File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Graph neural network for predicting the effective properties of polycrystalline materials: A comprehensive analysis

TitleGraph neural network for predicting the effective properties of polycrystalline materials: A comprehensive analysis
Authors
KeywordsGrain boundaries
Graph neural network
Ion conductivity
Microstructures
Sequential forward selection
Transfer learning
Issue Date2023
Citation
Computational Materials Science, 2023, v. 230, article no. 112461 How to Cite?
AbstractWe develop a polycrystal graph neural network (PGNN) model for predicting the effective properties of polycrystalline materials, using the Li7La3Zr2O12 ceramic as an example. A large-scale dataset with >5000 different three-dimensional polycrystalline microstructures of finite-width grain boundary is generated by Voronoi tessellation and processing of the electron backscatter diffraction images. The effective ion conductivities and elastic stiffness coefficients of these microstructures are calculated by high-throughput physics-based simulations. The optimized PGNN model achieves a low error of <1.4% in predicting all three diagonal components of the effective Li-ion conductivity matrix, outperforming a linear regression model and two baseline convolutional neural network models. Sequential forward selection method is used to quantify the relative importance of selecting individual grain (boundary) features to improving the property prediction accuracy, through which both the critical and unwanted node (edge) feature can be determined. The extrapolation performance of the trained PGNN model is also investigated. The transfer learning performance is evaluated by using the PGNN model pretrained for predicting conductivities to predict the elastic properties of the same set of microstructures
Persistent Identifierhttp://hdl.handle.net/10722/341419
ISSN
2023 Impact Factor: 3.1
2023 SCImago Journal Rankings: 0.741
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDai, Minyi-
dc.contributor.authorDemirel, Mehmet F.-
dc.contributor.authorLiu, Xuanhan-
dc.contributor.authorLiang, Yingyu-
dc.contributor.authorHu, Jia Mian-
dc.date.accessioned2024-03-13T08:42:40Z-
dc.date.available2024-03-13T08:42:40Z-
dc.date.issued2023-
dc.identifier.citationComputational Materials Science, 2023, v. 230, article no. 112461-
dc.identifier.issn0927-0256-
dc.identifier.urihttp://hdl.handle.net/10722/341419-
dc.description.abstractWe develop a polycrystal graph neural network (PGNN) model for predicting the effective properties of polycrystalline materials, using the Li7La3Zr2O12 ceramic as an example. A large-scale dataset with >5000 different three-dimensional polycrystalline microstructures of finite-width grain boundary is generated by Voronoi tessellation and processing of the electron backscatter diffraction images. The effective ion conductivities and elastic stiffness coefficients of these microstructures are calculated by high-throughput physics-based simulations. The optimized PGNN model achieves a low error of <1.4% in predicting all three diagonal components of the effective Li-ion conductivity matrix, outperforming a linear regression model and two baseline convolutional neural network models. Sequential forward selection method is used to quantify the relative importance of selecting individual grain (boundary) features to improving the property prediction accuracy, through which both the critical and unwanted node (edge) feature can be determined. The extrapolation performance of the trained PGNN model is also investigated. The transfer learning performance is evaluated by using the PGNN model pretrained for predicting conductivities to predict the elastic properties of the same set of microstructures-
dc.languageeng-
dc.relation.ispartofComputational Materials Science-
dc.subjectGrain boundaries-
dc.subjectGraph neural network-
dc.subjectIon conductivity-
dc.subjectMicrostructures-
dc.subjectSequential forward selection-
dc.subjectTransfer learning-
dc.titleGraph neural network for predicting the effective properties of polycrystalline materials: A comprehensive analysis-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.commatsci.2023.112461-
dc.identifier.scopuseid_2-s2.0-85171618304-
dc.identifier.volume230-
dc.identifier.spagearticle no. 112461-
dc.identifier.epagearticle no. 112461-
dc.identifier.isiWOS:001077445000001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats