Response Prediction of Structural System Subject to Earthquake Motions using Artificial Neural Network

This paper uses Artificial Neural Network (ANN) models to compute structural response of a structural system by training the model for a particular earthquake. Here, the earthquakes in India viz. at Chamoli and Uttarkashi ground motion data have been considered for the analysis. The neural network is first trained here for a single real earthquake data on a single degree of freedom structural system. The trained ANN architecture is then used to simulate earthquakes by feeding various intensities as well as other earthquake data and it is found that the predicted responses given by ANN model are good for practical purposes. If the ANN is trained by a part of the ground motion data then it can also identify the responses of the structural system well for the total period. The safety of the structural systems may be predicted in case of future earthquakes without having to wait for the earthquake to occur for the lessons.