Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches

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.

Authors

Institutions

Publication Details

Journal
Journal of structural design and construction practice.
Published
2026-11-20
DOI
https://doi.org/10.1061/jsdccc.sceng-2217
Primary Topic
Structural Behavior of Reinforced Concrete
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches

Iman Kattoof Harith, Akram Jawdhari, Maher K. Abbas, Mustafa Kareem Moosa et al.
5 links
Journal of structural design and construction practice.
Structural Behavior of Reinforced Concrete
article

Predicting the One-Way Shear Capacity of FRP-Reinforced Concrete Members through Soft Computing Approaches

Iman Kattoof Harith, Akram Jawdhari, Maher K. Abbas, Mustafa Kareem Moosa, Wissam Nadir
article en

Abstract

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.

Journal of structural design and construction practice.Vol. 32(2)
University of Babylon (IQ), South Dakota State University (US), Al-Qasim Green University (IQ)
Structural Behavior of Reinforced Concrete
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon