Determination of displacement and failure loads formed in reinforced concrete construction with overhang and without overhang by ANN modeling

Abstract

AbstractDetermination of fracture load and displacement values that might be formed in a reinforced concrete (RC) construction having different overhang types by artificial neural network (ANN) modeling was investigated in this study. Nonlinear static pushover analysis of the key parameters in change defined in Turkish earthquake code (TEC) [1] for columns and beams was carried out, and the capacity curves, failure loads, and displacements were obtained. In total, 64 RC buildings were analyzed according to the change intervals of the parameters chosen. In addition, regression analysis was performed with Statistical Packages for the Social Sciences (SPSS) statistical program (SPSS Inc., Chicago, IL, USA) by using the same parameters for the same model types. Consequently, separate equations were obtained for displacement and load values, and their R2 values were calculated. As a result of ANN modeling, 91.77% convergence for displacement values and 90.61% convergence for load values were obtained. The graphs between the calculated values and expected values are given.