AI Based Surrogate Model for Digital Twins in Reinforced Concrete

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F28399269%3A_____%2F25%3AN0000007" target="_blank" >RIV/28399269:_____/25:N0000007 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

AI Based Surrogate Model for Digital Twins in Reinforced Concrete

Popis výsledku v původním jazyce

Artificial Intelligence (AI), particularly using Artificial Neural Networks (ANNs), is increasingly integrated into various domains of human activity and industrial applications. A significant area of application is the development of real-time, fast-response surrogate models within the digital twin framework for structural health monitoring. Within the presented framework, ANNs serve two primary functions. First, during the calibration phase, ANNs ensure that the virtual twin accurately reflects the behavior of the physical structure. Once calibrated, the virtual twin facilitates the training of the ANN through physically informed deep learning, utilizing data derived from sensitivity analyses conducted via nonlinear finite element analysis using ATENA software. The second function involves deploying the trained ANN as a fast-response surrogate model, providing critical safety information for the ongoing structural health monitoring of bridges. This paper outlines the development of an efficient and accurate ANN-based surrogate model, emphasizing the advancements in physically informed deep learning methodologies for structural analysis and life cycle assessment of infrastructures.

Název v anglickém jazyce

AI Based Surrogate Model for Digital Twins in Reinforced Concrete

Popis výsledku anglicky

Artificial Intelligence (AI), particularly using Artificial Neural Networks (ANNs), is increasingly integrated into various domains of human activity and industrial applications. A significant area of application is the development of real-time, fast-response surrogate models within the digital twin framework for structural health monitoring. Within the presented framework, ANNs serve two primary functions. First, during the calibration phase, ANNs ensure that the virtual twin accurately reflects the behavior of the physical structure. Once calibrated, the virtual twin facilitates the training of the ANN through physically informed deep learning, utilizing data derived from sensitivity analyses conducted via nonlinear finite element analysis using ATENA software. The second function involves deploying the trained ANN as a fast-response surrogate model, providing critical safety information for the ongoing structural health monitoring of bridges. This paper outlines the development of an efficient and accurate ANN-based surrogate model, emphasizing the advancements in physically informed deep learning methodologies for structural analysis and life cycle assessment of infrastructures.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

20102 - Construction engineering, Municipal and structural engineering

Projekt

<a href="/cs/project/TM04000012" target="_blank" >TM04000012: Systém pro zjišťování stavu betonových mostů založený na na vzájemné podpoře velkých dat a mechaniky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů