About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Phase Stability, Phase Transformations, and Reactive Phase Formation in Electronic Materials XXI
|
Presentation Title |
Electronic Material Properties Exploration Using Machine Learning: In Effective Charge, Hardness, and Dissipation Factor |
Author(s) |
Yu-Chen Liu, Shih-kang Lin |
On-Site Speaker (Planned) |
Yu-Chen Liu |
Abstract Scope |
Machine learning (ML) methods have been aggressively pursued as a powerful tool to decipher and predict the complex physical properties of materials. In this talk, we will show how we employed the ML method to develop models for exploring properties of electronic materials. These properties included the effective charge in electromigration effect, the hardness of Sn-based solders, and dissipation factor of the low-temperature cofired ceramics. We used these models to design potential candidates for real applications. For instance, we designed solders with hardness as high as 40.7 and as low as 5.5 Hv and characterized their properties. The microstructure was complicated, but our ML model was able to capture the hardness of given alloys after only being informed by the composition. In general, ML is potentially a powerful tool for exploring material properties in complex systems by using solely the composition and the process information. |
Proceedings Inclusion? |
Planned: |
Keywords |
Electronic Materials, Machine Learning, Computational Materials Science & Engineering |