🤖 AI Summary
Bayesian model updating in structural health monitoring (SHM) suffers from high computational cost due to reliance on expensive forward simulations and challenges in decoupling feature extraction from parameter inversion.
Method: This paper proposes an end-to-end learnable mapping framework that jointly trains a deep neural network to simultaneously learn a damage-sensitive feature extractor and a surrogate model mapping parameters to features. A novel co-learnable mapping mechanism between feature and parameter spaces is introduced, integrated with multi-fidelity surrogate modeling to generate physically consistent, damage-sensitive training data—thereby eliminating repeated numerical simulations required by MCMC.
Contribution/Results: Evaluated on three synthetic benchmarks, the method achieves average parameter estimation errors below 3% and accelerates computation by two orders of magnitude, significantly enhancing the practicality, accuracy, and scalability of Bayesian model updating in SHM.
📝 Abstract
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.