AI-based prediction of shear strength in FRP-reinforced concrete beams

The aim of this study is to predict the shear strength of fiber-reinforced polymer (FRP)-reinforced concrete beams using artificial intelligence-based modeling approaches, with particular focus on carbon fiber-reinforced polymer (CFRP) and glass fiber-reinforced polymer (GFRP) strengthening systems. An experimental database was compiled from the scientific literature, comprising 535 beam specimens. Five supervised machine learning algorithms were developed and evaluated: Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Extreme Gradient Boosting (XGBoost). Model performance was assessed using the coefficient of determination (R 2 ), root mean square error (RMSE), and mean absolute error (MAE). The SVM and XGBoost models demonstrated the highest predictive accuracy and overall robustness. The results confirm the capability of machine learning methods to capture the nonlinear and complex behavior of shear-strengthened reinforced concrete beams and to identify the most influential geometric and mechanical parameters. This work contributes to the optimization of FRP strengthening design by integrating artificial intelligence tools into structural engineering practice.