Metals are often subjected to various types of stresses, usually under tensile stress, quick failure material can be encouraged especially when poor combinations process parameters employed in joining the material. Tensile strength is regarded as maximum stress that a sustain tension. The aim this study predict weld tungsten inert gas (TIG) mild steel welds using Response Surface Methodology (R...

This paper proposes a machine learning based methodology for predicting the buckling response of tubular structures. An extensive dataset force-time curves is generated using calibrated finite element model within parametric space where highly non-linear. Based on fully connected neural network template, hyper-parameters are determined and resulting evaluated separate test set, with regard to m...