All Issue

2026 Vol.36, Issue 2 Preview Page

Research Paper

Design of High-Entropy Alloys Using Conditional Generative Models and Multi-objective Bayesian Optimization

조건부 생성 모델과 다중 목적 베이지안 최적화를 활용한 고엔트로피 합금 설계

Mingyu Kim1
,
Chunghee Nam1†
김 민규1
,
남 충희1†
1Department of Electrical and Electronic Engineering, Hannam University, Daejeon 34430, Republic of Korea
1한남대학교 전기전자공학과
†Corresponding author E-Mail : chnam@hnu.ac.kr (C. Nam, Hannam Univ.)
27 February 2026. pp. 55-63
PDF XML Citation
Abstract

This study of a high-entropy alloy (HEA) explored two strategies to simultaneously satisfy two mechanical properties, ultimate tensile strength (UTS) and total elongation. The first strategy used inverse design based on a conditional variational autoencoder (CVAE), and the second employed multi-objective Bayesian optimization. Using a dataset of 501 literature-based HEAs, three models were trained with alloy composition and experimental conditions as inputs. Among these, extreme gradient boosting (XGBoost) exhibited the highest predictive performance for both properties and was selected as the final prediction model. CVAE was employed to generate 1,000 new samples from the latent space under the condition that both UTS and total elongation exceeded their mean values. Of these, 310 physically feasible compositions were validated using the XGBoost model, and approximately 17.7 % satisfied the target properties. Next, expected hypervolume improvement (EHVI)-based Bayesian optimization, beginning with 130 initial compositions that demonstrated superior properties, proposed five recommended candidates. These samples were found to differ in compositional characteristics from the existing dataset, which can be interpreted as exploration driven by the uncertainty of the probabilistic machine learning model. The candidate compositions generated by both methods were predicted by the XGBoost model to have the potential to achieve the target properties.

Keywords
conditional variational autoencoder
high entropy alloys
Bayesian optimization
References
1

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

10.1007/s11837-015-1583-5
2

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

10.1016/j.apsusc.2018.01.050
3

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

10.1016/j.ultsonch.2017.09.044
4

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

10.1002/adem.200300567
5

E. Ma, X. Wu, Nat. Commun., 10, 5623 (2019).

6

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

10.1038/s41524-023-01010-x
7

T. Li, S. Wang, W. Fan, Y. Lu, T. Wang, T. Li, P. K. Liaw, Acta Mater., 246, 118728 (2023).

10.1016/j.actamat.2023.118728
8

M. Li, J. Gazquez, A. Borisevich, R. Mishra, K. M. Flores, Intermetallics, 95, 110 (2018).

10.1016/j.intermet.2018.01.021
9

M. N. Hasan, Y. F. Liu, X. H. An, J. Gu, M. Song, Y. Cao, Y. S. Li, Y. T. Zhu, X. Z. Liao, Int. J. Plast., 123, 178 (2019).

10.1016/j.ijplas.2019.07.017
10

Z. Zhou, Y. Shang, X. Liu, Y. Yang, npj Comput. Mater., 9, 15 (2023).

10.1038/s41524-023-00968-y
11

D. Khatamsaz, B. Vela, P. Singh, D. D. Johnson, D. Allaire, R. Arróyave, npj Comput. Mater., 9, 49 (2023).

10.1038/s41524-023-01006-7
12

J.-W. Lee, C. Park, B. D. Lee, J. Park, N. H. Goo, K.-S. Sohn, Sci. Rep., 11, 11012 (2021).

10.1038/s41598-021-90237-z34040040PMC8155048
13

C.-Y. Lee, C.-Y. Jui, A.-C. Yeh, Y.-J. Chang, W.-J. Lee, J. Alloys Compd., 976, 173144 (2024).

10.1016/j.jallcom.2023.173144
14

H. Li, R. Yuan, H. Liang, W. Y. Wang, J. Li, J. Wang, Mater. Des., 223, 111186 (2022).

10.1016/j.matdes.2022.111186
15

Y. Sohail, C. Zhang, D. Xue, J. Zhang, D. Zhang, S. Gao, Y. Yang, X. Fan, H. Zhang, G. Liu, J. Sun, E. Ma, Nature, 643, 119 (2025).

10.1038/s41586-025-09160-240533553PMC12221976
16

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

17

J. Hou, M. Zhang, S. Ma, P. K. Liaw, Y. Zhang, J. Qiao, Mater. Sci. Eng. A, 707, 593 (2017).

10.1016/j.msea.2017.09.089
18

S. Schmidt, G. D. Sathiaraj, S. S. Kumar, B. Sulkowski, S. Suwas, J. Jaschinski, A. Pukenas, B. Gu and W. Skrotzki, Mater. Chem. Phys., 270, 124830 (2021).

10.1016/j.matchemphys.2021.124830
19

I. S. Wani, T. Bhattacharjee, S. Sheikh, Y. Lu, S. Chatterjee, S. Guo, P. P. Bhattacharjee and N. Tsuji, IOP Conf. Ser.: Mater. Sci. Eng., 194, 012018 (2017).

10.1088/1757-899X/194/1/012018
20

Z. Li, L. Fu, J. Peng, H. Zheng, A. Shan, Mater. Sci. Eng. A, 786, 139446 (2020).

10.1016/j.msea.2020.139446
21

J. Zhang, H. Qiu, H. Zhu, Z. Xie, Mater. Charact., 175, 111091 (2021).

10.1016/j.matchar.2021.111091
Information
  • Publisher :Materials Research Society of Korea
  • Publisher(Ko) :한국재료학회
  • Journal Title :Korean Journal of Materials Research
  • Journal Title(Ko) :한국재료학회지
  • Volume : 36
  • No :2
  • Pages :55-63
  • Received Date : 2025-12-26
  • Revised Date : 2026-01-15
  • Accepted Date : 2026-01-24
  • DOI :https://doi.org/10.3740/MRSK.2026.36.2.55
Journal Informaiton Korean Journal of Materials Research Korean Journal of Materials Research
Online Submission
  • scopus
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close