Flow Stress Behavior and Constitutive Model Based on Artificial Neural Network of Ti60 Alloy

Wang  Tianxiang; Lu Shiqiang; Wang Kelu; Ouyang Delai; Yao Quan

doi:10.15980/j.tzzz.2020.09.022

Views : 0 下载量: 98 CSCD: 0

Export
Share
Collection
Album

Flow Stress Behavior and Constitutive Model Based on Artificial Neural Network of Ti60 Alloy
Vol. 40, Issue 9, Pages: 1019-1023(2020)
Published： 2020 ，
DOI： 10.15980/j.tzzz.2020.09.022

扫描看全文

[1]王天祥,鲁世强,王克鲁,欧阳德来,姚泉.Ti60合金的流变应力行为及人工神经网络本构模型[J].特种铸造及有色合金,2020,40(09):1019-1023.

Wang Tianxiang, Lu Shiqiang, Wang Kelu, et al. Flow Stress Behavior and Constitutive Model Based on Artificial Neural Network of Ti60 Alloy. [J]. Special Casting & Nonferrous Alloys 40(9):1019-1023(2020)
[1]王天祥,鲁世强,王克鲁,欧阳德来,姚泉.Ti60合金的流变应力行为及人工神经网络本构模型[J].特种铸造及有色合金,2020,40(09):1019-1023. DOI： 10.15980/j.tzzz.2020.09.022.

Wang Tianxiang, Lu Shiqiang, Wang Kelu, et al. Flow Stress Behavior and Constitutive Model Based on Artificial Neural Network of Ti60 Alloy. [J]. Special Casting & Nonferrous Alloys 40(9):1019-1023(2020) DOI： 10.15980/j.tzzz.2020.09.022.

摘要

采用Thermecmaster-Z型热加工模拟试验机对Ti60合金试样进行等温恒应变速率压缩试验

研究该合金在变形温度为600～950℃

应变速率为0.001～10s

-1

条件下的流变应力行为

并构建人工神经网络（ANN）本构模型。结果表明

Ti60合金的流变应力随变形温度的升高和应变速率的下降而减小。在不同的变形条件下

Ti60合金的流变应力-应变曲线分别呈现流动稳态型和流动软化型两种特征。基于ANN所建立的本构模型预测精度高

流变应力试验值与预测值之间的相对误差在±5%以内

平均相对误差为1.82%

且相关系数趋近于1

能准确地描述并预测Ti60合金的流变应力行为。

Abstract

The isothermal constant strain rate compression experiment of Ti60 alloy samples was carried out by Thermecmaster-Zthermal processing simulation machine.The flow stress behavior of the alloy in at 600～950℃and 0.001～10 s

-1

was investigated

and the artificial neural network（ANN）constitutive model was constructed.The results reveal that the flow stress of Ti60 alloy is decreased with the increase of deformation temperature and the decrease of strain rate.The flow stress-strain curves of Ti60 alloy is characterized by steady flow type and soft flow type under different deformation conditions.The constitutive model established based on ANN has the satisfied prediction accuracy.The relative error between the experimental value of flow stress and the predicted value is basically ranged within ±5%

and the average relative error is 1.82%

meanwhile

the correlation coefficient tends to 1

which can accurately describe and predict the flow stress behavior of Ti60 alloy.