Seismic damage assessment and prediction using artificial neural network of RC building considering irregularities

This paper investigated multi-objective seismic damage assessment procedure. Primarily, it estimates damage index (DI) of reinforcement concrete (RC) framed low-rise residential buildings under the seismic ground motions. Three-dimensional DI has been estimated for a four-storey building by Park-Ang method considering irregularities. With increasing storey level, calculation of Park-Ang DI becomes tedious and more time consuming; therefore, this method is difficult to implement in large-scale damage evaluation. In this study, a simplified method has been proposed to estimate global DI (GDI) for regular and irregular buildings. It has been observed that ground floor experiences maximum damage where roof is experiencing least damage. Alternatively, an artificial neural network based prediction model has also been adopted in this paper to minimize the error. Factors affecting GDI of RC framed building has been narrated. To visualize the weightage of the relation between input parameters and GDI, a neural interpretation diagram has also been presented. The present study could be useful for designers to estimate GDI as performance criteria within short time frame.