机器学习在非晶合金逆向设计中的应用

doi:10.11896/cldb.25020053

材料导报

2026, Vol. 40

Issue (4): 25020053-9 https://doi.org/10.11896/cldb.25020053

金属与金属基复合材料

机器学习在非晶合金逆向设计中的应用

龙卓, 傅伊凡, 杨功记^*

湖南科技大学材料科学与工程学院,湖南湘潭 411201

Application of Machine Learning in Reverse Design of Amorphous Alloys

LONG Zhuo, FU Yifan, YANG Gongji^*

School of Materials Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, Hunan, China

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

全文 ( PDF ) ( 24428KB )
输出: BibTeX | EndNote (RIS)

摘要逆向设计范式,通过构建从“性能需求”回溯至“材料结构”乃至“成分组成”的逆向映射关系,为突破材料传统研发模式提供了革命性思路。非晶合金因其优异力学性能和应用潜力在材料科学研究中备受关注,但其长程无序的原子排布与复杂的构效关系,致使传统试错法难以实现性能导向的精准设计。机器学习技术通过整合高通量计算、实验数据库和智能算法,构建多重特征到目标性能的预测模型,显著提升了非晶合金成分设计效率与可靠性。为加深对这一新兴交叉领域的理解,本文对近年来机器学习在非晶合金逆向设计方面的研究进展进行了系统综述。首先,简要介绍了机器学习驱动的材料设计框架。其次,探讨了高通量实验与主动学习协同挖掘关键特征的机制,以及全局优化策略在多目标性能平衡中的应用。再次,详细阐述了生成式模型在高维成分空间探索中的独特优势。最后,归纳了非晶合金逆向设计方面的研究成果与面临的挑战,并展望了未来发展方向。旨在为非晶合金设计提供系统性知识参考框架,促进新型材料研发体系的建立及应用拓展。

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	龙卓
	傅伊凡
	杨功记

关键词: 机器学习非晶合金性能预测逆向设计

Abstract: The inverse design paradigm provides a revolutionary idea for breaking through the conventional material research and development model by constructing a reverse mapping relationship from “performance requirements” back to “material structure” and even “composition”. Amorphous alloys have garnered considerable attention in materials science research due to their excellent mechanical properties and promising practical value. However, the characteristic long-range disordered atomic arrangement and the complex structure-property relationships make it highly challenging to achieve performance-oriented precise design using conventional trial-and-error methods. Machine learning technology integrates high-throughput computation, experimental databases, and intelligent algorithms to construct predictive models mapping multi-dimensional features to target properties, thereby significantly enhancing both the efficiency and reliability of alloy composition design. To enhance the understanding of this emerging interdisciplinary field, this summary systematically reviews the recent progress of machine learning in the inverse design of amorphous alloys. Firstly, the framework of machine learning-driven material design is briefly introduced. Secondly, the synergistic mechanism between high-throughput experiments and active learning in identifying key features, as well as the application of global optimization strategies in balancing multi-objective properties, is discussed. Thirdly, the unique advantages of generative models in exploring high-dimensional composition spaces are elaborated in detail. Finally, the achievements and challenges in the inverse design of amorphous alloys are summarized, perspectives on future research directions are provided. This paper aims to provide a systematic knowledge framework for the design of amorphous alloys, thereby accelerating the development of next-generation material development systems and application expansion.

Key words: machine learning amorphous alloy performance prediction reverse design

出版日期: 2026-02-25 发布日期: 2026-02-13

ZTFLH:	TB31
	TP18

基金资助: 湖南省教育厅科学研究项目(24B0460);湖南省自然科学基金(2020JJ5191);陕西省重点研发项目 (2024CY2-GJHX-71)

通讯作者: * 杨功记,博士,湖南科技大学校聘副教授、硕士研究生导师。目前主要从事非晶合金分子动力学模拟及机器学习等方面的研究。yanggj@hnust.edu.cn

作者简介: 龙卓,湖南科技大学材料科学与工程学院硕士研究生,在杨功记教授的指导下研究非晶合金成分设计与性能调控。

引用本文:

龙卓, 傅伊凡, 杨功记. 机器学习在非晶合金逆向设计中的应用[J]. 材料导报, 2026, 40(4): 25020053-9.
LONG Zhuo, FU Yifan, YANG Gongji. Application of Machine Learning in Reverse Design of Amorphous Alloys. Materials Reports, 2026, 40(4): 25020053-9.

链接本文:

https://www.mater-rep.com/CN/10.11896/cldb.25020053 或 https://www.mater-rep.com/CN/Y2026/V40/I4/25020053

1 Gu J, Yang X, Zhang A, et al. Journal of Non-Crystalline Solids, 2019, 512, 206.
2 Khan M M, Shabib I, Haider W. Scripta Materialia, 2019, 162, 223.
3 Mitchell T M. Machine Learning, McGraw-Hill Education, US, 1997, pp. 2.
4 Zhang J, Cai C, Kim G, et al. npj Computational Materials, 2022, 8(1), 89.
5 Qiao L, Ramanujan R V, Zhu J. Materials Science and Engineering:A, 2022, 845, 143198.
6 Pan S, Yu J, Han J, et al. Acta Materialia, 2023, 243, 118484.
7 Yang B, Vassilev-Galindo V, Llorca J. npj Computational Materials, 2024, 10(1), 26.
8 Tang Y, He Y, Fan Z, et al. Science China Technological Sciences, 2024, 67(5), 1431.
9 Zhang T, Long Z L, Peng L. Transactions of Nonferrous Metals Society of China, 2024, 34(5), 1558.
10 Verma J, Bohane P, Bhatt J, et al. Journal of Non-Crystalline Solids, 2024, 624, 122710.
11 Wu Y C, Yan L, Liu J F, et al. Materials Today Communications, 2024, 40, 109440.
12 Zeng Y, Tian Z, Zheng Q, et al. Journal of Materials Science, 2024, 59(19), 8318.
13 Amigo N, Palominos S, Valencia F J. Scientific Reports, 2023, 13(1), 348.
14 Rickman J M, Chan H M, Harmer M P, et al. Nature Communications, 2019, 10(1), 2618.
15 Li J, Zhang Y, Cao X, et al. Communications Materials, 2020, 1(1), 1.
16 Lee S Y, Byeon S, Kim H S, et al. Materials & Design, 2021, 197, 109260.
17 Butler K T, Davies D W, Cartwright H, et al. Nature, 2018, 559(7715), 547.
18 Chang D, Lu T, Lu W, et al. Computational Materials Science, 2024, 235, 112794.
19 Liu C, Lu Y, Feng J, et al. Materials Today Communications, 2024, 38, 107667.
20 Long T, Long Z L, Pang B. Transactions of Nonferrous Metals Society of China, 2025, 35(1), 169.
21 Jeon J, Kim G, Seo N, et al. Journal of Materials Research and Technology, 2022, 16, 129.
22 Pang B, Long Z, Long T, et al. Materials & Design, 2023, 231, 112054.
23 Li X, Shan G, Shek C H. Journal of Materials Science & Technology, 2022, 103, 113.
24 Goodfellow I, Pouget-Abadie J, Mirza M, et al. Communications of the ACM, 2020, 63(11), 139.
25 Fang J, Xie M, He X, et al. Materials Today Communications, 2022, 33, 104900.
26 Xie W, Wang W, Liu Y. Materials Genome Engineering Advances, 2023, 1(1), e8.
27 Sarker S, Tang-Kong R, Schoeppner R, et al. Applied Physics Reviews, 2022, 9(1), 011403.
28 Wieczerzak K, Groetsch A, Pajor K, et al. Advanced Science, 2023, 10(31), 2302997.
29 Ren F, Ward L, Williams T, et al. Science Advances, 2018, 4(4), eaaq1566.
30 Lookman T, Alexander F J, Bishop A R. APL Materials, 2016, 4(5), 053501.
31 Gubernatis J E, Lookman T. Physical Review Materials, 2018, 2(12), 120301.
32 Rao Z, Tung P Y, Xie R, et al. Science, 2022, 378(6615), 78.
33 Sivaraman G, Krishnamoorthy A N, Baur M, et al. npj Computational Materials, 2020, 6(1), 104.
34 Sulley G A, Raush J, Montemore M M, et al. Scripta Materialia, 2024, 249, 116180.
35 Xu N, Shi Y, He Y, et al. The Journal of Physical Chemistry C, 2020, 124(30), 16278.
36 Ma W, Liu B, Lu T, et al. Journal of Materials Research and Technology, 2024, 32, 4316.
37 Kusne A G, Yu H, Wu C, et al. Nature Communications, 2020, 11(1), 5966.
38 Makino A, Kubota T, Chang C, et al. Materials Transactions, 2007, 48(11), 3024.
39 Makino A, Kubota T, Makabe M, et al. Materials Science and Enginee-ring, B, 2008, 148(1), 166.
40 Wang A, Zhao C, He A, et al. Journal of Alloys and Compounds, 2016, 656, 729.
41 Dou Z X, Li Y L, Lv K, et al. Materials Science and Engineering: B, 2021, 264, 114942.
42 Wang Y, Tian Y, Kirk T, et al. Acta Materialia, 2020, 194, 144.
43 Storn R, Price K. Journal of Global Optimization, 1997, 11(4), 341.
44 Yoshizawa Y, Oguma S, Yamauchi K. Journal of Applied Physics, 1988, 64(10), 6044.
45 Zhang Y X, Xie S J, Guo W, et al. Journal of Alloys and Compounds, 2023, 960, 170793.
46 Battezzati L, Habib A, Baldissin D, et al. Journal of Alloys and Compounds, 2010, 504, S48.
47 Su C, Chen Y, Yu P, et al. Journal of Alloys and Compounds, 2016, 663, 867.
48 Jeon J, Seo N, Kim H J, et al. Metals, 2021, 11(5), 729.
49 M. Forrest R, Lindsay Greer A. Digital Discovery, 2023, 2(1), 202.
50 Ward L, O’Keeffe S C, Stevick J, et al. Acta Materialia, 2018, 159, 102.
51 Chu D, Lashgari H, Jiang Y, et al. Nanotechnology Reviews, 2014, 3(2), 153.
52 Tang Y, Wan Y, Wang Z, et al. Materials & Design, 2022, 219, 110726.
53 Cho K, Courville A, Bengio Y. IEEE Transactions on Multimedia, 2015, 17(11), 1875.
54 Badrinarayanan V, Kendall A, Cipolla R. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12), 2481.
55 Segler M H S, Preuss M, Waller M P. Nature, 2018, 555(7698), 604.
56 Kim K, Kang S, Yoo J, et al. npj Computational Materials, 2018, 4(1), 67.
57 Gómez-Bombarelli R, Wei J N, Duvenaud D, et al. ACS Central Science, 2018, 4(2), 268.
58 Lee J W, Park W B, Do Lee B, et al. Scientific Reports, 2020, 10(1), 20443.
59 Pei Z, Rozman K A, Doğan Ö N, et al. Advanced Science, 2021, 8(23), 2101207.
60 Li K Y, Li M Z, Wang W H. Journal of Applied Physics, 2024, 135(2), 025102.
61 Long T, Zhang Y, Fortunato N M, et al. Acta Materialia, 2022, 231, 117898.
62 Sanchez-Lengeling B, Aspuru-Guzik A. Science, 2018, 361(6400), 360.
63 Zhou Z, Shang Y, Liu X, et al. npj Computational Materials, 2023, 9(1), 15.
64 Xu X, Hu J. Journal of Non-Crystalline Solids, 2023, 613, 122378.
65 Li K Y, Liu L C, Shao L L, et al. Journal of Alloys and Compounds, 2025, 1010, 178325.

