机器学习辅助镁基材料性能预测与设计进展

彭国胜 ,  王辉 ,  杜博文 ,  熊落保 ,  乔勇 ,  董曦曦

安徽工业大学学报(自然科学版) ›› 2026, Vol. 43 ›› Issue (5) : 481 -496.

PDF (8636KB)
安徽工业大学学报(自然科学版) ›› 2026, Vol. 43 ›› Issue (5) : 481 -496. DOI: 10.12415/j.issn.1671−7872.26091
智能冶金与先进材料 • 先进金属材料设计与制造专刊

机器学习辅助镁基材料性能预测与设计进展

作者信息 +

Research Progress in Machine Learning-assisted Property Prediction and Design of Mg-based Materials

Author information +
文章历史 +
PDF (8842K)

摘要

镁基材料在轻量化结构件、可降解植入体、固态储氢及镁空气电池等领域具有重要应用前景,其性能受成分、加工工艺、微观组织、界面状态与服役环境等多因素耦合影响,传统逐项实验难以覆盖由此产生的高维参数空间。近年来,机器学习在该领域的应用已从拉伸性能预测拓展至加工组织调控、腐蚀与生物降解评价、储氢材料筛选以及镁空气电池阳极和电解液设计。本文围绕数据收集与特征构建、模型验证与解释、候选筛选与实验反馈等环节,评述代表性研究的建模方法及其材料学结论,并比较结构镁合金、生物医用镁合金、镁基储氢材料与镁空气电池在设计变量、验证方式与评价尺度上的差异。现有研究表明,成分和常规工艺数据相对充足,但组织演化、服役环境、失效样本及跨来源验证仍较薄弱;基于随机划分所得的高精度结果,尚不能替代新合金、新工艺或独立实验的检验。未来应着力构建可追溯的多源数据库,在候选筛选中引入相稳定性、组织演化与电化学约束,并通过多目标优化结合实验反馈,提升设计结果的可制备性与复现性。

Abstract

Magnesium-based materials hold significant application prospects in lightweight structural components, biodegradable implants, solid-state hydrogen storage, and Mg-air batteries. Their performance is governed by the combined effects of composition, processing, microstructure, interfacial state, and service environment, while conventional trial-and-error experiments are inadequate to cover the resulting high-dimensional parameter space. In recent years, machine learning has been applied to these materials, extending from tensile property prediction to processing–microstructure control, corrosion and biodegradation evaluation, hydrogen-storage material screening, and anode and electrolyte design for Mg-air batteries. This review focused on three interconnected aspects, namely data collection and feature engineering, model validation and interpretation, and candidate screening with experimental feedback, and critically evaluated the modeling methodologies and materials-related findings of representative studies. A cross-system comparison was presented among structural magnesium alloys, biomedical magnesium alloys, Mg-based hydrogen-storage materials, and Mg-air batteries, with emphasis on their differences in design variables, validation strategies, and evaluation metrics. Existing studies have demonstrated that compositional and conventional processing data are relatively abundant, whereas information on microstructural evolution, service environments, failed specimens, and cross-source validation remains insufficient. High-accuracy results obtained from random data splits cannot replace the validation through new alloys, new processing routes, or independent experiments. Future efforts should be directed toward establishing traceable and multi-source databases, incorporating constraints of phase stability, microstructural evolution, and electrochemistry into candidate screening, and enhancing the fabricability and reproducibility of designed materials through multi-objective optimization coupled with experimental feedback.

关键词

机器学习 / 镁基材料 / 镁合金 / 材料信息学 / 性能预测 / 反向设计 / 主动学习

Key words

machine learning / Mg-based materials / magnesium alloys / materials informatics / property prediction / inverse design / active learning

引用本文

引用格式 ▾
彭国胜,王辉,杜博文,熊落保,乔勇,董曦曦. 机器学习辅助镁基材料性能预测与设计进展[J]. 安徽工业大学学报(自然科学版), 2026, 43(5): 481-496 DOI:10.12415/j.issn.1671−7872.26091

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

XU T C, YANG Y, PENG X D, et al. Overview of advancement and development trend on magnesium alloy[J]. Journal of Magnesium and Alloys, 2019, 7(3): 536-544.

[2]

NIE J F, SHIN K S, ZENG Z R. Microstructure, deformation, and property of wrought magnesium alloys[J]. Metallurgical and Materials Transactions A, 2020, 51(12): 6045-6109.

