Prediction of steel nanohardness by using graph neural networks on surface polycrystallinity maps
| Autor: | Kamran Karimi, Henri Salmenjoki, Katarzyna Mulewska, Lukasz Kurpaska, Anna Kosińska, Mikko J. Alava, Stefanos Papanikolaou |
|---|---|
| Přispěvatelé: | National Centre for Nuclear Research, Complex Systems and Materials, Department of Applied Physics, Aalto-yliopisto, Aalto University |
| Rok vydání: | 2023 |
| Předmět: |
Condensed Matter - Materials Science
Mechanical Engineering Misorientation Modeling Metals and Alloys Materials Science (cond-mat.mtrl-sci) FOS: Physical sciences Graph Neural Network Condensed Matter Physics Condensed Matter - Other Condensed Matter Hardness Mechanics of Materials Hall–Petch effect General Materials Science Other Condensed Matter (cond-mat.other) |
| Zdroj: | Scripta Materialia. 234:115559 |
| ISSN: | 1359-6462 |
| DOI: | 10.1016/j.scriptamat.2023.115559 |
| Popis: | Funding Information: This research was funded by the European Union Horizon 2020 research and innovation program under grant agreement no. 857470 and from the European Regional Development Fund via Foundation for Polish Science International Research Agenda PLUS program grant no. MAB PLUS/2018/8 . We wish to acknowledge fruitful discussions with Daniel Cieslinski. | openaire: EC/H2020/857470/EU//NOMATEN Nanoscale hardness in polycrystalline metals is strongly dependent on microstructural features that are believed to be influenced from polycrystallinity — namely, grain orientations and neighboring grain properties. We train a graph neural networks (GNN) model, with grain centers as graph nodes, to assess the predictability of micromechanical responses of nano-indented 310S steel surfaces, based on surface polycrystallinity, captured by electron backscatter diffraction maps. The grain size distribution ranges between 1–100 μm, with mean size at 18μm. The GNN model is trained on nanomechanical load-displacement curves to make predictions of nano-hardness, with sole input being the grain locations and orientations. We explore model performance and its dependence on various structural/topological grain-level descriptors (e.g. grain size and number of neighbors). Analogous GNN-based frameworks may be utilized for quick, inexpensive hardness estimates, for guidance to detailed nanoindentation experiments, akin to cartography tool developments in the world exploration era. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect