Deep learning predicting method and modeling of plastic constitutive relation of sheet metal

FENG Yi-shuang, HE Ji, HAN Guo-feng, LI Shu-hui, LIN Zhong-qin

Journal of Plasticity Engineering ›› 2021, Vol. 28 ›› Issue (6) : 34-46.

PDF(2854 KB)
PDF(2854 KB)
Journal of Plasticity Engineering ›› 2021, Vol. 28 ›› Issue (6) : 34-46. DOI: 10.3969/j.issn.1007-2012.2021.06.005
Special Column for Constitutive and Failure Models of Sheet Forming

Deep learning predicting method and modeling of plastic constitutive relation of sheet metal

  • FENG Yi-shuang1,2, HE Ji1,2, HAN Guo-feng1,2, LI Shu-hui1,2, LIN Zhong-qin1,2
Author information +
History +

Abstract

According to the characteristic that the plastic behavior of sheet metal is history-dependent,sequential learning method in deep learning was adopted to predict the plastic constitutive relation of advanced high-strength steel sheet by constructing a long short term memory network. The deformation data under different loading conditions obtained by finite element simulation based on Abaqus were used to train and test the model. The training methods and training characteristics of the model were studied. The established deep learning model accurately predicts the yield behavior and hardening curve of materials without introducing any elastic-plastic physical quantities or constitutive laws. The proposed method is able to represent the plastic constitutive behavior of sheet metal with large data volume and compared with traditional methods,it has great advantages in terms of computational efficiency,model flexibility and robustness.

Key words

sheet metal / plastic constitutive relation / deep learning / deformation prediction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
FENG Yi-shuang, HE Ji, HAN Guo-feng, LI Shu-hui, LIN Zhong-qin. Deep learning predicting method and modeling of plastic constitutive relation of sheet metal[J]. Journal of Plasticity Engineering, 2021, 28(6): 34-46 https://doi.org/10.3969/j.issn.1007-2012.2021.06.005

