A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Neural operator for structural simulation and bridge health monitoring
AbstractInfusing deep learning with structural engineering has received widespread attention for both forward problems (structural simulation) and inverse problems (structural health monitoring). Based on Fourier neural operator, this study proposes VINO (Vehicle–Bridge Interaction Neural Operator) to serve as a surrogate model of bridge structures. VINO learns mappings between structural response fields and damage fields. In this study, vehicle–bridge interaction (VBI)–finite element (FE) data set was established by running parametric FE simulations of the VBI system, considering a random distribution of the structural initial damage field. Subsequently, vehicle‐bridge interaction (VB)–experimental (EXP) dataset was produced by conducting an experimental study under four damage scenarios. After VINO was pretrained by VBI‐FE and fine‐tuned by VBI‐EXP from the bridge at the healthy state, the model achieved the following two improvements. First, forward VINO can predict structural responses from damage field inputs more accurately than the FE model. Second, inverse VINO can determine, localize, and quantify damages in all scenarios, validating the accuracy and efficiency of data‐driven approaches.
Neural operator for structural simulation and bridge health monitoring
AbstractInfusing deep learning with structural engineering has received widespread attention for both forward problems (structural simulation) and inverse problems (structural health monitoring). Based on Fourier neural operator, this study proposes VINO (Vehicle–Bridge Interaction Neural Operator) to serve as a surrogate model of bridge structures. VINO learns mappings between structural response fields and damage fields. In this study, vehicle–bridge interaction (VBI)–finite element (FE) data set was established by running parametric FE simulations of the VBI system, considering a random distribution of the structural initial damage field. Subsequently, vehicle‐bridge interaction (VB)–experimental (EXP) dataset was produced by conducting an experimental study under four damage scenarios. After VINO was pretrained by VBI‐FE and fine‐tuned by VBI‐EXP from the bridge at the healthy state, the model achieved the following two improvements. First, forward VINO can predict structural responses from damage field inputs more accurately than the FE model. Second, inverse VINO can determine, localize, and quantify damages in all scenarios, validating the accuracy and efficiency of data‐driven approaches.
Neural operator for structural simulation and bridge health monitoring
Computer aided Civil Eng
Kaewnuratchadasorn, Chawit (author) / Wang, Jiaji (author) / Kim, Chul‐Woo (author)
Computer-Aided Civil and Infrastructure Engineering ; 39 ; 872-890
2024-03-01
Article (Journal)
Electronic Resource
English
Structural health monitoring for bridge maintenance
IOS Press | 2005
Integrated Bridge Structural Health Monitoring System
| Springer Verlag | 2024
Structural health monitoring for Bosphorus Bridge
| British Library Conference Proceedings | 2010
Bridge Health-Monitoring for Structural Performance
| British Library Conference Proceedings | 2000