[3]

YANG Y, XIONG X M, CHEN J, et al. Research advances of magnesium and magnesium alloys worldwide in 2022[J]. Journal of Magnesium and Alloys, 2023, 11(8): 2611-2654.

[4]

赵磊杰, 马立峰, 韩廷状, 等. 变形镁合金轧制成形研究进展[J]. 材料导报, 2020, 34(21): 21135-21145.

[5]

ZHAO L J, MA L F, HAN T Z, et al. Research progress of wrought magnesium alloy rolling forming[J]. Materials Reports, 2020, 34(21): 21135-21145.

[6]

ESMAILY M, SVENSSON J E, FAJARDO S, et al. Fundamentals and advances in magnesium alloy corrosion[J]. Progress in Materials Science, 2017, 89: 92-193.

[7]

SONG G L, ATRENS A. Recently deepened insights regarding Mg corrosion and advanced engineering applications of Mg alloys[J]. Journal of Magnesium and Alloys, 2023, 11(11): 3948-3991.

[8]

MALINOVA T, GUO Z X. Artificial neural network modelling of hydrogen storage properties of Mg—based alloys[J]. Materials Science and Engineering A, 2004, 365(1/2): 219-227.

[9]

DENG M, WANG L Q, VAGHEFINAZARI B, et al. High—energy and durable aqueous magnesium batteries: recent advances and perspectives[J]. Energy Storage Materials, 2021, 43: 238-247.

[10]

LI S B, LI X N, ZHAO C C, et al. Recent progress of electrolytes for Mg—air batteries: a review[J]. Journal of Magnesium and Alloys, 2024, 12(11): 4395-4421.

[11]

HUANG X, DAI Q W, XIANG Q, et al. Microstructure design of advanced magnesium—air battery anodes[J]. Journal of Magnesium and Alloys, 2024, 12(2): 443-464.

[12]

SCHLEDER G R, PADILHA A C M, ACOSTA C M, et al. From DFT to machine learning: recent approaches to materials science: a review[J]. Journal of Physics: Materials, 2019, 2(3): 032001.

[13]

SCHMIDT J, MARQUES M R G, BOTTI S, et al. Recent advances and applications of machine learning in solid—state materials science[J]. NPJ Computational Materials, 2019, 5: 83.

[14]

吴铮, 李全安, 陈晓亚, 等. 机器学习在镁合金应用中的研究进展[J]. 工程科学学报, 2024, 46(10): 1797-1811.

[15]

WU Z, LI Q A, CHEN X Y, et al. Applications of machine learning on magnesium alloys[J]. Chinese Journal of Engineering, 2024, 46(10): 1797-1811.

[16]

CHENG Y, WEI C, HUANG H, et al. A brief review of machine learning—assisted Mg alloy design, processing, and property predictions[J]. Journal of Materials Research and Technology, 2024, 30: 8108-8127.

[17]

HART G L, MUELLER T, TOHER C, et al. Machine learning for alloys[J]. Nature Reviews Materials, 2021, 6(8): 730-755.

[18]

GHORBANI M, BOLEY M, NAKASHIMA P N H, et al. A machine learning approach for accelerated design of magnesium alloys. Part A: alloy data and property space[J]. Journal of Magnesium and Alloys, 2023, 11(10): 3620-3633.

[19]

BLAISZIK B, WARD L, SCHWARTING M, et al. A data ecosystem to support machine learning in materials science[J]. MRS Communications, 2019, 9(4): 1125-1133.

[20]

GHORBANI M, BOLEY M, NAKASHIMA P N H, et al. A machine learning approach for accelerated design of magnesium alloys. Part B: regression and property prediction[J]. Journal of Magnesium and Alloys, 2023, 11(11): 4197-4205.

[21]

WIESE B, BERGER S, BOHLEN J, et al. Property design of extruded magnesium—gadolinium alloys through machine learning[J]. Materials Today Communications, 2023, 36: 106566.

[22]

LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[C]// Advances in Neural Information Processing Systems 30. Long Beach: Curran Associates, Inc, 2017: 4765-4774.

[23]

PILANIA G. Machine learning in materials science: from explainable predictions to autonomous design[J]. Computational Materials Science, 2021, 193: 110360.

