Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-629740
PINNs-MPF: A Physics-Informed Neural Network framework for Multi-Phase-Field simulation of interface dynamics
- We present PINNs-MPF framework, an application of Physics-Informed Neural Networks (PINNs) to handle Multi-Phase-Field (MPF) simulations of microstructure evolution. A combination of optimization techniques within PINNs and in direct relation to MPF method are extended and adapted. The numerical resolution is realized through a multi-variable time-series problem by using fully discrete resolution. Within each interval, space, time, and phases/grains are treated separately, constituting discrete subdomains. PINNs-MPF is equipped with an extended multi-networking (parallelization) concept to subdivide the simulation domain into multiple batches, with each batch associated with an independent NN trained to predict the solution. To ensure continuity across the spatio-temporal-phasic subdomains, a Master NN efficiently is to handle interactions among the multiple networks and facilitates the transfer of learning. A pyramidal training approach is proposed to the PINN community as aWe present PINNs-MPF framework, an application of Physics-Informed Neural Networks (PINNs) to handle Multi-Phase-Field (MPF) simulations of microstructure evolution. A combination of optimization techniques within PINNs and in direct relation to MPF method are extended and adapted. The numerical resolution is realized through a multi-variable time-series problem by using fully discrete resolution. Within each interval, space, time, and phases/grains are treated separately, constituting discrete subdomains. PINNs-MPF is equipped with an extended multi-networking (parallelization) concept to subdivide the simulation domain into multiple batches, with each batch associated with an independent NN trained to predict the solution. To ensure continuity across the spatio-temporal-phasic subdomains, a Master NN efficiently is to handle interactions among the multiple networks and facilitates the transfer of learning. A pyramidal training approach is proposed to the PINN community as a dual-impact method: to facilitate the initialization of training when dealing with multiple networks, and to unify the solution through an extended transfer of learning. Furthermore, a comprehensive approach is adopted to specifically focus the attention on the interfacial regions through a dynamic meshing process, significantly simplifying the tuning of hyper-parameters, serving as a key concept for addressing MPF problems using machine learning. We perform a set of systematic simulations that benchmark foundational aspects of MPF simulations, i.e., the curvature-driven dynamics of a diffuse interface, in the presence and absence of an external driving force, and the evolution and equilibrium of a triple junction. The proposed PINNs-MPF framework successfully reproduces benchmark tests with high fidelity and Mean Squared Error (MSE) loss values ranging from 10^−6 to 10^−4 compared to ground truth solutions.…


| Autor*innen: | Seif ElfetniORCiD, Reza Darvishi KamachaliORCiD |
|---|---|
| Dokumenttyp: | Zeitschriftenartikel |
| Veröffentlichungsform: | Verlagsliteratur |
| Sprache: | Englisch |
| Titel des übergeordneten Werkes (Englisch): | Engineering Analysis with Boundary Elements |
| Jahr der Erstveröffentlichung: | 2025 |
| Organisationseinheit der BAM: | 5 Werkstofftechnik |
| 5 Werkstofftechnik / 5.5 Materialmodellierung | |
| Veröffentlichende Institution: | Bundesanstalt für Materialforschung und -prüfung (BAM) |
| Verlag: | Elsevier |
| Verlagsort: | Amsterdam |
| Jahrgang/Band: | 176 |
| Aufsatznummer: | 106200 |
| Erste Seite: | 1 |
| Letzte Seite: | 22 |
| DDC-Klassifikation: | Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten |
| Freie Schlagwörter: | Machine learning; Microstructure evolution; Neural networks; PINNs; Parallel training; Phase-field method |
| Themenfelder/Aktivitätsfelder der BAM: | Material |
| Material / Materialdesign | |
| DOI: | 10.1016/j.enganabound.2025.106200 |
| URN: | urn:nbn:de:kobv:b43-629740 |
| ISSN: | 0955-7997 |
| Verfügbarkeit des Dokuments: | Datei für die Öffentlichkeit verfügbar ("Open Access") |
| Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |
| Datum der Freischaltung: | 17.04.2025 |
| Referierte Publikation: | Ja |
| Datum der Eintragung als referierte Publikation: | 30.04.2025 |
| Schriftenreihen ohne Nummerierung: | Wissenschaftliche Artikel der BAM |


