Analysis and Assessment of Behaviour of Infilled Frames : Using Artificial Neural Networks

This monograph presents an artificial neural network (ANN) model for the analysis and assessment of infilled frames subjected to lateral loading. A multilayer feedforward network with backpropagation learning algorithm has been adopted to model the behaviour of infilled frames. Both reinforced concrete and steel frames were considered in the analysis. Based on a parametric study the optimum architecture of the network was arrived at, and it is observed that the trained networks are able to predict the failure loads and displacement of both reinforced concrete and steel infilled frames for all the test patterns satisfactorily. The equations which were formed based on a regression analysis between the predicted results and the actual results showed good agreement with new set of data. Hence, these equations can be used to obtain the actual capacity of the infilled frames. An experimental investigation also has been carried out in this monograph to check the efficacy of the developed model. The monograph focuses on the work carried by the first author at Anna University, Chennai, India; as a part of her doctoral study.