Mechanism-aware physics-guided XGBoost model for shear strength prediction of FRP-strengthened RC beams
Discover Civil Engineering · 19.04.2026 · 3 (1)
DOI: 10.1007/s44290-026-00476-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Discover Civil Engineering, online erschienen am 19.04.2026. Verfasst von Badhon Singha und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Shear strengthening of existing reinforced concrete beams via externally bonded fiber-reinforced polymer (FRP) systems is widely practiced; however, accurate prediction of shear capacity remains challenging due to complex interaction mechanisms, regime-dependent failure behavior, and the limited generalization of existing design-code equations. Code-based models calibrated on restricted experimental data often exhibit bias and large scatter across varying geometries, shear span-depth ratios, and FRP layouts, whereas purely data-driven machine-learning approaches typically lack physical interpretability. To address these limitations, a mechanism-aware physics-guided machine-learning framework is proposed for predicting the shear strength of FRP-strengthened reinforced concrete beams. The framework decomposes total shear resistance into a mechanics-based concrete contribution and a data-driven residual component modeled via XGBoost, enabling variance reduction and physically informed learning. A compiled database of 275 experimental beam tests is classified into low $$\:\frac{a}{d}\le\:2.5$$ and high $$\:\frac{a}{d}>2.5$$ shear span-depth regimes to reflect distinct dominant failure mechanisms. In the high $$\:a/d$$ regime, the model achieves R² = 0.927, RMSE = 19.33 kN, and MAE = 14.58 kN, whereas in the low $$\:a/d$$ regime it attains R² = 0.771, RMSE = 72.67 kN, and MAE = 44.69 kN, consistent with greater mechanism variability. Explainable-AI analyses confirm regime-dependent parameter influence and saturation of FRP effectiveness, demonstrating mechanically coherent and interpretable predictions. Potential applications to reliability-based assessment and design-code calibration require additional uncertainty quantification and external validation beyond the scope of this study.
Zitieren
APA
Singha, B., Islam, M. S., & Chowdhury, N. N. (2026). Mechanism-aware physics-guided XGBoost model for shear strength prediction of FRP-strengthened RC beams. Discover Civil Engineering, 3(1). https://doi.org/10.1007/s44290-026-00476-0
Vancouver
Singha B, Islam MS, Chowdhury NN. Mechanism-aware physics-guided XGBoost model for shear strength prediction of FRP-strengthened RC beams. Discover Civil Engineering. 2026;3(1). doi:10.1007/s44290-026-00476-0
BibTeX
@article{Singha2026,
author = {Singha, Badhon and Islam, Md. Sadiqul and Chowdhury, Nafis Niaz},
title = {Mechanism-aware physics-guided XGBoost model for shear strength prediction of FRP-strengthened RC beams},
journal = {Discover Civil Engineering},
year = {2026},
volume = {3},
number = {1},
doi = {10.1007/s44290-026-00476-0}
}
EUVIMED