[24]

XUE D Z, BALACHANDRAN P V, HOGDEN J, et al. Accelerated search for materials with targeted properties by adaptive design[J]. Nature Communications, 2016, 7: 11241.

[25]

HATTRICK−SIMPERS J R, GREGOIRE J M, KUSNE A G. Perspective: composition—structure—property mapping in high—throughput experiments: turning data into knowledge[J]. APL Materials, 2016, 4(5): 053211.

[26]

ZUO Y X, QIN M, CHEN C, et al. Accelerating materials discovery with Bayesian optimization and graph deep learning[J]. Materials Today, 2021, 51: 126-135.

[27]

JUAN Y, DAI Y, YANG Y, et al. Accelerating materials discovery using machine learning[J]. Journal of Materials Science & Technology, 2021, 79: 178-190.

[28]

PYZER−KNAPP E O, PITERA J W, JOHN P, et al. Accelerating materials discovery using artificial intelligence, high performance computing and robotics[J]. NPJ Computational Materials, 2022, 8: 84.

[29]

ZHU G S, DU X M, SUN D D. Machine learning accelerated design of magnesium alloys with high strength and high ductility[J]. Materials Today Communications, 2025, 44: 111894.

[30]

JAIN R, JAIN S, DEWANGAN S K, et al. Prediction of alloying element effects on the mechanical behavior of high—pressure die—cast Mg—based alloys[J]. Journal of Magnesium and Alloys, 2025, 13(8): 3819-3828.

[31]

XU P C, CHEN H L, LI M J, et al. Multi—objective optimization in machine learning assisted materials design and discovery[J]. Journal of Materials Informatics, 2025, 5: 26.

[32]

MI X X, TIAN L J, TANG A T, et al. A reverse design model for high—performance and low—cost magnesium alloys by machine learning[J]. Computational Materials Science, 2022, 201: 110881.

[33]

MOSQUEIRA−REY E, HERNANDEZ−PEREIRA E, ALONSO—RIOS D, et al. Human—in—the—loop machine learning: a state of the art[J]. Artificial Intelligence Review, 2023, 56(4): 3005-3054.

[34]

KUSNE A G, YU H, WU C, et al. On—the—fly closed—loop materials discovery via Bayesian active learning[J]. Nature Communications, 2020, 11: 5966.

[35]

TERAYAMA K, SUMITA M, TAMURA R, et al. Black—box optimization for automated discovery[J]. Accounts of Chemical Research, 2021, 54(6): 1334-1346.

[36]

LOOKMAN T, BALACHANDRAN P V, XUE D, et al. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design[J]. NPJ Computational Materials, 2019, 5: 21.

[37]

GHORBANI M, BOLEY M, NAKASHIMA P N H, et al. An active machine learning approach for optimal design of magnesium alloys using Bayesian optimisation[J]. Scientific Reports, 2024, 14: 8299.

[38]

XU X N, WANG L Y, ZHU G M, et al. Predicting tensile properties of AZ31 magnesium alloys by machine learning[J]. JOM, 2020, 72(11): 3935-3942.

[39]

SUH J S, SUH B C, LEE S E, et al. Quantitative analysis of mechanical properties associated with aging treatment and microstructure in Mg−Al−Zn alloys through machine learning[J]. Journal of Materials Science & Technology, 2022, 107: 52-64.

[40]

SUH J S, KIM Y M, YIM C D, et al. Interpretable machine learning—based analysis of mechanical properties of extruded Mg−Al−Zn−Mn−Ca−Y alloys[J]. Journal of Alloys and Compounds, 2023, 968: 172007.

[41]

ZHANG J, LIU S, WU R Z, et al. Recent developments in high—strength Mg−RE—based alloys: focusing on Mg−Gd and Mg−Y systems[J]. Journal of Magnesium and Alloys, 2018, 6(3): 277-291.

[42]

LU J, CHEN Y, XU M, et al. Prediction of mechanical properties of Mg—rare earth alloys by machine learning[J]. Materials Research Express, 2022, 9(10): 106519.

[43]

MURUGESAN M, YU J H, CHUNG W, et al. Hybrid artificial neural network—based models to investigate deformation behavior of AZ31B magnesium alloy at warm tensile deformation[J]. Materials, 2023, 16(15): 5308.

[44]

HUANG S J, MOSE M P, KANNAIYAN S. A study of the mechanical properties of AZ61 magnesium composite after equal channel angular processing in conjunction with machine learning[J]. Materials Today Communications, 2022, 33: 104707.

[45]

LIU Y W, WANG L Y, ZHANG H, et al. Accelerated development of high—strength magnesium alloys by machine learning[J]. Metallurgical and Materials Transactions A, 2021, 52(3): 943-954.

[46]

NANDAL V, BENEŠ V, BALÁŽ P, et al. Accelerating the design of resorbable magnesium alloys: a machine learning approach to property prediction[J]. Materials & Design, 2026, 266: 116060.

[47]

LI M H, MESBAH M, FALLAHPOUR A, et al. Mechanical strength estimation of ultrafine—grained magnesium implant by neural—based predictive machine learning[J]. Materials Letters, 2021, 305: 130627.

[48]

HOU H B, WANG J F, YE L, et al. Prediction of mechanical properties of biomedical magnesium alloys based on ensemble machine learning[J]. Materials Letters, 2023, 348: 134605.

[49]

MI X X, JING X R, WANG H L, et al. A machine learning enabled ultra—fine grain design strategy of Mg−Mn—based alloys[J]. Journal of Materials Research and Technology, 2023, 23: 4576-4588.

[50]

GUI Y W, LI Q A, ZHU K G, et al. A combined machine learning and EBSD approach for the prediction of {10−12} twin nucleation in an Mg−RE alloy[J]. Materials Today Communications, 2021, 27: 102282.

[51]

GUAN B, CHEN C, XIN Y C, et al. Predicting the Hall−Petch slope of magnesium alloys by machine learning[J]. Journal of Magnesium and Alloys, 2024, 12(11): 4436-4442.

[52]

ZHANG S, ZHU G M, FAN Y H, et al. A machine learning study of grain boundary damage in Mg alloy[J]. Materials Science and Engineering A, 2023, 867: 144721.

[53]

YU J, OH S J, BAEK S, et al. Predicting the effect of processing parameters on caliber—rolled mg alloys through machine learning[J]. Applied Sciences, 2022, 12(20): 10646.

[54]

BYUN S, YU J, CHEON S, et al. Enhanced prediction of anisotropic deformation behavior using machine learning with data augmentation[J]. Journal of Magnesium and Alloys, 2024, 12(1): 186-196.

[55]

PAGADALA N D, JAISWAL J, RADHA R. Machine learning based corrosion prediction of as cast Mg−Sn alloys for biomedical applications[J]. Materials Today Communications, 2023, 35: 106108.

[56]

MOSES A, CHEN D, WAN P, et al. Prediction of electrochemical corrosion behavior of magnesium alloy using machine learning methods[J]. Materials Today Communications, 2023, 37: 107285.

[57]

LU Z X, SI S J, HE K Y, et al. Prediction of Mg alloy corrosion based on machine learning models[J]. Advances in Materials Science and Engineering, 2022, 2022: 9597155.

[58]

ZHAO X Q, QIN X, XIA S X, et al. Data—driven corrosion assessment of magnesium alloys: a multi—level graph attention network for quantitative hydrogen—evolution prediction[J]. Journal of Magnesium and Alloys, 2026, 18: 101964.

[59]

BADKOOBEH F, MOSTAAN H, RAFIEI M, et al. Additive manufacturing of biodegradable magnesium—based materials: design strategies, properties, and biomedical applications[J]. Journal of Magnesium and Alloys, 2023, 11(3): 801-839.

[60]

KIM J, PAN H B. Effects of magnesium alloy corrosion on biological response: perspectives of metal—cell interaction[J]. Progress in Materials Science, 2023, 133: 101039.

[61]

PENG P, PENG Y, LIU F G, et al. Bayesian optimization and explainable machine learning for high—dimensional multi—objective optimization of biodegradable magnesium alloys[J]. Journal of Materials Science & Technology, 2025, 238: 132-145.

[62]

RAGURAMAN S, PRIYADARSHINI M S, NGUYEN T, et al. Machine learning—guided accelerated discovery of structure—property correlations in lean magnesium alloys for biomedical applications[J]. Journal of Magnesium and Alloys, 2024, 12(6): 2267-2283.

[63]

MA S Y, ZHANG D W, ZHANG P L, et al. Rapid prediction of the corrosion behaviour of coated biodegradable magnesium alloys using phase field simulation and machine learning[J]. Computational Materials Science, 2025, 247: 113546.

