摘要

In the present work, the isothermal compression tests of PM alloy Ti-47Al-2Nb-2Cr were carried out in the temperature range of 950-1200 degrees C. A Gleeble 1500D thermosimulation machine was used, and samples were tested at strain rates ranging from 10(-3) to 10(-1) s(-1). Based on the obtained flow stress curves, the hot deformation behavior was presented. The constitutive relationship of powder metallurgy (PM) Ti-47Al-2Nb-2Cr alloy was developed using an Arrhenius-type constitutive model that involves strain compensation in addition to an artificial neural network model. The accuracy and reliability of the developed models were quantified in terms of statistical parameters such as correlation coefficient and absolute value of relative error. It was found that deformation temperature and strain rate have obvious effects on the flow characteristics, and the flow stress increases with the increasing strain rate and the decreasing temperature. Moreover, the proposed models possess excellent prediction capability of flow stresses for the present alloy during hot deformation. Compared with the traditional Arrhenius-type model, the backpropagation neural network model is more accurate when presenting the isothermal compressing deformation behavior at elevated temperatures for PM Ti-47Al-2Nb-2Cr alloy.