Abstract
Hot compression experiments of 316LN stainless steel were carried out on Gleeble-3500 thermo-simulator in deformation temperature range of 1 223–1 423 K and strain rate range of 0.001–1 s−1. The flow behavior was investigated to evaluate the workability and optimize the hot forging process of 316LN stainless steel pipes. Constitutive relationship of 316LN stainless steel was comparatively studied by a modified Arrhenius-type analytical constitutive model considering the effect of strain and by an artificial neural network model. The accuracy and effectiveness of two models were respectively quantified by the correlation coefficient and absolute average relative error. The results show that both models have high reliabilities and could meet the requirements of engineering calculation. Compared with the analytical constitutive model, the artificial neural network model has a relatively higher predictability and is easier to work in cooperation with finite element analysis software.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have