| 引用本文: | 余晖,于化顺,YOU Bong-sun,郑超,闵光辉.基于人工神经网络的Mg-Zn-Zr-Ce合金热压缩变形研究[J].材料科学与工艺,2012,20(4):26-32,37.DOI:10.11951/j.issn.1005-0299.20120405. |
| YU Hui,YU Hua-shun,YOU Bong-sun,ZHENG Chao,MIN Guang-hui.Prediction of flow stress in Mg-Zn-Zr-Ce magnesium alloy by artificial neural network[J].Materials Science and Technology,2012,20(4):26-32,37.DOI:10.11951/j.issn.1005-0299.20120405. |
|
| 摘要: |
| 为研究含稀土元素铈的镁合金中高温流变行为,利用热模拟试验机对Mg-6Zn-0.5Zr-1.5Ce合金在变形温度523～673 K、应变速率0.001～1 s-1范围内进行热压缩实验.基于真应力真应变实验数据构建了单隐层前馈误差反向传播人工神经网络模型,利用该模型对ZK60-1.5Ce合金的流变应力行为进行预测,并分析了变形温度、应变速率与真应变对流变应力的影响.研究表明:Ce添加可显著细化晶粒;该镁合金的流变应力随变形温度降低和应变速率升高而增加;其流变应力行为可用双曲正弦函数进行描述,依据峰值应力拟合求得该合金的表观激活能为161.13 kJ/mol;变形温度和应变速率对流变应力的影响高于真应变.所建立的人工神经网络模型可以很好地描述该镁合金的流变应力,其预测值与实验数值吻合良好. |
| 关键词: 镁合金 流变应力 热压缩变形 本构关系 人工神经网络 |
| DOI：10.11951/j.issn.1005-0299.20120405 |
| 分类号: |
| 基金项目:韩国材料科学研究院项目(R&D Program);韩国知识经济部项目(World Premier Materials Program). |
|
| Prediction of flow stress in Mg-Zn-Zr-Ce magnesium alloy by artificial neural network |
|
YU Hui1,2, YU Hua-shun1, YOU Bong-sun2, ZHENG Chao1, MIN Guang-hui1
|
|
1.Key Laboratory for Liquid-solid Evolution and Processing of Materials,Ministry of Education,School of Materials Science and Engineering,Shandong University,Jinan 250061,China;2.ALMG Research Group,Light Metal Division,Korea Institute of Materials Science,Changwon 642831,South Korea
|
| Abstract: |
| To investigate the rheological behavior of ZK60 alloy with rare earth addition,a T4-treated Mg-6Zn-0.5Zr-1.5Ce magnesium alloy was investigated by compressive test using Gleeble 3800 thermal-simulator.The deformation temperature and the strain rate are in the range of 523～673 K and 0.001～1 s-1,respectively.According to the true strain-true stress curves,a feed-forward back-propagation artificial neural network (ANN) was established to study the flow behaviors.We found that the addition of Ce resulted in refinement of microstructure.The flow stress increased as the deformation temperature decreased or as the strain rate increased.The flow stress behavior can be described using the hyperbolic sine constitutive equation and the average activation energy of this alloy was calculated as 161.13 kJ/mol.The effects of deformation temperature,strain rate and strain on the flow stress behavior were studied by comparing the experimental and predicted results using the developed ANN model.A good agreement between experimental and predicted result was obtained. |
| Key words: Mg alloy flow stress deformation behavior constitutive equation artificial neural network |
