机器学习辅助高性能银合金电接触材料的快速发现

doi:10.11900/0412.1961.2021.00002

金属学报

2022, Vol. 58

Issue (6): 816-826 DOI: 10.11900/0412.1961.2021.00002

研究论文

本期目录 | 过刊浏览

机器学习辅助高性能银合金电接触材料的快速发现

何兴群¹^,²^,³, 付华栋¹^,²^,³(

), 张洪涛¹^,²^,³, 方继恒⁴, 谢明⁴, 谢建新¹^,²^,³(

)

^1.北京科技大学北京材料基因工程高精尖创新中心北京 100083
^2.北京科技大学现代交通金属材料与加工技术北京实验室北京 100083
^3.北京科技大学材料先进制备技术教育部重点实验室北京 100083
^4.昆明贵金属研究所稀贵金属综合利用新技术国家重点实验室昆明 650106

Machine Learning Aided Rapid Discovery of High Perfor-mance Silver Alloy Electrical Contact Materials

HE Xingqun¹^,²^,³, FU Huadong¹^,²^,³(

), ZHANG Hongtao¹^,²^,³, FANG Jiheng⁴, XIE Ming⁴, XIE Jianxin¹^,²^,³(

)

^1.Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China
^2.Beijing Laboratory of Metallic Materials and Processing for Modern Transportation, University of Science and Technology Beijing, Beijing 100083, China
^3.Key Laboratory for Advanced Materials Processing (Ministry of Education), University of Science and Technology Beijing, Beijing 100083, China
^4.State Key Laboratory of Advanced Technologies for Comprehensive Utilization of Platinum Metals, Kunming Institute of Precious Metals, Kunming 650106, China

引用本文:

何兴群, 付华栋, 张洪涛, 方继恒, 谢明, 谢建新. 机器学习辅助高性能银合金电接触材料的快速发现[J]. 金属学报, 2022, 58(6): 816-826.
Xingqun HE, Huadong FU, Hongtao ZHANG, Jiheng FANG, Ming XIE, Jianxin XIE. Machine Learning Aided Rapid Discovery of High Perfor-mance Silver Alloy Electrical Contact Materials[J]. Acta Metall Sin, 2022, 58(6): 816-826.

全文: PDF(3397 KB) HTML

摘要:

为了快速发现高性能银合金电接触材料,从文献中收集了32组铸造法制备的银合金电接触材料的成分和性能数据,采用特征量筛选方法识别出影响合金性能的关键合金因子,采用支持向量机算法建立了合金导电率和硬度预测模型,实现了合金成分的快速设计。选取预测性能优异的Ag-19.53Cu-1.36Ni、Ag-10.20Cu-0.20Ni-0.05Ce和Ag-11.43Cu-0.66Ni-0.05Ce (质量分数,%) 3种成分设计方案进行工业生产条件的实验验证,性能预测结果与实验结果误差均小于10%,3种合金导电率均≥ 79%IACS,Vickers硬度均≥ 87 HV,综合性能均优于已有铸造法制备的银合金电接触材料。上述研究结果表明,本工作建立的机器学习成分设计方法可靠性好,有助于提高合金成分设计效率,快速发现综合性能优异的银合金电接触材料。

关键词 ：机器学习, 银合金, 电接触材料, 成分设计

Abstract：

Thirty-two groups of data of composition and performance of silver alloy electrical contact materials prepared via casting were collected from the literature to quickly find high-performance silver alloy electrical contact materials. The key alloy factors affecting the alloy properties were identified using the feature selection method. The prediction model of alloy electrical conductivity and hardness was established using a support vector machine (SVM) algorithm, which achieved the rapid design of alloy composition. Three composition designs of Ag-19.53Cu-1.36Ni, Ag-10.20Cu-0.20Ni-0.05Ce, and Ag-11.43Cu-0.66Ni-0.05Ce (mass fraction, %) with excellent predictive performance were selected for experimental validation under industrial production conditions. The error between the performance prediction and experimental results is less than 10%, the electrical conductivity of the three alloys designed is greater than 79%IACS, and the Vickers hardness is greater than 87 HV. Both the electrical conductivity and hardness are better than those of previous silver alloy electrical contact materials prepared via casting. The above results show that the machine learning composition design method established in this study has good reliability, helps improve the efficiency of alloy composition design, and quickly finds silver alloy electrical contact materials with excellent comprehensive properties.

