About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Energy Technology 2026: Advancement in Energy Materials - Theory, Simulation, Characterization, Application
|
| Presentation Title |
Machine learning-enhanced tomographic analysis of L12-type chemical short-range ordering in compositionally-complex alloys |
| Author(s) |
Yue Li |
| On-Site Speaker (Planned) |
Yue Li |
| Abstract Scope |
Compositionally complex alloys (CCAs) exhibit exceptional mechanical and catalytic properties, driven by diverse local atomic configurations. Among these, chemical short-range ordering (CSRO)—the self-organization of specific atomic neighborhoods—plays a critical role. However, direct 3D imaging of CSRO within chemically homogeneous matrices remains challenging. We recently developed a machine learning-enhanced atom probe tomography (ML-APT) approach to characterize CSRO in binary and ternary alloys. Here, we extend this method to CoCrNiFeMn systems, exploring how composition and heat treatment influence the formation of L1₂-type CSRO. Our results provide direct tomographic evidence of Cr-depleted L1₂-CSRO domains, with size and morphology distributions in agreement with Monte Carlo simulations. The extent of CSRO is shown to be highly sensitive to alloy composition and thermal history. We also propose a standardized ML-APT workflow for CCAs, outlining its capabilities and limitations, and offering a foundation for future studies aimed at tailoring CSRO to optimize alloy performance. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
High-Entropy Alloys, Characterization, Machine Learning |