J (1997) Long short-term memory [J]. Neural Comput 9(8):1735–1780
Yuan M, Wu Y, Lin L (2016) Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. In: proceedings of the 2016 IEEE international conference on aircraft utility systems (AUS), F. IEEE
Zheng S, Ristovski K, Farahat A et al (2017) [C] Long short-term memory network for remaining useful life estimation. In: Proceedings of the 2017 IEEE international conference on prognostics and health management (ICPHM), F. IEEE
Chen Z, Wu M, Zhao R et al (2020) Machine remaining useful life prediction via an attention-based deep learning approach [J]. IEEE Trans Industr Electron 68(3):2521–2531
Plank B, Søgaard A, Goldberg Y (2016) Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss [J]. arXiv preprint arXiv:160405529
Zhao R, Yan R, Wang J et al (2017) Learning to monitor machine health with convolutional bi-directional LSTM networks [J]. Sensors 17(2):273
Yu W, Kim IY, Mechefske C (2019) Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme [J]. Mech Syst Signal Process 129:764–780
Song JW, Park YI, Hong J-J, Systems F et al (2021) [C] IEEE
Jin R, Chen Z, Wu K et al (2022) Bi-LSTM-Based Two-Stream Network for machine remaining useful life prediction [J]. IEEE Trans Instrum Meas 71:1–10
Wang B, Lei Y, Li N et al (2018) A hybrid prognostics approach for estimating remaining useful life of rolling element bearings [J]. IEEE Trans Reliab 69(1):401–412
Lei Y, He Z, Zi Y et al (2007) Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs [J]. Mech Syst Signal Process 21(5):2280–2294
Grafarend EW (2006) Linear and nonlinear models: fixed effects, random effects, and mixed models [J]. Walter De Gruyter
Vysochanskij D, Petunin YI (1980) Justification of the 3σ rule for unimodal distributions [J]. Theory Prob Math Stat 21:25–36
PUKELSHEIM F (1994) The three sigma rule [J]. Am Stat 48(2):88–91
ZHOU Z-H (2021) Machine learning [M]. Springer Nature
SMAGULOVA K (2019) JAMES A P. A survey on LSTM memristive neural network architectures and applications [J]. Eur Phys J Special Top 228(10):2313–2324
GOLDBERG Y (2016) A primer on neural network models for natural language processing [J]. J Artif Intell Res 57:345–420
Jin X, Sun Y, Que Z et al (2016) Anomaly detection and fault prognosis for bearings [J]. IEEE Trans Instrum Meas 65(9):2046–2054
Lawson CL, Hanson RJ (1995) Solving least squares problems [M]. SIAM
Qiu H, Lee J, Lin J et al (2006) Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics [J]. J Sound Vib 289(4–5):1066–1090
Coble JB (2010) Merging data sources to predict remaining useful life–an automated method to identify prognostic parameters [J].
Wang H, Li M (2021) Comput Electr Eng 92:107156YUE X. IncLSTM: incremental ensemble LSTM model towards time series data [J]
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (Grants 61976141 and 51807124), in part by the State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures of Shijiazhuang Tiedao University (Grant KF2022-10).
Author information
Authors and Affiliations
Corresponding author
Additional information
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.
About this article
Cite this article
Liu, J., Hao, R., Liu, Q. et al. Prediction of remaining useful life of rolling element bearings based on LSTM and exponential model. Int. J. Mach. Learn. & Cyber. 14, 1567–1578 (2023). https://doi.org/10.1007/s13042-023-01807-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01807-8