In recent years, the need for structural health monitoring has been increasing to confirm the safety of the building after the earthquake promptly. This study focuses on developing end-to-end deep learning models for estimating post-earthquake structural damage in buildings, aiming to apply them to a structural health monitoring system. The deep learning model takes story-level acceleration data as input and estimates post-earthquake story-level damage using a five-level scale. The dataset for this approach is created by conducting seismic response analyses on an 18-story steel building using 24,385 earthquake cases. The dataset includes story-level acceleration and story-level damage, each categorized into five levels based on hinge occurrence at each timestamp. Since the dataset consists of a time series with spatial relations at the story level, various architectures of deep learning models can be adopted. In the experiment, we evaluate the damage estimation capabilities of four different architectures: RNN, CNN, CRNN, and Transformer-based models. Initially, the deep learning models are trained and evaluated using training and test datasets, which are subsets of the dataset created by seismic response analysis. The Transformer-based model demonstrates the highest accuracy on the test dataset. Subsequently, the trained models are used to infer the results of a previous study¹⁰⁾ on the collapse process of an 18-story high-rise steel building based on the large-scale shaking table test. The results indicate that the estimations of the Transformer-based model differed from the experimental results, likely due to the influence of the analysis model's consistency range and the seismic level in the seismic response analysis.

It is important to reveal conditions of the places where destructive ground motions occurred. To reduce the risk of earthquake damage, especially when constructing important buildings, it is crucial to select a location where high-amplitude ground motions are unlikely to occur. In this report, we investigated a difference between places occurred seismic intensity 7 and 6 upper, using distances from a seismic fault of an inland earthquake, a shear wave velocity averaged upper top 30 m (AVS30), and a geomorphological classification. As a result, we summarized the following three requirements to occur seismic intensity 7. (1) AVS30 should be equal to or less than 500 m/s, (2) R_JB should be equal to or less than 2 km; additionally, both ends of the fault are extended by 2 km, and (3) the geomorphological classification should not be reclaimed land. There was little possibility that seismic intensity 7 occurs at the place where even one of these conditions did not meet. We did not confirm that there was clear dependence of moment magnitudes up to M7 class in the range of R_JB of the records of the seismic intensity 6 upper and 7.