journal article·2025-07-05Open access

Prediction of Forming Limit Diagram by Convolution Neural Networks and Crystal Plasticity Finite Element Method

Han-Jun Lee, Jaimyun Jung, Sehyeok Oh, Dong-Kyu Kim, Ji Hoon Kim, Ho Won Lee

Abstract

This paper presents a novel deep learning (DL) approach to predict the forming limit diagrams (FLDs) of sheet metals, addressing the limitations of traditional experimental and numerical simulation methods. By utilizing orientation distribution function (ODF) data and crystal plasticity finite element (CPFE) results, an efficient DL prediction model was developed. First, numerous orientation datasets of the AA6061 alloy were generated and converted into ODFs to assess the impact of various texture components. Then, FLD data were computed using virtual forming tests via CPFE analysis and transformed into a format suitable for training the DL model. The model is based on the ResNet18 architecture and its hyperparameters were optimized using the Optuna framework. The model demonstrated rapid loss reduction, achieving an R2 score of approximately 0.7 on the test dataset. However, a decline in prediction performance was observed, particularly when minor strain values were greater than zero. This suggests the need to incorporate additional input data such as the positional information of representative volume elements in future work. This study demonstrates that leveraging microstructural data for FLD prediction via DL can reduce time and costs compared to traditional methods, and it opens new possibilities for predicting material behavior under diverse conditions.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Metal Forming Simulation Techniques · Metallurgy and Material Forming · Microstructure and Mechanical Properties of Steels

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (27)

Show source-provided references
1. 10.4028/www.scientific.net/msf.812.27110.4028/www.scientific.net/msf.812.271 ↗
2. 10.1016/j.jmatprotec.2010.01.00610.1016/j.jmatprotec.2010.01.006 ↗
3. 10.1016/j.matdes.2013.04.08010.1016/j.matdes.2013.04.080 ↗
4. 10.1016/j.ijmecsci.2012.08.00910.1016/j.ijmecsci.2012.08.009 ↗
5. 10.1016/0020-7403(67)90066-510.1016/0020-7403(67)90066-5 ↗
6. 10.1016/j.promfg.2020.04.21710.1016/j.promfg.2020.04.217 ↗
7. Evangelista · 2002 · 135
8. 10.4028/www.scientific.net/amr.1135.20210.4028/www.scientific.net/amr.1135.202 ↗
9. 10.1016/j.ijplas.2008.01.00510.1016/j.ijplas.2008.01.005 ↗
10. 10.1016/j.ijplas.2017.04.00710.1016/j.ijplas.2017.04.007 ↗
11. 10.3365/kjmm.2023.61.12.95810.3365/kjmm.2023.61.12.958 ↗
12. 10.3365/kjmm.2023.61.1.1810.3365/kjmm.2023.61.1.18 ↗
13. 10.1016/j.engfracmech.2019.10664210.1016/j.engfracmech.2019.106642 ↗
14. 10.1016/j.ijplas.2022.10340310.1016/j.ijplas.2022.103403 ↗
15. Erice · 2022 · 95
16. 10.1063/1.165600310.1063/1.1656003 ↗
17. 10.1016/j.matchar.2011.10.00710.1016/j.matchar.2011.10.007 ↗
18. 10.1016/j.msea.2007.03.02410.1016/j.msea.2007.03.024 ↗
19. He · 2016 · 770
20. LeCun · 2004 · 97
21. He · 2015 · 1026
22. Akiba · 2019 · 2623
23. Kingma · 2014
24. Loshchilov · 2017
25. Reddi · 2019
26. 10.3390/met1405050310.3390/met14050503 ↗
27. 10.1016/j.jmatprotec.2007.08.04010.1016/j.jmatprotec.2007.08.040 ↗