| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing and Alloy Design: Bridging Fundamental Physical Metallurgy, Advanced Characterization Techniques, and Integrated Computational Materials Engineering for Advanced Materials
|
| Presentation Title |
A Bayesian Approach to the Discovery and Optimization of Printable Refractory Alloys |
| Author(s) |
Raymundo Arroyave |
| On-Site Speaker (Planned) |
Raymundo Arroyave |
| Abstract Scope |
The extreme strength of refractory alloys at elevated temperatures can enable many important technologies. Yet, it makes their manufacturing into complex shapes with anything other than additive manufacturing (AM) quite challenging. Yet, their intrinsic physical properties make these alloys extremely challenging to print. Here, I will present some recent developments involving the use of advanced Bayesian alloy design schemes to discover and optimize printable refractory alloys (PRAs), accounting not only for performance and manufacturability but also supply chain risks. The framework accounts for multiple objectives and constraints and seamlessly integrates experiments and simulations at different levels of fidelity and cost within a Bayesian setting. Importantly, the iterative nature of the approach enables the continuous learning of the alloy+process space. Moreover, our framework is capable of guiding the discovery in batch mode, dramatically accelerating the discovery process. Some preliminary results will be presented and future directions will be discussed. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, High-Entropy Alloys, Machine Learning |