Estimation of the shear strength of UHPC beams via interpretable deep learning models: Comparison of different optimization techniques

Basit Öğe Kaydı
dc.authoridKatlav, Metin/0000-0001-9093-7195
dc.authorwosidKatlav, Metin/HSF-7829-2023
dc.contributor.authorErgen, Faruk
dc.contributor.authorKatlav, Metin
dc.date.accessioned2024-08-04T20:56:05Z
dc.date.available2024-08-04T20:56:05Z
dc.date.issued2024
dc.departmentİnönü Üniversitesien_US
dc.description.abstractIn this article, optimized deep learning (DL) models with different algorithms are adopted to estimate the shear strength of rectangular ultra-high performance concrete beams (UHPC-Bs) in order to overcome the challenges in traditional mechanics-based approaches. Long short-term memory (LSTM) and gated recurrent unit (GRU) are chosen as the DL models, whereas the recent popular optimization algorithms are phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), mountain gazelle optimizer (MGO), and atom search optimization (ASO). A thorough and reliable dataset of 244 UHPC-Bs test results with ten input features has been used to construct the hybrid DL models. The performance of the optimized hybrid LSTM and GRU models with different algorithms is extensively assessed and compared based on various statistical metrics, error, and score analyses. Then, the model with the best estimation performance is determined and compared with the mechanics-based formulas in the current international design codes. Additionally, Shapley additive explanations (SHAP) analysis is used to assist in the interpretability of DL models and to reveal the effects of input features that contribute to the model's estimation. According to the results of the present work, all DL models successfully estimate the shear strength of UHPC-Bs. Among these models, the MGO-LSTM model stands out compared to the other models in terms of several performance measures for both the training and testing phases, like a higher R-2 value, lower RMSE, MAPE, and MAE values, as well as a smaller error ratio and a higher final score. The performance of the algorithms applied to optimize the hyper-parameters of the LSTM and GRU models can be ranked as follows: MGO > DMO > PPSO > ASO. Moreover, a graphical user interface (GUI) was constructed based on the best estimation model that was built so that the shear strength of UHPC-Bs could be estimated in real-world situations without the need for any extra software or tools. This enables more users to quickly and easily estimate the shear strength of UHPC-Bs, optimize design processes, and decrease experimental testing costs.en_US
dc.identifier.doi10.1016/j.mtcomm.2024.109394
dc.identifier.issn2352-4928
dc.identifier.scopus2-s2.0-85195380996en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1016/j.mtcomm.2024.109394
dc.identifier.urihttps://hdl.handle.net/11616/102042
dc.identifier.volume40en_US
dc.identifier.wosWOS:001252376200001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.ispartofMaterials Today Communicationsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectUHPCen_US
dc.subjectDeep learningen_US
dc.subjectShear strengthen_US
dc.subjectOptimization techniquesen_US
dc.subjectGraphical user interfaceen_US
dc.titleEstimation of the shear strength of UHPC beams via interpretable deep learning models: Comparison of different optimization techniquesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu