高熵硼化物陶瓷机器学习力场的构建与高温性能计算

doi:10.15541/jim20250299

无机材料学报

• •

高熵硼化物陶瓷机器学习力场的构建与高温性能计算

龚焕¹, 张旭^1,2, 张小锋³, 李蓓^1,2, 刘凯¹

1.武汉理工大学材料科学与工程学院,武汉 430070;
2.武汉理工大学材料复合新技术全国重点实验室,武汉 430070;
3.广东省科学院新材料研究所特种材料表面工程全国重点实验室, 广州 510650

收稿日期:2025-07-17 修回日期:2025-09-15
通讯作者: 李蓓, 副教授. E-mail: libei@whut.edu.cn
作者简介:龚焕(1997-), 男, 硕士研究生. E-mail: 1252744637@qq.com
基金资助:
国家自然科学基金(52202066)

Machine Learning Potential Development and High-Temperature Property Calculation for High-Entropy Boride Ceramics

GONG Huan¹, ZHANG Xu^1,2, ZHANG Xiaofeng³, LI Bei^1,2, LIU Kai¹

1. School of Materials Science and Engineering, Wuhan University of Technology, Wuhan 430070, China;
2. State Key Laboratory of Advanced Technology for Materials Synthesis and Processing, Wuhan University of Technology, Wuhan 430070, China;
3. National Key Laboratory of Special Materials Surface Engineering, Institute of New Materials, Guangdong Academy of Sciences, Guangzhou 510650, China

Received:2025-07-17 Revised:2025-09-15
Contact: LI Bei, associate professor. E-mail: libei@whut.edu.cn
About author:GONG Huan (1997-), male, Master candidate. E-mail: 1252744637@qq.com
Supported by:
National Natural Science Foundation of China (52202066)

摘要/Abstract

摘要： 高熵硼化物陶瓷在极端高温环境中的分子动力学模拟受限于经验力场的精度与温度适用性。本研究针对(Hf_0.2Zr_0.2Ta_0.2Ti_0.2Nb_0.2)B₂体系,基于第一性原理计算与深度学习方法,开发了高精度深度学习势能。通过主动学习优化训练数据集,显著提升了模型在高温(~3000 K)下的模拟稳定性。该力场在模拟中同时兼具高精度与高效率。验证结果表明,体积状态方程预测与第一性原理较为吻合,证明了模型的良好可扩展性;计算所得晶格常数及力学性能参数与实验值的偏差<2%。尤为重要的是,本研究成功揭示了高熵硼化物陶瓷热膨胀各向异性规律,修正了已有研究中的反常趋势。这项成果为极端条件下高熵硼化物陶瓷的原子尺度模拟提供了可靠工具,对深入理解其高温服役行为具有重要科学价值。

关键词: 高熵硼化物陶瓷, 分子动力学, 深度学习势能, 高温性能

Abstract: Molecular dynamics simulations of high-entropy boride ceramics (HEBCs) in extreme high-temperature environments are constrained by the limited accuracy and temperature stability of empirical force fields. In this work, an high-accuracy deep-learning potential (DP) was proposed and developed for (Hf_0.2Zr_0.2Ta_0.2Ti_0.2Nb_0.2)B₂ systems via first-principles calculations and deep learning method. It is shown that, through expanding datasets via the active learning strategy, the DP model stability under high-temperature conditions (i.e., ~3000 K) could be significantly enhanced. The developed DP achieves high accuracy while maintaining computational efficiency. The validation results manifest that the predictions of the volumetric equation of state align well with first-principles calculations, demonstrating the model’s good scalability; and the lattice constants and mechanical properties predicted by DP-enabled molecular dynamics simulations show excellent agreements with experimental observation, with relative errors within 2%. Furthermore, the simulations successfully reveal the anisotropic thermal expansion behavior of HEBCs and rectify the anomalous trends reported in previous research. This DP model provides a reliable tool for atomic-scale simulations of high-entropy boride ceramics under extreme conditions, and holds significant scientific value for advancing the in-depth understanding of their high-temperature service behavior.

Key words: high-entropy boride ceramics, molecular dynamics, deep-learning potential, high temperature property

中图分类号:

TB35

龚焕, 张旭, 张小锋, 李蓓, 刘凯. 高熵硼化物陶瓷机器学习力场的构建与高温性能计算[J]. 无机材料学报, DOI: 10.15541/jim20250299.

GONG Huan, ZHANG Xu, ZHANG Xiaofeng, LI Bei, LIU Kai. Machine Learning Potential Development and High-Temperature Property Calculation for High-Entropy Boride Ceramics[J]. Journal of Inorganic Materials, DOI: 10.15541/jim20250299.

参考文献

[1] 贾成科, 张鑫, 任先京, 等. 硼化物陶瓷基涂层制备技术的研究进展. 热喷涂技术, 2012, 4(1): 5.
[2] MONTEVERDE F, GUICCIARDI S, BELLOSI A.Advances in microstructure and mechanical properties of zirconium diboride based ceramics.Materials Science and Engineering: A, 2003, 346(1): 310.
[3] WU W W, ZHANG G J, KAN Y M,et al. Synthesis and microstructural features of ZrB₂-SiC-based composites by reactive spark plasma sintering and reactive hot pressing. Scripta Materialia, 2007, 57(4): 317.
[4] ZOU J, ZHANG G J, KAN Y M,et al. Pressureless densification of Zrb₂-SiC composites with vanadium carbide. Scripta Materialia, 2008, 59(3): 309.
[5] YEH J W, CHEN S K, LIN S J,et al. Nanostructured high-entropy alloys with multiple principal elements: novel alloy design concepts and outcomes. Advanced Engineering Materials, 2004, 6(5): 299.
[6] MIRACLE D B, SENKOV O N.A critical review of high entropy alloys and related concepts.Acta Materialia, 2017, 122: 448.
[7] GEORGE E P, RAABE D, RITCHIE R O.High-entropy alloys.Nature Reviews Materials, 2019, 4(8): 515.
[8] WANG Y P, GAN G Y, WANG W,et al. First-principles study of mechanical and thermal properties of high-entropy diborides. Physica Status Solidi (B), 2018, 255(10): 1800011.
[9] ZHANG Y, CHEN G, SHI X,et al. Atomic simulations and experimental of the effect of transition metal on the high-temperature oxidation behavior of ZrB₂. Corrosion Science, 2024, 236: 112218.
[10] MENG X Y, ZHANG H X, MEZEI M,et al. Molecular docking: a powerful approach for structure-based drug discovery. Current Computer-Aided Drug Design, 2011, 7(2): 146.
[11] ALDER B J, WAINWRIGHT T E.Studies in molecular dynamics. I. General method. Journal of Chemical Physics, 1959, 31(2): 459.
[12] BEHLER J, PARRINELLO M.Generalized neural-network representation of potential-energy surfaces.Physical Review Letters, 2007; 98(14): 146401.
[13] DAI F Z, SUN Y J, WEN B,et al. Temperature dependent thermal and elastic properties of high entropy (Ti_0.2Zr_0.2Hf_0.2Nb_0.2Ta_0.2)B₂: molecular dynamics simulation by deep learning potential. Journal of Materials Science and Technology, 2021, 72: 8.
[14] ZHANG X, LI B, ZHOU J,et al. Deep-learning enabled atomic insights into the phase transitions and nanodomain topology of lead-free (K,Na)NbO₃ ferroelectrics. Science China Materials, 2024, 67(9): 3029.
[15] VAN DE WALLE A, TIWARY P, DE JONG M,et al. Efficient stochastic generation of special quasirandom structures. Calphad, 2013, 42: 13.
[16] THOMPSON A P, AKTULGA H M, BERGER R,et al. LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Computer Physics Communications, 2022, 271: 108171.
[17] GU J, ZOU J, SUN S K,et al. Dense and pure high-entropy metal diboride ceramics sintered from self-synthesized powders via boro/carbothermal reduction approach. Science China Materials, 2019, 62(12): 1898.
[18] LIU J, YANG Q, ZOU J,et al. Strong high-entropy diborides ceramics with oxide impurities at 1800 °C. Science China Materials, 2023, 66(5): 1892.

高熵硼化物陶瓷机器学习力场的构建与高温性能计算

Machine Learning Potential Development and High-Temperature Property Calculation for High-Entropy Boride Ceramics

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	刘国昂, 王海龙, 方成, 黄飞龙, 杨欢. B₄C含量对(Ti_0.25Zr_0.25Hf_0.25Ta_0.25)B₂-B₄C陶瓷力学性能及抗氧化性能的影响[J]. 无机材料学报, 2024, 39(6): 697-706.
[2]	张修瑜,陈晓菲,王浩,郭寻,薛建明. 6H-SiC辐照点缺陷诱发化学无序的分子动力学分析[J]. 无机材料学报, 2020, 35(8): 889-894.
[3]	赵超锋, 金佳人, 霍英忠, 孙陆, 艾玥洁. 氧化石墨烯吸附水体中酚类有机污染物的分子动力学模拟[J]. 无机材料学报, 2020, 35(3): 277-283.
[4]	郝海青, 袁致涛, 李丽匣, 张晨. 油酸钠控制硫酸钙晶须晶面生长的机理研究[J]. 无机材料学报, 2016, 31(11): 1184-1190.
[5]	孙玲玲, 马颖, 周益春. 分子动力学方法模拟压强对Bi₄Ti₃O₁₂铁电相变行为的影响[J]. 无机材料学报, 2011, 26(5): 491-494.
[6]	汪刘应, 徐卓, 华绍春, 刘顾. 微弧等离子喷涂碳纳米管/纳米 Al₂O₃-TiO₂ 复合涂层高温性能研究[J]. 无机材料学报, 2011, 26(3): 239-243.
[7]	刘柏年, 马颖, 周益春. BaTiO₃铁电体中应变-极化耦合效应的分子动力学模拟[J]. 无机材料学报, 2010, 25(12): 1247-1251.
[8]	叶雅静,张立同,成来飞,徐永东. 无定形 Si-B-C体系扩散行为分子动力学模拟[J]. 无机材料学报, 2006, 21(4): 843-848.
[9]	李稳,姜长印,万春荣. 表面包覆Yb(OH)₃的球形氢氧化镍的高温性能研究[J]. 无机材料学报, 2006, 21(1): 121-127.
[10]	吴永全,尤静林,蒋国昌. 铝酸钙熔体结构的分子动力学模拟研究[J]. 无机材料学报, 2003, 18(3): 619-626.
[11]	陈福义,介万奇. 分子动力学模拟Lennard-Jones熔体结构迁移[J]. 无机材料学报, 2002, 17(2): 259-264.
[12]	蒋洋,赵修建,梁开明. CdF₂-BaF₂-LiF系统玻璃的X射线衍射与分子动力学研究[J]. 无机材料学报, 1998, 13(2): 138-144.