Lightweight Kolmogorov-Arnold Network with dual-objective optimization for axial capacity prediction of square coal gangue concrete-filled steel tube stub columns based on finite element simulation

Square coal gangue concrete-filled steel tube (CGCFST) stub columns offer both environmental benefits from solid waste utilization and enhanced mechanical performance from steel tube confinement. However, accurate prediction of their axial compressive bearing capacity ( N _u ) remains challenging due to the absence of dedicated design codes and limitations of existing machine learning approaches. Specifically, tree-based models yield piecewise constant predictions incapable of capturing the smooth continuous parameter relationship, while conventional neural networks struggle to balance model compactness with prediction accuracy. To address these gaps, this study proposes a dual-objective optimized Kolmogorov-Arnold Network (KAN) framework that simultaneously minimizes root mean square error ( RMSE ) and model complexity (edge function count). A parametric database of 1470 samples was generated via ABAQUS batch simulations, covering five key design parameters: cross-section side length ( D ), steel tube thickness ( t ), coal gangue replacement ratio ( r ), concrete compressive strength ( f _c ' ), and steel yield strength ( f _y ). Six existing design codes were systematically evaluated, revealing significant errors when applied to CGCFST. The optimized KAN achieves a coefficient of determination ( R ² ) of 0.9993, outperforming Multilayer Perceptron (MLP) variants and all other Bayesian-optimized tree models except Extreme Gradient Boosting (XGBoost), while providing inherently continuous predictions. After two pruning iterations, KAN retains high accuracy ( R ² = 0.9713) with only 2.8% degradation, confirming its lightweight potential. Sensitivity and parametric analyses quantify the contribution of each design parameter to N _u . Finally, a Graphical User Interface (GUI) integrating ABAQUS batch simulation with KAN prediction is developed to facilitate rapid and accurate capacity assessment for engineering applications.