Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning

Roya Solhmirzaei; Hadi Salehi; Venkatesh Kodur

Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning

Roya Solhmirzaei, Hadi Salehi, Venkatesh Kodur

Department of Architectural & Urban Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

A computational framework employing machine learning (ML) is applied to predict failure mode of ultra high performance concrete (UHPC) beams. For this purpose, results from a number of tests on UHPC beams with different geometric and loading configurations and material characteristic are collected and utilized as an input to the ML framework. Results from numerical studies are not included in the data set due to the fact that they are highly dependent upon the adopted material models, meshing practices, as well as other assumptions used in modeling. Artificial neural network is used to predict the failure mode of the UHPC beams. Results indicate that the proposed ML framework is capable of predicting failure mod of UHPC beams with varying reinforcement and configurations, and can be considered for use in design applications. This paper aims to promote the applicability of ML for a practical engineering problem, detecting structural response of UHPC beams.

Original language	English
Title of host publication	The Concrete Industry in the Era of Artificial Intelligence
Editors	M.Z. Naser, Kevin Mueller
Publisher	American Concrete Institute
Pages	113-120
Number of pages	8
ISBN (Electronic)	9781641951623
State	Published - 1 Nov 2021
Event	The Concrete Industry in the Era of Artificial Intelligence 2020 - ACI Spring Concrete Convention 2020 - Virtual, Online Duration: 29 Mar 2020 → 2 Apr 2020

Publication series

Name	American Concrete Institute, ACI Special Publication
Volume	SP-350
ISSN (Print)	0193-2527

Conference

Conference	The Concrete Industry in the Era of Artificial Intelligence 2020 - ACI Spring Concrete Convention 2020
City	Virtual, Online
Period	29/03/20 → 2/04/20

Bibliographical note

Publisher Copyright:
© 2021 American Concrete Institute. All rights reserved.

Keywords

artificial intelligence
data-driven framework
failure mode
machine learning
ultra high performance concrete (UHPC)

Cite this

@inproceedings{674007d7115a4412a66c6f7e756e2eeb,

title = "Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning",

abstract = "A computational framework employing machine learning (ML) is applied to predict failure mode of ultra high performance concrete (UHPC) beams. For this purpose, results from a number of tests on UHPC beams with different geometric and loading configurations and material characteristic are collected and utilized as an input to the ML framework. Results from numerical studies are not included in the data set due to the fact that they are highly dependent upon the adopted material models, meshing practices, as well as other assumptions used in modeling. Artificial neural network is used to predict the failure mode of the UHPC beams. Results indicate that the proposed ML framework is capable of predicting failure mod of UHPC beams with varying reinforcement and configurations, and can be considered for use in design applications. This paper aims to promote the applicability of ML for a practical engineering problem, detecting structural response of UHPC beams.",

keywords = "artificial intelligence, data-driven framework, failure mode, machine learning, ultra high performance concrete (UHPC)",

author = "Roya Solhmirzaei and Hadi Salehi and Venkatesh Kodur",

note = "Publisher Copyright: {\textcopyright} 2021 American Concrete Institute. All rights reserved.; The Concrete Industry in the Era of Artificial Intelligence 2020 - ACI Spring Concrete Convention 2020 ; Conference date: 29-03-2020 Through 02-04-2020",

year = "2021",

month = nov,

day = "1",

language = "English",

series = "American Concrete Institute, ACI Special Publication",

publisher = "American Concrete Institute",

pages = "113--120",

editor = "M.Z. Naser and Kevin Mueller",

booktitle = "The Concrete Industry in the Era of Artificial Intelligence",

address = "United States",

}

Solhmirzaei, R, Salehi, H & Kodur, V 2021, Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning. in MZ Naser & K Mueller (eds), The Concrete Industry in the Era of Artificial Intelligence. American Concrete Institute, ACI Special Publication, vol. SP-350, American Concrete Institute, pp. 113-120, The Concrete Industry in the Era of Artificial Intelligence 2020 - ACI Spring Concrete Convention 2020, Virtual, Online, 29/03/20.

Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning. / Solhmirzaei, Roya; Salehi, Hadi; Kodur, Venkatesh.
The Concrete Industry in the Era of Artificial Intelligence. ed. / M.Z. Naser; Kevin Mueller. American Concrete Institute, 2021. p. 113-120 (American Concrete Institute, ACI Special Publication; Vol. SP-350).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning

AU - Solhmirzaei, Roya

AU - Salehi, Hadi

AU - Kodur, Venkatesh

PY - 2021/11/1

Y1 - 2021/11/1

N2 - A computational framework employing machine learning (ML) is applied to predict failure mode of ultra high performance concrete (UHPC) beams. For this purpose, results from a number of tests on UHPC beams with different geometric and loading configurations and material characteristic are collected and utilized as an input to the ML framework. Results from numerical studies are not included in the data set due to the fact that they are highly dependent upon the adopted material models, meshing practices, as well as other assumptions used in modeling. Artificial neural network is used to predict the failure mode of the UHPC beams. Results indicate that the proposed ML framework is capable of predicting failure mod of UHPC beams with varying reinforcement and configurations, and can be considered for use in design applications. This paper aims to promote the applicability of ML for a practical engineering problem, detecting structural response of UHPC beams.

AB - A computational framework employing machine learning (ML) is applied to predict failure mode of ultra high performance concrete (UHPC) beams. For this purpose, results from a number of tests on UHPC beams with different geometric and loading configurations and material characteristic are collected and utilized as an input to the ML framework. Results from numerical studies are not included in the data set due to the fact that they are highly dependent upon the adopted material models, meshing practices, as well as other assumptions used in modeling. Artificial neural network is used to predict the failure mode of the UHPC beams. Results indicate that the proposed ML framework is capable of predicting failure mod of UHPC beams with varying reinforcement and configurations, and can be considered for use in design applications. This paper aims to promote the applicability of ML for a practical engineering problem, detecting structural response of UHPC beams.

KW - artificial intelligence

KW - data-driven framework

KW - failure mode

KW - machine learning

KW - ultra high performance concrete (UHPC)

UR - http://www.scopus.com/inward/record.url?scp=85139876739&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85139876739

T3 - American Concrete Institute, ACI Special Publication

SP - 113

EP - 120

BT - The Concrete Industry in the Era of Artificial Intelligence

A2 - Naser, M.Z.

A2 - Mueller, Kevin

PB - American Concrete Institute

T2 - The Concrete Industry in the Era of Artificial Intelligence 2020 - ACI Spring Concrete Convention 2020

Y2 - 29 March 2020 through 2 April 2020

ER -

Response Prediction of Ultra-High-Performance Concrete Beams using Machine Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Fingerprint

Cite this