About this Abstract |
Meeting |
MS&T24: Materials Science & Technology
|
Symposium
|
High Entropy Materials: Concentrated Solid Solutions, Intermetallics, Ceramics, Functional Materials and Beyond V
|
Presentation Title |
ML-Based Identification, Synthesis and Characterization Refractory High Entropy Alloy with Trade-Off Mechanical Properties |
Author(s) |
Debasis Sengupta, Stephen Giles, Hugh Shortt, Peter K Liaw |
On-Site Speaker (Planned) |
Debasis Sengupta |
Abstract Scope |
Identifying Refractory High Entropy Alloy (RHEA) compositions with desired high temperature strength and room temperature ductility/plasticity from the vast composition space is a challenging task. Generally, compositions with higher yield strength tend to have lower room temperature ductility or sometime show brittle behavior. In this work, we developed ML models for prediction of high temperature compressive strength and ductility, composition optimization and high-throughput composition screening through a “Figure of Merit” criteria. A set of RHEA compositions with trade-off mechanical properties were identified using the ML models. A selected number of RHEA compositions were then processed in arc melter and tested for compressive strength and ductility at high temperatures in air and vacuum. Microstructures, phases, C, N and O contents were also determined using various analytical techniques. This work will discuss how ML models coupled with experimental work can be effective in discovering novel RHEA compositions with desired properties. |