[1]	迟钧瀚, 胡会娥, 王皓, 周雄, 苏小红. 钨颗粒增强Zr基非晶复合材料在侵彻/破碎弹芯材料中的应用进展[J]. 材料导报, 2026, 40(4): 25030170-12.
[2]	周祥胥, 段锋, 朱博. 基于机器学习的SHAP和PDP分析对UHPC流变性能的研究[J]. 材料导报, 2026, 40(2): 24100237-8.
[3]	宋海鹏, 张冠, 范雪茹, 黄勇, 谢磊, 赵冬梅, 李强, 任铁真. 过渡族金属微量添加对Fe基块状金属玻璃的玻璃形成能力、力学性能和耐腐蚀性的影响[J]. 材料导报, 2026, 40(2): 24120223-7.
[4]	李自强, 崔素萍, 马忠诚, 王亚丽, 王晶, 刘云, 乔志杨. 机器学习算法用于水泥强度预测的研究进展[J]. 材料导报, 2025, 39(5): 23120133-12.
[5]	刘朝晖, 盛佳豪, 柳力. 数据驱动下的沥青混合料材料组成设计方法[J]. 材料导报, 2025, 39(4): 24010230-9.
[6]	秦龙, 何建丽, 董万鹏, 黄少波, 王辉, 王志海. 镁合金高温本构模型研究进展[J]. 材料导报, 2025, 39(23): 24110218-8.
[7]	田根, 朱甫宏, 王文宇, 王晓明, 赵阳, 韩国峰, 任智强, 朱胜. 基于机器学习的传感器监测在金属激光增材制造中的应用[J]. 材料导报, 2025, 39(2): 23080174-16.
[8]	李俊炎, 张伟强, 高志玉. 机器学习辅助高熵合金设计的研究进展[J]. 材料导报, 2025, 39(18): 24080091-10.
[9]	王晓龙, 商怀帅, 陆兆虎, 肖振浩, 徐少辉. FRP筋相关因素对粘结性能的影响综述[J]. 材料导报, 2025, 39(17): 24070179-8.
[10]	葛宇飞, 刘东青, 程海峰, 桂博恒, 王新飞, 贾岩. 基于机器学习的光谱选择性红外辐射材料设计研究进展[J]. 材料导报, 2025, 39(15): 24080168-9.
[11]	李歌, 马子然, 闾菲, 彭胜攀, 佟振伟. 基于机器学习高通量筛选二氧化碳还原电催化剂的研究进展[J]. 材料导报, 2025, 39(1): 23110048-13.
[12]	李娇娇, 范婧, 王重. 非晶合金中剪切温升的研究进展[J]. 材料导报, 2024, 38(8): 22050070-8.
[13]	柯松, 陈卓坤, 艾诚, 李尧, 虢婷, 孙志平. 非晶合金薄膜的复合强韧化研究进展[J]. 材料导报, 2024, 38(5): 22090022-9.
[14]	邱国兴, 蔡明冲, 张毅, 苏炳瑞, 杨永坤, 李小明. 基于灰色关联分析和机器学习的高炉铁水硅含量预测[J]. 材料导报, 2024, 38(20): 23080170-6.
[15]	王博, 盛鹏, 徐丽, 李圣驿, 白会涛, 李慧, 薛晴. 材料基因工程技术在电工材料研发中的应用与展望[J]. 材料导报, 2024, 38(13): 23020098-17.

