Design of High-Strength High-Entropy Alloys Using a Variational Autoencoder-Based Inverse Design

Min-Gyu Kim; Chunghee Nam

doi:10.3740/MRSK.2025.35.10.486

All Issue

2025 Vol.35, Issue 10 Preview Page Next Page

Research Paper

Design of High-Strength High-Entropy Alloys Using a Variational Autoencoder-Based Inverse Design VAE 기반 소재 역설계를 이용한 고강도 고엔트로피 합금 설계

27 October 2025. pp. 486-496

PDF XML

Abstract

High-entropy alloys (HEAs) are alloys that contain multiple principal elements, each in the range of 5–35%. HEAs exhibit excellent properties, however, even with conventional trial-and-error, high-throughput experimentation, and computational materials approaches, exploring their vast compositional space remains highly challenging. Accordingly, data-driven machine learning and generative-model-based inverse design methods are increasingly essential. In this study, we propose a generative-model-enabled HEA inverse design framework aimed at improving ultimate tensile strength (UTS). We first compiled 501 HEA data points from published literature and performed statistical analyses to understand their characteristics. Next, we tuned the hyperparameters of XGBoost and random forest (RF) models via Bayesian optimization, compared their performance with that of a deep neural network (DNN), and selected XGBoost as the optimal predictive model. In the subsequent stage, we trained a PyTorch-based variational autoencoder (VAE) on data from regions of the latent space associated with high-UTS probability. We randomly sampled 1,000 latent vectors, decoded them to generate candidate alloy compositions, and evaluated these candidates using the optimized XGB model. Finally, Shapley additive explanations (SHAP) interpretability analysis and a network plot were used to quantify the contributions and interactions of each feature variable, thereby assessing the physical plausibility of the model-suggested compositions.

Keywords

variational auto-encoder

high entropy alloys

inverse design

References

J.-W. Yeh, JOM, 67, 2254 (2015).

10.1007/s11837-015-1583-5

W. Huo, X. Liu, S. Tan, F. Fang, Z. Xie, J. Shang and J. Jiang, Appl. Surf. Sci., 439, 222 (2018).

10.1016/j.apsusc.2018.01.050

R. B. Nair, H. S. Arora, S. Mukherjee, S. Singh, H. Singh and H. S. Grewal, Ultrason. Sonochem., 41, 252 (2018).

10.1016/j.ultsonch.2017.09.044

J.-W. Yeh, S.-K. Chen, S.-J. Lin, J.-Y. Gan, T.-S. Chin, T.-T. Shun, C.-H. Tsau and S.-Y. Chang, Adv. Eng. Mater., 6, 299 (2004).

10.1002/adem.200300567

B. Cantor, Prog. Mater. Sci., 120, 100754 (2021).

10.1016/j.pmatsci.2020.100754

R. Machaka, Comput. Mater. Sci., 188, 110244 (2021).

10.1016/j.commatsci.2020.110244

S. Liu, B. Bocklund, J. Diffenderfer, S. Chaganti, B. Kailkhura, S. K. McCall, B. Gallagher, A. Perron and J. T. McKeown, npj Comput. Mater., 10, 172 (2024).

10.1038/s41524-024-01335-1

D. Klimenko, N. Stepanov, J. Li, Q. Fang and S. Zherebtsov, Materials, 14, 7213 (2021).

10.3390/ma1423721334885366PMC8658560

S. Y. Lee, S. Byeon, H. S. Kim, H. Jin and S. Lee, Mater. Des., 197, 109260 (2021).

10.1016/j.matdes.2020.109260

K. Y. Li, L. C. Liu, L. L. Shao, J. Zhou, H. B. Ke, M. Z. Li and W. H. Wang, J. Alloys Compd., 1010, 178325 (2025).

10.1016/j.jallcom.2024.178325

Y. Long, C. Zhong, X. Ma, J. Zhang, H. Yao, J. Liu, K. Hu, Q. Zhang and X. Lin, ACS Appl. Mater. Interfaces, 17, 19856 (2025).

10.1021/acsami.4c19494

S. Kim, L. Zhang, S.-H. Kim and Y. S. Choi, Met. Mater. Int., 30, 1817 (2024).

10.1007/s12540-023-01610-8

K. Y. Li, M. Z. Li and W. H. Wang, J. Appl. Phys., 135, 025102 (2024).

J. Wang, H. Kwon, H. S. Kim and B.-J. Lee, npj Comput. Mater., 9, 60 (2023).

10.1038/s41524-023-01010-x

C. Chen, L. Ma, Y. Zhang, P. K. Liaw and J. Ren, Intermetallics, 154, 107819 (2023).

10.1016/j.intermet.2022.107819

J. Qin, F. Zhang, M. Ma, Y. Li and Z. Liu, Mater. Genome Eng. Adv., 2025, e70005 (2025).

H. Jung, S. Lee, T. Kang, A. Zargaran, P.-P. Choi and S. S. Sohn, J. Mater. Sci. Technol., 181, 71 (2024).

10.1016/j.jmst.2023.09.033

J. Tian, K. Tang, Y. K. Wu, T. H. Cao, J. B. Pang and F. Jiang, Mater. Sci. Eng. A, 811, 141054 (2021).

10.1016/j.msea.2021.141054

F. Zheng, G. Zhang, X. Chen, X. Yang, Z. Yang, Y. Li and J. Li, Mater. Sci. Eng. A, 774, 138940 (2020).

10.1016/j.msea.2020.138940

R. Chang, W. Fang, J. Yan, H. Yu, X. Bai, J. Li, Z. Wang, S. Zheng and F. Yin, J. Mater. Sci. Technol., 62, 25 (2021).

10.1016/j.jmst.2020.04.062

H. Kwon, J. Moon, J. W. Bae, J. M. Park, S. Son, H.-S. Do, B.-J. Lee and H. S. Kim, Scr. Mater., 188, 140 (2020).

10.1016/j.scriptamat.2020.07.023

S. M. Lundberg and S.-I. Lee in Proceedings of the 31st Conference on Neural Information Processing Systems (Long Beach, CA, December 2017).

Y. Wang, J. Chen, R. Ding, W. Wang, J. He and X. Zhou, J. Mater. Res. Technol., 27, 6065 (2023).

10.1016/j.jmrt.2023.11.064

S. W. Wu, L. Xu, X. D. Ma, Y. F. Jia, Y. K. Mu, Y. D. Jia, G. Wang and C. T. Liu, Mater. Sci. Eng. A, 805, 140523 (2021).

10.1016/j.msea.2020.140523

Information

Publisher :Materials Research Society of Korea
Publisher(Ko) :한국재료학회
Journal Title :Korean Journal of Materials Research
Journal Title(Ko) :한국재료학회지
Volume : 35
No :10
Pages :486-496
Received Date : 2025-08-19
Revised Date : 2025-09-20
Accepted Date : 2025-09-22
DOI :https://doi.org/10.3740/MRSK.2025.35.10.486

Korean Journal of Materials Research ISSN:1225-0562(Print) 2287-7258(Online) 한국재료학회지

All Issue