Machine Learning Approaches for Predicting Compressive and Shear Strength of EB FRP-Reinforced Concrete Elements: A Comprehensive Review

The reinforcement of concrete structures with externally bonded fiber-reinforced polymer (EB FRP) composites has emerged as an innovative technique for enhancing structural performance, durability, and service life, yet accurately predicting the shear strength of these elements remains complex due to intricate interactions between influencing factors that conventional empirical equations struggle to capture. This comprehensive review critically analyzes state-of-the-art machine learning (ML) approaches as data-driven alternatives to model the strength behavior of EB FRP-reinforced concrete elements with improved accuracy and reliability. It encompasses techniques including artificial neural networks (ANNs), support vector machines (SVMs), genetic programming (GP), ensemble learning (random forests, gradient boosting), and emerging methods like gene expression programming (GEP) and multigene genetic programming (MGP). By synthesizing the latest advances, evaluating different ML approaches, and identifying gaps and future directions, this review aims to provide a comprehensive understanding of ML's potential and limitations in predicting the compressive and shear strength of EB FRP-reinforced concrete elements.