Sep 2026· ENGINEERING Structure and Civil Engineering· Vol 20, pp. 1708 - 1731· 0 citations· 119 references
TL;DR
A data-driven approach to predict the buckling resistance of stainless steel circular hollow section beam–columns by combining finite element analysis and machine learning is presented, supporting the value of machine-learning-based predictions.
Stainless steel–clad bimetallic steel bars (SCBSBs) as composite structures exhibit complex stress–strain behavior due to dimensional and material heterogeneity, limiting engineering applications. This paper describes a novel approach to effectively predict the stress–strain behavior of SCBSB using machine learning (...
Xiao-Ping Zhong, Xin-Yao Huang, Rui Zhang et al.· Journal of materials in civi...· 2 citations
Feature importance analysis revealed that axial load (Pu) is primarily governed by FRP stiffness, steel yield strength, and concrete strength, whereas ultimate axial strain (εcu) is dominated by steel tube geometry and strength, confirming that axial load and strain are controlled by distinct governing mechanisms.
P. Kumar, S. B. Singh, S. Barai· The Indian Concrete Journal· 0 citations
Building on previous experimental work by the authors on hybrid T‐stubs with carbon steel webs and stainless steel flanges under tension, this study presents the development and validation of an advanced finite element (FE) model capable of accurately predicting the overall behaviour, failure modes, and fracture mechan...
Abdulnasser Albanna, M. Cabrera, Huan-Xin Yuan et al.· ce/papers· 0 citations
Cold formed steel columns are extensively used due to their high strength to weight ratio. However, their thin-walled section is susceptible to local buckling, which limits their load-carrying capacity. This study is a numerical investigation of core-enhanced cold formed steel hexagonal columns with internal stiffeners...
Kavya Somasundaram, K. S. K. Karthik Reddy· Frontiers in Built Environme...· 0 citations
This study presents a numerical investigation of the compressive and flexural behavior of short circular concrete-filled steel tubular (CFST) columns composed of high-strength materials under eccentric loading. A total of 27 specimens were analyzed using three-dimensional nonlinear finite element models developed in Ab...
H. D. Phan, Dat Van Duong, Hai Tran· IOP Conference Series: Earth...· 0 citations
Three ML algorithms, including Categorical Boosting (CatBoost), Multilayer Perceptron (MLP) and Kolmogorov‐Arnold Networks (KAN), were tested and the results show that the KAN model provides the most accurate predictions of CFDST strengths, with an R2 of 0.9903, compared with 0.9084 for Eurocode 4.
