Predicting the response of a Double-Story Single-Bay (DSSB) RC Frame through hybrid FEA-ANN

Abstract

Predicting the brittle response of reinforced concrete (RC) frames remains an active research problem. Different industries and research tools predict brittle responses with varying accuracy and analysis times, due to their inherent limitations. Also, the sophisticated Finite Element Tools, i.e., (ABAQUS, ANSYS, and DIANA), require costly computational costs and deep knowledge of defining material compared to the industry tool (SAP 2000). An Artificial Neural Network Finite Element Analysis (ANN-FEA) method is proposed to address this issue without incurring additional computational costs. This ANN-FEA method is designed for the analysis and design of both new and existing RC structures, such as Double-story single-bay (DSSB) Frames. For this study, one experimental control model (ECM) frame with three additional finite element models (FEM) is examined. The additional FEM models have: (i) Half Diameter of Stirrups in the Beam (HDB), (ii) Half Diameter of Stirrups in both Beam and Columns (HDBC), and (iii) Double Spacing of Stirrups in Beam and Columns (DSBC), as compared to the experimental model. This assessment focused on measuring the influence of critical design parameters, such as transverse reinforcement ratio (ρt), on the load-carrying capacity of DSSB, especially in a brittle manner. The findings confirmed that all the new FEA models and ANN-FEA exhibited less lateral load than CM, with reductions of 4.45% for HDB, 13.8% for HDBC, and 5.2% for DSBC.