Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金本构关系的BP神经网络模型

王克鲁; 鲁世强; 李鑫; 董显娟; 杨化娟

试验研究 | 浏览量 : 0 下载量: 211 CSCD: 3

导出
分享
收藏
专辑

Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金本构关系的BP神经网络模型
A Constitutive Relation Model for the Ti-6.5Al-3.5Mo-1.5Zr-0.3Si Alloy Based on BP Neural Network
2008年第8期页码：575-578
纸质出版日期： 2008 ，
DOI：

扫描看全文

[1]王克鲁,鲁世强,李鑫,董显娟,杨化娟.Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金本构关系的BP神经网络模型[J].特种铸造及有色合金,2008(08):575-578+569.

Wang Kelu, Lu Shiqiang, Li Xin, et al. A Constitutive Relation Model for the Ti-6.5Al-3.5Mo-1.5Zr-0.3Si Alloy Based on BP Neural Network[J]. Special Casting & Nonferrous Alloys, 2008,(8):575-578.
[1]王克鲁,鲁世强,李鑫,董显娟,杨化娟.Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金本构关系的BP神经网络模型[J].特种铸造及有色合金,2008(08):575-578+569. DOI：

Wang Kelu, Lu Shiqiang, Li Xin, et al. A Constitutive Relation Model for the Ti-6.5Al-3.5Mo-1.5Zr-0.3Si Alloy Based on BP Neural Network[J]. Special Casting & Nonferrous Alloys, 2008,(8):575-578. DOI：

摘要

利用THERMECMASTOR-Z型热力模拟试验机

在变形温度为780

080℃

应变速率为0.001

0.0s-1条件下对Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金进行等温恒应变速率压缩试验

获得不同变形温度、不同应变速率和不同真应变下的流动应力数据。结合试验数据和神经网络知识

构建了采用BP算法的人工神经网络

训练结束后的神经网络即成为Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金的一个知识基的本构关系模型。利用所建立的BP网络模型对材料的流动应力进行了预测

发现预测值与试验数据吻合良好

说明该BP网络本构关系模型具有较高的精度

可用于指导Ti-6.5Al-3.5Mo-1.5Zr-0.3Si合金热加工工艺的制定。

Abstract

The hot deformation behavior of Ti-6.5Al-3.5Mo-1.5Zr-0.3Si alloy was investigated with THERMECMASTOR-Z tester at strain rates of 0.001 s-1

0 s-1 at temperature of 780

080 ℃

obtaining the flow stress data at varied temperatures and varied strain rates as well as different true strain. Based on experimental data and neural network knowledge

a BP neural network with error-back propagation algorithm was established

which forms a knowledge-based constitutive relation model after training. The flow stress in the alloys was predicted by the BP neural network model. The results show that the predicted results are well in agreement with the experimental ones

confirming the availability of the model.