A Prognostic Framework for Wheel Treads Integrating Parameter Correlation and Multiple Uncertainties
Source abstract
Abstract
As crucial rotary components of high-speed trains, wheel treads in realistic operation environment usually suffer severe cyclic shocks, which damage the health status and ultimately cause safety risks. Timely and precise health prognosis based on vibration signals is an effective technology to mitigate such risks. In this work, a new parameter-related Wiener process model is proposed to capture multiple uncertainties existed in on-site prognosis of wheel treads. The proposed model establishes a quantitative relationship between degradation rate and variations, and integrates uncertainties via heterogeneity analysis of both criterions. A maximum-likelihood-based method is presented to initialize the unknown model parameters, followed by a recursive update algorithm with fully utilization of historical lifetime information. An investigation of real-world wheel tread signals demonstrates the superiority of the proposed model in accuracy improvement.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Reliability and Maintenance Optimization · Mechanical Failure Analysis and Simulation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China
Beijing Tangzhi Science and Technology Development Co., Ltd., Beijing 100043, China
Funding
National Natural Science Foundation of China
References (33)
Show source-provided references
1. Study on safety boundary for high-speed train running in severe environments10.1080/23248378.2013.790138 ↗
2. Intelligent Fault Diagnosis of the High-Speed Train with Big Data Based on Deep Neural Networks10.1109/TII.2017.2683528 ↗
3. Gearbox fault diagnosis of high-speed railway train10.1016/j.engfailanal.2016.04.020 ↗
4. Fault Diagnosis of High Speed Train Bogie Based on Ensemble Empirical Mode Decomposition
5. Practical options for selecting data-driven or physics-based prognostics algorithms with reviews10.1016/j.ress.2014.09.014 ↗
6. Remaining useful life estimation-A review on the statistical data driven approaches10.1016/j.ejor.2010.11.018 ↗
7. Prognostics and Health Management: A review on data driven approaches10.1155/2015/793161 ↗
8. Residual life predictions from vibration-based degradation signals: A neural network approach
9. A recurrent neural network based health indicator for remaining useful life prediction of bearings10.1016/j.neucom.2017.02.045 ↗
10. Ensemble of optimized echo state networks for remaining useful life prediction10.1016/j.neucom.2017.11.062 ↗
11. Bidirectional Handshaking LSTM for Remaining Useful Life Prediction10.1016/j.neucom.2018.09.076 ↗
12. Combining Relevance Vector Machines and exponential regression for bearing residual life estimation10.1016/j.ymssp.2012.03.011 ↗
13. Machine Performance Degradation Assessment and Remaining Useful Life Prediction Using Proportional Hazard Model and SVM10.1016/j.ymssp.2012.02.015 ↗
14. Prognosis of Bearing Failures using Hidden Markov Models and the Adaptive Neuro-Fuzzy Inference System10.1109/TIE.2013.2274415 ↗
15. A multi-step predictor with a variable input pattern for system state forecasting10.1016/j.ymssp.2008.09.006 ↗
16. A method for remaining useful life prediction of crystal oscillators using the Bayesian approach and extreme learning machine under uncertainty10.1016/j.neucom.2018.04.043 ↗
17. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network
18. Application of relevance vector machine and logistic regression for machine degradation assessment10.1016/j.ymssp.2009.10.011 ↗
19. A framework for predicting the remaining useful life of a single unit under time varying operating conditions
20. RUL Prediction of Deteriorating Products Using an Adaptive Wiener Process Model10.1109/TII.2017.2684821 ↗
21. Computing and updating the first-passage time distribution for randomly evolving degradation signals
22. Remaining useful lifetime estimation and noisy gamma deterioration process10.1016/j.ress.2015.12.016 ↗
23. Degradation Data Analysis and Remaining Useful Life Estimation, A Review on Wiener-Process-Based Methods10.1016/j.ejor.2018.02.033 ↗
24. An improved exponential model for predicting remaining useful life of rolling element bearings10.1109/TIE.2015.2455055 ↗
25. Remaining Useful Life Prediction Using a Novel Two-stage Wiener Process with Stage correlation10.1109/ACCESS.2018.2877630 ↗
26. Degradation data analysis using wiener processes with measurement errors10.1109/TR.2013.2284733 ↗
27. Degradation modeling for real-time estimation of residual lifetimes in dynamic environments10.1080/0740817X.2014.955153 ↗
28. A random-effects Wiener degradation model based on accelerated failure time10.1016/j.ress.2018.07.003 ↗
29. Steel Material Degradation Assessment Via Vibro-Acoustic Modulation Technique10.1177/0361198119838271 ↗
30. Vibro-acoustic amplitude and frequency modulations during fatigue damage evolution10.1063/1.5099754 ↗
31. A Wiener Process Model-based Method for Remaining Useful Life Prediction Considering Unit-to-Unit Variability10.1109/TIE.2018.2838078 ↗
32. A Wiener-process-based degradation model with a recursive filter algorithm for remaining useful life estimation10.1016/j.ymssp.2012.08.016 ↗
33. Group maintenance scheduling for two-component systems with failure interaction10.1016/j.apm.2019.01.036 ↗