Predicting the Wear Rate and Thickness of Train Contact Wire Using Data-Driven Modelling
Source abstract
Abstract
Predictive maintenance of railroads is essential to prevent costly disruptions. A critical aspect of this maintenance is ensuring the integrity of the pantograph-catenary system, where copper alloy wires experience continuous friction and wear. The degradation rate and condition of these wires are vital factors in planning maintenance activities. Current wear rate prediction methods are largely theoretical and often inaccurate, overlooking essential contextual details. Additionally, wire condition data frequently show inaccuracies and inconsistencies in spatial and temporal resolution, complicating the feasibility of using data-driven approaches. This research investigates a data-driven framework to accurately predict wear rates, emphasizing data processing and optimized data use. A dataset spanning nine years of Dutch railway infrastructure measurements is used, employing various machine learning techniques to determine the most effective approach. Findings indicate that, in 95% of cases, average wire thickness can be predicted with a precision of ±0.12 mm over a four-year period. This study advances the field by proposing a framework that addresses measurement errors, a common challenge in sensor-based assessments, making data-driven maintenance a more reliable option.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Electrical Contact Performance and Analysis · Railway Engineering and Dynamics · Mechanical stress and fatigue analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Construction Management and Engineering, University of Twente, Horst Complex, Room Z232, De Horst 2, 7522 LW Enschede, The Netherlands
Department of Architecture and Civil Engineering, City University of Hong Kong, Hong Kong, China
ProRail, 3511 EP Utrecht, The Netherlands
References (60)
Show source-provided references
1. Zeng, Y., Qin, Y., Liu, D., Fu, Y., Gong, M., and Zhang, X. (2020, January 5–7). Railway Train Device Fault Causality Model Based on Knowledge Graph. Proceedings of the 2020 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC, Beijing, China.10.1109/SDPC49476.2020.9353132 ↗
2. Developments, challenges, and perspectives of railway inspection robots10.1016/j.autcon.2022.104242 ↗
3. Multimodal deep learning for point cloud panoptic segmentation of railway environments10.1016/j.autcon.2023.104854 ↗
4. A taxonomy of railway track maintenance planning and scheduling: A review and research trends10.1016/j.ress.2021.107827 ↗
5. Vithanage, R.K.W., Harrison, C.S., and Desilva, A.K.M. (2019). Importance and Applications of Robotic and Autonomous Systems (RAS) in Railway Maintenance Sector: A Review. Computers, 8.10.3390/computers8030056 ↗
6. Preventive and corrective maintenance—Cost comparison and cost–benefit analysis10.1080/15732479.2015.1032983 ↗
7. Rail maintenance analysis using Petri nets10.1080/15732479.2016.1190767 ↗
8. Xie, J., Huang, J., Zeng, C., Jiang, S.H., and Podlich, N. (2020). Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering. Geosciences, 10.10.3390/geosciences10110425 ↗
9. Predictive maintenance using tree-based classification techniques: A case of railway switches10.1016/j.trc.2019.02.001 ↗
10. High-speed train wheel set bearing analysis: Practical approach to maintenance between end of life and useful life extension assessment10.1016/j.rineng.2024.103696 ↗
11. Image quality enhancement using HybridGAN for automated railway track defect recognition10.1016/j.autcon.2022.104669 ↗
12. Prediction of railroad track geometry change using a hybrid CNN-LSTM spatial-temporal model10.1016/j.aei.2023.102235 ↗
13. Data-driven optimization of railway maintenance for track geometry10.1016/j.trc.2018.02.019 ↗
14. Enhancing railway track maintenance with real-time ultrasonic and moisture sensing: Proactive and zone-specific management strategies10.1016/j.rineng.2024.103472 ↗
15. An end-to-end approach to detect railway track defects based on supervised and self-supervised learning10.1016/j.rineng.2024.103326 ↗
16. Automatic detection of arbitrarily oriented fastener defect in high-speed railway10.1016/j.autcon.2021.103913 ↗
17. A subtle defect recognition method for catenary fastener in high-speed railroad using destruction and reconstruction learning10.1016/j.aei.2024.102393 ↗
18. Decision support models for annual catenary maintenance task identification and assignment10.1016/j.tre.2021.102402 ↗
19. Lin, S., Li, N., Sun, X., and Feng, D. (2021, January 18–21). Research on Maintenance Efficiency Optimization for the Catenary System of Electrified Railways. Proceedings of the 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia, Chengdu, China.10.1109/ICPSAsia52756.2021.9621505 ↗
20. Revamping structural health monitoring of advanced rail transit systems: A paradigmatic shift from digital shadows to digital twins10.1016/j.aei.2024.102450 ↗
21. An Optimization Method for Maintenance Resource Allocation in Electrified Railway Catenary Systems10.1109/TIA.2022.3217107 ↗
22. Service life prediction of worn contact wires under multiple failure modes10.1080/15732479.2022.2035405 ↗
23. Contact Model for The Pantograph-Catenary Interaction
24. Modeling the mechanical wear of the contact elements of pantograph during high-speed movement10.1051/e3sconf/202015701022 ↗
25. Identification of short-wavelength contact wire irregularities in electrified railway pantograph–catenary system10.1016/j.mechmachtheory.2021.104338 ↗
26. Wear analysis and prediction of rigid catenary contact wire and pantograph strip for railway system10.1016/j.wear.2019.203118 ↗
27. A heuristic wear model for the contact strip and contact wire in pantograph—Catenary interaction for railway operations under 15 kV 16.67 Hz AC systems10.1016/j.wear.2020.203401 ↗
28. Estimation of Wear and Strain of Contact Wire Using Contact Force of Pantograph10.2219/rtriqr.48.170 ↗
29. Shing, W.C. (2011). A Survey of Contact Wire Wear Parameters and the Development of a Model to Predict Wire Wear by Using the Artifical Neural Network. [Ph.D. Thesis, City University of Hong Kong].
