About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Computational Thermodynamics and Kinetics
|
Presentation Title |
Machine Learning-assisted High-throughput Exploration of Interface Energy Space in Multi-phase-field Model with CALPHAD Potential |
Author(s) |
Vahid Attari, Raymundo Arroyave |
On-Site Speaker (Planned) |
Vahid Attari |
Abstract Scope |
Computational methods are increasingly being incorporated into the exploitation of microstructure–property relationships for microstructure-sensitive materials design. We propose non-intrusive materials informatics methods for high-throughput exploration and analysis of a synthetic microstructure space using a machine learning-reinforced multi-phase-field modeling scheme in the framework of ICME. We study the interface energy space as one of the most uncertain inputs in phase-field modeling and its impact on the shape of a growing secondary phase between solid and liquid phases. We use variational autoencoder, a deep generative neural network method, and label spreading, a semi-supervised machine learning method for establishing correlations between inputs and outputs of the model. A structure map in the interface energy space is developed that shows $\sigma_{SI}$ and $\sigma_{SL}$ alter the shape of the intermetallic synchronously where an increase in the latter and decrease in the former changes the shape from dewetting structures to wetting. |
Proceedings Inclusion? |
Planned: |
Keywords |
Modeling and Simulation, Machine Learning, Phase Transformations |