Hybrid intelligence framework for optimizing shear capacity of lightweight FRP-reinforced concrete beams

This study rigorously assesses the shear capacity of fiber-reinforced polymer (FRP) reinforced concrete (RC) beams as a lightweight material alternative, scrutinizing the efficacy of the Eurocode and ACI design codes. Leveraging a dataset of 260 experimental FRP-RC beam cases, two distinct Artificial Neural Network (ANN) models were developed using the Levenberg-Marquardt algorithm. Beams with and without stirrups were considered, with parameters including beam width (b), depth (d), length (L), concrete compressive strength (fc′), FRP modulus of elasticity (Efr, Efs) and FRP reinforcement ratios (ρf, ρfs). Multi-objective optimization was deployed to integrate Genetic Algorithms (GA) and fmincon to optimize beam parameters for maximizing the shear capacity, Vc. Sensitivity analysis allowed to quantify the influence of each parameter, revealing that b and d significantly affect Vc, with sensitivity scores of 0.39 and 0.35, respectively. The optimization process, highlighted by a 3D scatter plot, dynamically illustrated trade-offs among key design parameters (ρf, ρfs, d), giving insights into the complex interplay in FRP beam design. The hybrid intelligence models reached superior predictive accuracy over traditional codes, achieving R2 values of 0.89. Notably, for beams without stirrups, model predictions closely matched experimental data, with a lower average ratio (1.02) compared to Eurocode (1.65) and ACI (1.58). Principal Component Analysis (PCA) has elucidated the intricate interactions among variables, thereby deepening insights into the structural dynamics of FRP-RC beams. Incorporating artificial intelligence, sophisticated optimization methodologies, and thorough statistical evaluations establishes a holistic approach for the structural examination of FRP-RC beams, providing improved precision and valuable viewpoints for the refinement of future designs.