Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams

Glass fiber-reinforced polymer (GFRP)-reinforced concrete (RC) flexural elements are typically designed to fulfill the serviceability criteria, including deflection and crack width. Crack width control in RC structures enhances durability, increases service life, and improves aesthetic appearance. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Omid Habibi, Omar Gouda, Khaled Galal
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Case Studies in Construction Materials
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214509525008034
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850096123497152512
author Omid Habibi
Omar Gouda
Khaled Galal
author_facet Omid Habibi
Omar Gouda
Khaled Galal
author_sort Omid Habibi
collection DOAJ
description Glass fiber-reinforced polymer (GFRP)-reinforced concrete (RC) flexural elements are typically designed to fulfill the serviceability criteria, including deflection and crack width. Crack width control in RC structures enhances durability, increases service life, and improves aesthetic appearance. The design provisions of ACI 440.11–22 and CSA S806–12 incorporate a bond-dependent coefficient, kb, into equations controlling crack width to account for the bond between GFRP bars and concrete. The primary objective of this research is to apply eight machine learning (ML) models, including extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), adaptive boosting (AdaBoost), gradient boosting (GB), random forest (RF), K nearest neighbors (KNN), Ridge, and Lasso, to enhance crack width prediction accuracy in GFRP-RC beams. The study also considers the importance of the kb coefficient in estimating the crack width and investigates the key factors that primarily impact its value. The results indicated that existing design provisions generally overestimate crack width, whereas ML models demonstrate a noticeably closer alignment with experimental data. Additionally, AdaBoost stands out as the most accurate predictor of crack width. SHapley Additive exPlanations (SHAP) analysis highlights that GFRP bar strain, bar spacing, and concrete cover significantly impact the kb coefficient.
format Article
id doaj-art-e94736c607a94975b5db3b4154e776d1
institution DOAJ
issn 2214-5095
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Case Studies in Construction Materials
spelling doaj-art-e94736c607a94975b5db3b4154e776d12025-08-20T02:41:17ZengElsevierCase Studies in Construction Materials2214-50952025-12-0123e0500510.1016/j.cscm.2025.e05005Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beamsOmid Habibi0Omar Gouda1Khaled Galal2Department of Building, Civil and Environmental Engineering, Concordia University, Montreal, Quebec H3G 2W1, CanadaDepartment of Building, Civil and Environmental Engineering, Concordia University, Montreal, Quebec H3G 2W1, CanadaCorresponding author.; Department of Building, Civil and Environmental Engineering, Concordia University, Montreal, Quebec H3G 2W1, CanadaGlass fiber-reinforced polymer (GFRP)-reinforced concrete (RC) flexural elements are typically designed to fulfill the serviceability criteria, including deflection and crack width. Crack width control in RC structures enhances durability, increases service life, and improves aesthetic appearance. The design provisions of ACI 440.11–22 and CSA S806–12 incorporate a bond-dependent coefficient, kb, into equations controlling crack width to account for the bond between GFRP bars and concrete. The primary objective of this research is to apply eight machine learning (ML) models, including extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), adaptive boosting (AdaBoost), gradient boosting (GB), random forest (RF), K nearest neighbors (KNN), Ridge, and Lasso, to enhance crack width prediction accuracy in GFRP-RC beams. The study also considers the importance of the kb coefficient in estimating the crack width and investigates the key factors that primarily impact its value. The results indicated that existing design provisions generally overestimate crack width, whereas ML models demonstrate a noticeably closer alignment with experimental data. Additionally, AdaBoost stands out as the most accurate predictor of crack width. SHapley Additive exPlanations (SHAP) analysis highlights that GFRP bar strain, bar spacing, and concrete cover significantly impact the kb coefficient.http://www.sciencedirect.com/science/article/pii/S2214509525008034GFRPRC structuresCrack widthBond-dependent coefficientMachine learningSHAP
spellingShingle Omid Habibi
Omar Gouda
Khaled Galal
Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
Case Studies in Construction Materials
GFRP
RC structures
Crack width
Bond-dependent coefficient
Machine learning
SHAP
title Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
title_full Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
title_fullStr Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
title_full_unstemmed Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
title_short Machine learning-based prediction of crack width and bond-dependent coefficient (kb) in GFRP-reinforced concrete beams
title_sort machine learning based prediction of crack width and bond dependent coefficient kb in gfrp reinforced concrete beams
topic GFRP
RC structures
Crack width
Bond-dependent coefficient
Machine learning
SHAP
url http://www.sciencedirect.com/science/article/pii/S2214509525008034
work_keys_str_mv AT omidhabibi machinelearningbasedpredictionofcrackwidthandbonddependentcoefficientkbingfrpreinforcedconcretebeams
AT omargouda machinelearningbasedpredictionofcrackwidthandbonddependentcoefficientkbingfrpreinforcedconcretebeams
AT khaledgalal machinelearningbasedpredictionofcrackwidthandbonddependentcoefficientkbingfrpreinforcedconcretebeams