Transformer-Based High-Speed Train Axle Temperature Monitoring and Alarm System for Enhanced Safety and Performance
Source abstract
Abstract
As the fleet of high-speed rail vehicles expands, ensuring train safety is of the utmost importance, emphasizing the critical need to enhance the precision of axel temperature warning systems. Yet, the limited availability of data on the unique features of high thermal axis temperature conditions in railway systems hinders the optimal performance of intelligent algorithms in alarm detection models. To address these challenges, this study introduces a novel dynamic principal component analysis preprocessing technique for tolerance temperature data to effectively manage missing data and outliers. Furthermore, a customized generative adversarial network is devised to generate distinct data related to high thermal axis temperature, focusing on optimizing the network’s objective functions and distinctions to bolster the efficiency and diversity of the generated data. Finally, an integrated model with an optimized transformer module is established to accurately classify alarm levels, provide a comprehensive solution to pressing train safety issues, and, in a timely manner, notify drivers and maintenance departments (DEPOs) of high-temperature warnings.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Aerodynamics and Fluid Dynamics Research · Structural Health Monitoring Techniques · Thermography and Photoacoustic Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Railway Transportation, Shanghai Institute of Technology, Shanghai 201418, China
Funding
Shanghai Science and Technology Commission “Belt and Road” China-Laos Railway Project International Joint Laboratory
References (31)
Show source-provided references
1. Epistemological research problems of rail transport as a social institution10.1016/j.trpro.2022.06.200 ↗
2. Cross-cultural communication in the belt and road strategy
3. Analysis on temperature distribution of failure axle box bearings of high speed train
4. Randall, R.B. (2011). Vibration-Based Condition Monitoring: Industrial, Aerospace and Automotive Applications, John Wiley & Sons.10.1002/9780470977668 ↗
5. Faults diagnostics of railway axle bearings based on IMF’s confidence index algorithm for ensemble EMD10.3390/s150510991 ↗
6. Torsional-vibration assessment and gear-fault diagnosis in railway traction system10.1109/TIE.2011.2106094 ↗
7. Wind turbine condition monitoring: State-of-the-art review, new trends, and future challenges10.3390/en7042595 ↗
8. Cyclostationarity of Acoustic Emissions (AE) for monitoring bearing defects10.1016/j.ymssp.2011.01.020 ↗
9. The application of spectral kurtosis on acoustic emission and vibrations from a defective bearing10.1016/j.ymssp.2010.06.010 ↗
10. Wind turbine fault detection using multiwavelet denoising with the data-driven block threshold10.1016/j.apacoust.2013.04.016 ↗
11. Envelope calculation of the multi-component signal and its application to the deterministic component cancellation in bearing fault diagnosis10.1016/j.ymssp.2014.05.033 ↗
12. Diagnostics of bearings in presence of strong operating conditions non-stationarity—A procedure of load-dependent features processing with application to wind turbine bearings10.1016/j.ymssp.2013.09.010 ↗
13. Review of fault detection in rolling element bearing
14. Liu, C., and Wang, F. (2017, January 10–12). A review of current condition monitoring and fault diagnosis methods for low-speed and heavy-load slewing bearings. Proceedings of the 2017 9th International Conference on Modelling, Identification and Control (ICMIC), Kunming, China.10.1109/ICMIC.2017.8321619 ↗
15. Corni, I., Symonds, N., Wood, R.J.K., Wasenczuk, A., and Vincent, D. (2015, January 21–23). Real-time on-board condition monitoring of train axle bearings. Proceedings of the Stephenson Conference, London, UK.
16. Machine fault signature analysis10.1155/2008/583982 ↗
17. Singh, K. (2021). Smart Components: Creating a Competitive Edge through Smart Connected Drive Train on Mining Machines. [Master’s Thesis, KTH, School of Industrial Engineering and Management (ITM)].
18. Xu, Q., Sun, S., Xu, Y., Hu, C., Chen, W., and Xu, L. (2022). Influence of temperature gradient of slab track on the dynamic responses of the train-CRTS III slab track on subgrade nonlinear coupled system. Sci. Rep., 12.10.1038/s41598-022-18898-y ↗
19. High-temperature mechanical properties and microstructure of 2.5 DC/C–SiC composites applied for the brake disc of high-speed train10.1016/j.jeurceramsoc.2024.116683 ↗
20. Real-time pavement temperature prediction through ensemble machine learning10.1016/j.engappai.2024.108870 ↗
21. Li, G., Qin, S.J., and Chai, T. (2014, January 4–6). Multi-directional reconstruction based contributions for root-cause diagnosis of dynamic processes. Proceedings of the 2014 American Control Conference, Portland, OR, USA.10.1109/ACC.2014.6859002 ↗
22. Song, Y., Ma, Q., Zhang, T., Li, F., and Yu, Y. (2023). Research on fault diagnosis strategy of air-conditioning systems based on DPCA and machine learning. Processes, 11.10.3390/pr11041192 ↗
23. Robust principal component analysis?
24. Prediction of railcar remaining useful life by multiple data source fusion10.1109/TITS.2015.2400424 ↗
25. Yan, G., Yu, C., and Bai, Y. (2021). A new hybrid ensemble deep learning model for train axle temperature short term forecasting. Machines, 9.10.3390/machines9120312 ↗
26. Pan, Z., Xu, D., Zhang, Y., Wang, M., Wang, Z., Yu, J., and Zhang, G. (2024, January 29–30). New energy transmission line fault location method based on Pearson correlation coefficient. Proceedings of the 2nd International Conference on Smart Energy, Fenghuang, China.
27. A modified generative adversarial network for fault diagnosis in high-speed train components with imbalanced and heterogeneous monitoring data
28. A survey on generative adversarial networks: Variants, applications, and training10.1145/3463475 ↗
29. Sensor-driven condition-based generator maintenance scheduling—Part I: Maintenance problem10.1109/TPWRS.2015.2506600 ↗
30. Matetić, I., Štajduhar, I., Wolf, I., and Ljubic, S. (2022). A review of data-driven approaches and techniques for fault detection and diagnosis in HVAC systems. Sensors, 23.10.3390/s23010001 ↗
31. Attention mechanism in intelligent fault diagnosis of machinery: A review of technique and application10.1016/j.measurement.2022.111594 ↗