摘要
利用Gleeble-1500热模拟实验机，进行了Ti-26合金等温恒应变速率压缩试验，获得了不同温度（700～940oC）、应变速率（0．01～10s^-1）、真应变下的流变应力数据。基于实验数据，根据BP人工神经网络原理算法，建立了Ti-26钛合金高温塑性变形时流变应力的预测模型，训练结束后的神经网络即成为Ti-26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，可用于指导Ti-26钛合金热加工工艺的制定及热成形过程的有限元模拟。
Thermal compressive tests of Ti-26 titanium alloy at different temperatures, strain and strain rate were carried on Gleeble 1 500 thermal simulator. Based on the experimental data and network knowledge, an artificial neural network with back propagation algorithm was established and knowledge based constitutive relationship model was developed after training. Error analysis shows that the neural network model for constitutive relationship has higher predicted precision, and it can be used for guiding the hot forming process and applied in finite element simulation of Ti-26 titanium alloy.
出处
《钛工业进展》
CAS
2010年第1期39-43,共5页
Titanium Industry Progress
基金
国家重点基础研究发展计划(973计划)(2007CB613805)
关键词
Ti-26钛合金
神经网络
本构关系
Ti-26 titanium alloy
neural network
constitutive relationship
