Developing fragility curves based on neural network IDA predictions

A Soft Computing (SC) based framework for the fragility assessment of 3D buildings is proposed in this work. The computational effort required for a fragility analysis of structural systems can become excessive, far beyond the capability of modern computing systems, especially when dealing with real-world structures. For the purpose of making attainable fragility analyses, a Neural Network (NN) implementation is presented in this work, which can provide accurate predictions of the structural response at a fraction of computational time required by a conventional analysis. The main advantage of using NN predictions is that they can deal with problems, without having an algorithmic solution or with an algorithmic solution that is too complex to be found. The proposed methodology is applied to 3D reinforced concrete buildings where it was found that with the proposed implementation of NN, a reduction of one order of magnitude is achieved in the computational effort for performing a full fragility analysis.

► Neural network based incremental dynamic analysis. ► Maximum likelihood method in conjunction with harmony search in vertical statistics. ► Major reduction of the computational effort for the fragility analysis procedure. ► Increased seismic risk estimation accuracy with more than 80 seismic records.