[1]	LI Chaolei. Study on Radial Pores Structure of Microporous Layer with High Mass Transportation in Proton Exchange Membrane Fuel Cells[J]. Materials Reports, 2026, 40(1): 25010096 -5 .
[2]	ZHOU Jiajia. Uniaxial Tensile Properties and Compressive Strength of Limestone Calcined Clay-based Engineered Cementitious Composites[J]. Materials Reports, 2026, 40(1): 24120246 -8 .
[3]	ZHAO Jiazheng. Metallic Heterostructured Materials: Classification,Toughening Mechanisms,and Development Trends[J]. Materials Reports, 2026, 40(1): 25020015 -16 .
[4]	ZHANG Xiaohang. Research Progress on Brazing Methods of Silicon Nitride Ceramics and Metals[J]. Materials Reports, 2026, 40(1): 25010049 -12 .
[5]	XU Chaoliang. Review of the Effect of Irradiation-Assisted Stress Corrosion Cracking on Stainless Steel in Light Water Reactor Environments[J]. Materials Reports, 2026, 40(1): 25010139 -11 .
[6]	FENG Kaibin, LIU Runcong, LI Silong, WU Yunfei, NA Xianzhao, WANG Xiaodong. Detection of the Oscillation Marks on Casting Slabs Using Magnetic Flux Variation and the Nonexcitation Method[J]. Materials Reports, 2026, 40(1): 25010165 -10 .
[7]	LI Bin. Research Progress of Abrasive Flow Machining in the Processing of Complex Microporous Structures Materials for Aeronautic Applications[J]. Materials Reports, 2026, 40(1): 25020122 -12 .
[8]	WAN Yuhui. Study on Room Temperature Deformation Behavior of Magnesium-Bismuth Binary Alloy[J]. Materials Reports, 2026, 40(1): 25010137 -6 .
[9]	YI Shifeng, CHEN Xiaomin. Prediction of High-temperature Tensile Fracture Behavior of GH4169 Alloy Based on the Oyane-Sato Criterion[J]. Materials Reports, 2026, 40(1): 25010099 -7 .
[10]	YIN Ziluo. Dielectric and Mechanical Properties of Polypropylene Fiber-reinforced Cross-linked Polystyrene[J]. Materials Reports, 2026, 40(1): 25010020 -6 .

Viewed

Full text

Abstract

Cited

Shared

Discussed