Prediction of Bidirectional Shear Strength of Rectangular RC Columns Subjected to Multidirectional Earthquake Actions for Collapse Prevention

The understanding of the effects multidirectional loadings imposed on major load bearing elements such as reinforced concrete (RC) columns by seismic actions for collapse prevention is utmost importance, and a few simplified models are available in literature. In this study, distinguishing features two machine-learning (ML) methods, namely, multi expression programming (MEP) adaptive neuro-fuzzy inference system (ANFIS) exploited first time to develop eight novel prediction (M1-to M4-MEP M1-to M4-ANFIS) with different combinations input parameters predict biaxial shear strength RC (V). performance developed was assessed using various statistical indicators comparing them experimental values. Based analysis models, M1-ANFIS M1-MEP performed very well exhibited best overall efficiency studied ML methods. Simple mathematical formulations were also provided MEP algorithm V, which model finalized based its performance, accuracy, generalization capability. A parametric show that formulation accurately represents under consideration imperative purposes. can thus be recommended update current code provisions engineering practices.