论文部分内容阅读
本构方程是描述材料变形的基本信息和有限元模拟中不可缺少的数学模型,反映了流动应力与应变、应变速率以及温度之间的相互关系。文章运用Gleeble-1500热模拟机对Ti-22Al-25Nb钛合金试样进行等温压缩变形试验,以试验所得数据(变形温度940℃～1030℃,应变速率0.001s-1～1s-1)为基础,采用BP神经网络的方法建立了该合金的高温本构关系,并与传统回归拟合的方法计算出的结果进行了对比。结果表明,BP神经网络本构关系模型的预测精度明显优于传统公式的计算结果,而且模型还可以很好地描述该合金在高温变形时,各热力学参数之间的复杂非线性关系,为该合金本构关系方程模型的建立,提供了一种便捷有效的方法。
The constitutive equation is an indispensable mathematical model describing the basic information of the material deformation and the finite element simulation. It reflects the interrelation between the flow stress and strain, strain rate and temperature. In this paper, the isothermal compressive deformation test of Ti-22Al-25Nb titanium alloy was performed by Gleeble-1500 thermal simulator. Based on the experimental data (deformation temperature 940 ℃ ~ 1030 ℃ and strain rate 0.001s-1 ~ 1s-1) The high temperature constitutive relation of the alloy was established by BP neural network and compared with the results calculated by the traditional regression fitting method. The results show that the predictive accuracy of the constitutive model of BP neural network is obviously superior to that of the traditional formulas, and the model can well describe the complex nonlinear relationship between the thermodynamic parameters of the alloy under high temperature deformation. The establishment of the alloy constitutive equation model provides a convenient and effective method.