An interval prediction system for track irregularity after tamping based on multi‐module machine learning and pointwise scaling approach
Computer-Aided Civil and Infrastructure Engineering · 2025-11 · 40 (27) · 4797-4823
DOI: 10.1111/mice.13504 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer-Aided Civil and Infrastructure Engineering, 2025-11. Verfasst von Yuxiao Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Beijing Municipality, Fundação para a Ciência e a Tecnologia.
Abstract (Originalsprache)
Predicting changes in track irregularity after tamping is important for assisting maintenance decisions and improving construction efficiency. To date, most prediction methods lack consideration for the uncertainties related to tamping effects. To fill this gap, a multi‐module prediction interval system composed of feature selection, interval scaling, and intelligent predictor has been constructed. The feature selection module integrates the processes of relevance, redundancy, complementarity, and weighting. The interval scaling module assigns scaling factors to each point in a data‐driven manner, offering great flexibility. Research found that the composite model has significant advantages over traditional models, improving the interval coverage probability by 5.83%–40.62%. It can accurately predict the track relative smoothness after tamping, with the R2 between the measurement and the prediction of the 60 m mid‐chord offset reaching 0.95. This model can serve as a reliable and feasible tool for predicting the static irregularity of ballasted tracks after tamping.
Förderung
- Natural Science Foundation of Beijing Municipality
- Fundação para a Ciência e a Tecnologia
Zitieren
APA
Zhang, Y., Shi, J., Varandas, J. N., & Ding, Y. (2025). An interval prediction system for track irregularity after tamping based on multi‐module machine learning and pointwise scaling approach. Computer-Aided Civil and Infrastructure Engineering, 40(27), 4797-4823. https://doi.org/10.1111/mice.13504
Vancouver
Zhang Y, Shi J, Varandas JN, Ding Y. An interval prediction system for track irregularity after tamping based on multi‐module machine learning and pointwise scaling approach. Computer-Aided Civil and Infrastructure Engineering. 2025;40(27):4797-4823. doi:10.1111/mice.13504
BibTeX
@article{Zhang2025,
author = {Zhang, Yuxiao and Shi, Jin and Varandas, José Nuno and Ding, Youkang},
title = {An interval prediction system for track irregularity after tamping based on multi‐module machine learning and pointwise scaling approach},
journal = {Computer-Aided Civil and Infrastructure Engineering},
year = {2025},
volume = {40},
number = {27},
pages = {4797--4823},
doi = {10.1111/mice.13504}
}
EUVIMED