Constitutive and Artificial Neural Network Modeling to Predict Hot Deformation Behavior of CoFeMnNiTi Eutectic High-Entropy Alloy

In the present work, the Arrhenius-type constitutive equation and artificial neural network (ANN) model have been used to predict the hot deformation behavior of CoFeMnNiTi eutectic high-entropy alloy in the temperature range 1073-1273 K and strain rate range 0.001-1 s(-1). The performance of both models is assessed by using the coefficient of correlation (R) and average absolute relative error (AARE). The ANN model with R = 0.9997 and AARE = 1.52 % better predicts flow behavior than the Arrhenius type model with R = 0.9769 and AARE = 11.5 %. The rate of softening and mean free path value are also evaluated at different thermomechanical conditions to understand the deformation mechanism. The compressive flow behavior of EHEA also studied and understood the softening and globularization phenomenon during deformation and proposed the deformation mechanism.

Automated summary

In this study, the hot deformation behavior of the CoFeMnNiTi eutectic high-entropy alloy was predicted using the Arrhenius-type constitutive equation and artificial neural network (ANN) model. The performance of both models was compared using correlation coefficient (R) and average absolute relative error (AARE), and the ANN model outperformed the Arrhenius type model in predicting flow behavior. The rate of softening and mean free path value were also evaluated to understand the deformation mechanism under different thermomechanical conditions.