摘要

Isothermal compression experiment was performed on TiAl-based alloy prepared by the elemental powder method using Gleeble-1500D thermal simulator at the experimental temperature of 1100-1200℃ and strain rate of 0.1-0.001 s-1. The research results show that obvious dynamic recrystallization of powder metallurgy Ti-44Al-2Cr-4Nb-0.2W-0.2B alloy appears during isothermal constant strain rate compression process, and the flow stress is characterized by flow softening, and the flow stress decreases with the increase of deformation temperature and increases with the increase of strain rate; the activation energy obtained under peak stress is 563.67 kJ?mol-1. A constitutive model of the alloy was established based on BP neural network. The results show that the fitting correlation coefficient between the predicted and experimental values is 0.9995. The average relative error of the established constitutive model is within 4%. By comparing with various statistical parameters of the prediction results of Arrhenius-type constitutive model, it is found that the BP neural network model has a better prediction effect and can objectively and truly describe the high temperature plastic deformation behavior of Ti-44Al-2Cr-4Nb-0.2W-0.2B alloy.

全文