基于特征工程和机器学习的铝基高熵合金稳定性预测

doi:10.12066/j.issn.1007-2861.2381

上海大学学报(自然科学版) ›› 2022, Vol. 28 ›› Issue (3): 476-484.doi: 10.12066/j.issn.1007-2861.2381

基于特征工程和机器学习的铝基高熵合金稳定性预测

胡瑞¹, 刘庆¹, 张光捷¹, 李俊杰¹, 陈晓玉², 魏晓¹^,³, 戴东波¹()

1.上海大学计算工程与科学学院, 上海 200444
2.上海大学材料基因组工程研究院材料信息与数据科学中心, 上海 200444
3.之江实验室, 浙江杭州 311100

收稿日期:2022-02-25 出版日期:2022-06-30 发布日期:2022-05-27
通讯作者: 戴东波 E-mail:dbdai@shu.edu.cn
作者简介:戴东波(1977—), 男, 讲师, 博士, 研究方向为材料信息学、数据挖掘等. E-mail: dbdai@shu.edu.cn
基金资助:
国家重点研发计划资助项目(2018YFB0704400);云南省重大科技专项资助项目(202002AB080001-2);之江实验室科研攻关资助项目(2021PE0AC02)

Phase stability prediction of hign entropy alloys in aluminum matrix composites based on feature engneering and machine learning

HU Rui¹, LIU Qing¹, ZHANG Guangjie¹, LI Junjie¹, CHEN Xiaoyu², WEI Xiao¹^,³, DAI Dongbo¹()

1. School Computer Engineering and Science, Shanghai University, Shanghai 200444, China
2. Centerof Materials Informatics and Data Science, Materials Genome Institute, Shanghai University, Shanghai 200444, China
3. Zhejiang Laboratory, Hangzhou 311100, Zhejiang, China

Received:2022-02-25 Online:2022-06-30 Published:2022-05-27
Contact: DAI Dongbo E-mail:dbdai@shu.edu.cn

摘要/Abstract

摘要：

铝基复合材料具有众多优异的性能, 应用前景较好. 以简单稳定相的高熵合金可以作为增强颗粒来制备铝基复合材料, 其各方面力学性能都显著提升. 提出了一种基于结合了特征工程和机器学习的新方法来研究高熵合金相稳定性. 该方法利用特征工程筛选出影响目标属性的重要因素, 然后选择相应的回归方法预测相稳定性. 使用 50% 的数据集进行训练, 并在其余数据集上进行测试验证. 研究结果表明, 该方法在预测高熵合金的相稳定性方面具有较高的准确性($R^{2}$=0.994), 且能辅助找到影响相稳定性的关键因素.

关键词: 铝基复合材料, 高熵合金, 特征工程, 机器学习, 相稳定性预测

Abstract:

Aluminum matrix composites offer many excellent properties and wide application prospects. High entropy alloys with a simple and stable phase can be used as reinforcement to prepare aluminum matrix composites with significantly improved performance in all aspects. Herein, a new method based on feature engineering and machine learning is proposed to investigate the phase stability of high entropy alloys. This method uses feature engineering to determine the important factors affecting the target attributes, and then selects the corresponding regression method to predict the phase stability. A model on 50% of the datasets is trained and then the model is verified on other datasets. The results show that this method is highly accurate in predicting the phase stability of high entropy alloys ($R^2=0.994$). In addition, this method can be used to identify key factors affecting phase stability.

Key words: aluminum matrix composite, high entropy alloy, feature engineering, machine learning, phase stability prediction

中图分类号:

TB 331

胡瑞, 刘庆, 张光捷, 李俊杰, 陈晓玉, 魏晓, 戴东波. 基于特征工程和机器学习的铝基高熵合金稳定性预测[J]. 上海大学学报(自然科学版), 2022, 28(3): 476-484.

HU Rui, LIU Qing, ZHANG Guangjie, LI Junjie, CHEN Xiaoyu, WEI Xiao, DAI Dongbo. Phase stability prediction of hign entropy alloys in aluminum matrix composites based on feature engneering and machine learning[J]. Journal of Shanghai University（Natural Science Edition）, 2022, 28(3): 476-484.

