A Hybrid Degradation Modeling and Prognostic Method for the Multi-Modal System
Source abstract
Abstract
Engineering systems typically go through complicated degradation processes, partially due to their multiple operating modes. Therefore, how to accurately estimate their remaining useful life is a critical issue. To address this challenge, a hybrid degradation modeling and prognostic method for the multi-modal system is proposed. Firstly, the cumulative dynamic differential health indicator is constructed for the multi-modal switching system using a multi-objective optimization approach. The long-term cumulative degradation assessment model is constructed based on the gated recurrent unit. Then, considering that the damage in the latest stage has a significant impact on the remaining useful life, the time window is used to extract local features of the sequence, including energy features and statistical features. The latest stage degradation is predicted based on the light gradient boosting machine. Finally, model averaging is used to integrate the two predicted results, which is expected to improve the prognostic robustness. The proposed model is evaluated with synthetic analysis and NASA turbofan aero-engine datasets. Extensive experimental results demonstrate the proposed method provides a better characterization of the degradation status of the system and provides a higher estimation accuracy than existing methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Reliability and Maintenance Optimization · Machine Fault Diagnosis Techniques · Risk and Safety Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Central South University, Changsha 410075, China
School of Automation, Central South University, Changsha 410075, China
College of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, China
Funding
National Natural Science Foundation of China · Fundamental Research Funds for Central Universities of the Central South University
References (41)
Show source-provided references
1. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics10.1109/TNNLS.2016.2582798 ↗
2. Yang, D. (2014, January 12–15). Physics-of-failure-based prognostics and health management for electronic products. Proceedings of the 2014 15th International Conference on Electronic Packaging Technology (ICEPT2014), Chengdu, China.10.1109/ICEPT.2014.6922862 ↗
3. Huang, B., Cohen, K., and Zhao, Q. (, January 15–20). Active anomaly detection in heterogeneous processes. Proceedings of the 2018 International Conference on Acoustics, Speech, and Signal Processing (ICASSP2018), Calgary, AB, Canada.10.1109/ICASSP.2018.8461950 ↗
4. Remaining useful life prediction based on a general expression of stochastic process models10.1109/TIE.2017.2677334 ↗
5. Reliable fault diagnosis for low-speed bearings using individually trained support vector machines with kernel discriminative feature analysis10.1109/TPEL.2014.2358494 ↗
6. A novel approach for bearing remaining useful life estimation under neither failure nor suspension histories condition10.1007/s10845-015-1077-x ↗
7. Diagnosis of stator faults of the single-phase induction motor using acoustic signals10.1016/j.apacoust.2016.10.012 ↗
8. Active anomaly detection in heterogeneous processes10.1109/TIT.2018.2866257 ↗
9. A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system10.1016/j.ress.2009.08.001 ↗
10. Cheng, Y., Peng, J., Gu, X., Zhang, X., Liu, W., Yang, Y., and Huang, Z. (2018, January 11–13). RLCP: A Reinforcement Learning Method for Health Stage Division Using Change Points. Proceedings of the 2018 IEEE International Conference on Prognostics and Health Management (ICPHM2014), Seattle, WA, USA.10.1109/ICPHM.2018.8448499 ↗
11. An Energy-Based Nonlinear Pressure Observer for Fast and Precise Braking Force Control of the ECP Brake10.1007/s12541-018-0170-4 ↗
12. Li, H., Zhang, X., Peng, J., He, J., Huang, Z., and Wang, J. (2020). Cooperative CC-CV charging of supercapacitors using multi-charger systems. IEEE Trans. Ind. Electron.10.1109/TIE.2019.2962485 ↗
13. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks10.1016/j.neucom.2017.05.063 ↗
14. Direct remaining useful life estimation based on support vector regression10.1109/TIE.2016.2623260 ↗
