基于BP神经网络的TA15钛合金流动应力预测  

Flow Stress Model of TA15 Titanium Alloy Based on BP Neural Network

作　　者：朱景川[1] 王洋[1] 岳洋[1] 尤逢海 

机构地区：[1]哈尔滨工业大学材料科学与工程学院,黑龙江哈尔滨150001 [2]北京航星机器制造公司,北京100013

出　　处：《热处理技术与装备》2008年第1期36-38,共3页Heat Treatment Technology and Equipment

摘　　要：利用Gleeble 1500热模拟机进行了TA15钛合金不同变形温度、变形程度和应变速率条件下的热压缩试验。在试验数据基础上,应用BP神经网络建立TA15钛合金高温变形本构关系。研究结果表明,通过BP神经网络得到的流动应力具有较高的精度,能够客观地反映TA15钛合金在塑性加工过程中的动态行为,具有重要的工程应用价值。Thermal compressive tests of TA15 titanium alloy at different temperatures, strain and strain rate were carried on Gleeble 1500 thermal simulator. Based on the test data, constitutive relation was set up through BP neural network. The results show that the flow stress caculated from BP neural network is precise and reflects the dynamic behavior of TA15 titanium alloy during plastic process. BP neural network has valuable application in engineering.

关 键 词：神经网络 TA15钛合金 流变应力 本构关系 

分 类 号：TG146.23[一般工业技术—材料科学与工程]