锻压技术

基于深度神经网络的TA15高温拉伸变形行为精确预测

英文标题：Accurate prediction on TA15 high temperature tensile deformation behavior based on deep neural network

单位：1.华中科技大学材料成形与模具技术国家重点实验室 2. 黛杰汉金（沧州）精密模具有限公司 3.上海电机学院机械学院

分类号：TG301

出版年,卷(期):页码：2021,46(9):67-75

摘要：

通过不同温度（760、810、860和910 ℃）和不同应变速率（0.01、0.1和0.5 s-1）下的等温拉伸实验，研究了TA15钛合金板材的拉伸变形和软化行为。为了对TA15钛合金的高温拉伸变形行为实现精确预测，建立了基于深度神经网络（DNN）的TA15钛合金高温拉伸本构模型。结果表明，DNN模型能够准确地预测TA15钛合金在不同拉伸变形条件下的流动应力，预测结果与实际结果的平均绝对误差为1.3%，相关系数可达0.999。并且,相比于单个隐含层的神经网络，具有多个隐含层的DNN模型具有更高的预测精度和更好的泛化能力。此外，构建了TA15钛合金热加工图，并且通过理论分析验证了此热加工图，结果表明了此热加工图的准确性和有效性。

The tensile deformation and softening behavior of TA15 titanium alloy sheet were studied by isothermal tensile experiments at different temperatures (760, 810, 860, and 910 ℃) and different strain rates (0.01, 0.1 and 0.5 s-1）, and a high temperature tensile constitutive model of TA15 titanium alloy based on deep neural network (DNN) was established to accurately predict the high temperature tensile deformation behavior of TA15 titanium alloy. The results show that DNN model accurately predicts the flow stress of TA15 titanium alloy under different tensile deformation conditions, the average absolute error between the predicted results and the actual results is 1.3%, and the correlation coefficient reaches 0.999. Moreover, compared with a neural network with a single hidden layer, DNN model with multiple hidden layers has higher prediction accuracy and better generalization ability. In addition, the hot processing map of TA15 titanium alloy is constructed, and the theoretical analysis is carried out to verify the hot processing map, which shows the accuracy and effectiveness of the hot processing map.

基金项目：

国家自然科学基金重大项目（52090043）；华中科技大学自主创新基金（2020kfyXJJS053）

唐学峰（1989-），男，博士，讲师 E-mail：xftang@hust.edu.cn 通信作者：王新云（1973-），男，博士，教授 E-mail：wangxy_hust@hust.edu.cn

参考文献：

[1]李兴无, 沙爱学, 张旺峰, 等. TA15合金及其在飞机结构中的应用前景[J]. 钛工业进展, 2003，20(4-5): 90-94.

Li X W, Sha A X, Zhang W F, et al. TA15 titanium alloy and its applying prospects on airframe[J]. Titanium Industry Progress, 2003，20(4-5): 90-94.

[2]Zhang T, Liu Y, Sanders D G, et al. Development of fine-grain size titanium 6Al-4V alloy sheet material for low temperature superplastic forming[J]. Materials Science and Engineering: A, 2014，608: 265-272.

[3]Velay V, Matsumoto H, Vidal V, et al. Behavior modeling and microstructural evolutions of Ti-6Al-4V alloy under hot forming conditions[J]. International Journal of Mechanical Sciences, 2016，108-109: 1-13.

[4]Wu Y, Liu G, Wang K, et al. Loading path and microstructure study of Ti-3Al-2.5V tubular components within hot gas forming at 800 ℃[J]. International Journal of Advanced Manufacturing Technology, 2016, 87(5-8): 1823-1833.

[5]Kopec M, Wang K, Politis D J, et al. Formability and microstructure evolution mechanisms of Ti6Al4V alloy during a novel hot stamping process[J]. Materials Science and Engineering: A,2018, 719: 72-81.

[6]Souza P M, Beladi H, Singh R, et al. Constitutive analysis of hot deformation behavior of a Ti6Al4V alloy using physical based model[J]. Materials Science and Engineering: A, 2015,648: 265-273.

[7]刘海军, 张治民, 徐健, 等. 等离子烧结态TC4钛合金热变形行为及本构模型研究[J]. 塑性工程学报, 2019,26(6): 263-270.

Liu H J，Zhang Z M，Xu J，et al. Study on hot deformation behavior and constitutive model of SPSed TC4 titanium alloy[J].Journal of Plasticity Engineering， 2019, 26 (6): 263-270.

[8]周盛武, 董洪波, 姜智勇, 等. TB17钛合金热压缩流变应力分析及本构方程[J]. 塑性工程学报, 2018,25(1): 218-223.

Zhou S W，Dong H B，Jiang Z Y，et al. Flow stress analysis and constitutive equation of TB17 titanium alloy during hot compression[J]. Journal of Plasticity Engineering，2018，25 (1): 218-223.

[9]刘建军, 王克鲁, 鲁世强, 等. Ti-25Nb合金的热变形行为及本构关系模型[J]. 塑性工程学报, 2020,27(6): 148-154.

Liu J J，Wang K L，Lu S Q，et al. Hot deformation behavior and constitutive relation model of Ti-25Nb alloy[J]. Journal of Plasticity Engineering，2020，27 (6): 148-154.

[10]Tang X, Wang B, Huo Y, et al. Unified modeling of flow behavior and microstructure evolution in hot forming of a Ni-based superalloy[J]. Materials Science and Engineering: A, 2016,662: 54-64.

[11]Yang L,Wang B, Liu G, et al. Behavior and modeling of flow softening and ductile damage evolution in hot forming of TA15 alloy sheets[J]. Materials & Design, 2015,85: 135-148.

[12]Gao P F,Guo J, Zhan M,et al. Microstructure and damage based constitutive modelling of hot deformation of titanium alloys[J]. Journal of Alloys and Compounds, 2020,831:154851.

[13]李鸿江, 于洋, 宋晓云,等. 新型Ti-6554钛合金热变形行为及热加工图[J]. 稀有金属, 2020, 44(5): 462-468.

Li H J, Yu Y, Song X Y, et al. Thermal deformation behavior and processing map of a new type of Ti-6554 alloy[J]. Chines Journal of Rare Metals,2020,44(5):462-468.

[14]石尚, 董洪波, 姜智勇, 等. 基于BP神经网络的TB17钛合金热变形行为研究[J]. 特种铸造及有色合金, 2019，39(4): 434-438.

Shi S, Dong H B, Jiang Z Y, et al.Hot deformation behavior of TB17 titanium alloy based on BP neural network[J]. Special Casting & Nonferrous Alloys, 2019，39(4): 434-438.

[15]Neyshabur B, Bhojanapalli S, McAllester D, et al. Exploring generalization in deep learning[EB/OL]. https://arxiv.org/abs/1706.08947, 2017-06-27.

[16]Li C L, Narayana P L, Reddy N S, et al. Modeling hot deformation behavior of low-cost Ti-2Al-9.2Mo-2Fe beta titanium alloy using a deep neural network[J]. Journal of Materials Science & Technology,2019, 35(5): 907-916.

[17]Raj R. Development of a processing map for use in warm-forming and hot forming processes[J]. Metallurgical Transactions A, 1981, 12: 1089-1097.

服务与反馈：

【文章下载】【加入收藏】