15. Zheng, S., Ristovski, K., Farahat, A., and Gupta, C. (2018, January 13–17). Long short-term memory network for remaining useful life estimation. Proceedings of the 2017 IEEE International Conference on Prognostics and Health Management (ICPHM 2017), Chiba, Japan.10.1109/ICPHM.2017.7998311 ↗
16. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life10.1016/j.ress.2012.03.008 ↗
17. Machinery health prognostics: A systematic review from data acquisition to RUL prediction10.1016/j.ymssp.2017.11.016 ↗
18. A framework for predicting the remaining useful life of a single unit under time-varying operating conditions10.1080/0740817X.2012.705451 ↗
19. A new method based on stochastic process models for machine remaining useful life prediction10.1109/TIM.2016.2601004 ↗
20. The application of a general mathematical morphological particle as a novel indicator for the performance degradation assessment of a bearing10.1016/j.ymssp.2016.05.038 ↗
21. A relevance vector machine-based approach with application to oil sand pump prognostics10.3390/s130912663 ↗
22. Health assessment and life prediction of cutting tools based on support vector regression10.1007/s10845-013-0774-6 ↗
23. A model-based method for remaining useful life prediction of machinery10.1109/TR.2016.2570568 ↗
24. A recurrent neural network based health indicator for remaining useful life prediction of bearings10.1016/j.neucom.2017.02.045 ↗
25. Zhang, Y., Xiong, R., He, H., and Liu, Z. (2017, January 9–12). A lstm-rnn method for the lithuim-ion battery remaining useful life prediction. Proceedings of the 2017 Prognostics and System Health Management Conference (PHM-Harbin 2017), Harbin, China.10.1109/PHM.2017.8079316 ↗
26. Song, Y., Li, L., Peng, Y., and Liu, D. (2018, January 17–19). Lithium-Ion Battery Remaining Useful Life Prediction Based on GRU-RNN. Proceedings of the 2018 12th International Conference on Reliability, Maintainability, and Safety (ICRMS 2018), Shanghai, China.10.1109/ICRMS.2018.00067 ↗
27. Zheng, C., Liu, W., Chen, B., Gao, D., and Cheng, Y. (2018, January 4–7). A data-driven approach for remaining useful life prediction of aircraft engines. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC 2018), Maui, HI, USA.10.1109/ITSC.2018.8569915 ↗
28. Wang, S., Zhang, X., Gao, D., Chen, B., Cheng, Y., Yang, Y., and Peng, J. (2018, January 4–7). A Remaining Useful Life Prediction Model Based on Hybrid Long-Short Sequences for Engines. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC 2018), Maui, HI, USA.10.1109/ITSC.2018.8569668 ↗
29. A novel soft computing method for engine RUL prediction10.1007/s11042-017-5204-x ↗
30. Chen, T., and Guestrin, C. (2016, January 15–19). Xgboost: A scalable tree boosting system. Proceedings of the 2016 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining (ACM 2016), Amsterdam, The Netherlands.10.1145/2939672.2939785 ↗
31. Ke, G., Meng, Q., and Finley, T. (2017, January 3–9). Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the Advances in Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
32. Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction10.1007/s10845-014-0933-4 ↗
33. Machine health condition prediction via online dynamic fuzzy neural networks10.1016/j.engappai.2014.05.015 ↗
34. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction10.1109/TR.2014.2299152 ↗
35. Learning long-term dependencies with gradient descent is difficult10.1109/72.279181 ↗
36. Remaining Useful Life Estimation Using CNN-XGB with Extended Time Window
37. Coble, J.B., and Hines, J.W. (2008, January 6–9). Prognostic algorithm categorization with PHM challenge application. Proceedings of the 2008 International Conference on Prognostics and Health Management (ICPHM2008), Denver, CO, USA.10.1109/PHM.2008.4711456 ↗
38. Saxena, A., Goebel, K., and Simon, D. (2008, January 6–9). Damage propagation modeling for aircraft engine run-to-failure simulation. Proceedings of the 2008 International Conference on Prognostics and Health Management (ICPHM2008), Denver, CO, USA.10.1109/PHM.2008.4711414 ↗
39. Frederick, D.K., DeCastro, J.A., and Litt, J.S. (2007). User’s Guide for the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS).
40. Saxena, A., and Goebel, K. (2018, November 20). Turbofan Engine Degradation Simulation Data Set. NASA Ames Prognostics Data Repository, Available online: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-datarepository/.
41. Principal component analysis10.1016/0169-7439(87)80084-9 ↗