Data-driven moment-carrying capacity prediction of hybrid beams consisting of UHPC-NSC using machine learning-based models

Basit Öğe Kaydı
dc.authoridErgen, Faruk/0000-0002-1509-8720
dc.authoridKatlav, Metin/0000-0001-9093-7195
dc.authorwosidErgen, Faruk/JUF-1244-2023
dc.authorwosidKatlav, Metin/HSF-7829-2023
dc.contributor.authorKatlav, Metin
dc.contributor.authorErgen, Faruk
dc.date.accessioned2024-08-04T20:54:57Z
dc.date.available2024-08-04T20:54:57Z
dc.date.issued2024
dc.departmentİnönü Üniversitesien_US
dc.description.abstractThis paper presents, for the first time in the literature, a study on the development of data-driven machine learning (ML) models to predict the moment-carrying capacity of ultra-high performance concrete (UHPC)normal strength concrete (NSC) hybrid beams. A database of 56 specimens of rectangular-section UHPC-NSC hybrid beams subjected to flexural loading is adopted to train the models. In this context, ten ML algorithms that are most preferred in structural engineering applications are selected to develop prediction-based models: linear regression (LR), lasso regression (LASSO), ridge regression (RR), support vector regression (SVR), multilayer perception (MLP), random forest (RF), extremely randomized trees (ERT), extreme gradient boosting (XGBoost), K-nearest neighbors regression (KNN), and adaptive boosting regression (AdaBoost). Moreover, the Shapley additive explanation (SHAP) method is used to assess the impact of the input features on the prediction results. Lastly, user-friendly a graphical user interface (GUI) has been developed to ensure the interpretability of the prediction models and to overcome the black box problem of ML methods. The GUI, which is designed based on the model with the most effective prediction ability obtained from this work, allows design engineers to analyze their own data and customize the parameters of the model for the prediction of the moment-carrying capacity of UHPC-NSC hybrid beams. The results indicated that ML models can be an effective tool for predicting the moment-carrying capacity of UHPC-NSC hybrid beams. In this regard, notably, the XGBoost model exhibited superior performance in terms of prediction accuracy and generalization ability (R2 = 0.996 and 0.945 in the training and test datasets, respectively). On the other hand, according to the SHAP analysis results, the three most important input parameters influencing the moment-carrying capacity of UHPC-NSC hybrid beams are the effective depth (d), UHPC thickness at the bottom of the beam (UHPCbottom layer) and compressive strength of UHPC (fc,UHPC), respectively. Moreover, it has been found that the placement of the UHPC layer at the bottom of the beam rather than at the upper part of the beam is more effective in enhancing the moment-carrying capacity of UHPC-NSC hybrid beams.en_US
dc.identifier.doi10.1016/j.istruc.2023.105733
dc.identifier.issn2352-0124
dc.identifier.scopus2-s2.0-85180440714en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1016/j.istruc.2023.105733
dc.identifier.urihttps://hdl.handle.net/11616/101736
dc.identifier.volume59en_US
dc.identifier.wosWOS:001137635600001en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier Science Incen_US
dc.relation.ispartofStructuresen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectUltra-high performance concreteen_US
dc.subjectUHPC-NSC hybrid beamsen_US
dc.subjectFlexural performanceen_US
dc.subjectMachine learningen_US
dc.subjectXGBoosten_US
dc.titleData-driven moment-carrying capacity prediction of hybrid beams consisting of UHPC-NSC using machine learning-based modelsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu