A hybrid seismic analysis computing the full nonlinear response of building structures is proposed and validated in this paper. Recurrent neural networks are trained to predict the nonlinear hysteretic response of isolation devices with deformation- and velocity-dependent behavior. Then, they are implemented in an explicit time integration method for time history analysis. A comprehensive framework is proposed to develop and test deep learning models considering the data framing, the network architecture, and the learning behavior. Hybrid seismic analyses of three base-isolated building models subjected to four ground motions with different properties were performed in order to check their efficiency. The small relative errors of computed results to those of the conventional analysis successfully validate the accuracy of the proposed analysis. Its computation time depends mainly on the ground motion duration and is considered negligible. The development of the machine learning model is more time-consuming but nonrepetitive since it can be saved and reused to analyze any new structure containing the same target components. The proposed hybrid seismic analysis overcomes the shortcomings of usual applications of machine learning in structural response prediction problems being limited to specific response quantity(s) of the same structure(s) used at the training process. By taking advantage of both mechanics-based and data-driven methods, results reveal that hybrid analysis is an efficient tool for building-response simulation.

If damage to a building caused by an earthquake is not detected immediately, the opportunity to decide on quick action, such as evacuating the building, is lost. For this reason, it is necessary to develop modern technologies that can quickly obtain the structural safety condition of buildings after an earthquake in order to resume economic and social activities and mitigate future damage by aftershocks. A methodology for the prediction of damage identification is proposed in this study. Using the wavelet spectrum of the absolute acceleration record measured by a single accelerometer located on the upper floor of a building as input data, a CNN model is trained to predict the damage information of the building. The maximum ductility factor, inter-story drift ratio, and maximum response acceleration of each floor are predicted as the damage information, and their accuracy is verified by comparing with the results of seismic response analysis using actual earthquakes. Finally, when an earthquake occurs, the proposed methodology enables immediate action by revealing the damage status of the building from the accelerometer observation records.

It is necessary to detect the structural damage condition of essential buildings immediately after an earthquake to identify safe structures, evacuate, or resume crucial activities. For this reason, a CNN methodology proposed to detect the structural damage condition of a building is here improved and validated for two currently instrumented essential buildings (Tahara City Hall and Toyohashi Fire Station). Three-dimensional frames instead of lumped mass models are used for the buildings. Besides this, a methodology to select records is introduced to reduce the variability of the structural responses. The maximum inter-storey drift and absolute acceleration of each storey are used as damage indicators. The accuracy is evaluated by the usability of the building, total damage condition, storey damage condition, and total comparison of the damage indicators. Finally, the maximum accuracy and R² of the responses are obtained as follows: for the Tahara City Hall building, 90.0% and 0.825, respectively; for the Toyohashi Fire Station building, 100% and 0.909, respectively.