Explainable machine learning models for predicting the ultimate bending capacity of slotted perforated cold-formed steel beams under distortional buckling

Abstract

This study develops explainable machine learning (ML) models to predict the ultimate bending capacity of cold-formed steel (CFS) beams with staggered slotted perforations, focusing on distortional buckling behavior. Utilizing a dataset from 432 non-linear finite element analysis simulations of CFS Lipped channels, ten ML algorithms, including four basic and six ensemble models, were evaluated. Ensemble models, specifically CatBoost and XGBoost, demonstrated superior accuracy, with test-set performances reaching a coefficient of determination ( R 2 ) of 99.9%, outperforming traditional analytical methods such as the Direct Strength Method (DSM). SHapley Additive Explanations (SHAP) were applied to highlight how features like plate thickness and root radius critically influence predictions. The findings underscore the enhanced predictive capabilities of ML models for structural performance, suggesting a significant potential to refine traditional design methodologies and optimize CFS beam designs. • Evaluated 10 ML models on slotted CFS beams; CatBoost and XGBoost were top performers. • Achieved 99.9% accuracy with CatBoost and XGBoost, surpassing other methods. • SHAP analysis highlighted thickness and corner radius as critical factors. • Demonstrated ML’s edge over empirical methods in bending capacity prediction. • Insights provided for optimizing slotted CFS beam design and efficiency.