High-precision Constitutive Model of Ti6242s Alloy Hot Deformation Based on Artificial Neural Network

The forged Ti6242s titanium alloy was subjected to a thermal compression simulation experiment with 75% deformation at 950 similar to 1010 degrees C and a strain rate of 0.01 similar to 10 s(-1) by Gleeble-3800. Based on the true stress-true strain curve obtained from the experiment, the artificial neural network (ANN) and Arrhenius equation were used to establish the constitutive model of Ti6242s alloy, and its thermal deformation behavior was studied. The results show that the flow stress rapidly rises to the peak stress after the deformation begins, and then the hardening and softening reach a dynamic balance. After the true strain reaches 0.6, the work hardening gradually dominates, and the hardening amplitude increases with the increase of the strain rate. The average relative error (AARE) of the artificial neural network predicted value of the constitutive model is 2.25%, and the coefficient of determination (R-2) is 0.999 06; the AARE of the predicted value of the Arrhenius equation constitutive model is 14.40%, R-2 is 0.954 68, and the accuracy fluctuates greatly within the parameter range. The accuracy of the ANN constitutive model is much higher than that of the Arrhenius constitutive model, and it is consistent in the entire parameter range; the ANN constitutive model has good generalization ability, and it still has high accuracy in predicting flow stress outside the range of experimental parameters.