图/表 8

图1

表1

图2

表2

图3

图4

图5

图6

[1]	Zhang Y, Zuo T T, Tang Z, et al. Microstructures and properties of high-entropy alloys[J]. Progress in Materials Science, 2014, 61: 1-93. doi: 10.1016/j.pmatsci.2013.10.001
[2]	Liu Y, Chen J, Li Z, et al. Formation of transition layer and its effect on mechanical properties of AlCoCrFeNi high-entropy alloy/Al composites[J]. J Alloys Compd, 2019, 780: 558-564. doi: 10.1016/j.jallcom.2018.11.364
[3]	Zhu D Z, Ding X, Qi L F, et al. Microstructure and mechanical properties of Al$_{0.25}$Cu$_{0.75}$ FeNiCo HEAs particulates reinforced aluminum alloy[J]. Rare Matel Materials and Engineering, 2017, 46(11): 3400-3404.
[4]	Zhang L S, Ma G L, Fu L C, et al. Recent progress in high-entropy alloys[J]. Advanced Materials Research, 2013, 631: 227-232.
[5]	Gurao N P, Biswas K. In the quest of single phase multi-component multiprincipal high entropy alloys[J]. J Alloys Compd, 2017, 697: 434-442. doi: 10.1016/j.jallcom.2016.11.383
[6]	Yang X, Zhang Y. Prediction of high-entropy stabilized solid-solution in multi-component alloys[J]. Materials Chemistry & Physics, 2012, 132(2/3): 233-238.
[7]	Wang Z, Guo S, Liu C T. Phase selection in high-entropy alloys: from nonequilibrium to equilibrium[J]. JOM, 2014, 66(10): 1966-1972. doi: 10.1007/s11837-014-0953-8
[8]	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[J]. Advanced Engineering Materials, 2004, 6(5): 299-303. doi: 10.1002/adem.200300567
[9]	Raghavan R, Kumar H K C, Murty B S, et al. Analysis of phase formation in multi-component alloys[J]. J Alloys Compd, 2012, 544(32): 152-158. doi: 10.1016/j.jallcom.2012.07.105
[10]	Jiang C, Uberuaga B P. Efficient Ab initio modeling of random multicomponent alloys[J]. Physical Review Letters, 2016, 116(10): 105501. doi: 10.1103/PhysRevLett.116.105501
[11]	黎威, 龙连春, 刘静毅, 等. 基于机器学习的无机磁性材料磁性基态分类与磁矩预测[J]. 物理学报, 2022, 71(6): 060202.
[12]	Chang X J, Zeng M Q, Liu K L, et al. Phase engineering of high-entropy alloys[J]. Advanced Materials, 2020, 32: 1907226-1907238. doi: 10.1002/adma.201907226
[13]	Butler K T, Davies D W, Cartwright H, et al. Machine learning for molecular and materials science[J]. Nature, 2018, 559(7715): 547-555. doi: 10.1038/s41586-018-0337-2
[14]	Mohammadi P, Wang Z J. Machine learning for quality prediction in abrasion-resistant material manufacturing process[C]// Electrical & Computer Engineering. 2016.
[15]	Li S, Zhang H, Dai D, et al. Study on the factors affecting solid solubility in binary alloys: an exploration by machine learning[J]. J Alloys Compd, 2019, 782: 110-118. doi: 10.1016/j.jallcom.2018.12.136
[16]	宿彦京, 付华栋, 白洋, 等. 中国材料基因工程研究进展[J]. 金属学报, 2020, 56(10): 1313-1323.
[17]	谢建新, 宿彦京, 薛德祯, 等. 机器学习在材料研发中的应用[J]. 金属学报, 2021, 57(11): 1343-1361. doi: 10.11900/0412.1961.2021.00357
[18]	Tan Y, Li J, Tang S, et al. Design of high-entropy alloys with a single solid-solution phase: average properties vs. their variances[J]. J Alloys Compd, 2018, 742: 430-441. doi: 10.1016/j.jallcom.2018.01.252
[19]	Wolpert D H, Macready W G. No free lunch theorems for optimization[J]. IEEE Transactions on Evolutionary Computation, 1997, 1(1): 67-82. doi: 10.1109/4235.585893
[20]	Pilania G, Balacgabdran P V, Kim C, et al. Finding new perovskite halides via machine learning[EB/OL]. [2022-01-05]. https://www.frontiersin.org/articles/10.3389/fmats.2016.00019/full.
[21]	Mangal A, Holm E A. A Comparative study of feature selection methods for stress hotspot classification in materials[J]. Integrating Materials & Manufacturing Innovation, 2018, 8: 1-9.
[22]	Tang H S, Yao Y W. Research on decision tree in data mining[J]. Application Research of Computers, 2001, 8: 18-19.
[23]	Yao D J, Yang J, Zhan X J. Feature selection algorithm based on random forest[J]. Journal of Jilin University, 2014, 1: 142-146.
[24]	Marsin S M, Ling S L, Zalilah N, et al. Comparison of signal-to-noise, blank determination, and linear regression methods for the estimation of detection and quantification limits for volatile organic compounds by gas chromatography[EB/OL]. [2022-01-11]. https://xueshu.baidu.com/usercenter/paper/show?paperid=6d31c0611b24694ee820ad145e037e77.
[25]	Xu M, Powers D A. Bayesian ridge estimation of age-period-cohort models[M]. Switzerland: Springer International Publishing, 2016.
[26]	Ye Y F, Wang Q, Lu J, et al. Design of high entropy alloys: a single-parameter thermodynamic rule[J]. Scr Mater, 2015, 104: 53-55. doi: 10.1016/j.scriptamat.2015.03.023
[27]	Ye Y F, Wang Q, Lu J, et al. High-entropy alloy: challenges and prospects[J]. Materials Today, 2016, 19(6): 349-362. doi: 10.1016/j.mattod.2015.11.026
[28]	Zhang H R, Zhang Y, Dai D B, et al. Modelling and optimization of the superconducting transition temperature[J]. Materials & Design, 2016, 92: 371-377.
[29]	Tan Y, Li J, Tang Z, et al. Design of high-entropy alloys with a single solid-solution phase: average properties vs. their variances[J]. J Alloys Compd, 2018, 742: 430-441. doi: 10.1016/j.jallcom.2018.01.252
[30]	Luan H W, Yang S, Li J F, et al. Phase stabilities of high entropy alloys[J]. Scripta Materialia, 2020, 179: 40-44. doi: 10.1016/j.scriptamat.2019.12.041

