An Artificial Neural Network Model for Dynamic Analysis of RC Buildings Subjected to Near-Fault Ground Motions Having Forward Directivity

The near field region of an earthquake is considered to be the region within several kilometers of the extension to the ground surface of the rupture plane. Recordings from recent earthquakes have provided facts that ground motions in the near field of a rupturing fault can contain a large energy, or "directivity," pulse. The objective of this study is to investigate the sufficiency of Artificial Neural Networks (ANN) to determine the three dimensional dynamic response of buildings under the near-fault earthquakes. For this purpose, four ANN models are proposed to estimate the fundamental periods, base shear force, base bending moments and roof displacement of buildings in two directions. The same input layer was submitted to different types of ANN models and the results monitored. A training set of 168 and a validation set of 21 buildings were produced from dynamic response of RC buildings under the near-fault earthquakes by IDARC program. It was demonstrated that the neural network-based approach is highly successful to determine the response of RC buildings subjected to near-fault earthquakes.