| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advances in Multi-Principal Element Alloys II
|
| Presentation Title |
J-47: Machine Learning On-the-fly KMC Study of Vacancy Diffusion of Concentrated Ni-Fe Model Alloys |
| Author(s) |
Wenjiang Huang, Xianming Bai |
| On-Site Speaker (Planned) |
Wenjiang Huang |
| Abstract Scope |
Defect diffusion in concentrated alloys plays a key role on governing their unique properties. The defect diffusion depends on its local atomic environment and varies from site to site in such alloys due to the chemical disorder. On-the-fly determination of the defect migration barrier using the standard nudged elastic band (NEB) method is computationally expensive and often impractical. In this work, we coupled machine learning and kinetic Monte Carlo (KMC) to study vacancy diffusion in concentrated Ni-Fe model alloys. Based on about 23,000 pre-calculated NEB barriers, an artificial neural network (ANN) based model is developed to predict the vacancy migration barriers for arbitrary local atomic environments. The ANN model is then coupled with the on-the-fly KMC to study the vacancy diffusion in the full composition range at both high and low temperatures. The sluggish diffusion mechanism in this specific alloy system is discussed based on our ANN-KMC results. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, High-Entropy Alloys |