The solder wettability is a key factor for assessing joint reliability. However, the extensive range of solder composition, substrate material and reflow temperature make it challenging to modulate wettability through experimental methods. This study utilizes the machine learning method to develop a surrogate model fitted to experimental wetting angle data, aiming to predict the solder wettability as a function of composition, substrate material, and reflow temperature. The model full-fit (five-fold cross validation) root-mean-square error was 4.27 (6.73 ± 1.42). The model performance was characterized by using the cross-plot method, and the input feature contribution was determined through SHapley Additive exPlanations analysis. The model extrapolation to unknown alloys, which were not shown in the training data set showed a good agreement with experimental data.
ChenWMMcCloskeyPO’MathunaSC. Isothermal aging effects on the microstructure and solder bump shear strength of eutectic Sn37Pb and Sn3.5Ag solders. Microelectr Reliab2006; 46: 896–904.
2.
JungD-HJungJ-P. Review of the wettability of solder with a wetting balance test for recent advanced microelectronic packaging. Critical Rev Sol Stat Mat Sci2019; 44: 324–343.
3.
MatsumotoTNogiK. Wetting in soldering and microelectronics. Ann Rev Mater Res2008; 38: 251–273.
4.
YoonJ-WNohB-IKimB-K, et al.Wettability and interfacial reactions of Sn–Ag–Cu/Cu and Sn–Ag–Ni/Cu solder joints. J All Comp2009; 486: 142–147.
5.
ShenJPuYYinH,et al.Effects of Cu, Zn on the wettability and shear mechanical properties of Sn-Bi-based lead-free solders. J Elect Mat2015; 44: 532–541.
6.
YangMJiHWangS, et al.Effects of Ag content on the interfacial reactions between liquid Sn–Ag–Cu solders and Cu substrates during soldering. J Alloy Comp2016; 679: 18–25.
7.
ŠeboPŠvec SrPJaničkovičD, et al.The influence of silver content on structure and properties of Sn–Bi–Ag solder and Cu/solder/Cu joints. Mat Sci Eng A2013; 571: 184–192.
8.
WangFLiDWangJ, et al.Comparative study on the wettability and interfacial structure in Sn–xZn/Cu and Sn/Cu–xZn system. J Mat Sci Mat Elect2017; 28: 1631–1643.
9.
JiangJLeeJ-EKimK-S,et al.Oxidation behavior of Sn–Zn solders under high-temperature and high-humidity conditions. J Alloy Comp2008; 462: 244–251.
10.
ShenY-A. Effect of indium addition on mechanical, thermal, and soldering properties of eutectic Sn–9Zn alloy. Mat Chem Phys2024; 315: 128992.
11.
WuXSunLLiuY, et al.Preparation and performance of Sn-based composite solder joints by solid-liquid low-temperature solder bonding technology. J Mat Res Technol2023; 24: 6378–6390.
12.
ShenY-A. Cu–Cu joint with great strength using In/Sn–58Bi hybrid soldering at low temperature (90 °C). J Mat Res Technol2024; 33: 4473–4480.
13.
HeSShenY-AXiongB, et al.Behavior of Sn-3.0Ag-0.5Cu solder/Cu fluxless soldering via Sn steaming under formic acid atmosphere. J Mat Res Technol2022; 21: 2352–2361.
14.
NoorEEMNasirNFMIdrisSRA. A review: lead free solder and its wettability properties.Solder Surf Mt Technol2016; 28: 125–132.
15.
WangHWangFGaoF, et al.Reactive wetting of Sn0.7Cu–xZn lead-free solders on Cu substrate. J Alloy Comp2007; 433: 302–305.
16.
GambaroSMuoloMLValenzaF, et al.Wettability of transparent YAG (Y3Al5O12) by molten Ag–Cu–Ti alloys. J Europ Ceram Soc2015; 35: 2895–2906.
17.
LinS-KChangH-MChoC-L, et al.Formation of solid-solution Cu-to-Cu joints using Ga solder and Pt under bump metallurgy for three-dimensional integrated circuits. Elect Mat Let2015; 11: 687–694.
18.
ErerACandanEGüvenM,et al.Measurement and prediction of contact angles of Pb-free Sn-Ag solder alloys on cu substrate. Europ Phys J Appl Phys2011; 54: 11302.
19.
MorganDJacobsR. Opportunities and challenges for machine learning in materials science. In: ClarkeDR (eds) Annual review of materials research, vol 50. Palo Alto: Annual Reviews, 2020, pp.71–103.
20.
