Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches
Journal of Structural Design and Construction Practice · 01.05.2027 · 32 (2)
DOI: 10.1061/jsdccc.sceng-2217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Structural Design and Construction Practice, erschienen am 01.05.2027. Verfasst von Wissam Nadir und 4 weiteren Autor:innen. Die Arbeit nennt 111 Literaturangaben.
Abstract (Originalsprache)
Fiber-reinforced polymer (FRP) composites have increasingly been adopted as internal reinforcement in RC structures due to their corrosion resistance and high strength-to-weight ratio. However, accurately predicting the shear capacity of FRP-RC members remains challenging due to the complexity of shear behavior and the relatively smaller experimental database and field evidence compared with steel-reinforced concrete members. To address this gap, this study aims to evaluate and improve the prediction of the one-way shear capacity of FRP-RC members using data-driven approaches. A comprehensive database comprising 434 experimental test specimens was compiled and used to develop and assess six machine-learning (ML) models alongside two regression-based models, linear regression (LR) and stepwise polynomial regression (SPR). The results demonstrate that the M5Prime (M5P) ML model provides the best predictive performance, achieving the highest coefficient of determination ( R 2 = 90.34 ) and the lowest root-mean square error ( RMSE = 14.66 ). Based on this model, a user-friendly web application was developed to facilitate practical design implementation. The SPR model also exhibited strong accuracy ( R 2 = 89.18 and RMSE = 15.63 ) and was subsequently used to propose a new shear capacity equation. Sensitivity analysis and Taylor diagrams were employed to quantify the influence of key input parameters. Additionally, the study reviewed existing design code provisions, finding that most tend to be overly conservative and exhibit considerable scatter. These findings highlight the potential of ML-based approaches in improving the accuracy and efficiency of shear strength predictions for FRP-RC members.
Zitieren
APA
Nadir, W., Harith, I. K., Jawdhari, A., Abbas, M. K., & Moosa, M. K. (2027). Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches. Journal of Structural Design and Construction Practice, 32(2). https://doi.org/10.1061/jsdccc.sceng-2217
Vancouver
Nadir W, Harith IK, Jawdhari A, Abbas MK, Moosa MK. Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches. Journal of Structural Design and Construction Practice. 2027;32(2). doi:10.1061/jsdccc.sceng-2217
BibTeX
@article{Nadir2027,
author = {Nadir, Wissam and Harith, Iman Kattoof and Jawdhari, Akram and Abbas, Maher K. and Moosa, Mustafa Kareem},
title = {Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches},
journal = {Journal of Structural Design and Construction Practice},
year = {2027},
volume = {32},
number = {2},
doi = {10.1061/jsdccc.sceng-2217}
}
EUVIMED