(哈尔滨工业大学 材料科学与工程学院，哈尔滨 150001)
摘 要: 研究了变形参数对Ti-15-3合金热变形后晶粒轴比的影响，并采用人工神经网络方法建立了其晶粒轴比与变形程度、变形速率和变形 温度之间的数学模型。将此模型与热力耦合刚粘塑性有限元方法相结，对Ti-15-3合金热反挤成型过程的晶粒轴比场进行数值模拟和相应实验研究，结果表明，预测值与实测值吻合较好。
关键字: Ti-15-3合金；人工神经网络；晶粒轴比；有限元法
of grain axial ratio of Ti-15-3
alloy during hot deformation
（School of Materials Science and Engineering，
Harbin Institute of Technology，Harbin 150001,China）
Abstract:The effect of processing parameters on the grain axial ratio of Ti-15-3 was studied and the predicting model for the relation between grain axial ratio and strain，strain rate and temperature for Ti-15-3 alloy was developed by an artificial neural network method.This model was incorporated into rigid-viscoplastic thermo-coupled finite element method and the hot back-extrusion process of Ti-15-3 alloy was simulated. Corresponding experimental research was performed.The coincidence of the predicted results with measured ones shows that the method is able to successfully predict the grain axial ratio of Ti-15-3 alloy after hot deformation.
Key words: Ti-15-3 alloy；artificial neural network; grain axial ratio; finite element method
