Flexural capacity prediction of partially encased composite beams using explainable machine learning
Journal of the Croatian Association of Civil Engineers · 2026-02 · 78 (01) · 1-19
DOI: 10.14256/jce.4344.2025 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Croatian Association of Civil Engineers, 2026-02. Verfasst von Hongxin Liu und 4 weiteren Autor:innen.
Abstract (Originalsprache)
To address traditional limitations, this study investigated the flexural performance of large-section PEC beams with varied web openings using experiments and machine learning (ML). Four-point bending tests on specimens with different sections and openings demonstrated excellent ductility (coefficient >4.0), although openings slightly reduced yield strength without significantly affecting overall performance. A database of 15 variables was used to train and validate four ML models (RF, CatBoost, KNN, LightGBM). The RF model achieved the highest accuracy (~2.6% MAE). Shapley analysis improved interpretability by identifying key parameters. Integrating explainable ML substantially enhances the prediction accuracy and interpretability of PEC flexural capacity, offering a promising approach for intelligent structural design and assessent.
Zitieren
APA
Liu, H., Yang, P., Li, Y., Jia, S., & Xie, X. (2026). Flexural capacity prediction of partially encased composite beams using explainable machine learning. Journal of the Croatian Association of Civil Engineers, 78(01), 1-19. https://doi.org/10.14256/jce.4344.2025
Vancouver
Liu H, Yang P, Li Y, Jia S, Xie X. Flexural capacity prediction of partially encased composite beams using explainable machine learning. Journal of the Croatian Association of Civil Engineers. 2026;78(01):1-19. doi:10.14256/jce.4344.2025
BibTeX
@article{Liu2026,
author = {Liu, Hongxin and Yang, Ping and Li, Yaming and Jia, Shuizhong and Xie, Xiaomeng},
title = {Flexural capacity prediction of partially encased composite beams using explainable machine learning},
journal = {Journal of the Croatian Association of Civil Engineers},
year = {2026},
volume = {78},
number = {01},
pages = {1--19},
doi = {10.14256/jce.4344.2025}
}
EUVIMED