Artifcial Neural Network (ANN) Based Prediction of Ultimate Axial Load Capacity of Concrete‑Filled Steel Tube Columns (CFSTCs)
Yazarlar (1)
Doç. Dr. Çiğdem AVCI KARATAŞ Yalova Üniversitesi, Türkiye
| Makale Türü | Özgün Makale (SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale) | ||
| Dergi Adı | International Journal of Steel Structures (Q3) | ||
| Dergi ISSN | 1598-2351 Dergi Bilgileri (2022) | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | Ingilizce | Basım Tarihi | 08-2022 |
| Cilt / Sayı / Sayfa | 22 / 5 / 1341–1358 | DOI | 10.1007/s13296-022-00645-8 |
| Makale Linki | http://dx.doi.org/10.1007/s13296-022-00645-8 | ||
| UAK Araştırma Alanları |
Çelik Yapılar
Deprem
|
||
| Özet |
| Concrete-filled steel tube columns (CFSTCs) are preferred due to enhanced ductility and energy absorption. The capability of an artificial neural network (ANN) based analytical model on estimating the ultimate load capacity of circular CFSTCs under axial loadings has been investigated in this study. To provide a better prediction in modeling, 150 comprehensive experimental data were obtained from circular CFSTC’s geometrical and mechanical properties, such as height, diameter, thickness, the yield stress of steel, unconfined concrete strength, Young’s modulus of steel and concrete, etc., were examined. The backpropagation-training practice available in ANN was used to update the weights of each layer based on the network output error. For feedforward–backpropagation, the Levenberg–Marquardt algorithm was employed. The effectiveness of the ANN model was developed using general-purpose … |
| Anahtar Kelimeler |
| Artificial neural network (ANN) | Composite structures | Concrete-filled steel tube column | Soft computing method | Statistical modeling tool | Ultimate axial load capacity |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Web of Science | 24 |
| Scopus | 29 |
| Google Scholar | 33 |