December 4, 2025Engineering With ComputersOpen Access

Enhancing Bayesian model updating in structural health monitoring via learnable mappings

View Full Paper

Ask AI

Bookmark

High accuracy in estimating structural health parameters is achieved using a novel surrogate model approach.
The surrogate model reduces reliance on computationally expensive numerical models, streamlining the evaluation process.
Training used synthetic datasets labeled for precise mapping of structural health parameters through a multi-fidelity strategy.
The approach shows significant computational efficiency, benefiting structural health monitoring in various conditions.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

This work demonstrates how deep neural networks and surrogate models improve parameter estimates in structural health monitoring, suggesting increased efficiency.

Cite This Study

Matteo Torzoni (2025) studied this question.

synapsesocial.com/papers/6930e8bdea1aef094cca3301 https://doi.org/10.1007/s00366-025-02224-x

View Full Paper

Ask AI

Bookmark

Implication

This work demonstrates how deep neural networks and surrogate models improve parameter estimates in structural health monitoring, suggesting increased efficiency.

Enhancing Bayesian model updating in structural health monitoring via learnable mappings

Key Points

Discussion

Implication

Cite This Study

Enhancing Bayesian model updating in structural health monitoring via learnable mappings

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider