journal article·2021-11-05Open access

Generating the Microstructure of Al-Si Cast Alloys Using Machine Learning

In-Kyu Hwang, Hyun-Ji Lee, Sang-Jun Jeong, In-Sung Cho, Hee-Soo Kim

Abstract

In this study, we constructed a deep convolutional generative adversarial network (DCGAN) to generate the microstructural images that imitate the real microstructures of binary Al-Si cast alloys. We prepared four combinations of alloys, Al-6wt%Si, Al-9wt%Si, Al-12wt%Si and Al-15wt%Si for machine learning. DCGAN is composed of a generator and a discriminator. The discriminator has a typical convolutional neural network (CNN), and the generator has an inverse shaped CNN. The fake images generated using DCGAN were similar to real microstructural images. However, they showed some strange morphology, including dendrites without directionality, and deformed Si crystals. Verification with Inception V3 revealed that the fake images generated using DCGAN were well classified into the target categories. Even the visually imperfect images in the initial training iterations showed high similarity to the target. It seems that the imperfect images had enough microstructural characteristics to satisfy the classification, even though human cannot recognize the images. Cross validation was carried out using real, fake and other test images. When the training dataset had the fake images only, the real and test images showed high similarities to the target categories. When the training dataset contained both the real and fake images, the similarity at the target categories were high enough to meet the right answers. We concluded that the DCGAN developed for microstructural images in this study is highly useful for data augmentation for rare microstructures.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Aluminum Alloy Microstructure Properties · Non-Destructive Testing Techniques · Machine Learning in Materials Science

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

References (24)

Show source-provided references
1. 2021
2. LeCun · 2004 · 97
3. 10.1561/200000003910.1561/2000000039 ↗
4. 10.1186/s41232-019-0103-310.1186/s41232-019-0103-3 ↗
5. 10.3389/fgene.2019.0021410.3389/fgene.2019.00214 ↗
6. Sarva mangala · 2021
7. Szegedy · 2016
8. Szegedy · 2017 · 4278
9. Szegedy · 2015 · 1
10. He · 2016 · 770
11. 10.3365/KJMM.2019.57.3.18410.3365/KJMM.2019.57.3.184 ↗
12. 10.3365/KJMM.2021.59.6.43010.3365/KJMM.2021.59.6.430 ↗
13. 10.1146/annurev-matsci-071312-12170310.1146/annurev-matsci-071312-121703 ↗
14. Tourret · 2021 · 100810
15. Goodfellow · 2013 · 1319
16. Lee · 2021 · 3
17. 10.1038/s41598-020-70149-010.1038/s41598-020-70149-0 ↗
18. 10.1007/s11837-020-04484-y10.1007/s11837-020-04484-y ↗
19. Radford · 2016
20. Goki · 2016
21. 10.1007/s12540-019-00535-510.1007/s12540-019-00535-5 ↗
22. Park · 2017 · 108
23. 10.1179/09506607979013640810.1179/095066079790136408 ↗
24. 10.1016/j.scriptamat.2011.01.01010.1016/j.scriptamat.2011.01.010 ↗