In the context of structural health monitoring (SHM), the selection and extraction of damage-sensitive features from raw sensor recordings represent a critical step towards solving the inverse problem underlying the identification of structural health conditions. This work introduces a novel approach that employs deep neural networks to enhance stochastic SHM methods. A learnable feature extractor and a feature-oriented surrogate model are synergistically exploited to evaluate a likelihood function within a Markov chain Monte Carlo sampling algorithm. The feature extractor undergoes pairwise supervised training to map sensor recordings onto a low-dimensional metric space, which encapsulates the sensitivity to structural health parameters. The surrogate model maps structural health parameters to their feature representation. The procedure enables the updating of beliefs about structural health parameters, eliminating the need for computationally expensive numerical models. A preliminary offline phase involves the generation of a labeled dataset to train both the feature extractor and the surrogate model. Within a simulation-based SHM framework, training vibration responses are efficiently generated using a multi-fidelity surrogate modeling strategy to approximate sensor recordings under varying damage and operational conditions. The multi-fidelity surrogate exploits model order reduction and artificial neural networks to speed up the data generation phase while ensuring the damage-sensitivity of the approximated signals. The proposed strategy is assessed through three synthetic case studies, demonstrating high accuracy in the estimated parameters and strong computational efficiency.

Nowadays, the aging, deterioration, and failure of civil structures are challenges of paramount importance, increasingly motivating the search of advanced Structural Health Monitoring (SHM) tools. In this work, we propose a SHM strategy for online structural damage detection and localization, combining Deep Learning (DL) and Model-Order Reduction (MOR). The developed data-based procedure is driven by the analysis of vibration and temperature recordings, shaped as multivariate time series and collected on the fly through pervasive sensor networks. Damage detection and localization are treated as a supervised classification task considering a finite number of predefined damage scenarios. During a preliminary offline phase, for each damage scenario, a collection of synthetic structural responses and temperature distributions, is numerically generated through a physics-based model. Several loading and thermal conditions are considered, thanks to a suitable parametrization of the problem, which controls the dependency of the model on operational and environmental conditions. Because of the huge amount of model evaluations, MOR techniques are employed in order to relieve the computational burden that is associated to the dataset construction. Finally, a deep neural network, featuring a stack of convolutional layers, is trained by assimilating both vibrational and thermal data. During the online phase, the trained DL network processes new incoming recordings in order to classify the actual state of the structure, thus providing information regarding the presence and localization of the damage, if any. Numerical performances of the proposed approach are assessed on the monitoring of a two-storey frame under low intensity seismic excitation.