Damage diagnostic method by artificial intelligence analysis of shaking table data of a typical Italian building prototype

A damage diagnostic method based on the use of artificial intelligence (AI) was pointed out for the analysis of displacement data recorded in shaking table tests of a prototype representing a typical Central Italy historic masonry building. The displacements were measured by the use of a 3D motion capture system capable of tracking the motion of passive optical markers located at several positions on the tested building. The state of damage was initially estimated by calculating a widely accepted Damage Index (DI) based on the first mode frequency decay of the building calculated by conventional Frequency Response Function (FRF) for modal analysis of the markers displacements data. Then, machine learning was used to develop a method to estimate the damage status of the tested prototype. More specifically, the proposed AI procedure exploits the Convolutional Variational Auto-Encoder (CVAE), which is an important generative model in unsupervised deep learning. CVAE was applied to the recorded displacement data to reconstruct the original data. The hidden features in the encoder latent spaces of the CVAE were used as a basis to assess the structural damage and compared to real values of DI. The proposed method by machine learning showed very promising potentialities of assessing the structural damage in typical historic masonry buildings.