Stack Denoising Autoencoder and State-Space Model Based Bearing RUL Prediction Method
Authors:
- 30 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Rolling element bearing is a critical component in a machinery, so its remaining useful life (RUL) prediction becomes a research hotspot in recent years. However, the RUL prediction has two difficulties: 1) effective health indicator (HI) is hard to be constructed; 2) degradation initial time is difficult to be identified accurately. To solve the problems, a RUL prediction method based on stack denoising autoencoder (SDA) and non-overlapping sliding window (NOSW) threshold method is proposed in this work. The HI is constructed by the SDA from 19 time-domain features, which balances the sensitivity and robustness of different features. A novel NOSW threshold method is used to identify the degradation initial time and divide the life cycle into normal operating stage and degradation stage. A state-space model based on the Paris-Erdogan model is established and its noise intensity is estimated by a smoothing estimation method. The particle filtering is employed to track the degradation path and quantify the uncertainty of RUL prediction. In order to verify the effectiveness of the proposed method, two real bearing datasets of XJTU-SY are utilized to experiment. The results demonstrate the proposed method can track the degradation path well and predict the RUL accurately.Keywords
Funding Information
- National Natural Science Foundation of China (51575424)
- National Key Research and Development Program of China (2019YFB1311903)
This publication has 30 references indexed in Scilit:
- Remaining useful lifetime estimation and noisy gamma deterioration processReliability Engineering & System Safety, 2016
- Particle filter-based prognostics: Review, discussion and perspectivesMechanical Systems and Signal Processing, 2016
- An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element BearingsIEEE Transactions on Industrial Electronics, 2015
- Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural networkMechanical Systems and Signal Processing, 2015
- Extended Kalman Filtering for Remaining-Useful-Life Estimation of BearingsIEEE Transactions on Industrial Electronics, 2014
- Data-driven prognostic method based on Bayesian approaches for direct remaining useful life predictionJournal of Intelligent Manufacturing, 2014
- Prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation modelMechanical Systems and Signal Processing, 2014
- Online particle-contaminated lubrication oil condition monitoring and remaining useful life prediction for wind turbinesWind Energy, 2014
- A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solutionEuropean Journal of Operational Research, 2013
- A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian trackingIEEE Transactions on Signal Processing, 2002