| About this Abstract |
| Meeting |
MS&T23: Materials Science & Technology
|
| Symposium
|
Light Metal Technology
|
| Presentation Title |
Physics-constrained, Inverse Design of High-temperature, High-strength, Creep-resistant Printable Al Alloys Using Machine Learning Methods |
| Author(s) |
S. Mohadeseh Taheri-Mousavi |
| On-Site Speaker (Planned) |
S. Mohadeseh Taheri-Mousavi |
| Abstract Scope |
Aluminum alloys that exhibit high strength and creep resistance at high temperatures can be our next-generation fan blades of jet engines and pistons of combustion engines. However, additive manufacturing (AM) of these alloys is traditionally challenging due to the presence of hot cracking. We demonstrate a physics-constrained, inverse design framework with data generated from integrated computational materials engineering (ICME) techniques to explore the compositional space of Al-Zr-Er-Y-Yb-Ni, and identify an optimal alloy composition achieving maximum predicted strength at a temperature of 250ºC. Using only 40 sampling data with our most efficient machine learning algorithm (neural network), we predict a microstructure with 3.5X higher stability of nanoscale hardening phases than a state-of-the-art printable Al-alloy. The mechanical testing and microstructural analysis of the 3D-printed optimal composition validated the predictions. The combined numerical and experimental techniques provide an efficient and robust pathway for transformative future alloy design by various manufacturing techniques, especially AM. |