About this Abstract |
| Meeting |
MS&T26: Materials Science & Technology
|
| Symposium
|
Progress in High Entropy Materials: Integrating Experiments, Computation, and Machine Learning
|
| Presentation Title |
Supply Risk and Cost-Aware Multi-Objective Materials Discovery |
| Author(s) |
Yuval Noiman, Sravya Josyula, Eric Payton |
| On-Site Speaker (Planned) |
Yuval Noiman |
| Abstract Scope |
Rapid exploration of complex compositional spaces through linking thermodynamic calculations with functional behavior and real-world constraints is desired to develop novel material for applications such as aerospace or electronics. We designed a data-driven framework for doing multi-objective optimization based on material properties, supply risk, cost and integrating high-throughput CALPHAD (calculation of phase diagrams) with machine learning (ML). The technique is sufficiently general to be applicable to any material family for which data is available. We demonstrate the approach through composition optimization of shape memory alloys (SMAs), then validate the result on several novel compositions predicted by the approach. The technique and its validation will be discussed in the context of machine learning predicted trends on future stability of supply chain and price. |
