Active learning accelerates the discovery of high strength and high ductility lead-free solder alloys

被引:11
作者
Cao, Bin [2 ]
Su, Tianhao [1 ]
Yu, Shuting [1 ]
Li, Tianyuan [1 ]
Zhang, Taolue [2 ]
Zhang, Jincang [1 ]
Dong, Ziqiang [1 ,3 ]
Zhang, Tong-Yi [1 ,2 ]
机构
[1] Shanghai Univ, Mat Genome Inst, Shanghai 200444, Peoples R China
[2] Hong Kong Univ Sci & Technol Guangzhou, Guangzhou Municipal Key Lab Mat Informat Sustainab, Adv Mat Thrust, Guangzhou 511400, Guangdong, Peoples R China
[3] Shanghai Univ, Shanghai Frontier Sci Ctr Mechanoinformat, Shanghai 200444, Peoples R China
关键词
Active learning; Adjustable weights; Mechanical properties; Ab initio; Sn-In solid solution; Bgolearn; MULTIOBJECTIVE OPTIMIZATION; MECHANICAL-PROPERTIES; SN; DESIGN; MICROSTRUCTURE; BI;
D O I
10.1016/j.matdes.2024.112921
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Developing new materials through traditional trial-and-error is time-consuming and costly due to the vast potential compositions to explore. Moreover, some desirable properties are mutually exclusive, presenting challenges for materials design. Herein, we employed an active learning strategy to address the strengthductility trade-off in SAC105 lead-free solders. We developed two Gaussian regression models, one for strength and one for elongation representing ductility. The Gaussian Upper Confidence Boundary algorithm, a Bayesian optimization method, was used to balance exploitation and exploration by considering prediction uncertainty. The variance weight was designed to decay with adaptive iterations. The two models were linearly combined and the maximal combined model recommended alloys on the Pareto front for experiments. After just three iterations, a new 91.4Sn-1.0Ag-0.5Cu-1.5Bi-4.4In-0.2Ti low-silver SAC solder was discovered, exhibiting 73.94 +/- 5.05 MPa strength and 24.37 +/- 5.92% elongation, representing the best comprehensive mechanical properties. Weldability experiments also showed excellent performance. Based on Ab initio molecular dynamics, a precise machine learning potential revealed the alloying mechanism in Sn-In solid solutions with quantum accuracy in systems of over 10 3 atoms, closely matching experimental X-ray diffraction pattern. To facilitate materials informatics development, all active learning algorithms was made open-source in our designed framework, Bgolearn.
引用
收藏
页数:9
相关论文
共 52 条
[31]   Influence of Indium addition on microstructural and mechanical behavior of Sn solder alloys: Experiments and first principles calculations [J].
Luktuke, Amey ;
Singaravelu, Arun Sundar Sundaram ;
Mannodi-Kanakkithodi, Arun ;
Chawla, Nikhilesh .
ACTA MATERIALIA, 2023, 249
[32]   Active learning guides discovery of a champion four-metal perovskite oxide for oxygen evolution electrocatalysis [J].
Moon, Junseok ;
Beker, Wiktor ;
Siek, Marta ;
Kim, Jiheon ;
Lee, Hyeon Seok ;
Hyeon, Taeghwan ;
Grzybowski, Bartosz A. .
NATURE MATERIALS, 2024, 23 (01) :108-115
[33]   How to measure uncertainty in uncertainty sampling for active learning [J].
Nguyen, Vu-Linh ;
Shaker, Mohammad Hossein ;
Huellermeier, Eyke .
MACHINE LEARNING, 2022, 111 (01) :89-122
[34]   Microstructure of Sn-1Ag-0.5Cu solder alloy bearing Fe under salt spray test [J].
Nordin, N. I. M. ;
Said, S. M. ;
Ramli, R. ;
Sabri, M. F. M. ;
Sharif, N. M. ;
Arifin, N. A. F. N. M. ;
Ibrahim, N. N. S. .
MICROELECTRONICS RELIABILITY, 2014, 54 (9-10) :2044-2047
[35]  
Perdew John P., 1998, Phys. Rev. Lett., V80, P891
[36]   Orthorhombic (Ru, Mn)2O3: A superior electrocatalyst for acidic oxygen evolution reaction [J].
Qin, Yin ;
Cao, Bin ;
Zhou, Xiao-Ye ;
Xiao, Zhuorui ;
Zhou, Hanxiang ;
Zhao, Zhenyi ;
Weng, Yibo ;
Lv, Jianshuai ;
Liu, Yang ;
He, Yan-Bing ;
Kang, Feiyu ;
Li, Kaikai ;
Zhang, Tong-Yi .
NANO ENERGY, 2023, 115
[37]   Autonomous experiments using active learning and AI [J].
Ren, Zhichu ;
Ren, Zekun ;
Zhang, Zhen ;
Buonassisi, Tonio ;
Li, Ju .
NATURE REVIEWS MATERIALS, 2023, 8 (09) :563-564
[38]  
Rickman J.M., 2019, Acta Mater
[39]   Effects of Ag content on microstructure evolution, intermetallic compound (IMC) and mechanical behaviour of SAC solder joints [J].
Sabbar, Ehsan H. ;
Al-Zubaidi, Hazim A. ;
Aljumaili, Amer K. ;
Al-Jumaili, Mustafa H. ;
Al-Jumaili, Ahmed I. ;
Alsheakh, Hussein .
MICROELECTRONICS RELIABILITY, 2023, 147
[40]   Active learning for the power factor prediction in diamond-like thermoelectric materials [J].
Sheng, Ye ;
Wu, Yasong ;
Yang, Jiong ;
Lu, Wencong ;
Villars, Pierre ;
Zhang, Wenqing .
NPJ COMPUTATIONAL MATERIALS, 2020, 6 (01)