Prediction of axial compressive capacity and interpretability analysis of web perforated Σ-shaped cold-formed steel

Abstract

The Σ-shaped cold-formed steel with web opening (ΣSCFSWWO) is a critical component in modern structural systems, and accurate calculations of its axial compressive capacity are essential for ensuring the overall stability and safety of structures. However, traditional finite element analysis (FEA) and experimental methods are often inefficient and require complex modeling techniques for capacity calculations. Moreover, the interaction between section design parameters and structural capacity remains unclear. This study integrates FEA, experimental methods, and machine learning to propose a novel approach for predicting capacity and analyzing parameter interpretability. A dataset comprising 1000 numerical simulation results and 260 experimental data points was established. Machine learning techniques, including BP (Backpropagation) neural networks, RBF (Radial Basis Function) neural networks, Decision trees, Random Forests, and XGBoost algorithms, were employed to develop predictive models for capacity. The SHapley Additive exPlanation (SHAP) method was utilized for interpretability analysis. Results indicate a good correlation between FEA and experimental outcomes, effectively simulating the mechanical behavior of the components. Comparative analysis reveals that the XGBoost model demonstrates the highest predictive accuracy and generalization capability. SHAP analysis elucidates the influence of various input parameters on axial compressive capacity predictions and clarifies the interactions among these parameters. This research provides a novel reference for calculating the axial compressive capacity of ΣSCFSWWO, and the proposed methodologies can be extended to other similar components.