Development of Predictive Models for Shear Strength of HSC Slender Beams Without Web Reinforcement Using Machine-Learning-Based Techniques

The present chapter presents two robust methods to predict bond strength between FRP reinforcement and masonry units. The M5′ algorithm as a rule based method is used to develop practical equations for estimating bond strength. The MARS algorithm besides its high predictive ability is used to determine the most important parameters in predicting bond strength. To develop the models, a comprehensive database including 575 test series is collected from different sources in literature for the first time. The reinforcement width, ratio between widths of FRP reinforcement and masonry unit, tensile strength of support, axial strength of reinforcement and bond length are the five influential parameters considered to estimate the maximum bond strength.