About this Abstract |
Meeting |
2026 TMS Annual Meeting & Exhibition
|
Symposium
|
Thermodynamics and Kinetics of Alloys IV
|
Presentation Title |
Predicting Precipitation Kinetics in 347H Stainless Steel: Multiscale Simulations and Machine Learning |
Author(s) |
Michael C. Gao, Saro San, David Alman, Michael Glazoff, Jianguo Yu, Cedric Neumann, Q.Q. Ren, Yukinori Yamamoto, Laurent Capolungo |
On-Site Speaker (Planned) |
Michael C. Gao |
Abstract Scope |
This work aimed to predict the precipitation kinetics of key strengthening precipitate phases in 347H stainless steel at 600-750 C with dislocation density 1e^12-1e^14 using physics-informed machine learning (ML) approach. Density functional theory (DFT) calculations were first carried out to predict the interfacial energies between the precipitates (NbC, Cr23C6, and sigma FeCr) and FCC Fe without and with dopants B, N, and C at the interface, revealing significant reduction in the interfacial energies by B doping. DFT-determined interfacial energies were input to mean field simulations via ThermoCalc PRISMA. The simulations were performed up to 100,000 hours with different temperatures and dislocation densities, and the results on the evolution of average particle size, volume fraction, and number density for these precipitate phases agreed well with experimental results. Based on the simulation results, ML models are developed to predict the evolution of these precipitates within the temperature and dislocation ranges validated. |
Proceedings Inclusion? |
Planned: |
Keywords |
Modeling and Simulation, Computational Materials Science & Engineering, Other |