A parametric study for distortional buckling stress on cold-formed steel using a neural network

The process of prediction of distortional buckling stress of cold-formed steel members is often cumbersome and it is also difficult to perform parametric studies in this field to investigate the effect of geometric parameters on Elastic Distortional Buckling Stress (EDBS). To overcome this difficulty a neural network based model and formulation which was presented in a companion paper by the author [Pala M. A new formulation for distortional buckling stress in cold formed steel members. Journal of Constructional Steel Research 2006;62:716–22] is proposed as an alternative approach to investigate the effect of geometric parameters on distortional buckling stress. The model considers the effect of web height, flange width, angle of lip, lip length and flange thickness. The results of the Neural Network model are quite satisfactory and are consistent with the literature.