References

[1] DEMERI M Y. Forming of advanced high-strength steels[M]. Demeri: Metalworking:Sheet Forming(ASM Handbook), 2006.
[2] KLEINER M, CHATTI S, KLAUS A. Metal forming techniques for lightweight construc-tion [J]. Journal of Materials Processing Technology, 2006, 177(1): 2-7.
[3] 李永兵, 陈长年, 郎利辉,等. 汽车铝车身关键制造技术研究[J]. 汽车工艺与材料, 2013,(3): 56-64. LI Yongbing, CHEN Changnian, LANG Lihui, et al. Research on key manufacturing technology of automobile aluminum body[J]. Automobile Technology & Material, 2013,(3): 56-64.
[4] STEGLICH D, WAFAI H, BESSON J. Interaction between anisotropic plastic deformation and damage evolution in Al 2198 sheet metal[J]. Engineering Fracture Mechanics, 2010, 77(17): 3501-3518.
[5] KIANI M, GANDIKOTA I, RAIS-ROHANI M, et al. Design of lightweight magnesium car body structure under crash and vibration constraints[J]. Journal of Magnesium and Alloys, 2014, 2(2): 99-108.
[6] 宋燕利, 杨龙, 郭巍, 等. 面向汽车轻量化应用的碳纤维复合材料关键技术[J]. 材料导报, 2016, 30(17): 16-25, 50. SONG Yanli, YANG Long, GUO Wei, et al. A survey on key technologies for carbon fiber-reinforced plastics with applications to automobile lightening[J]. Materials Reports, 2016, 30(17): 16-25, 50.
[7] ZHENG K, DONG Y, ZHENG J H, et al. The effect of hot form quench (HFQ®) conditions on precipitation and mechanical properties of aluminum alloys[J]. Materials Science & Engineering, 2019, 761(22): 1-13.
[8] 吴义. 基于损伤的7075-T6铝合金HFQ工艺成形性实验研究[D]. 大连:大连理工大学, 2017. WU Yi. Experimental study on formability of 7075-T6 aluminum alloy HFQ based on damage[D].Dalian: Dalian University of Technology, 2017.
[9] KOCANDA A, SADLOWSKA H. Automotive component development by means of hydroforming[J]. Archives of Civil and Mechanical Engineering, 2008, 8(3): 55-72.
[10] THIRUVARUDCHELVAN S, WANG H B, SEET G. Hydraulic pressure enhancement of the deep-drawing process to yield deeper cups[J]. Journal of Materials Processing Technology, 1998, 82(1-3): 156-164.
[11] NAKAMURA K, NAKAGAWA T. Sheet metal forming with hydraulic counter pressure in Japan[J]. Cirp Annals Manufacturing Technology, 1987, 36(1): 191-194.
[12] 李亚光, 李大永, 丁士超, 等. 先进高强钢U型件链模成形缺陷机理分析及影响因素研究[J]. 锻压技术, 2019, 44(7): 62-71. LI Yaguang, LI Dayong, DING Shichao, et al. Research on defect mechanism and influential factors in chain-die forming for U-shaped part of advanced high strength steel[J]. Forging & Stamping Technology, 2019, 44(7): 62-71.
[13] SOTIROV N, FALKINGER G, GRABNER F, et al. Improved formability of AA5182 aluminium alloy sheet at cryogenic temperatures[J]. Materials Today Proceedings, 2015, 2(S):113-118.
[14] GRABNER F, STERREICHER J A, GRUBER B, et al. Cryogenic forming of aluminum alloy sheet for car outer body applications[J]. Advanced Engineering Materials, 2019, 21(8): 190-209.
[15] KUBLI W, REISSNER J. Optimization of sheet-metal forming processes using the special purpose program AUTOFORM[J]. Journal of Materials Processing Technology, 1995, 50(1): 292-305.
[16] 李飞舟. 板料成形CAE设计及应用: 基于AUTOFORM[M]. 北京:北京航空航天大学出版社, 2010. LI Feizhou. CAE sheet forming design and application: Based on AUTOFORM[M].Beijing:Beihang University Press, 2010.
[17] 岳陆游, 姜银方, 陈炜, 等. DYNAFORM-PC软件及其在钣金冲压中的应用[J]. 江苏大学学报(自然科学版), 2002, 23(6): 51-55. YUE Luyou, JIANG Yinfang, CHEN Wei, et al. Introduction of the software DYNAFORM-PC and its application in sheet metal stamping[J]. Journal of Jiangsu University(Natural Science Edition), 2002, 23(6): 51-55.
[18] 王秀凤, 郞利辉. 板料成形CAE设计及应用: 基于DYNAFORM[M].北京:北京航空航天大学出版社, 2008. WANG Xiufeng, LANG Lihui. CAE sheet forming design and application: Based on DYNAFORM[M]. Beijing:Beihang University Press, 2008.
[19] 李泷杲. 金属板料成形有限元模拟基础: PAMSTAMP2G(Autostamp)[M]. 北京:北京航空航天大学出版社, 2008. LI Longgao. Finite element simulation foundation for sheet metal forming: PAMSTAMP2G(Autostamp)[M]. Beijing:Beihang University Press, 2008.
[20] CHOUDHURY I A, LAI O H, WONG L T. PAM-STAMP in the simulation of stamping process of an automotive component[J]. Simulation Modelling Practice & Theory, 2006, 14(1): 71-81.
[21] 李彦波, 刘红武. 基于Jstamp／NV的数值模拟技术在汽车车身件成形中的应用[J].模具CAD/CAM,2011,(10):4-6. LI Yanbo, LIU Hongwu. Application of numerical simulation based on JSTAMP/NV in stamping process of auto body parts[J]. Die & Mould Manufacture, 2011,(10):4-6.
[22] BRON F, BESSON J. A yield function for anisotropic materials Application to alumi-num alloys[J]. International Journal of Plasticity, 2004, 20(4-5): 937-963.
[23] LI S H, HE J, GU B, et al. Anisotropic fracture of advanced high strength steel sheets: Experiment and theory[J]. International Journal of Plasticity, 2018,103:95-118.
[24] 邹丹青. QP钢应变诱发相变动力学模型及回弹特性研究[D]. 上海:上海交通大学, 2018. ZOU Danqing. Kinetics model of deformation induced martensitic transformation and springback behavior for QP steel sheet forming[D]. Shanghai: Shanghai Jiao Tong University,2018.
[25] GHABOUSSI J, GARRETT J H, WU X. Knowledge-based modeling of material behavior with neural networks[J]. Journal of Engineering Mechanics, 1991, 117(1): 132-153.
[26] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[J]. Advances in Neural Information Processing Systems, 2014.
[27] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016. ZHOU Zhihua. Machine learning[M]. Beijing: Tsinghua University Press, 2016.
[28] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989, 2(5): 359-366.
[29] KINGMA D P, BA J L. Adam: A method for stochastic optimization[J]. Computer Science, 2014,1:1-15.
PDF(2854 KB)

1988

Accesses

0

Citation

Detail
Sections
Recommended
　 Copyright © Journal of Plasticity Engineering, All Rights Reserved.
Powered by Beijing Magtech Co. Ltd,.

/

〈 〉