基于特征工程和机器学习的铝基高熵合金稳定性预测

Phase stability prediction of hign entropy alloys in aluminum matrix composites based on feature engneering and machine learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

相关文章 14

编辑推荐

Metrics

本文评价

[1]	郑晨路, 张孟喜, 吴惠明, 李刚. 基于机器学习算法超大直径泥水盾构施工地表沉降预测[J]. 上海大学学报(自然科学版), 2026, 32(3): 544-553.
[2]	许浩, 石晨昕, 何文福, 赵慧玲, 詹浩南. 交通荷载下场地振动响应及衰减预测模型[J]. 上海大学学报(自然科学版), 2025, 31(6): 1007-1022.
[3]	王伟冠, 丁静, 刘鑫. 基于线性回归和神经网络的期权对冲方法: 以 SSE 50 ETF 期权为例[J]. 上海大学学报(自然科学版), 2024, 30(6): 1067-1079.
[4]	赵浩然1, 沈强2, 王鹏2. 经典与机器学习原子间相互作用势的发展及应用进展[J]. 上海大学学报(自然科学版), 2024, 30(5): 802-812.
[5]	宗宇杨, 李俊辉, 朱向东, 单光存, 马汝广. 机器学习在高熵电催化材料中的研究进展 [J]. 上海大学学报(自然科学版), 2023, 29(5): 859-885.
[6]	张涵, 陈龙龙, 张建华, 蒋海珍. 耐高温透明聚酰亚胺的结构设计与性能预测[J]. 上海大学学报(自然科学版), 2022, 28(5): 794-812.
[7]	陈水洲, 王晓书, 欧阳求保, 张瑞. 数据驱动的铝基复合材料性能预测和逆向设计[J]. 上海大学学报(自然科学版), 2022, 28(3): 512-522.
[8]	武星, 胡明涛, 丁鹏. 陶瓷涂层材料多模态数据表征学习[J]. 上海大学学报(自然科学版), 2022, 28(3): 492-503.
[9]	麦嘉琪, 徐鹏程, 丁松, 孙阳庭, 陆文聪. 支持向量回归预测不锈钢的点蚀电位[J]. 上海大学学报(自然科学版), 2022, 28(3): 485-491.
[10]	岳溪朝, 冯燕, 刘健, 于烨泳, 席慷杰, 钱权. 材料基因组工程专用数据库[J]. 上海大学学报(自然科学版), 2022, 28(3): 399-412.
[11]	陶立, 朱杰江, 蔡洪浩. 基于经典机器学习的墙柱施工图图像识别[J]. 上海大学学报(自然科学版), 2021, 27(5): 940-949.
[12]	李一航, 肖斌, 唐宇超, 刘馥, 王小梦, 刘轶. 尖晶石氧化物能量和结构的第一性原理计算和机器学习[J]. 上海大学学报(自然科学版), 2021, 27(4): 635-649.
[13]	谢亚茜, 陈业新, 马星星. 硼含量对 FeCoNiCrAl$_{\bf 0.1}$B$_{ x}$ 高熵合金组织和力学性能的作用[J]. 上海大学学报(自然科学版), 2021, 27(2): 280-288.
[14]	游洋, 杜婉, 李惟驹, 陈竞哲. 基于机器学习方法的二维材料带隙预测[J]. 上海大学学报(自然科学版), 2020, 26(5): 824-833.