Key words： machine learning silver alloy electrical contact material composition design

收稿日期: 2021-01-15

ZTFLH:

TG146.3

基金资助:国家自然科学基金项目(U1602271);国家自然科学基金项目(51974028);北京市科委项目(Z191100001119125);中央高校基本科研业务费项目(FRF-IDRY-19-019)

作者简介: 付华栋, hdfu@ustb.edu.cn,主要从事金属材料机器学习领域研究谢建新, jxxie@mater.ustb.edu.cn,主要从事材料基因工程领域研究
何兴群,男,1992年生,博士生

	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
	何兴群
	付华栋
	张洪涛
	方继恒
	谢明
	谢建新
44.8K

链接本文:

https://www.ams.org.cn/CN/10.11900/0412.1961.2021.00002 或 https://www.ams.org.cn/CN/Y2022/V58/I6/816

图1 机器学习辅助银合金成分设计策略

表1 数据集的空间分布范围

图2 银合金电接触材料导电率模型和硬度模型的合金因子线性相关性表现

图3 银合金电接触材料导电率模型和硬度模型的合金因子后向递归筛选结果

图4 银合金电接触材料导电率模型和硬度模型的关键合金因子穷举筛选结果

表2 导电率模型关键合金因子筛选结果

表3 硬度模型关键合金因子筛选结果

图5 采用支持向量机建立的机器学习预测模型结果

表4 设计合金的名义成分与实际成分 (mass fraction / %)

