Remaining Useful Life Prediction of Hybrid Ceramic Bearings Using an Integrated Deep Learning and Particle Filter Approach
Source abstract
Abstract
Bearings are one of the most critical components in many industrial machines. Predicting remaining useful life (RUL) of bearings has been an important task for condition-based maintenance of industrial machines. One critical challenge for performing such tasks in the era of the Internet of Things and Industrial 4.0, is to automatically process massive amounts of data and accurately predict the RUL of bearings. This paper addresses the limitations of traditional data-driven prognostics, and presents a new method that integrates a deep belief network and a particle filter for RUL prediction of hybrid ceramic bearings. Real data collected from hybrid ceramic bearing run-to-failure tests were used to test and validate the integrated method. The performance of the integrated method was also compared with deep belief network and particle filter-based approaches. The validation and comparison results showed that RUL prediction performance using the integrated method was promising.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Gear and Bearing Dynamics Analysis · Engineering Diagnostics and Reliability
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical and Industrial Engineering, University of Illinois at Chicago, Chicago, IL 60607, USA
College of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China
References (41)
Show source-provided references
1. On the use of mean residual life as a condition index for condition-based maintenance decision-making10.1109/TSMC.2013.2290772 ↗
2. Vachtsevanos, G., Lewis, F.L., Roemer, M., Hess, A., and Wu, B. (2006). Intelligent Fault Diagnosis and Prognosis for Engineering System, John Wiley & Sons, Inc.10.1002/9780470117842 ↗
3. Prognosis of defect propagation based on recurrent neural networks10.1109/TIM.2010.2078296 ↗
4. Heimes, F. (2008, January 6–9). Recurrent neural networks for remaining useful life estimation. Proceedings of the 2008 IEEE International Conference of Prognostics and Health Management, Denver, CO, USA.10.1109/PHM.2008.4711422 ↗
5. Lim, P., Goh, C.K., Tan, K.C., and Dutta, P. (October, January 29). Estimation of remaining useful life based on switching Kalman filter neural network ensemble. Proceedings of the 2014 Annual Conference of the Prognostics and Health Management Society, Fort Worth, TX, USA.10.36001/phmconf.2014.v6i1.2348 ↗
6. A Kalman filter-based ensemble approach with application to turbine creep prognostics10.1109/TR.2012.2221037 ↗
7. Bechhoefer, E., Clark, S., and He, D. (2010, January 10–16). A state space model for vibration based prognostics. Proceedings of the 2010 Annual Conference of the Prognostics and Health Management Society, Portland, OR, USA.10.36001/phmconf.2010.v2i1.1863 ↗
8. Dynamic Bayesian networks for fault detection, identification, and recovery in autonomous spacecraft10.1109/TSMC.2014.2323212 ↗
9. Reliable decentralized fault prognosis of discrete-event systems10.1109/TSMC.2015.2499178 ↗
10. Model-based prognostics with concurrent damage progression processes10.1109/TSMCA.2012.2207109 ↗
11. Ensemble neural network-based particle filtering for prognostics10.1016/j.ymssp.2013.07.010 ↗
12. Machine condition prediction based on adaptive neuro–fuzzy and high-order particle filtering10.1109/TIE.2010.2098369 ↗
13. He, D., Bechhoefer, E., Ma, J., and Li, R. (2011, January 25–29). Particle filtering based gear prognostics using one-dimensional health index. Proceedings of the 2011 Annual Conference of the Prognostics and Health Management Society, Montreal, QC, Canada.
14. Prognosis and health monitoring of nonlinear systems using a hybrid scheme through integration of PFs and neural networks
15. A new approach for fuzzy predictive adaptive controller design using particle swarm optimization algorithm
16. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking10.1109/78.978374 ↗
17. Development of an efficient prognostic estimator10.1007/s11668-014-9902-7 ↗
18. A fast learning algorithm for deep belief nets10.1162/neco.2006.18.7.1527 ↗
19. Representation learning: A review and new perspectives10.1109/TPAMI.2013.50 ↗
20. Mastering the game of Go with deep neural networks and tree search10.1038/nature16961 ↗
21. Deep learning10.1038/nature14539 ↗
22. Chen, Z., Zeng, X., Li, W., and Liao, G. (2016, January 23–26). Machine fault classification using deep belief network. Proceedings of the 2016 IEEE International Instrumentation and Measurement Technology Conference, Taipei, Taiwan.10.1109/I2MTC.2016.7520473 ↗
23. Rolling bearing fault diagnosis using an optimization deep belief network10.1088/0957-0233/26/11/115002 ↗
24. Traffic flow prediction with big data: A deep learning approach
25. Hossain, M., Rekabdar, B., Louis, S.J., and Dascalu, S. (2015, January 12–17). Forecasting the weather of Nevada: A deep learning approach. Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland.10.1109/IJCNN.2015.7280812 ↗
26. Tao, Y., Chen, H., and Qiu, C. (2014, January 7–10). Wind power prediction and pattern feature based on deep learning method. Proceedings of the 2014 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Hong Kong, China.10.1109/APPEEC.2014.7066166 ↗
27. Oliveira, T.P., Barbar, J.S., and Soares, A.S. (2014, January 18–20). Multilayer perceptron and stacked autoencoder for Internet traffic prediction. Proceedings of the 11th IFIP International Conference on Network and Parallel Computing (NPC), Ilan, Taiwan.10.1007/978-3-662-44917-2_6 ↗
28. Using deep learning based approach to predict remaining useful life of rotating components
29. Smolensky, P. (1986). Information Processing in Dynamical Systems: Foundations of Harmony Theory. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations, MIT Press. Chapter 6.
30. Training products of experts by minimizing contrastive divergence10.1162/089976602760128018 ↗
31. Greedy layer-wise training of deep networks
32. Why does unsupervised pre-training help deep learning?
33. Novel approach to nonlinear/non-Gaussian Bayesian state estimation10.1049/ip-f-2.1993.0015 ↗
34. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
35. Time series prediction and neural networks10.1023/A:1012074215150 ↗
36. Comprehensive review of neural network-based prediction intervals and new advances10.1109/TNN.2011.2162110 ↗
37. Remaining useful life estimation in heterogeneous fleets working under variable operating conditions10.1016/j.ress.2016.07.019 ↗
38. Metrics for offline evaluation of prognostic performance
39. Random search for hyper-parameter optimization
40. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS), Ft. Lauderdale, FL, USA.
41. Failure prognostics by a data-driven similarity-based approach