Statistical models for shear strength of RC beam-column joints using machine-learning techniques

Abstract

This paper proposes a new set of probabilistic joint shear strength models using the conventional multiple linear regression method, and advanced machine-learning methods of multivariate adaptive regression splines (MARS) and symbolic regression (SR). In order to achieve high-fidelity regression models with reduced model errors and bias, this study constructs extensive experimental databases for reinforced and unreinforced concrete joints by collecting existing beam-column joint subassemblage tests from multiple sources. Various influential parameters that affect joint shear strength such as material properties, design parameters, and joint configuration are investigated through tests of statistical significance. After performing a set of regression analyses, the comparison of simulation results indicates that MARS approach is the best estimation method. Moreover, the accuracy of analytical predictions of the derived MARS model is compared with that of existing joint shear strength relationships. The comparison results show that the proposed model is more accurate compared to existing relationships. This joint shear strength prediction model can be readily implemented into joint response models for evaluation of earthquake performance and inelastic responses of building frames.