表5 设计合金的预测性能与实测性能比较

图6 设计合金在加工和热处理过程中的导电率和硬度变化

图7 退火后的设计合金抗拉强度和断后伸长率及与文献[21,22,38~40]报道银合金电接触材料性能对比

图8 设计的银合金电接触材料的铸态组织和拉拔后退火的横截面及纵截面组织的SEM像

图9 设计合金550℃退火后显微组织的TEM像

表6 图9中点1~3的EDS结果

1	Findik F, Uzun H. Microstructure, hardness and electrical properties of silver-based refractory contact materials [J]. Mater. Des., 2003, 24: 489 doi: 10.1016/S0261-3069(03)00125-0
2	Biyik S, Arslan F, Aydin M. Arc-erosion behavior of boric oxide-reinforced silver-based electrical contact materials produced by mechanical alloying [J]. J. Electron. Mater., 2015, 44: 457 doi: 10.1007/s11664-014-3399-4
3	Jung H, Nestler D, Wielage B, et al. Reinforcement of conducting silver-based materials [J]. Mater. Sci., 2014, 20: 247
4	Li H Y, Wang X H, Liu Y F, et al. Effect of strengthening phase on material transfer behavior of Ag-based contact materials under different voltages [J]. Vacuum, 2017, 135: 55 doi: 10.1016/j.vacuum.2016.10.031
5	Wang J, Tie S N, Kang Y Q, et al. Contact resistance characteristics of Ag-SnO₂ contact materials with high SnO₂ content [J]. J. Alloys Compd., 2015, 644: 438 doi: 10.1016/j.jallcom.2015.05.035
6	Ray N, Kempf B, Wiehl G, et al. Novel processing of Ag-WC electrical contact materials using spark plasma sintering [J]. Mater. Des., 2017, 121: 262 doi: 10.1016/j.matdes.2017.02.070
7	Xue D Z, Xue D Q, Yuan R H, et al. An informatics approach to transformation temperatures of NiTi-based shape memory alloys [J]. Acta Mater., 2017, 125: 532 doi: 10.1016/j.actamat.2016.12.009
8	Ren F, Ward L, Williams T, et al. Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments [J]. Sci. Adv., 2018, 4: eaaq1566 doi: 10.1126/sciadv.aaq1566
9	Shen C G, Wang C C, Wei X L, et al. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel [J]. Acta Mater., 2019, 179: 201 doi: 10.1016/j.actamat.2019.08.033
10	Ling J, Hutchinson M, Antono E, et al. High-dimensional materials and process optimization using data-driven experimental design with well-calibrated uncertainty estimates [J]. Integr. Mater. Manuf. Innov., 2017, 6: 207 doi: 10.1007/s40192-017-0098-z
11	Liu R Q, Kumar A, Chen Z Z, et al. A predictive machine learning approach for microstructure optimization and materials design [J]. Sci. Rep., 2015, 5: 11551 doi: 10.1038/srep11551
12	Sun Y T, Bai H Y, Li M Z, et al. Machine learning approach for prediction and understanding of glass-forming ability [J]. J. Phys. Chem. Lett., 2017, 8: 3434 doi: 10.1021/acs.jpclett.7b01046 pmid: 28697303
13	Wang C S, Fu H D, Jiang L, et al. A property-oriented design strategy for high performance copper alloys via machine learning [J]. npj Comput. Mater., 2019, 5: 87 doi: 10.1038/s41524-019-0227-7
14	Zhang H T, Fu H D, He X Q, et al. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening [J]. Acta Mater., 2020, 200: 803 doi: 10.1016/j.actamat.2020.09.068
15	Xue D Z, Balachandran P V, Hogden J, et al. Accelerated search for materials with targeted properties by adaptive design [J]. Nat. Commun., 2016, 7: 11241 doi: 10.1038/ncomms11241
16	Wen C, Zhang Y, Wang C X, et al. Machine learning assisted design of high entropy alloys with desired property [J]. Acta Mater., 2019, 170: 109 doi: 10.1016/j.actamat.2019.03.010
17	Sun Y, Zeng W D, Han Y F, et al. Optimization of chemical composition for TC11 titanium alloy based on artificial neural network and genetic algorithm [J]. Comput. Mater. Sci., 2011, 50: 1064 doi: 10.1016/j.commatsci.2010.11.002
18	GroupWriting. Precious Metal Processing Manual [M]. Beijing: Metallurgical Industry Press, 1978: 1
18	《贵金属加工手册》编写组. 贵金属加工手册 [M]. 北京: 冶金工业出版社, 1978: 1
19	Ning Y T, Zhao H Z. Silver [M]. Changsha: Central South University Press, 2005: 1
19	宁远涛, 赵怀志. 银 [M]. 长沙: 中南大学出版社, 2005: 1
20	Hu C Y, Liu S J. New Materials of Precious Metals [M]. Changsha: Central South University Press, 2015: 1
20	胡昌义, 刘时杰. 贵金属新材料 [M]. 长沙: 中南大学出版社, 2015: 1
21	Wei M X, Liu Q, Gao Q Q, et al. Study the influence of rare earth elements on microstructure and property of AgCuNi alloy [J]. Precious Met., 2019, 40(suppl.1) : 31
21	魏明霞, 柳青, 高勤琴等. 稀土元素对AgCuNi合金材料组织性能影响研究 [J]. 贵金属, 2019, 40(): 31
22	Dong P, Ren T, Qin G Y, et al. Microstructure and properties of Ag-15Cu-10Au-2Ni alloy [J]. J. Funct. Mater., 2019, 50: 3174
