Machine learning in assessing the structural behavior of corroded reinforced concrete beams

Abstract Reinforcement corrosion is a major cause that leads to the deterioration of reinforced concrete (RC) structures. As a result, quickly assessing its impact on structural components has become a priority in recent research. This study examines the use of machine learning (ML) models, an advanced approach in structural engineering, to predict the performance of corroded RC beams, specifically their load‐carrying capacity and bending moment. A substantial database of 804 beam samples is utilized, consisting of 649 corroded beams and 155 uncorroded beams, to capture the complex relationships between input features and structural responses. Nine ML models are trained and compared to determine their effectiveness for this task. Additionally, advanced optimization techniques are employed to improve the predictive accuracy and feature selection of the best‐performing models. Finally, the optimized models are integrated into graphical user interfaces, offering a practical tool to support future research and facilitate predictions regarding the performance of corroded RC beams.