Abstract
A residual life prediction method based on the long short-term memory (LSTM) was proposed for remaining useful life (RUL) prediction in this paper. Firstly, feature parameters were extracted from time domain, frequency domain, time–frequency domain and related-similarity features; then three feature evaluation indicators were defined to select feature parameters that could better represent the degradation process of bearings and constructed the feature set with the time factor. The data of the feature set was used to train the LSTM network prediction model, and then the RUL was predicted by the trained neural network. The full life test of rolling bearing was provided to demonstrate that this method could accurately predict the remaining life of the rolling bearing, and the result was compared with the prediction results of BP neural network and support vector regression machine to verify the effectiveness.
Similar content being viewed by others
References
Qiu H, Lee J, Lin J et al (2003) Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Adv Eng Inform 17(3):127–140
Gebraeel N, Lawley M, Liu R et al (2004) Residual life predictions from vibration-based degradation signals: a neural network approach. IEEE Trans Ind Electron 51(3):694–700
Liu J, Wang W, Ma F et al (2012) A data-model-fusion prognostic framework for dynamic system state forecasting. Eng Appl Artif Intell 25(4):814–823
Luo Y, Luo Y, Liu J et al (2014) Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm. Neural Comput Appl 25(3–4):557–572
Li N, Lei Y, Lin J et al (2015) An improved exponential model for predicting remaining useful life of rolling element bearings. IEEE Trans Ind Electron 62(12):7762–7773
Ding F, He Z, Zi Y et al (2009) Reliability assessment based on equipment condition vibration feature using proportional hazards model. Chin J Mech Eng 45(12):89–94
Wang F, Chen X, Dun B et al (2017) Rolling bearing reliability assessment via kernel principal component analysis and Weibull proportional hazard model. Shock Vib 2017:1–11
Tamilselvan P, Wang P (2013) Failure diagnosis using deep belief learning based health state classification. Reliab Eng Syst Saf 115(7):124–135
Li C, Zurita G, Cerrada M et al (2015) Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis. Neurocomputing 168(C):119–127
Guo L, Li N, Jia F et al (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing 240(3):98–109
Cipollini F et al (2018) Unintrusive monitoring of induction motors bearings via deep learning on stator currents. In: INNS international conference on big data and deep learning (INNS BDDL)
Lifeng XI (2007) Residual life predictions for ball bearing based on neural networks. Chin J Mech Eng 43(10):137–143
Shao Y, Nezu K (2000) Prognosis of remaining bearing life using neural networks. Proc Inst Mech Eng Part I 214(3):217–230
Ali JB, Chebel-Morello B, Saidi L et al (2015) Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mech Syst Signal Process 56–57:150–172
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 Sound Vib 289(4):1066–1090
Zhang B, Zhang L, Xu J (2016) Degradation feature selection for remaining useful life prediction of rolling element bearings. Qual Reliab Eng Int 32(2):547–554
Wang F, Sun J, Yan D et al (2015) A feature extraction method for fault classification of rolling bearing based on PCA. J Phys: Conf Ser 628:012079
Su W, Wang F, Zhu H et al (2011) Feature extraction of rolling element bearing fault using wavelet packet sample entropy. J Vib Meas Diagn 31(2):162–380
Nectoux P, Gouriveau R, Medjaher K et al (2012) PRONOSTIA: an experimental platform for bearings accelerated degradation tests. In: IEEE international conference on prognostics and health management. IEEE, pp 1–8
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 51375067 and 51875075).
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
About this article
Cite this article
Wang, F., Liu, X., Deng, G. et al. Remaining Life Prediction Method for Rolling Bearing Based on the Long Short-Term Memory Network. Neural Process Lett 50, 2437–2454 (2019). https://doi.org/10.1007/s11063-019-10016-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-019-10016-w