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

► The Arrhenius-type constitutive and BP neural network model are obtained of flowing stress for XC45steel. ► The predictabilities of these two models can be evaluated based on the correlation coefficient, root mean square error and average absolute relative error. ► It can be found that the BP neural network model is better than the Arrhenius-type constitutive model in the predictable ability through several comparison methods.