AI Based Surrogate Model for Digital Twins in Structural Health Monitoring of Reinforced Concrete Structures

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F28399269%3A_____%2F25%3AN0000006" target="_blank" >RIV/28399269:_____/25:N0000006 - 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 Structural Health Monitoring of Reinforced Concrete Structures

Popis výsledku v původním jazyce

Artificial Intelligence (AI), with particular emphasis on Artificial Neural Networks (ANNs), has become an integral component of contemporary scientific and engineering disciplines. An important emerging application is the use of real-time surrogate models within digital twin frameworks for structural health monitoring. In the methodology presented, ANNs serve two principal functions. First, during the calibration phase, they are employed to ensure that the digital twin accurately reproduces the mechanical response of the corresponding physical structure. Following calibration, the digital twin provides a platform for ANN training through physics-informed deep learning, drawing on data generated by sensitivity analyses conducted via nonlinear finite element simulations in ATENA software. In the subsequent stage, the trained ANN is deployed as a rapid-response surrogate model, delivering critical safety-related information to support the continuous monitoring of bridge structures. This study presents the development of a computationally efficient and accurate ANN-based surrogate model and highlights advances in physics-informed deep learning methodologies for structural analysis, reliability assessment, and life-cycle evaluation of critical infrastructure. The calibrated numerical model has been successfully applied to the durability assessment and life-cycle prediction of reinforced concrete bridges.

Název v anglickém jazyce

AI Based Surrogate Model for Digital Twins in Structural Health Monitoring of Reinforced Concrete Structures

Popis výsledku anglicky

Artificial Intelligence (AI), with particular emphasis on Artificial Neural Networks (ANNs), has become an integral component of contemporary scientific and engineering disciplines. An important emerging application is the use of real-time surrogate models within digital twin frameworks for structural health monitoring. In the methodology presented, ANNs serve two principal functions. First, during the calibration phase, they are employed to ensure that the digital twin accurately reproduces the mechanical response of the corresponding physical structure. Following calibration, the digital twin provides a platform for ANN training through physics-informed deep learning, drawing on data generated by sensitivity analyses conducted via nonlinear finite element simulations in ATENA software. In the subsequent stage, the trained ANN is deployed as a rapid-response surrogate model, delivering critical safety-related information to support the continuous monitoring of bridge structures. This study presents the development of a computationally efficient and accurate ANN-based surrogate model and highlights advances in physics-informed deep learning methodologies for structural analysis, reliability assessment, and life-cycle evaluation of critical infrastructure. The calibrated numerical model has been successfully applied to the durability assessment and life-cycle prediction of reinforced concrete bridges.

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