Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers

In concrete construction, early-age thermal cracks in foundations, abutments, piers, and slabs can arise from non-uniform temperature distribution due to heat from cement hydration. These cracks negatively impact the integrity, load-bearing capacity, and service life of the concrete structures. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Tu Anh Do, Ba-Anh Le
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Forces in Mechanics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266635972400043X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846148838515015680
author Tu Anh Do
Ba-Anh Le
author_facet Tu Anh Do
Ba-Anh Le
author_sort Tu Anh Do
collection DOAJ
description In concrete construction, early-age thermal cracks in foundations, abutments, piers, and slabs can arise from non-uniform temperature distribution due to heat from cement hydration. These cracks negatively impact the integrity, load-bearing capacity, and service life of the concrete structures. This paper investigates the application of machine learning (ML) models to predict early-age thermal cracking in concrete bridge piers. The study aims to develop models to forecast thermal cracking potential (ηmax) and estimate the timing of potential cracking (t) based on a dataset of various cross-sectional bridge piers and typical tropical temperatures. Four ML models—Support Vector Machine (SVM), Extreme Gradient Boosting (XGB), Artificial Neural Network (ANN), and Genetic Programming (GP)—were trained on 759 samples. The dataset, prepared using the EACTSA program, included parameters like cross-sectional dimensions, ambient temperature, and initial concrete temperature, with ηmax and t as outputs. Results show that all the ML models achieved high prediction accuracy with R² scores over 0.96. The GP symbolic equations offer transparency and practical implementation. Compared to conventional methods, ML models provide a rapid, effective tool to optimize concrete member dimensions, formwork removal timing, and control concrete temperature, mitigating early-age thermal cracking risk.
format Article
id doaj-art-bee495d8ed8f4a5f84bf74fea3a10d5e
institution Kabale University
issn 2666-3597
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Forces in Mechanics
spelling doaj-art-bee495d8ed8f4a5f84bf74fea3a10d5e2024-11-30T07:14:07ZengElsevierForces in Mechanics2666-35972024-12-0117100297Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piersTu Anh Do0Ba-Anh Le1Faculty of Civil Engineering, University of Transport and Communications, 3 Cau Giay, Lang Thuong, Dong Da, Hanoi, VietnamCorresponding author.; Faculty of Civil Engineering, University of Transport and Communications, 3 Cau Giay, Lang Thuong, Dong Da, Hanoi, VietnamIn concrete construction, early-age thermal cracks in foundations, abutments, piers, and slabs can arise from non-uniform temperature distribution due to heat from cement hydration. These cracks negatively impact the integrity, load-bearing capacity, and service life of the concrete structures. This paper investigates the application of machine learning (ML) models to predict early-age thermal cracking in concrete bridge piers. The study aims to develop models to forecast thermal cracking potential (ηmax) and estimate the timing of potential cracking (t) based on a dataset of various cross-sectional bridge piers and typical tropical temperatures. Four ML models—Support Vector Machine (SVM), Extreme Gradient Boosting (XGB), Artificial Neural Network (ANN), and Genetic Programming (GP)—were trained on 759 samples. The dataset, prepared using the EACTSA program, included parameters like cross-sectional dimensions, ambient temperature, and initial concrete temperature, with ηmax and t as outputs. Results show that all the ML models achieved high prediction accuracy with R² scores over 0.96. The GP symbolic equations offer transparency and practical implementation. Compared to conventional methods, ML models provide a rapid, effective tool to optimize concrete member dimensions, formwork removal timing, and control concrete temperature, mitigating early-age thermal cracking risk.http://www.sciencedirect.com/science/article/pii/S266635972400043XBridge pierEarly-age thermal crackingTime of cracking occurrenceMachine learningGenetic programming
spellingShingle Tu Anh Do
Ba-Anh Le
Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
Forces in Mechanics
Bridge pier
Early-age thermal cracking
Time of cracking occurrence
Machine learning
Genetic programming
title Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
title_full Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
title_fullStr Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
title_full_unstemmed Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
title_short Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers
title_sort machine learning approach for predicting early age thermal cracking potential in concrete bridge piers
topic Bridge pier
Early-age thermal cracking
Time of cracking occurrence
Machine learning
Genetic programming
url http://www.sciencedirect.com/science/article/pii/S266635972400043X
work_keys_str_mv AT tuanhdo machinelearningapproachforpredictingearlyagethermalcrackingpotentialinconcretebridgepiers
AT baanhle machinelearningapproachforpredictingearlyagethermalcrackingpotentialinconcretebridgepiers