A Dual-Branch Deep Learning Framework for Macroscopic Area and Microscopic Contour Prediction of EMU Wheelset Wear
IEEE Access · 2026 · 14 · 123517-123531
DOI: 10.1109/access.2026.3719272 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Yanjie Cui und 3 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Academy of Railway Sciences Corporation Ltd..
Abstract (Originalsprache)
Accurately predicting the nonlinear degradation trajectories of electric multiple-unit (EMU) wheelset treads is crucial for ensuring dynamic safety and optimizing predictive maintenance. However, existing data-driven methods struggle to simultaneously quantify macroscopic material loss and reconstruct microscopic worn geometry under complex operating conditions. To address this limitation, this paper proposes a dual-task prediction framework based on multi-source state features and a parallel dual-branch neural network. First, Chebyshev polynomials are used to fit tread profiles accurately and extract the macroscopic equivalent cross-sectional wear area. Subsequently, a 47-dimensional feature space is constructed exclusively from information available before the predicted re-turning cycle, including operating exposure, geometric baseline and measurement-quality indicators, individual historical wear areas, individual historical wear rates, homologous-wheelset historical wear areas, homologous-wheelset historical wear rates, and polygonization-state descriptors. Based on this feature system, the Area Prediction Network (APN) branch combines a Transformer and a one-dimensional convolutional neural network (1D-CNN) to capture global dependencies and local feature combinations for scalar area estimation, whereas the Tread Contour Prediction Network (TCPN) branch uses an asymmetric autoencoder-style multilayer perceptron to map the same 47-dimensional state features to high-dimensional geometric coordinates. Validation using actual re-turning records collected from 2019 to 2025 for powered and trailer wheelsets demonstrates competitive and robust prediction performance. The APN achieves a coefficient of determination ( $R^{2}$ ) as high as 0.950 and a mean absolute error (MAE) as low as $3.128{\,}\mathrm {mm}^{2}$ . Concurrently, the TCPN reconstructs tread profiles with an $\mathrm {MAE}_{\mathrm {contour}}$ below $0.15{\,}\mathrm {mm}$ in most operating scenarios and reduces geometric deviations in critical high-curvature regions, such as the flange root. Furthermore, a feature-ablation study shows that historical wear-rate features provide important degradation-gradient information that improves prediction stability for the top 15% of severe-wear samples. This study links macroscopic wear quantification with microscopic morphological reconstruction and provides a data-driven basis for EMU wheelset maintenance decision-making.
Förderung
- National Natural Science Foundation of China
- China Academy of Railway Sciences Corporation Ltd.
Zitieren
APA
Cui, Y., Zhang, W., Wang, Z., & Li, X. (2026). A Dual-Branch Deep Learning Framework for Macroscopic Area and Microscopic Contour Prediction of EMU Wheelset Wear. IEEE Access, 14, 123517-123531. https://doi.org/10.1109/access.2026.3719272
Vancouver
Cui Y, Zhang W, Wang Z, Li X. A Dual-Branch Deep Learning Framework for Macroscopic Area and Microscopic Contour Prediction of EMU Wheelset Wear. IEEE Access. 2026;14:123517-123531. doi:10.1109/access.2026.3719272
BibTeX
@article{Cui2026,
author = {Cui, Yanjie and Zhang, Weijiao and Wang, Zhongkai and Li, Xuefeng},
title = {A Dual-Branch Deep Learning Framework for Macroscopic Area and Microscopic Contour Prediction of EMU Wheelset Wear},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {123517--123531},
doi = {10.1109/access.2026.3719272}
}
EUVIMED