Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures

Realistic structural analyses and optimisations using the non-linear finite element method are possible today yet suffer from being very time-consuming, particularly in case of reinforced concrete plates and shells. Hence such investigations are currently dismissed in the vast majority of cases in p...

Full description

Bibliographic Details
Main Authors: Michael A. Kraus, Rafael Bischof, Walter Kaufmann, Karel Thoma
Format: Article
Language:English
Published: CTU Central Library 2022-08-01
Series:Acta Polytechnica CTU Proceedings
Subjects:
Online Access:https://ojs.cvut.cz/ojs/index.php/APP/article/view/8386
_version_ 1811267828457668608
author Michael A. Kraus
Rafael Bischof
Walter Kaufmann
Karel Thoma
author_facet Michael A. Kraus
Rafael Bischof
Walter Kaufmann
Karel Thoma
author_sort Michael A. Kraus
collection DOAJ
description Realistic structural analyses and optimisations using the non-linear finite element method are possible today yet suffer from being very time-consuming, particularly in case of reinforced concrete plates and shells. Hence such investigations are currently dismissed in the vast majority of cases in practice. The "Artificial Intelligence - Finite Element - Hybrids" project addresses the current unsatisfactory situation with an approach that combines non-linear finite element models for reinforced concrete shells with scientific machine learning algorithms to create hybrid AI-FEM models. The AI-based surrogate material model provides the material stiffness as well as the stress tensor for given concrete design parameters and the strain tensor. This paper reports on the current status of the project and findings of the calibration of the AI-based reinforced concrete material model. We successfully calibrated and evaluated k-nearest-neighbour, LGBM and ResNet algorithms and report their predictive capabilities. Finally, some light is shed on the future work of integrating the AI surrogate material models back into the finite element method in the course of the numerical analysis of reinforced concrete structures.
first_indexed 2024-04-12T21:10:45Z
format Article
id doaj.art-b38ff272a4fe4073a3db32237fbc7590
institution Directory Open Access Journal
issn 2336-5382
language English
last_indexed 2024-04-12T21:10:45Z
publishDate 2022-08-01
publisher CTU Central Library
record_format Article
series Acta Polytechnica CTU Proceedings
spelling doaj.art-b38ff272a4fe4073a3db32237fbc75902022-12-22T03:16:36ZengCTU Central LibraryActa Polytechnica CTU Proceedings2336-53822022-08-01369910810.14311/APP.2022.36.00995626Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structuresMichael A. Kraus0Rafael Bischof1Walter Kaufmann2Karel Thoma3ETH Zürich, Institute of Structural Engineering (IBK), Chair for Concrete Structures and Bridge Design, Stefano-Franscini-Platz 5, CH-8093 Zürich, Switzerland; ETH Zürich, Center for Augmented Computational Design in Architecture, Engineering and Construction, Design++ Initiative and Immersive Design Lab, Stefano-Franscini-Platz 5, CH-8093 Zürich, SwitzerlandETH Zürich, Institute of Structural Engineering (IBK), Chair for Concrete Structures and Bridge Design, Stefano-Franscini-Platz 5, CH-8093 Zürich, SwitzerlandETH Zürich, Institute of Structural Engineering (IBK), Chair for Concrete Structures and Bridge Design, Stefano-Franscini-Platz 5, CH-8093 Zürich, Switzerland; ETH Zürich, Center for Augmented Computational Design in Architecture, Engineering and Construction, Design++ Initiative and Immersive Design Lab, Stefano-Franscini-Platz 5, CH-8093 Zürich, SwitzerlandETH Zürich, Institute of Structural Engineering (IBK), Chair for Concrete Structures and Bridge Design, Stefano-Franscini-Platz 5, CH-8093 Zürich, SwitzerlandRealistic structural analyses and optimisations using the non-linear finite element method are possible today yet suffer from being very time-consuming, particularly in case of reinforced concrete plates and shells. Hence such investigations are currently dismissed in the vast majority of cases in practice. The "Artificial Intelligence - Finite Element - Hybrids" project addresses the current unsatisfactory situation with an approach that combines non-linear finite element models for reinforced concrete shells with scientific machine learning algorithms to create hybrid AI-FEM models. The AI-based surrogate material model provides the material stiffness as well as the stress tensor for given concrete design parameters and the strain tensor. This paper reports on the current status of the project and findings of the calibration of the AI-based reinforced concrete material model. We successfully calibrated and evaluated k-nearest-neighbour, LGBM and ResNet algorithms and report their predictive capabilities. Finally, some light is shed on the future work of integrating the AI surrogate material models back into the finite element method in the course of the numerical analysis of reinforced concrete structures.https://ojs.cvut.cz/ojs/index.php/APP/article/view/8386concrete material modelmachine and deep learningnonlinear finite element methodsurrogate modelinguncertainty quantification
spellingShingle Michael A. Kraus
Rafael Bischof
Walter Kaufmann
Karel Thoma
Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
Acta Polytechnica CTU Proceedings
concrete material model
machine and deep learning
nonlinear finite element method
surrogate modeling
uncertainty quantification
title Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
title_full Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
title_fullStr Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
title_full_unstemmed Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
title_short Artificial intelligence - finite element method - hybrids for efficient nonlinear analysis of concrete structures
title_sort artificial intelligence finite element method hybrids for efficient nonlinear analysis of concrete structures
topic concrete material model
machine and deep learning
nonlinear finite element method
surrogate modeling
uncertainty quantification
url https://ojs.cvut.cz/ojs/index.php/APP/article/view/8386
work_keys_str_mv AT michaelakraus artificialintelligencefiniteelementmethodhybridsforefficientnonlinearanalysisofconcretestructures
AT rafaelbischof artificialintelligencefiniteelementmethodhybridsforefficientnonlinearanalysisofconcretestructures
AT walterkaufmann artificialintelligencefiniteelementmethodhybridsforefficientnonlinearanalysisofconcretestructures
AT karelthoma artificialintelligencefiniteelementmethodhybridsforefficientnonlinearanalysisofconcretestructures