Prediction of steel nanohardness by using graph neural networks on surface polycrystallinity maps

Prediction of steel nanohardness by using graph neural networks on surface polycrystallinity maps

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...

Full description

Bibliographic Details
Main Authors: Alava, M.J (Author), Karimi, K. (Author), Kosińska, A. (Author), Kurpaska, L. (Author), Mulewska, K. (Author), Papanikolaou, S. (Author), Salmenjoki, H. (Author)
Format: Article
Language:English
Published: Acta Materialia Inc 2023
Subjects:
Grain size and shape
Graph Neural Network
Graph neural networks
Hall–Petch effect
Hall-Petch effects
Hardness
Maps
Microstructural features
Misorientation
Misorientations
Modeling
Nano scale
Networks on surfaces
Neural network model
Polycrystalline metals
Polycrystallinity
Textures
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items