Hu, Yang ; Wang, Kai ; Spatschek, Robert (2024)
A data-driven strategy for phase field nucleation modeling.
In: npj materials degradation, 2024 (8)
doi: 10.1038/s41529-024-00529-8
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
We propose a data-driven strategy for parameter selection in phase field nucleation models using machine learning and apply it to oxide nucleation in Fe-Cr alloys. A grand potential-based phase field model, incorporating Langevin noise, is employed to simulate oxide nucleation and benchmarked against the Johnson-Mehl-Avrami-Kolmogorov model. Three independent parameters in the phase field simulations (Langevin noise strength, numerical grid discretization and critical nucleation radius) are identified as essential for accurately modeling the nucleation behavior. These parameters serve as input features for machine learning classification and regression models. The classification model categorizes nucleation behavior into three nucleation density regimes, preventing invalid nucleation attempts in simulations, while the regression model estimates the appropriate Langevin noise strength, significantly reducing the need for time-consuming trial-and-error simulations. This data-driven approach improves the efficiency of parameter selection in phase field models and provides a generalizable method for simulating nucleation-driven microstructural evolution processes in various materials.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Hu, Yang ; Wang, Kai ; Spatschek, Robert |
| Art des Eintrags: | Bibliographie |
| Titel: | A data-driven strategy for phase field nucleation modeling |
| Sprache: | Englisch |
| Publikationsjahr: | 30 Oktober 2024 |
| Ort: | [London] |
| Verlag: | Nature Research |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | npj materials degradation |
| Jahrgang/Volume einer Zeitschrift: | 2024 |
| (Heft-)Nummer: | 8 |
| Kollation: | 11 Seiten |
| DOI: | 10.1038/s41529-024-00529-8 |
| URL / URN: | https://www.nature.com/articles/s41529-024-00529-8 |
| Kurzbeschreibung (Abstract): | We propose a data-driven strategy for parameter selection in phase field nucleation models using machine learning and apply it to oxide nucleation in Fe-Cr alloys. A grand potential-based phase field model, incorporating Langevin noise, is employed to simulate oxide nucleation and benchmarked against the Johnson-Mehl-Avrami-Kolmogorov model. Three independent parameters in the phase field simulations (Langevin noise strength, numerical grid discretization and critical nucleation radius) are identified as essential for accurately modeling the nucleation behavior. These parameters serve as input features for machine learning classification and regression models. The classification model categorizes nucleation behavior into three nucleation density regimes, preventing invalid nucleation attempts in simulations, while the regression model estimates the appropriate Langevin noise strength, significantly reducing the need for time-consuming trial-and-error simulations. This data-driven approach improves the efficiency of parameter selection in phase field models and provides a generalizable method for simulating nucleation-driven microstructural evolution processes in various materials. |
| ID-Nummer: | Artikel-ID: 109 |
| Fachbereich(e)/-gebiet(e): | 11 Fachbereich Material- und Geowissenschaften 11 Fachbereich Material- und Geowissenschaften > Materialwissenschaft 11 Fachbereich Material- und Geowissenschaften > Materialwissenschaft > Fachgebiet Mechanik Funktionaler Materialien DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1548: FLAIR – Fermi Level Engineering Applied to Oxide Electroceramics |
| Hinterlegungsdatum: | 15 Nov 2024 14:49 |
| Letzte Änderung: | 15 Nov 2024 14:49 |
| PPN: | 523600151 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum