Physics-aware Deep Generative Models for Creating Synthetic Microstructures

dc.contributor.author Hegde, Chinmay
dc.contributor.author Singh, Rahul
dc.contributor.author Shah, Viraj
dc.contributor.author Ganapathysubramanian, Baskar
dc.contributor.author Pokuri, Balaji
dc.contributor.author Sarkar, Soumik
dc.contributor.author Ganapathysubramanian, Baskar
dc.contributor.author Hegde, Chinmay
dc.contributor.department Mechanical Engineering
dc.contributor.department Electrical and Computer Engineering
dc.contributor.department Plant Sciences Institute
dc.date 2018-12-13T02:54:21.000
dc.date.accessioned 2020-06-30T06:04:46Z
dc.date.available 2020-06-30T06:04:46Z
dc.date.copyright Mon Jan 01 00:00:00 UTC 2018
dc.date.issued 2018-01-01
dc.description.abstract <p>A key problem in computational material science deals with understanding the effect of material distribution (i.e., microstructure) on material performance. The challenge is to synthesize microstructures, given a finite number of microstructure images, and/or some physical invariances that the microstructure exhibits. Conventional approaches are based on stochastic optimization and are computationally intensive. We introduce three generative models for the fast synthesis of binary microstructure images. The first model is a WGAN model that uses a finite number of training images to synthesize new microstructures that weakly satisfy the physical invariances respected by the original data. The second model explicitly enforces known physical invariances by replacing the traditional discriminator in a GAN with an invariance checker. Our third model combines the first two models to reconstruct microstructures that respect both explicit physics invariances as well as implicit constraints learned from the image data. We illustrate these models by reconstructing two-phase microstructures that exhibit coarsening behavior. The trained models also exhibit interesting latent variable interpolation behavior, and the results indicate considerable promise for enforcing user-defined physics constraints during microstructure synthesis.</p>
dc.description.comments <p>This is a pre-print of the article Singh, Rahul, Viraj Shah, Balaji Pokuri, Soumik Sarkar, Baskar Ganapathysubramanian, and Chinmay Hegde. "Physics-aware Deep Generative Models for Creating Synthetic Microstructures." <em>arXiv preprint arXiv:1811.09669v1 </em>(2018). Posted with permission.</p>
dc.format.mimetype application/pdf
dc.identifier archive/lib.dr.iastate.edu/me_pubs/312/
dc.identifier.articleid 1314
dc.identifier.contextkey 13438770
dc.identifier.s3bucket isulib-bepress-aws-west
dc.identifier.submissionpath me_pubs/312
dc.identifier.uri https://dr.lib.iastate.edu/handle/20.500.12876/55179
dc.language.iso en
dc.source.bitstream archive/lib.dr.iastate.edu/me_pubs/312/2018_Ganapathysubramanian_PhysicsAware.pdf|||Fri Jan 14 23:31:40 UTC 2022
dc.subject.disciplines Computer-Aided Engineering and Design
dc.subject.disciplines Mechanical Engineering
dc.subject.disciplines Structural Materials
dc.title Physics-aware Deep Generative Models for Creating Synthetic Microstructures
dc.type article
dc.type.genre article
dspace.entity.type Publication
relation.isAuthorOfPublication 73ee39fa-8eac-4710-9169-afda79f90206
relation.isAuthorOfPublication da41682a-ff6f-466a-b99c-703b9d7a78ef
relation.isOrgUnitOfPublication 6d38ab0f-8cc2-4ad3-90b1-67a60c5a6f59
relation.isOrgUnitOfPublication a75a044c-d11e-44cd-af4f-dab1d83339ff
File
Original bundle
Now showing 1 - 1 of 1
Name:
2018_Ganapathysubramanian_PhysicsAware.pdf
Size:
2.52 MB
Format:
Adobe Portable Document Format
Description:
Collections