Modelling wetting angle of solder on substrate using machine learning approach
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Electronic Packaging and Soldering Technologies · Advancements in Semiconductor Devices and Circuit Design · 3D IC and TSV technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Materials Science and Engineering, National Cheng Kung University, Tainan, Taiwan
Department of Mechanical Engineering, National Cheng Kung University, Tainan, Taiwan
Hierarchical Green-Energy Materials (Hi-GEM) Research Center, National Cheng Kung University, Tainan, Taiwan
Program on Smart and Sustainable Manufacturing, Academy of Innovative Semiconductor and Sustainable Manufacturing, National Cheng Kung University, Tainan, Taiwan
Program on Semiconductor Packaging and Testing, Academy of Innovative Semiconductor and Sustainable Manufacturing, National Cheng Kung University, Tainan, Taiwan
Core Facility Center, National Cheng Kung University, Tainan, Taiwan
Funding
Ministry of Education · National Science and Technology Council
References (44)
Show source-provided references
1. 10.1016/j.microrel.2005.06.00610.1016/j.microrel.2005.06.006 ↗
2. 10.1080/10408436.2018.149024910.1080/10408436.2018.1490249 ↗
3. 10.1146/annurev.matsci.38.060407.13244810.1146/annurev.matsci.38.060407.132448 ↗
4. 10.1016/j.jallcom.2009.06.15910.1016/j.jallcom.2009.06.159 ↗
5. 10.1007/s11664-014-3460-310.1007/s11664-014-3460-3 ↗
6. 10.1016/j.jallcom.2016.03.17710.1016/j.jallcom.2016.03.177 ↗
7. 10.1016/j.msea.2013.02.01310.1016/j.msea.2013.02.013 ↗
8. 10.1007/s10854-016-5705-910.1007/s10854-016-5705-9 ↗
9. 10.1016/j.jallcom.2007.08.00710.1016/j.jallcom.2007.08.007 ↗
10. 10.1016/j.matchemphys.2024.12899210.1016/j.matchemphys.2024.128992 ↗
11. 10.1016/j.jmrt.2023.04.23410.1016/j.jmrt.2023.04.234 ↗
12. 10.1016/j.jmrt.2024.10.10810.1016/j.jmrt.2024.10.108 ↗
13. 10.1016/j.jmrt.2022.10.05610.1016/j.jmrt.2022.10.056 ↗
14. 10.1108/SSMT-08-2015-002210.1108/SSMT-08-2015-0022 ↗
15. 10.1016/j.jallcom.2006.06.07610.1016/j.jallcom.2006.06.076 ↗
16. 10.1016/j.jeurceramsoc.2015.03.03610.1016/j.jeurceramsoc.2015.03.036 ↗
17. 10.1007/s13391-015-5015-z10.1007/s13391-015-5015-z ↗
18. 10.1051/epjap/201110048710.1051/epjap/2011100487 ↗
19. 10.1146/annurev-matsci-070218-01001510.1146/annurev-matsci-070218-010015 ↗
20. 10.1038/s41524-022-00760-410.1038/s41524-022-00760-4 ↗
21. Liu YC, Liu TY, Huang TH, et al. Exploring dielectric constant and dissipation factor of LTCC using machine learning. Materials 2021; 14: 14.
22. 10.1021/acs.chemmater.1c0090510.1021/acs.chemmater.1c00905 ↗
23. 10.1016/j.actamat.2023.11914410.1016/j.actamat.2023.119144 ↗
24. 10.1016/j.msea.2022.14425710.1016/j.msea.2022.144257 ↗
25. Cao B, Su T, Yu S, et al. Active learning accelerates the discovery of high strength and high ductility lead-free solder alloys. Mat Des 2024; 241: 112921.
26. 10.1038/s41524-023-01150-010.1038/s41524-023-01150-0 ↗
27. 10.1016/j.jmrt.2024.07.22910.1016/j.jmrt.2024.07.229 ↗
28. 10.1038/npjcompumats.2016.2810.1038/npjcompumats.2016.28 ↗
29. 10.2320/matertrans.42.75110.2320/matertrans.42.751 ↗
30. 10.4028/www.scientific.net/SSP.273.2710.4028/www.scientific.net/SSP.273.27 ↗
31. Gasior W, Moser Z, Pstruś J, et al. (Sn-Ag) eut+ Cu soldering materials, part I: wettability studies. J Phase Equil Diff 2004; 25: 115–121.
32. Chen WX, Xue SB, Wang H, et al. Effects of Ag on microstructures, wettabilities of Sn–9Zn–xAg solders as well as mechanical properties of soldered joints. J Mat Sci 2010; 21: 461–467.
33. 10.1007/s10765-007-0363-z10.1007/s10765-007-0363-z ↗
34. 10.1016/j.commatsci.2020.10954410.1016/j.commatsci.2020.109544 ↗
35. Lundberg SM Lee S-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. 10.1108/SSMT-08-2015-002210.1108/SSMT-08-2015-0022 ↗
37. Bhat KN, Prabhu KN, Satyanarayan, Effect of reflow temperature and substrate roughness on wettability, IMC growth and shear strength of SAC387/cu bonds. J Mat Sci 2014; 25: 864–872.
38. 10.1038/s42005-023-01268-z10.1038/s42005-023-01268-z ↗
39. 10.1007/s11664-002-0013-y10.1007/s11664-002-0013-y ↗
40. 10.2320/matertrans.45.58810.2320/matertrans.45.588 ↗
41. 10.3390/ma1611405910.3390/ma16114059 ↗
42. 10.1038/s41596-018-0003-z10.1038/s41596-018-0003-z ↗
43. 10.1023/A:100892872921210.1023/A:1008928729212 ↗
44. 10.1016/j.jallcom.2016.08.03510.1016/j.jallcom.2016.08.035 ↗