This study aims to establish an appropriate design method for evaluating the bearing capacity of concrete-filled stainless steel tubular (CFSST) columns, with the objective of improving the rationality and safety of structural design and providing theoretical support for the broader application of stainless steel in civil engineering. Finite element models of CFSST columns were developed in ABAQUS using existing experimental data, and initial geometric imperfections, material nonlinearities and welding residual stresses were incorporated. The reliability of the models was verified through comparisons with experimental results. Based on the validated models, parametric numerical analysis were carried out to investigate the effects of slenderness ratio, width-to-thickness ratio, concrete strength and confinement on the mechanical behaviour of CFSST members. A modified design formula was then proposed with reference to existing design codes. The numerical simulations showed that the models can accurately reproduce the failure modes and load-bearing responses of CFSST columns. The influence patterns of the key parameters were clarified: higher concrete strength and stronger confinement significantly increased load capacity, whereas increases in slenderness ratio and width-to-thickness ratio reduced structural stability. Comparisons with current design codes indicated that design formulae developed for concrete-filled carbon steel tubular columns were not fully applicable to stainless steel and may lead to safety concerns or inefficient use of materials. The design formulae proposed in this study improve the utilization of material properties while ensuring structural safety. It provides higher prediction accuracy and better engineering applicability than existing code provisions. The findings offer a scientific basis and practical reference for the wider use of stainless steel in high-performance structures.
Corrosion of steel structures has become a critical factor affecting structural safety and service life, highlighting the urgent need for advanced technologies to achieve accurate corrosion detection and quantitative area assessment. This study proposed a deep learning-based intelligent detection and area measurement approach for steel structure corrosion. A total of eight models from three algorithmic families including You Only Look Once (YOLO) series, Mask R-convolutional neural network, and You Only Look At CoefficienTs were trained for pixel-level semantic segmentation of corrosion regions. To enhance the detection accuracy and robustness of small-scale corrosion areas, the YOLOv11 and YOLOv12 models were improved by introducing the hierarchical feature pyramid network feature fusion module and the convolutional block attention module (CBAM) attention mechanism, respectively. The optimal model was then identified through comparative analysis, and corrosion area quantification was performed based on semantic segmentation results. Finally, the optimal model and the area measurement algorithm were integrated to achieve intelligent corrosion detection and area evaluation for steel structures. The results demonstrate that the improved YOLO models achieve significantly better overall performance, making them well suited to corrosion detection tasks. In particular, the YOLOv12 model with the CBAM attention mechanism exhibits the best performance in detecting and segmenting corrosion regions, especially for small-scale corrosion.