[64]

RAHNAMA A, ZEPON G, SRIDHAR S. Machine learning based prediction of metal hydrides for hydrogen storage, part I: prediction of hydrogen weight percent[J]. International Journal of Hydrogen Energy, 2019, 44(14): 7337-7344.

[65]

SUWARNO S, DICKY G, SUYUTHI A, et al. Machine learning analysis of alloying element effects on hydrogen storage properties of AB2 metal hydrides[J]. International Journal of Hydrogen Energy, 2022, 47(23): 11938-11947.

[66]

DONG S Y, WANG Y Y, LI J Y, et al. Exploration and design of Mg alloys for hydrogen storage with supervised machine learning[J]. International Journal of Hydrogen Energy, 2023, 48(97): 38412-38424.

[67]

WANG N G, HUANG Y X, LIU J J, et al. AZ31 magnesium alloy with ultrafine grains as the anode for Mg—air battery[J]. Electrochimica Acta, 2021, 378: 138135.

[68]

CHEN X R, JIA Y H, SHI Z M, et al. Understanding the discharge behavior of an ultra—high—purity Mg anode for Mg—air primary batteries[J]. Journal of Materials Chemistry A, 2021, 9(37): 21387-21401.

[69]

XU W, SNIHIROVA D, DENG M, et al. A mathematical model describing the surface evolution of Mg anode during discharge of aqueous Mg—air battery[J]. Journal of Power Sources, 2022, 542: 231745.

[70]

LIANG H X, YANG K, ZHAO C C, et al. Mitigating the efficiency—voltage trade—off in magnesium air battery via a novel active learning framework[J]. Applied Surface Science, 2024, 657: 159806.

[71]

LING N, WANG Y Y, SONG S S, et al. Experimentally validated screening strategy for alloys as anode in Mg—air battery with multi—target machine learning predictions[J]. Chemical Engineering Journal, 2024, 496: 153824.

[72]

WANG L Q, SNIHIROVA D, DENG M, et al. Sustainable aqueous metal—air batteries:an insight into electrolyte system[J]. Energy Storage Materials, 2022, 52: 573-597.

[73]

GAO J X, LI X T, LIU Q F, et al. A chloride—free electrolyte to suppress the anodic hydrogen evolution corrosion of magnesium anode in aqueous magnesium air batteries[J]. Chemical Engineering Journal, 2023, 464: 142655.

[74]

WANG L Q, SNIHIROVA D, DENG M, et al. Tailoring electrolyte additives for controlled Mg−Ca anode activity in aqueous Mg—air batteries[J]. Journal of Power Sources, 2020, 460: 228106.

[75]

SNIHIROVA D, WANG L Q, LAMAKA S V, et al. Synergistic mixture of electrolyte additives: a route to a high—efficiency Mg—air battery[J]. The Journal of Physical Chemistry Letters, 2020, 11(20): 8790-8798.

[76]

HOCHE D, LAMAKA S V, VAGHEFINAZARI B, et al. Performance boost for primary magnesium cells using iron complexing agents as electrolyte additives[J]. Scientific Reports, 2018, 8: 7578.

[77]

LI L H, CHEN H, HE E, et al. High—energy—density magnesium—air battery based on dual—layer gel electrolyte[J]. Angewandte Chemie International Edition, 2021, 60: 15317-15322.

[78]

JIANG P L, LI K, HOU R Q, et al. Boosting discharge performance of primary Mg—air batteries via adopting sodium citrate as electrolyte to suppress self—corrosion of Mg anode during discharge[J]. Chemical Engineering Journal, 2025, 511: 162200.

[79]

WU Y L, SNIHIROVA D, WURGER T, et al. Machine learning—guided discovery of high—efficiency electrolyte additives for aqueous magnesium—air batteries[J]. Energy Storage Materials, 2025, 76: 104120.

[80]

DERINGER V L, BARTÓK A P, BERNSTEIN N, et al. Gaussian process regression for materials and molecules[J]. Chemical Reviews, 2021, 121(16): 10073-10141.

[81]

ZHANG Z Z, GU G X. Physics—informed deep learning for digital materials[J]. Theoretical and Applied Mechanics Letters, 2021, 11(1): 100220.

基金资助

国家重点研发计划项目(2021YFF0600504)

安徽省大学生创新创业计划(S202610360426)

AI Summary AI Mindmap
PDF (8636KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