Flow stress optimization for 304 stainless steel under cold and warm compression by artificial neural network and genetic algorithm

Abstract

Artificial neural network (ANN) and genetic algorithm were used in this study to obtain a relatively high flow stress in compression tests for 304 stainless steel. Cold and warm compression were carried out in a temperature range from 20 to 600 °C, strain-rate from 0.001 to 100 S −1 and a strain range from 0.1 to 0.5. Optimum conditions for each case were obtained experimentally and were evaluated by the ANN model. The ANN model was used as fitness function for genetic algorithm. The results indicated that this combined algorithm offers an effective condition for 304 stainless steel, which avoids flow localization, dynamic strain aging, adiabatic shear deformation and void generation.