It is evident that the response of linear structures under dynamic loads depends to two important dynamics parameters of structures, namely, the natural periods and structural damping. These parameters always characterize the oscillation and the energy dissipation of buildings. In fact, the values of these parameters differ significantly, before, during and after an earthquake from values selected during the design phase. This phenomenon, among other, introduces uncertainty into the building simulation process, which remarkably influences the structural response and associated performance of the structure under dynamic loads. This paper develops a new methodology to estimate the maximum absolute response for linear structures with uncertain damping using the Artificial Neural Networks (ANN) and the Monte Carlo method. The proposed method is illustrated using the target design response spectra corresponding to the EC8 for linear structures exposed to seismic loads. The numerical results revealed the practical applicability of the proposed methodology and the crucial influence of accounting the damping uncertainty in structural dynamics. Additionally, the method can be used in practice, mainly for important and special structures where uncertainty could lead to significant changes in structural response.
A study of the use of artificial neural networks to estimate dynamic displacements due to dynamic loads in bridges
