+高级检索
基于BP网络Ti-6Al-3Nb-2Zr-1Mo合金等温压缩流变应力预测
DOI:
作者:
作者单位:

西北工业大学,西部超导材料科技股份有限公司,西北工业大学,西部超导材料科技股份有限公司,西部超导材料科技股份有限公司,西北工业大学,西北工业大学,西北工业大学

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金资助项目(59493300);教育部博士点基金资助项目(9800462)


Isothermal compression flow stress prediction of Ti-6Al-3Nb-2Zr-1Mo alloy based on BP-ANN
Author:
Affiliation:

State Key Laboratory of Solidification Processing,Northwestern Polytechnical University,Xi’an,Western Superconducting Technologies Co., Ltd., Xi’an,State Key Laboratory of Solidification Processing,Northwestern Polytechnical University,Xi’an,Western Superconducting Technologies Co,Ltd,Xi’an,Western Superconducting Technologies Co., Ltd., Xi’an,State Key Laboratory of Solidification Processing,Northwestern Polytechnical University,Xi’an,State Key Laboratory of Solidification Processing,Northwestern Polytechnical University,Xi’an,State Key Laboratory of Solidification Processing,Northwestern Polytechnical University,Xi’an

Fund Project:

National International Scientific and Technological Cooperation Projects (2013DFB50180); Shaanxi Province Science and Technology Integrated Innovation Project (2015KTTSG01-08)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    通过对Ti-6Al-3Nb-2Zr-1Mo合金820-970℃, 0.001-1s-1条件下的热模拟压缩试验,得到不同变形条件下的高温变形真应力-真应变曲线。基于此实验数据建立了该合金BP-ANN本构预测模型和传统的回归模型。结果表明:两个模型的最大相对误差分别为4.35%和13.9%,平均绝对误差AARE分别为1.42%和6.53%,说明BP-ANN模型具有较优异的预测能力,此模型可作为Ti-6Al-3Nb-2Zr-1Mo钛合金高温变形本构模型。

    Abstract:

    Elevated-temperature flow behavior of Ti-6Al-3Nb-2Zr-1Mo titanium alloy was investigated by conducting isothermal hot compression tests at strain rate from 0.001 to 1 s-1 and in the temperature range of 820~970 ℃ on Gleeble-3800 simulator. The BP-ANN and regression models were established based on the experimental flow stress. Results show that the absolute value of maximum relative error obtained from the ANN model and regression method were 4.35% and 13.9%, respectively. The average absolute relative errors are 1.42% and 6.53% corresponding to the ANN model and regression method, which demonstrates that BP-ANN has a better prediction precision, and it can be used as the constitutive model of Ti-6Al-3Nb-2Zr-1Mo titanium alloy.

    参考文献
    相似文献
    引证文献
引用本文

陈海生,冯 勇,马凡蛟,毛友川,刘向宏,张平祥,寇宏超,傅恒志.基于BP网络Ti-6Al-3Nb-2Zr-1Mo合金等温压缩流变应力预测[J].稀有金属材料与工程,2016,45(6):1549~1553.[Chen Haisheng, Feng Yong, Ma Fanjiao, Mao Youchuan, Liu Xianghong, Zhang Pingxiang, Kou Hongchao, Fu Hengzhi. Isothermal compression flow stress prediction of Ti-6Al-3Nb-2Zr-1Mo alloy based on BP-ANN[J]. Rare Metal Materials and Engineering,2016,45(6):1549~1553.]
DOI:[doi]

复制
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2015-12-02
  • 最后修改日期:2016-03-13
  • 录用日期:2016-03-25
  • 在线发布日期: 2016-10-08
  • 出版日期: