Exploring Machine Learning for the Stability Analysis of Rotary‐straightened Steel Members with Multiple Stiffness Reduction Models

Abstract Rotary straightened structural steel cross‐sections have a different residual stress pattern compared to those without rotary straightening, which affects behavior, especially in members subjected inelastic buckling. A stiffness reduction material model for rotary‐straightened hot rolled sections was previously developed and validated specific set of cross‐section sizes load conditions. Previous research has indicated that the current specified Chapter C AISC 360 stability design does not accurately capture W‐shapes. Particularly, always derive conservative capacity with sections. This paper explores machine learning predicting beam‐column considering models estimating their limit capacity. Two extreme gradient boosting were beam‐columns under major or minor axis bending. The dataset contained 1,296 finite element simulations range geometries. Excellent prediction accuracy showed potential using analysis members.