人工神经网络算法在粗晶Ti_(2)AlNb合金本构关系模型建立中的应用

Application of Artificial Neural Network in Establishment of Constitutive Relationship Model of CoarseGrained Ti_(2)AlNb Alloy

用CS1110C热拉伸试验机对粗晶Ti-22Al-25Nb合金进行了热拉伸试验,并结合试验结果构建了合金流动应力同变形温度、应变速率的人工神经网络模型。结果表明,人工神经网络建立的本构关系模型能较好的描述该合金的热变形行为,且精度优于传统回归模型获得的本构方程的精度,有良好的实用价值。

The hot tensile test of coarse-grained Ti-22Al-25Nb alloy was carried out by CS1110C hot tensile testing machine.Combined with the test results,the artificial neural network model of alloy flow stress with deformation temperature and strain rate was constructed.The results show that the constitutive relationship model established by artificial neural network can better describe the thermal deformation behavior of the alloy,and the accuracy is better than that of the constitutive equation obtained by traditional regression model,which has good practical value.