基于BP神经网络Ti600合金本构关系模型的建立

运用Gleeble-1500热模拟机对Ti600合金的圆柱试样进行等温压缩变形试验，以试验所得数据（变形温度800~1100 ℃，应变速率0.01~10 s-1）为基础，基于BP神经网络方法建立了该合金的高温本构关系模型。结果表明：BP神经网络本构关系模型具有很高的预测精度，可以很好地描述Ti600合金在高温变形时各热力学参数之间高度非线性的复杂关系，为本构关系模型的建立提供了一种更加准确有效的方法。

Modeling of Constitutive Relationship of Ti600 Alloy Using BP Artificial Neural Network

Isothermal compression deformation tests were conducted for Ti600 alloy column samples by Gleeble-1500 thermal simulator. According to the obtained experimental data (deformation temperatures of 800-1100 oC and strain rates of 0.01-10 s-1), the high temperature constitutive relationship model for the alloy was built based on the BP neural network. Results show that the constitutive relationship model of BP neural network is of high prediction accuracy, which can describe the complicated nonlinear relationship of thermodynamical parameters well. Therefore it provides a more convenient and more effective way to establish the model of constitutive relationship for titanium alloys.