(1. 西安交通大学 金属材料强度国家重点实验室，西安 710049；
2. 西北有色金属研究院，西安 710016)
摘 要: 通过热压缩试验研究热加工条件下Ti26高强钛合金的热变形行为。结果表明：随着温度的升高和应变速率的降低，Ti26合金的流变应力显著降低，表现为较强的速率敏感性和温度敏感性；而变形温度对流变应力的影响程度与应变速率的大小有关。根据BP人工神经网络原理算法，基于试验数据，建立了Ti26钛合金的一个知识基的本构关系模型。预测结果表明：该神经网络本构关系模型具有很高的精度，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。
关键字: Ti26合金；热压缩；流变应力；本构模型；神经网络
（1. State Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong University,
Xi’an 710049, China;
2. Northwest Institute for Nonferrous Metal Research, Xi’an 710016, China）
Abstract:Hot deformation behavior of Ti26 alloy was investigated by the compression tests. The results show that the flow stress of Ti26 alloy reduces with the increase of temperature and decrease of strain rate, which presents strong strain rate sensitivity and temperature sensitivity. The effect of deformation temperature on flow stress is correlated with the strain rate. Based on the BP network knowledge and experimental data, the knowledge based constitutive relationship model was established. The results show that the neural network model for constitutive relationship has a higher predicted precision, which can describe the complicated nonlinear relationship of thermodynamic parameters well. Therefore, it provides a more convenient and more effective way to establish the model of constitutive relationship for titanium alloys.
Key words: Ti26 titanium alloy; hot compression; flow stress; constitutiver model; neural network
