NEURAL NETWORKING OF INFILLED RC LOW-RISE SERVICE BUILDINGS

Artificial neural networks (ANNs) are one of the most research areas that attracts the attention of experts of various scientific areas. Recent research activities regarding ANNs indicated that this method is a powerful tool to solve complicated problems in engineering fields. In this paper, ANNs were utilized to predict the lateral behavior of school buildings in Egypt. For this, reinforced concrete (RC) frames representing common school buildings with different characteristics were analyzed using nonlinear dynamic pushover analysis to obtain their capacity curves, failure loads and displacements. Parameters included number of stories, location and dimensions of the frames, distribution of masonry infill panels, and properties of concrete and reinforcement. Obtained data were used to train several ANN models with different topologies and learning algorithms. The most representative ANN was used to obtain more insight into the behavior of school building frames with different parameters.