摘要
使用Gleeble-3800对锻态Ti6242s钛合金在温度950-1010℃、应变速率0.01-10 s^(-1)的条件下进行了75%变形量的热压缩模拟试验。基于实验取得的真应力-真应变曲线,分别使用人工神经网络(ANN)和Arrhenius方程建立Ti6242s合金本构模型,研究其热变形行为。结果表明:流变应力在变形开始后迅速上升至峰值应力,随后硬化与软化达到动态平衡,在真应变达到0.6后加工硬化逐渐占据主导,硬化幅度随应变速率的增大而提高;人工神经网络本构模型预测值的平均相对误差(AARE)为2.25%,决定系数(R2)为0.99906;Arrhenius方程本构模型预测值的AARE为14.40%,R2为0.95468,精度在参数范围内波动较大;ANN本构模型精度远高于Arrhenius本构模型,且在整个参数范围内具有一致的精度;ANN本构模型具有良好的泛化能力,在实验参数范围外预测流变应力仍具有较高的精度。
The forged Ti6242 s titanium alloy was subjected to a thermal compression simulation experiment with 75% deformation at 950-1010 ℃ and a strain rate of 0.01-10 s^(-1) by Gleeble-3800. Based on the true stress-true strain curve obtained from the experiment, the artificial neural network(ANN) and Arrhenius equation were used to establish the constitutive model of Ti6242 s alloy, and its thermal deformation behavior was studied. The results show that the flow stress rapidly rises to the peak stress after the deformation begins, and then the hardening and softening reach a dynamic balance. After the true strain reaches 0.6, the work hardening gradually dominates, and the hardening amplitude increases with the increase of the strain rate. The average relative error(AARE) of the artificial neural network predicted value of the constitutive model is 2.25%, and the coefficient of determination(R2) is 0.999 06;the AARE of the predicted value of the Arrhenius equation constitutive model is 14.40%, R2 is 0.954 68, and the accuracy fluctuates greatly within the parameter range. The accuracy of the ANN constitutive model is much higher than that of the Arrhenius constitutive model, and it is consistent in the entire parameter range;the ANN constitutive model has good generalization ability, and it still has high accuracy in predicting flow stress outside the range of experimental parameters.
作者
雷锦文
薛祥义
张思远
任勇
王凯旋
辛社伟
李倩
Lei Jinwen;Xue Xiangyi;Zhang Siyuan;Ren Yong;Wang Kaixuan;Xin Shewei;Li Qian(Northwestern Polytechnical University,Xi'an 710129,China;Western Superconducting Technologies Co.,Ltd,Xi'an 710018,China;Northwest Institute for Nonferrous Metal Research,Xi’an 710016,China)
出处
《稀有金属材料与工程》
SCIE
EI
CAS
CSCD
北大核心
2021年第6期2025-2032,共8页
Rare Metal Materials and Engineering
基金
国家自然科学基金(51871176)
陕西省自然科学基金(2018JM5098)
陕西省重点研发计划(2019KW-030)。
