Composite action between the components of the concrete-filled steel tube (CFT) is complex and it is difficult to accurately obtain the experimental relationship between the steel tube and the core concrete of CFT columns. The triaxially stressed core concrete has been studied by hydrostatic test in past research, while little research has been focused on the mechanical behavior of steel tube of CFT columns. It is difficult to obtain the experimental constitutive relationship of the steel tube of CFT columns to reflect the real-time influence of biaxial stress state and local buckling of steel plate on the steel tube. To clarify the mechanical behavior of the steel tube of CFT columns, this paper proposed an elastoplastic analytical method considering biaxial stress state and local buckling of steel tube to obtain the stress–strain curve of the steel tube. This method applied the Hook’s law and the plasticity theory to interpret the information conveyed by the measured vertical and hoop strain histories of the steel tube. To verify its effectiveness, 11 circular concrete-filled steel tube stub columns were fabricated and tested under axial compression. Superposition results of the axial load–strain of steel tube and core concrete were compared against the experimental curves. The widely used Sakino–Sun model of the confined concrete was adopted to calculate the axial load–strain curve of the core concrete. Satisfactory agreements between the calculated and experimental results confirmed the rationality of the proposed method in tracing the constitutive relation of the biaxially stressed steel tube even after the occurrence of the local buckling. The obtained stress–strain relationship is critical for establishment of mathematical constitutive model and finite element model of steel tube.

The flexible high-neck flange is connected to the circular hollow section (CHS) tube through welding, and the placement of the weld seam and corresponding stress concentration factor (SCF) are crucial determinants of the joint’s fatigue performance. In this study, three hybrid models combining ant colony optimization (ACO), a genetic algorithm (GA), and grey wolf optimization (GWO) with a random forest (RF) model were developed to predict the stress distribution on the inner and outer walls of the CHS tube under different flange parameter combinations. To achieve this, an automated finite element (FE) analysis program for flexible high-neck flange joints was initially developed based on ABAQUS 2020 software. Parameter combinations were randomly selected within a reasonable range to simulate the nonlinear mechanical behavior of the joint under uniform tension, generating a dataset comprising 5417 sets of data. The accuracy of the FE model was validated through experimental data from the literature. Based on this, feature importance analysis was conducted to reveal the influence of different variable parameters on the stress distribution in the tube of the joint. The flange parameters and tube stress distribution are considered as inputs and outputs, respectively. Three hybrid RF models, specifically ant colony optimization-based random forest (ACO-RF), genetic algorithm-based random forest (GA-RF), and grey wolf optimization-based random forest (GWO-RF), are trained for regression prediction. The results demonstrate that the three hybrid models outperform the original machine learning model in predictive accuracy. The ACO-RF model achieved the highest accuracy with average coefficients of determination ($R_{mean}^2$) of 0.9983 and 0.9865 on the testing and training sets, respectively. Building upon this foundation, the study developed a corresponding open-source graphical user interface (GUI) as a tool for facilitating computations and visualizing results. Finally, a case study on fatigue damage assessment of a flexible high-neck flange joint in a wind-turbine tower is presented to demonstrate the application of the proposed model in this study.