30. Sliding wear behavior of copper alloy contact wire against copper-based strip for high-speed electrified railways10.1016/j.wear.2006.08.020 ↗
31. Analysis of the evolvement of contact wire wear irregularity in railway catenary based on historical data10.1080/00423114.2017.1408919 ↗
32. Deep learning models for predictive maintenance: A survey, comparison, challenges and prospects10.1007/s10489-021-03004-y ↗
33. Review—Deep Learning Methods for Sensor Based Predictive Maintenance and Future Perspectives for Electrochemical Sensors10.1149/1945-7111/ab67a8 ↗
34. Hassan, M.U., Steinnes, O.M.H., Gustafsson, E.G., Løken, S., and Hameed, I.A. (2023). Predictive Maintenance of Norwegian Road Network Using Deep Learning Models. Sensors, 23.10.3390/s23062935 ↗
35. Predictive maintenance decision-making for variable faults with non-equivalent costs of fault severities10.1016/j.aei.2023.102011 ↗
36. Development of Industry 4.0 predictive maintenance architecture for broadcasting chain10.1016/j.aei.2021.101324 ↗
37. A survey of modeling for prognosis and health management of industrial equipment10.1016/j.aei.2021.101404 ↗
38. Predictive maintenance system for high-end equipment in nuclear power plant under limited degradation knowledge10.1016/j.aei.2024.102506 ↗
39. Improving rail network velocity: A machine learning approach to predictive maintenance10.1016/j.trc.2014.04.013 ↗
40. A literature review of Artificial Intelligence applications in railway systems10.1016/j.trc.2022.103679 ↗
41. Few-shot learning for structural health diagnosis of civil infrastructure10.1016/j.aei.2024.102650 ↗
42. An innovative multisource multibranch metric ensemble deep transfer learning algorithm for tool wear monitoring10.1016/j.aei.2024.102659 ↗
43. Leveraging AI and Deep Learning for Predictive Rail Infrastructure Maintenance: Enhancing Safety and Reducing Downtime
44. Davari, N., Veloso, B., Ribeiro, R.P., Pereira, P.M., and Gama, J. (2021, January 6–9). Predictive maintenance based on anomaly detection using deep learning for air production unit in the railway industry. Proceedings of the 2021 IEEE 8th International Conference on Data Science and Advanced Analytics, DSAA, Porto, Portugal.10.1109/DSAA53316.2021.9564181 ↗
45. A graph convolutional network for optimal intelligent predictive maintenance of railway tracks10.1016/j.dajour.2024.100542 ↗
46. Development of surrogate models for evaluating energy transfer quality of high-speed railway pantograph-catenary system using physics-based model and machine learning10.1016/j.apenergy.2022.120608 ↗
47. Assessment of catenary condition monitoring by means of pantograph head acceleration and Artificial Neural Networks10.1016/j.ymssp.2023.110697 ↗
48. Kuźnar, M., and Lorenc, A. (2021). A Method of Predicting Wear and Damage of Pantograph Sliding Strips Based on Artificial Neural Networks. Materials, 15.10.3390/ma15010098 ↗
49. Panhead accelerations-based methodology for monitoring the stagger in overhead contact line systems10.1016/j.mechmachtheory.2022.104742 ↗
50. Phala, K., Doorsamy, W., and Paul, B.S. (2021). An Intelligent Fault Monitoring System for Railway Neutral Sections. Proceedings of International Conference on Communication and Computational Technologies, Springer.10.1007/978-981-16-3246-4_62 ↗
51. Yang, J., Duan, H., Li, L., Stewart, E., Huang, J., and Dixon, R. (2023). 1D CNN Based Detection and Localisation of Defective Droppers in Railway Catenary. Appl. Sci., 13.10.3390/app13116819 ↗
52. Kuźnar, M., Lorenc, A., and Kaczor, G. (2021). Pantograph Sliding Strips Failure—Reliability Assessment and Damage Reduction Method Based on Decision Tree Model. Materials, 14.10.3390/ma14195743 ↗
53. A robust method of the status monitoring of catenary poles installed along high-speed electrified train tracks10.1016/j.rineng.2021.100289 ↗
54. IoT for predictive assets monitoring and maintenance: An implementation strategy for the UK rail industry10.1016/j.autcon.2020.103486 ↗
55. Moussallik, L. (2021). Towards Condition-Based Maintenance of Catenary Wires Using Computer Vision. [Master’s Thesis, Luleå University of Technology].
56. Contact and Rubbing of Flat Surfaces10.1063/1.1721448 ↗
57. Kuhn, M., Johnson, K., and Modeling, A.P. (2023, November 02). Springer. Available online: http://ir.mksu.ac.ke/handle/123456780/6225.
58. Overhead Contact Line Monitoring and Prediction of Contact Wire Localized Wear Points
59. A procedure for the wear prediction of collector strip and contact wire in pantograph–catenary system10.1016/j.wear.2008.05.006 ↗
60. Electromechanical interaction between carbon-based pantograph strip and copper contact wire: A heuristic wear model10.1016/j.triboint.2015.05.019 ↗