Neural network model for improvement of strength–ductility compromise in low carbon sheet steels

Abstract

The goal of the work reported in the present paper is to develop a neural network model for describing the evolution of the compromise (UTS × EL) between ultimate tensile strength (UTS), and elongation (EL) mechanical properties on low carbon sheet steels. The model presented here take into account the influence of 21 parameters describing chemical composition, and thermomechanical processes such as austenite and ferrite rolling, coiling, cold working and subsequent annealing involved in the production route of low carbon steels. The results presented in the present paper demonstrate that this model can help with optimising simultaneously both strength and ductility for the various types of forming operation that the sheets can be subjected to.