Wheel-Flat Identification from Axle-Box Acceleration: Cross-Track Generalisation and In-Service Validation
Applied Sciences · 27.10.2026 · 16 (21) · 10628
DOI: 10.3390/app162110628 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 27.10.2026. Verfasst von Arianna Cavallo und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MOST—Sustainable Mobility National Re- 903 search Centre, Lucchini.
Abstract (Originalsprache)
The objective of this study is to assess cross-track generalisation and direct controlled-to-service transfer of wheel-flat classifiers based on three revolution-wise axle-box acceleration indicators: Root Mean Square (RMS), Crest Factor (CF), and Wheel-Flat Index (WFI). Full-scale controlled measurements were analysed across distinct track sections, and cross-track transferability was assessed through nested leave-one-track-out validation of speed-dependent k-nearest neighbour classifiers. Final all-track models were applied without retraining or field-specific adaptation to 403 acquisitions collected during commercial freight operation with a wireless axle-box sensor. The controlled measurements showed that the dynamic manifestation of a fixed wheel-flat is not spatially invariant, while the combined RMS–CF–WFI representation retained useful discrimination across track sections. Cross-track balanced accuracy ranged from 0.841 to 0.980; all-track models achieved mean balanced accuracies of 0.967, 0.937, and 0.931 at 30, 45, and 60 km/h. In service, balanced accuracy was 0.878, specificity 0.984, and binary-decision coverage 0.978 against a manually reviewed signal-based reference. Applicability analysis of the exploratory high-speed extension indicated that speed extrapolation does not necessarily imply feature-space extrapolation, although false-positive acquisitions showed substantial departures from the controlled support. These results support compact, transferable axle-box diagnostics for in-service wheel-flat monitoring.
Förderung
- MOST—Sustainable Mobility National Re- 903 search Centre
- Lucchini
Zitieren
APA
Cavallo, A., Tomasini, G., & Castelli-Dezza, F. (2026). Wheel-Flat Identification from Axle-Box Acceleration: Cross-Track Generalisation and In-Service Validation. Applied Sciences, 16(21), 10628. https://doi.org/10.3390/app162110628
Vancouver
Cavallo A, Tomasini G, Castelli-Dezza F. Wheel-Flat Identification from Axle-Box Acceleration: Cross-Track Generalisation and In-Service Validation. Applied Sciences. 2026;16(21):10628. doi:10.3390/app162110628
BibTeX
@article{Cavallo2026,
author = {Cavallo, Arianna and Tomasini, Gisella and Castelli-Dezza, Francesco},
title = {Wheel-Flat Identification from Axle-Box Acceleration: Cross-Track Generalisation and In-Service Validation},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {21},
pages = {10628},
doi = {10.3390/app162110628}
}
EUVIMED