Predicting bond strength of corroded reinforced concrete after high-temperature exposure: A stacking model and feature selection

IF 7.4 1区 工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY
Peng Ge , Ou Yang , Xugang Hua , Zhengqing Chen , Jia He , Zhiyu Liu , Kailun Zhang
{"title":"Predicting bond strength of corroded reinforced concrete after high-temperature exposure: A stacking model and feature selection","authors":"Peng Ge ,&nbsp;Ou Yang ,&nbsp;Xugang Hua ,&nbsp;Zhengqing Chen ,&nbsp;Jia He ,&nbsp;Zhiyu Liu ,&nbsp;Kailun Zhang","doi":"10.1016/j.conbuildmat.2024.139290","DOIUrl":null,"url":null,"abstract":"<div><div>The bond strength between concrete and steel reinforcement bars is crucial for determining the ultimate load-carrying capacity and serviceability of reinforced concrete (RC) structures. However, rebar corrosion and exposure to high temperatures significantly affect this bond strength. Regrettably, research on the combined effect of these two factors on bond strength is scarce, and there is a lack of a unified, precise, and efficient predictive model. This research developed a stacking model to forecast bond strength under the combined impact of high temperature and corrosion. The initial layer of the model comprises SVR, KNN, MLP, RF, GBDT, and XGBoost as base learners, with the second layer being the linear regression model. The analysis led to the following conclusions: In a comparative study, the stacked model demonstrated superior performance compared to the six base learner models (SVR, KNN, MLP, RF, GBDT, and XGBoost). Among all combinations, Stacking Model Three showed the most robust predictive performance, achieving an R² value of 0.9439, an MAE of 0.8553, an MSE of 2.2721, and an RMSE of 1.5073. Stacking Model Three surpassed XGBoost, the most effective base learner, showing improvements of 1.78 % in R², 20.69 % in MAE, 22.66 % in MSE, and 12.05 % in RMSE. The machine learning model’s enhanced reliability was further confirmed by comparison with existing models. Stacking Model Three outshone the Australian Standard model with improvements of 639.04 % in MAE, 2568.77 % in MSE, and 416.61 % in RMSE. Similarly, XGBoost, the top base learner, exceeded the Australian Standard model with gains of 486.09 % in MAE, 1964.39 % in MSE, and 354.36 % in RMSE. The outcomes of the SHapley Additive exPlanations (SHAP) affirm the interpretability and physical validity of the stacking model employed. The SHAP analysis indicates that the corrosion level of steel bars (CL) and temperature (T) are the critical factors influencing bond strength. This research underscores the practical value of SHAP feature importance in feature selection by comparing the predictive performance of stacked models with various input feature combinations, thus confirming that feature selection significantly impacts the model’s predictive accuracy. In optimizing traditional civil engineering standards and empirical formulas, the feature selection results of machine learning can be referenced.</div></div>","PeriodicalId":288,"journal":{"name":"Construction and Building Materials","volume":"456 ","pages":"Article 139290"},"PeriodicalIF":7.4000,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Construction and Building Materials","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950061824044325","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The bond strength between concrete and steel reinforcement bars is crucial for determining the ultimate load-carrying capacity and serviceability of reinforced concrete (RC) structures. However, rebar corrosion and exposure to high temperatures significantly affect this bond strength. Regrettably, research on the combined effect of these two factors on bond strength is scarce, and there is a lack of a unified, precise, and efficient predictive model. This research developed a stacking model to forecast bond strength under the combined impact of high temperature and corrosion. The initial layer of the model comprises SVR, KNN, MLP, RF, GBDT, and XGBoost as base learners, with the second layer being the linear regression model. The analysis led to the following conclusions: In a comparative study, the stacked model demonstrated superior performance compared to the six base learner models (SVR, KNN, MLP, RF, GBDT, and XGBoost). Among all combinations, Stacking Model Three showed the most robust predictive performance, achieving an R² value of 0.9439, an MAE of 0.8553, an MSE of 2.2721, and an RMSE of 1.5073. Stacking Model Three surpassed XGBoost, the most effective base learner, showing improvements of 1.78 % in R², 20.69 % in MAE, 22.66 % in MSE, and 12.05 % in RMSE. The machine learning model’s enhanced reliability was further confirmed by comparison with existing models. Stacking Model Three outshone the Australian Standard model with improvements of 639.04 % in MAE, 2568.77 % in MSE, and 416.61 % in RMSE. Similarly, XGBoost, the top base learner, exceeded the Australian Standard model with gains of 486.09 % in MAE, 1964.39 % in MSE, and 354.36 % in RMSE. The outcomes of the SHapley Additive exPlanations (SHAP) affirm the interpretability and physical validity of the stacking model employed. The SHAP analysis indicates that the corrosion level of steel bars (CL) and temperature (T) are the critical factors influencing bond strength. This research underscores the practical value of SHAP feature importance in feature selection by comparing the predictive performance of stacked models with various input feature combinations, thus confirming that feature selection significantly impacts the model’s predictive accuracy. In optimizing traditional civil engineering standards and empirical formulas, the feature selection results of machine learning can be referenced.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Construction and Building Materials
Construction and Building Materials 工程技术-材料科学:综合
CiteScore
13.80
自引率
21.60%
发文量
3632
审稿时长
82 days
期刊介绍: Construction and Building Materials offers an international platform for sharing innovative and original research and development in the realm of construction and building materials, along with their practical applications in new projects and repair practices. The journal publishes a diverse array of pioneering research and application papers, detailing laboratory investigations and, to a limited extent, numerical analyses or reports on full-scale projects. Multi-part papers are discouraged. Additionally, Construction and Building Materials features comprehensive case studies and insightful review articles that contribute to new insights in the field. Our focus is on papers related to construction materials, excluding those on structural engineering, geotechnics, and unbound highway layers. Covered materials and technologies encompass cement, concrete reinforcement, bricks and mortars, additives, corrosion technology, ceramics, timber, steel, polymers, glass fibers, recycled materials, bamboo, rammed earth, non-conventional building materials, bituminous materials, and applications in railway materials.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信