LiuYCWuHMayeshibaT, et al.Machine learning predictions of irradiation embrittlement in reactor pressure vessel steels. Npj Comput Mater2022; 8: 11.
21.
LiuYCLiuTYHuangTH, et al.Exploring dielectric constant and dissipation factor of LTCC using machine learning. Materials2021; 14: 14.
22.
GeorgescuABRenPTolandAR, et al.Database, features, and machine learning model to identify thermally driven metal–insulator transition compounds. Chem Mat2021; 33: 5591–5605.
23.
LiuY-CMorganDYamamotoT,et al.Characterizing the flux effect on the irradiation embrittlement of reactor pressure vessel steels using machine learning. Acta Materialia2023; 256: 119144.
24.
DongZYouKYuanH, et al.Machine learning assisted design of high-strength Sn-3.8Ag-0.7Cu alloys with the co-additions of bi and in. Mat Sci Eng A2022; 861: 144257.
25.
CaoBSuTYuS, et al.Active learning accelerates the discovery of high strength and high ductility lead-free solder alloys. Mat Des2024; 241: 112921.
26.
WeiQCaoBYuanH, et al.Divide and conquer: machine learning accelerated design of lead-free solder alloys with high strength and high ductility. Npj Comput Mater2023; 9: 201.
27.
LianZChenYZhouC, et al.Accelerated discovery of lead-free solder alloys with enhanced creep resistance via complementary machine learning strategy. J Mat Res Technol2024; 32: 1256–1267.
28.
WardLAgrawalAChoudharyA,et al.A general-purpose machine learning framework for predicting properties of inorganic materials. Npj Comput Mater2016; 2: 16028.
29.
LeeC-BJungS-BShinY-E,et al.The effect of Bi concentration on wettability of cu substrate by Sn-Bi solders. Mat Trans2001; 42: 751–755.
30.
RamliMIIYusofMSSMohd SallehMAA, et al.Influence of Bi addition on wettability and mechanical properties of Sn-0.7Cu solder alloy. Solid State Phenomena2018; 273: 27–33.
31.
GasiorWMoserZPstruśJ, et al.(Sn-Ag) eut+ Cu soldering materials, part I: wettability studies. J Phase Equil Diff2004; 25: 115–121.
32.
ChenWXXueSBWangH, et al.Effects of Ag on microstructures, wettabilities of Sn–9Zn–xAg solders as well as mechanical properties of soldered joints. J Mat Sci2010; 21: 461–467.
33.
MoserZGąsiorWPstruśJ,et al.Wettability studies of Pb-free soldering materials. Int J Thermophys2008; 29: 1974–1986.
34.
JacobsRMayeshibaTAfflerbachB, et al.The materials simulation toolkit for machine learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research. Comput Mat Sci2020; 176: 109544.
35.
LundbergSMLeeS-I. A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, 2017, pp.4768–4777.
36.
Mhd NoorEEMhd NasirNFIdrisSRA. A review: lead free solder and its wettability properties. Solder Surf Mt Technol2016; 28: 125–132.
37.
BhatKNPrabhuKNSatyanarayan, Effect of reflow temperature and substrate roughness on wettability, IMC growth and shear strength of SAC387/cu bonds. J Mat Sci2014; 25: 864–872.
38.
DanielDVuckovacMBackholmM, et al.Probing surface wetting across multiple force, length and time scales. Comm Phys2023; 6: 52.
39.
MoserZGasiorWPstruśJ,et al.Surface-tension measurements of the eutectic alloy (Ag-Sn 96.2 at.%) with Cu additions. J Electr Mat2002; 31: 1225–1229.
40.
HuangC-WLinK-L. Wetting properties of and interfacial reactions in lead-free Sn-Zn based solders on Cu and Cu plated with an electroless Ni-P/Au layer. Mat Trans2004; 45: 588–594.
41.
GaoYBianXQiuX, et al.Investigation of microstructure and mechanical properties of SAC105 solders with Sb, In, Ni, and Bi additions. Materials2023; 16: 4059.
42.
HuhtamäkiTTianXKorhonenJT,et al.Surface-wetting characterization using contact-angle measurements. Nat Protoc2018; 13: 1521–1538.
43.
MiaoH-WDuhJ-GChiouB-S. Thermal cycling test in Sn-Bi and Sn-Bi-Cu solder joints. J Mat Sci Mat Elect2000; 11: 609–618.
44.
GiurannoDDelsanteSBorzoneG,et al.Effects of Sb addition on the properties of Sn-Ag-Cu/(Cu, Ni) solder systems. J Alloy Comp2016; 689: 918–930.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