22	董鹏, 任涛, 秦国义等. Ag-15Cu-10Au-2Ni合金的显微组织与性能 [J]. 功能材料, 2019, 50: 3174
23	Chen Y T, Wang S, Xie M, et al. Research progress in silver based sliding electrical contact material [J]. Precious Met., 2015, 36(1): 68
23	陈永泰, 王松, 谢明等. 银基滑动电接触材料的研究进展 [J]. 贵金属, 2015, 36(1): 68
24	Li S Z, Zhang H R, Dai D B, et al. Study on the factors affecting solid solubility in binary alloys: An exploration by machine learning [J]. J. Alloys Compd., 2019, 782: 110 doi: 10.1016/j.jallcom.2018.12.136
25	Wojtasik K, Missol W. PM helps develop cadmium-free electrical contacts [J]. Met. Powd. Rep., 2004, 59: 34.
26	Huang F X, Li M, Ying P, et al. Effect of trace cerium on the as-cast microstructure of Ag-Cu-Ni alloy [J]. Mater. Sci. Forum, 2011, 687: 44 doi: 10.4028/www.scientific.net/MSF.687.44
27	Ferro R, Delfino S. Comments on the properties of Ag-rich alloys in the silver-rare earth systems [J]. J. Less Common Met., 1979, 68: 23 doi: 10.1016/0022-5088(79)90269-8
28	Hsueh H W, Hung F Y, Lui T S. Recrystallization of Ag and Ag-La alloy wire in wire bonding process [J]. Adv. Mater. Res., 2013, 804: 151
29	Louw N, Steel S J. Variable selection in kernel fisher discriminant analysis by means of recursive feature elimination [J]. Comput. Stat. Data An., 2006, 51: 2043 doi: 10.1016/j.csda.2005.12.018
30	Nagata K, Kitazono J, Nakajima S, et al. An exhaustive search and stability of sparse estimation for feature selection problem [J]. IPSJ Online Trans., 2015, 8: 25
31	Luo H T, Chen S W. Phase equilibria of the ternary Ag-Cu-Ni system and the interfacial reactions in the Ag-Cu/Ni couples [J]. J. Mater. Sci., 1996, 31: 5059 doi: 10.1007/BF00355906
32	Wloch G, Sokolowski K, Ostachowski P, et al. Decomposition of supersaturated solid solution during non-isothermal aging and its effect on the physical properties and microstructure of the Ag-Cu7.5 Alloy [J]. J. Mater. Eng. Perform., 2020, 29: 1488 doi: 10.1007/s11665-019-04517-x
33	Ghosh G, Miyake J, Fine M E, et al. The systems-based design of high-strength, high-conductivity alloys [J]. JOM, 1997, 49(3): 56
34	Zhan C G, Nichols J A, Dixon D A. Ionization potential, electron affinity, electronegativity, hardness, and electron excitation energy: Molecular properties from density functional theory orbital energies [J]. J. Phys. Chem., 2003, 107A: 4184
35	Li M, Lu P, Zhang H Q, et al. Electrochemical determination of the ionization potential and electron affinity of PF derivatives [J]. Chin. J. Lumin., 2006, 27: 80
35	李茂, 路萍, 张海全等. 含芴聚合物电子亲合能和电离能的确定 [J]. 发光学报, 2006, 27: 80
36	Demir D, Turşucu A, Önülüer T. Studies on mass attenuation coefficient, effective atomic number and electron density of some vitamins [J]. Radiat. Environ. Biophys., 2012, 51: 469 doi: 10.1007/s00411-012-0427-8 pmid: 22733080
37	Owen P E A, Roberts E W. XXIX. Factors affecting the limit of solubility of elements in copper and silver [J]. Lond. Edinb. Dubl. Phil. Mag. J. Sci., 1939, 27: 294
38	Li J, Yang F T, Zhou S P, et al. Influence of trace amounts of cerium on properties of AgCuNi alloy [J]. Chin. J. Rare Met., 2007(suppl. 1) : 1
38	李季, 杨富陶, 周世平等. 微量稀土元素铈对AgCuNi合金的性能影响 [J]. 稀有金属, 2007(): 1
39	Lu S P, Yang H M, Yang F T, et al. The effect of Zn on the properties of AgCuNi4-0.5 alloy [J]. Precious Met., 2013, 34(1): 21
39	卢绍平, 杨红梅, 杨富陶等. Zn对AgCuNi4-0.5合金性能的影响 [J]. 贵金属, 2013, 34(1): 21
40	He X Y, Zhou S P, Wang J, et al. Effect of Cu on mechanical properties and recrystallization temperature of AgCe alloy [J]. Precious Met., 2008, 29(2): 11
40	贺晓燕, 周世平, 王健等. Cu对AgCe合金机械性能及再结晶温度的影响 [J]. 贵金属, 2008, 29(2): 11
41	Hou J T, Hao Q L, Zhang L, et al. Study on the evolution of microstructure and properties during recrystallization of Ag-Cu alloy [J]. Precious Met., 2019, 40(suppl.1) : 40
41	侯江涛, 郝庆乐, 张雷等. 银铜合金再结晶过程组织性能演变研究 [J]. 贵金属, 2019, 40(): 40
42	Dong P. Effects of Au(In、Sn) on microstructure and properties of Ag-20Cu-2Ni alloy [D]. Kunming: Yunnan University, 2019
42	董鹏. Au(In、Sn)对Ag-20Cu-2Ni合金显微组织与性能的影响 [D]. 昆明: 云南大学, 2019
43	Xie J X, Su Y J, Xue D Z, et al. Machine learning for materials research and development [J]. Acta Metall. Sin., 2021, 57: 1343
43	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: 1343 doi: 10.11900/0412.1961.2021.00357

