Two flowing stress models for hot deformation of XC45 steel at high temperature

Arrhenius-type constitutive equation considering strain compensation and BP neural network model are used to analyze the hot deformation behavior of XC45 steel. The experimental data are acquired from hot compression tests in Gleeble-1500 thermal–mechanical simulator in the range of temperature from 1053 K to 1253 K and strain rates from 0.01 s−1 to 10 s−1. The predictabilities of Arrhenius-type constitutive model and back propagation (BP) neural network model can be evaluated based on the correlation coefficient (R), root mean square error (RMSE) and average absolute relative error (AARE), and their predictabilities can be compared through several verification methods. It can be found that the BP neural network model is better in the predictable ability than the Arrhenius-type constitutive model.