Adapting U-Net for linear elastic stress estimation in polycrystal Zr microstructures
File(s)
Author(s)
Langcaster, JD
Balint, DS
Wenman, MR
Type
Journal Article
Abstract
A variant of the U-Net convolutional neural network architecture is proposed to estimate linear elastic compatibility stresses in α
-Zr (hcp) polycrystalline grain structures. Training data was generated using VGrain software with a regularity
α of 0.73 and uniform random orientation for the grain structures and ABAQUS to evaluate the stress fields using the finite element method. The initial dataset contains 200 samples with 20 held from training for validation. The network gives speedups of around 200x to 6000x using a CPU or GPU, with significant memory savings, compared to finite element analysis with a modest reduction in accuracy of up to 10%. Network performance is not correlated with grain structure regularity or texture, showing generalisation of the network beyond the training set to arbitrary Zr crystal structures. Performance when trained with 200 and 400 samples was measured, finding an improvement in accuracy of approximately 10% when the size of the dataset was doubled.
-Zr (hcp) polycrystalline grain structures. Training data was generated using VGrain software with a regularity
α of 0.73 and uniform random orientation for the grain structures and ABAQUS to evaluate the stress fields using the finite element method. The initial dataset contains 200 samples with 20 held from training for validation. The network gives speedups of around 200x to 6000x using a CPU or GPU, with significant memory savings, compared to finite element analysis with a modest reduction in accuracy of up to 10%. Network performance is not correlated with grain structure regularity or texture, showing generalisation of the network beyond the training set to arbitrary Zr crystal structures. Performance when trained with 200 and 400 samples was measured, finding an improvement in accuracy of approximately 10% when the size of the dataset was doubled.
Date Issued
2024-04
Date Acceptance
2024-02-06
Citation
Mechanics of Materials, 2024, 191
ISSN
0167-6636
Publisher
Elsevier
Journal / Book Title
Mechanics of Materials
Volume
191
Copyright Statement
Copyright © 2024 Published by Elsevier Ltd. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
http://dx.doi.org/10.1016/j.mechmat.2024.104948
Publication Status
Published
Article Number
104948
Date Publish Online
2024-02-07