[1]	穆亚航, 张雪, 陈梓名, 孙晓峰, 梁静静, 李金国, 周亦胄. 基于热力学计算与机器学习的增材制造镍基高温合金裂纹敏感性预测模型[J]. 金属学报, 2023, 59(8): 1075-1086.
[2]	冀秀梅, 侯美伶, 王龙, 刘玠, 高克伟. 基于机器学习的中厚板变形抗力模型建模与应用[J]. 金属学报, 2023, 59(3): 435-446.
[3]	朱智浩, 陈志鹏, 刘田雨, 张爽, 董闯, 王清. 基于不同 α / β 团簇式比例的Ti-Al-V合金的铸态组织和力学性能[J]. 金属学报, 2023, 59(12): 1581-1589.
[4]	杨累, 赵帆, 姜磊, 谢建新. 机器学习辅助2000 MPa级弹簧钢成分和热处理工艺开发[J]. 金属学报, 2023, 59(11): 1499-1512.
[5]	高建宝, 李志诚, 刘佳, 张金良, 宋波, 张利军. 计算辅助高性能增材制造铝合金开发的研究现状与展望[J]. 金属学报, 2023, 59(1): 87-105.
[6]	汪东红, 孙锋, 疏达, 陈晶阳, 肖程波, 孙宝德. 数据驱动镍基铸造高温合金设计及复杂铸件精确成形[J]. 金属学报, 2022, 58(1): 89-102.
[7]	赵婉辰, 郑晨, 肖斌, 刘行, 刘璐, 余童昕, 刘艳洁, 董自强, 刘轶, 周策, 吴洪盛, 路宝坤. 基于Bayesian采样主动机器学习模型的6061铝合金成分精细优化[J]. 金属学报, 2021, 57(6): 797-810.
[8]	谢建新, 宿彦京, 薛德祯, 姜雪, 付华栋, 黄海友. 机器学习在材料研发中的应用[J]. 金属学报, 2021, 57(11): 1343-1361.
[9]	耿遥祥, 樊世敏, 简江林, 徐澍, 张志杰, 鞠洪博, 喻利花, 许俊华. 选区激光熔化专用AlSiMg合金成分设计及力学性能[J]. 金属学报, 2020, 56(6): 821-830.
[10]	吴静,刘永长,李冲,伍宇婷,夏兴川,李会军. 高Fe、Cr含量多相Ni₃Al基高温合金组织与性能研究进展[J]. 金属学报, 2020, 56(1): 21-35.
[11]	丁健翔,田无边,汪丹丹,张培根,陈坚,孙正明. Ag/Ti₂AlC复合材料的电弧侵蚀及退化机理[J]. 金属学报, 2019, 55(5): 627-637.
[12]	耿遥祥,林鑫,羌建兵,王英敏,董闯. Finemet型纳米晶软磁合金的双团簇特征与成分优化[J]. 金属学报, 2017, 53(7): 833-841.
[13]	耿遥祥,张志杰,王英敏,羌建兵,董闯,汪海斌,特古斯. 高Fe含量Fe-B-Si-Hf块体非晶合金的结构-性能关联[J]. 金属学报, 2017, 53(3): 369-375.
[14]	周雪峰,陈光,严世坦, 郑功,李沛,陈锋. 新型无Re镍基单晶高温合金探索研究[J]. 金属学报, 2013, 49(11): 1467-1472.
[15]	王清查钱锋刘恩雪董闯王学军谭朝鑫冀春俊. 基于团簇模型的高强度马氏体沉淀硬化不锈钢成分设计[J]. 金属学报, 2012, 48(10): 1201-1206.

Viewed

Full text

Abstract

Cited

Shared

Discussed