Explainable ensemble learning data-driven modeling of mechanical properties of fiber-reinforced rubberized recycled aggregate concrete

dc.contributor.authorÇakıroğlu, Celal
dc.contributor.authorShahjalal, Md.
dc.contributor.authorIslam, Kamrul
dc.contributor.authorMahmood, S.M. Faisal
dc.contributor.authorBillah, A.H.M. Muntasir
dc.date.accessioned2024-04-04T18:41:54Z
dc.date.available2024-04-04T18:41:54Z
dc.date.issued2023
dc.departmentTAÜ, Mühendislik Fakültesi, İnşaat Mühendisliği Bölümüen_US
dc.description.abstractColossal amounts of construction and demolition waste (C&D) and waste tires have become a considerable global environmental concern. To alleviate this issue, it is proposed to use crumb rubber (CR) derived from waste tires and recycled coarse aggregate (RCA) from C&D as a replacement for natural aggregates in new construction materials. However, the wide variability in the mechanical properties of recycled concrete and the lack of reliable predictive tools in the literature make the wide-scale adoption of these new materials a challenging task. Robust methodologies for predicting the mechanical properties of these materials are needed to advance them as viable alternatives to natural aggregates. Hence, this study compiled a comprehensive experimental database comprising 451, 151, and 102 samples from the literature, including compressive, tensile, and flexural strength values of fiber-reinforced rubberized recycled aggregate concrete (FRRAC). Based on these experimental results, seven data-driven machine learning models were developed. A total of 16 input variables were considered in developing these machine-learning models. It was demonstrated that the CatBoost model performed best for predicting the compressive and tensile strengths, whereas for flexural strength, Random Forest models provided better performance. According to SHapley Additive exPlanations (SHAP) values, the age of concrete, fineness modulus of the natural fine aggregate and the replacement percentage of the RCA were the most impactful input features in the prediction of the compressive, tensile, and flexural strength, respectively. Moreover, it was found that the usage of fiber reinforcement increased the impact of the w/c ratio. Based on the results, it is suggested to limit the replacement level of RCA and CR to 30% and 15%, respectively. Finally, this study highlights the importance of data-driven models in optimizing the mechanical properties of FRRAC, offering a useful tool for industry-scale developments.
dc.identifier.citationÇakıroğlu, C., Shahjalal, Md., Islam, K., Mahmood, S.M. F., Billah, A.H.M. M. (2023). Explainable ensemble learning data-driven modeling of mechanical properties of fiber-reinforced rubberized recycled aggregate concrete. Journal of Building Engineering, 76.
dc.identifier.doi10.1016/j.jobe.2023.107279
dc.identifier.scopus2-s2.0-85165366537
dc.identifier.urihttps://hdl.handle.net/20.500.12846/1029
dc.identifier.volume76en_US
dc.identifier.wosWOS:001045227000001
dc.indekslendigikaynakWeb of Science
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofJournal of Building Engineering
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectCrumb rubberen_US
dc.subjectRecycled aggregateen_US
dc.subjectFiber-reinforced rubberized recycled aggregate concreteen_US
dc.subjectMechanical propertiesen_US
dc.subjectExplainable ensemble learning methodsen_US
dc.titleExplainable ensemble learning data-driven modeling of mechanical properties of fiber-reinforced rubberized recycled aggregate concrete
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
1-s2.0-S2352710223014596-main.pdf
Boyut:
13.31 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: