A cU-Net-based surrogate model for predicting rough surface contact parameters in line-contact friction
Friction · 09.11.2026
DOI: 10.26599/frict.2026.9441313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Friction, online erschienen am 09.11.2026. Verfasst von Yichun Xia und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.
Abstract (Originalsprache)
Accurate and efficient prediction of contact parameters on rough surfaces is critical for the tribological design, condition monitoring, and failure analysis of line-contact components. Although physics-based models offer high prediction fidelity, their multifield-coupled iterative solvers are computationally expensive and complex, limiting practical engineering deployment. This work proposes a digital surrogate model based on conditional U-Net (cU-Net) for predicting the spatial distributions of contact parameters, including contact temperature, pressure, and heat flux, on rough surfaces in line-contact friction. Real surface topographies are augmented via the generative patch nearest neighbor (GPNN) model, and a wide-ranging training dataset is constructed through batch computation using a boundary lubrication physics-based model. The cU-Net incorporates an operating-condition embedding mechanism to enable unified prediction across multiple operating conditions. Multiscale spatial and channel attention modules are further integrated to enhance cross-scale feature extraction. A four-component progressive composite loss, assembled from established loss terms and tailored to the sparse extreme-value characteristics of rough surface contact parameters, is combined with Bayesian hyperparameter optimization and a three-stage progressive training strategy. On completely unseen rough surfaces, the model achieves mean relative errors (MREs) of 3.53%, 12.32%, and 13.66% for the temperature, pressure, and heat flux fields, respectively, with peak and top-5% errors that are lower still, and it is approximately 105 times faster than the physics-based model on the same workstation. Out-of-distribution (OOD) tests quantify the degradation of accuracy under extrapolated operating conditions. Retraining with datasets generated from the corresponding physics-based models is expected to extend the framework to other lubrication regimes.
Zitieren
APA
Xia, Y., Cao, H., & Meng, Y. (2026). A cU-Net-based surrogate model for predicting rough surface contact parameters in line-contact friction. Friction. https://doi.org/10.26599/frict.2026.9441313
Vancouver
Xia Y, Cao H, Meng Y. A cU-Net-based surrogate model for predicting rough surface contact parameters in line-contact friction. Friction. 2026. doi:10.26599/frict.2026.9441313
BibTeX
@article{Xia2026,
author = {Xia, Yichun and Cao, Hui and Meng, Yonggang},
title = {A cU-Net-based surrogate model for predicting rough surface contact parameters in line-contact friction},
journal = {Friction},
year = {2026},
doi = {10.26599/frict.2026.9441313}
}
EUVIMED