锻压技术

基于机器学习的大锻件拔长变形预测

英文标题：Prediction of drawing deformation for heavy forgings based on machine learning

作者：张梓煜曾攀雷丽萍

单位：清华大学

分类号：TG302

出版年,卷(期):页码：2020,45(10):209-216

摘要：

大锻件成形通常借助有限元模拟来进行研究，由于大锻件的尺寸大、工序长而导致有限元计算耗费了大量时间。因此，首先，采用有限元软件DEFORM对大锻件拔长过程进行模拟，获得成形数据，构建了19维的输入特征量和以应力、应变为输出特征量的数据集。然后，应用机器学习中的随机森林和神经网络方法对数据集进行学习，训练对应模型。最后，利用机器学习模型对一个新的拔长过程进行应力和应变分布预测，与有限元模拟结果对比后发现，这些预测结果与有限元模拟结果相近。研究表明，通过机器学习可以快速预测拔长成形结果，进而进一步分析成形质量，节省计算时间。

The forming of heary forgings is usually studied by means of finite element simulation, and because of large size and long working procedure for heavy forgings, the finite element calculation takes a lot of time. Therefore, firstly the drawing process of heavy forgings was simulated by finite element software DEFORM, and the forming data were obtained to construct a data set which consisted of nineteen dimensional input characteristic variables and output characteristic variables of stress and strain. Then, the data set was learned by random forest and neural network methods in machine learning, and the corresponding model was trained. Finally, the stress and strain distributions of a new drawing process was predicted by the machine learning model. Compared with the results of finite element simulation, the predicted results were similar to those of finite element simulation. The results show that the machine learning quickly predicts the result of drawing and analyzes the forming quality to save a lot of calculation time.

基金项目：

国家重点研发计划(2017YFB0701803)

张梓煜（1995-），男，硕士研究生 E-mail：zyzhang17@mails.tsinghua.edu.cn 通讯作者：雷丽萍（1968-），女，博士，副教授 E-mail：leilp@tsinghua.edu.cn

参考文献：

［1］田峰, 贾琛. 大型锻件的锻造工艺研究进展
［J］. 热加工工艺, 2015，44(5):18-20.

Tian F, Jia C. Research progress on forging process for large forgings
［J］. Hot Working Technology, 2015，44(5):18-20.

［2］郭会光. 大型锻件制造核心技术的进展
［J］. 金属加工：热加工, 2012,(1):19-20.

Guo H G. The development of the core technology in the manufacture of large forgings
［J］. Metal Working, 2012,(1):19-20.

［3］龚虎, 徐月. 大锻件不同砧型拔长工艺的研究进展
［J］. 大型铸锻件, 2012,(1):19-20.

Gong H, Xu Y. Research progress of drawing process with different shape of anvils in heavy forgings
［J］. Heavy Casting and Forging, 2012,(1):19-20.

［4］吴贵军, 刘嵩, 何寒,等. 大锻件拔长工艺优化
［J］. 铸造技术, 2018, 39(6):1309-1311.

Wu G J, Liu S, He H, et al. Optimization design of heavy forgings stretching process
［J］. Foundry Technology, 2018, 39(6):1309-1311.

［5］陆卫倩, 陈映川. 60Si2Mn长轴大锻件淬火爆裂分析与研究
［J］. 铸造技术, 2012,(5):49-51.

Lu W Q, Chen Y C. Analysis and research of burst on 60Si2Mn long shaftforgings
［J］. Foundry Technology, 2012,(5):49-51.

［6］Raccuglia P, Elbert K C, Adler P D F, et al. Machinelearningassisted materials discovery using failed experiments
［J］. Nature, 2016, 533(7601):73-76.

［7］Orme A D, Chelladurai I, Rampton T M, et al. Insights into twinning in Mg AZ31: A combined EBSD and machine learning study
［J］. Computational Materials Science, 2016, 124:353-363.

［8］Alireza R, Sam C, Seetharaman S. Machine learning for predicting occurrence of interphase precipitation in HSLA steels
［J］. Computational Materials Science, 2018, 154:169-177.

［9］Moore B A, Rougier E, O'Malley D, et al. Predictive modeling of dynamic fracture growth in brittle materials with machine learning
［J］. Computational Materials Science, 2018, 148:46-53.

［10］Mohammed Alnaggar, Naina Bhanot. A machine learning approach for the identification of the Lattice discrete particle model parameters
［J］. Engineering Fracture Mechanics, 2018, 197：160-175.

［11］程小辉, 黄冠良, 吴岳森, 等. 水平V型砧和平砧联合拔长圆形棒料的多工步数值模拟
［J］. 装备制造技术, 2016, 253(1):72-74，86.

Chen X H, Huang G L, Wu Y S, et al. Multistage numerical simulation of stretching round rod with horizontal Vshaped anvils and flat anvils
［J］. Equipment Manufacturing Technology, 2016, 253(1):72-74,86.

［12］Wang R R, Zeng S M, Wang X M, et al. Machine learning for hierarchical prediction of elastic properties in FeCrAl system
［J］. Computational Materials Science, 2019, 166：119-123.

［13］周志华. 机器学习
［M］. 北京: 清华大学出版社, 2016.

Zhou Z H. Machine Learning
［M］. Beijing: Tsinghua University Press, 2016.

［14］王庆娟, 双翼翔, 孙亚玲,等. 锻造工艺对BTi20合金组织和力学性能的影响
［J］. 稀有金属, 2019,43(1):32-37.

Wang Q J, Shuang Y X, Sun Y L, et al. Effect of forging process on microstructure and mechanical properties of BTi20 alloy
［J］. Chinese Journal of Rare Metal,2019, 43(1):32-37.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】