Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning

Strengthening of damaged reinforced concrete (RC) structures with ultra high performance concrete (UHPC) can increase their load carrying capacity and durability. However, there are limited studies that forecast the moment improvement (Mu) in strengthening damaged RC beams. The aim of this study is...

Full description

Saved in:
Bibliographic Details
Main Authors: Weidong Xu, Decheng Ji, Yong Yu, Xianying Shi
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/S2214509525007375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422458415742976
author Weidong Xu
Decheng Ji
Yong Yu
Xianying Shi
author_facet Weidong Xu
Decheng Ji
Yong Yu
Xianying Shi
author_sort Weidong Xu
collection DOAJ
description Strengthening of damaged reinforced concrete (RC) structures with ultra high performance concrete (UHPC) can increase their load carrying capacity and durability. However, there are limited studies that forecast the moment improvement (Mu) in strengthening damaged RC beams. The aim of this study is to develop a reliable model that can precisely predict Mu. Initially, the researchers gathered 173 datasets from experimental studies. Due to the limited amount of data available, kernel density estimation (KDE) was employed to expand the data. Subsequently, six machine learning algorithms were developed to predict the Mu. In addition, a new prediction model was constructed by considering the failure modes of the strengthened beams. Finally, Shapley Additive Explanations were employed to conduct an evaluation of model explainability. The results show that KDE can improve the robustness and accuracy of the model. Extreme gradient boosting performed best in predicting Mu and considering the failure mode could improve the accuracy of the model. The height of the RC beam, the reinforcement ratio of the UHPC, and the width of the RC beam have a large and proportional effect on Mu. This study can provide guidance for the engineering design of UHPC strengthened damaged RC beams.
format Article
id doaj-art-c6facfd116a9476683d8182bee8640fa
institution Kabale University
issn 2214-5095
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Case Studies in Construction Materials
spelling doaj-art-c6facfd116a9476683d8182bee8640fa2025-08-20T03:31:06ZengElsevierCase Studies in Construction Materials2214-50952025-12-0123e0493910.1016/j.cscm.2025.e04939Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learningWeidong Xu0Decheng Ji1Yong Yu2Xianying Shi3College of Ocean and Civil Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Ocean and Civil Engineering, Dalian Ocean University, Dalian 116023, ChinaSchool of Future Transportation, Guangzhou Maritime University, Guangzhou 510725, China; Corresponding authors.College of Ocean and Civil Engineering, Dalian Ocean University, Dalian 116023, China; Corresponding authors.Strengthening of damaged reinforced concrete (RC) structures with ultra high performance concrete (UHPC) can increase their load carrying capacity and durability. However, there are limited studies that forecast the moment improvement (Mu) in strengthening damaged RC beams. The aim of this study is to develop a reliable model that can precisely predict Mu. Initially, the researchers gathered 173 datasets from experimental studies. Due to the limited amount of data available, kernel density estimation (KDE) was employed to expand the data. Subsequently, six machine learning algorithms were developed to predict the Mu. In addition, a new prediction model was constructed by considering the failure modes of the strengthened beams. Finally, Shapley Additive Explanations were employed to conduct an evaluation of model explainability. The results show that KDE can improve the robustness and accuracy of the model. Extreme gradient boosting performed best in predicting Mu and considering the failure mode could improve the accuracy of the model. The height of the RC beam, the reinforcement ratio of the UHPC, and the width of the RC beam have a large and proportional effect on Mu. This study can provide guidance for the engineering design of UHPC strengthened damaged RC beams.http://www.sciencedirect.com/science/article/pii/S2214509525007375Reinforced concrete structuresUltra high performance concreteMoment ImprovementMachine learningShapley additive explanations
spellingShingle Weidong Xu
Decheng Ji
Yong Yu
Xianying Shi
Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
Case Studies in Construction Materials
Reinforced concrete structures
Ultra high performance concrete
Moment Improvement
Machine learning
Shapley additive explanations
title Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
title_full Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
title_fullStr Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
title_full_unstemmed Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
title_short Prediction of moment improvement in UHPC strengthened damaged RC beams based on data augmented machine learning
title_sort prediction of moment improvement in uhpc strengthened damaged rc beams based on data augmented machine learning
topic Reinforced concrete structures
Ultra high performance concrete
Moment Improvement
Machine learning
Shapley additive explanations
url http://www.sciencedirect.com/science/article/pii/S2214509525007375
work_keys_str_mv AT weidongxu predictionofmomentimprovementinuhpcstrengtheneddamagedrcbeamsbasedondataaugmentedmachinelearning
AT dechengji predictionofmomentimprovementinuhpcstrengtheneddamagedrcbeamsbasedondataaugmentedmachinelearning
AT yongyu predictionofmomentimprovementinuhpcstrengtheneddamagedrcbeamsbasedondataaugmentedmachinelearning
AT xianyingshi predictionofmomentimprovementinuhpcstrengtheneddamagedrcbeamsbasedondataaugmentedmachinelearning