Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings

The objective of this study is to investigate the adequacy of Artificial Neural Networks (ANN) as a securer, quicker and more robust method to determine the dynamic response of buildings in 3D. For this purpose, two ANN models were proposed to estimate the fundamental periods, base shear force, base bending moments and top-floor displacement of buildings in two directions. Total moment of inertia for each storey was defined in order to avoid limitation to describe the structure due to the number of columns, shear-walls and number of bays. The same input layer was submitted to different types of ANN models for various outcomes. In the ANN models, a multilayer perceptron (MLP) with a back-propagation (BP) algorithm was employed using a scaled conjugate gradient. ANN models were developed, trained and tested in a based MATLAB program. A training set of 150 and a validation set of 15 buildings were produced from dynamic response of different buildings. Finite Element Analysis (FEA) was used to generate training and testing set of ANN models. It was demonstrated that the neural network based approach is highly successful to determine response of buildings subjected to earthquake.