An innovative multi-objective optimization approach for compact concrete-filled steel tubular (CFST) column design utilizing lightweight high-strength concrete

Abstract

Incorporating sustainability into Concrete-Filled Steel Tubular (CFST) columns' optimization can enhance efficiency and sustainability in construction. Discrepancies in international standards for ultimate load capacity computation in compact CFST columns under eccentric loading, particularly with lightweight high-strength concrete, pose challenges. This research compile a dataset of compact CFST columns, evaluating design codes (AISC 360-16, Eurocode 4) against experimental results. Besides, a comprehensive finite-element model predicts compact CFST column performance, investigating axial force-moment (P-M) interaction behavior with respect to the material strength ratio (fy/fc′). In the second phase of the study, an ANN model, incorporating input parameters, estimates axial load capacity, facilitating multi-objective optimization for optimal CFST column geometry. The results confirmed that Eurocode 4 outperforms AISC 360-16 in experimental axial capacity predictions (Nuc/Nuc,theoretical) where, the mean and standard deviation for Eurocode 4 were estimated at 1.07 and 0.22, respectively, compared to 1.21 and 0.29 for AISC 360-16. Besides, statistical metrics confirm the precision of the ANN model, particularly with high-strength concrete, promising efficiency in future computational intelligence-based structural design platforms.

Keywords

• Reinforced concrete
• CFST column
• Composite
• Finite element modeling
• Artificial intelligence
• Multi-objective optimization