Cargando…

PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials

The thermo-mechanical response of shock-initiated energetic materials (EMs) is highly influenced by their microstructures, presenting an opportunity to engineer EM microstructures in a “materials-by-design” framework. However, the current design practice is limited, as a large ensemble of simulation...

Descripción completa

Detalles Bibliográficos
Autores principales: Nguyen, Phong C. H., Nguyen, Yen-Thi, Choi, Joseph B., Seshadri, Pradeep K., Udaykumar, H. S., Baek, Stephen S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Association for the Advancement of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10146890/
https://www.ncbi.nlm.nih.gov/pubmed/37115927
http://dx.doi.org/10.1126/sciadv.add6868
_version_ 1785034686811078656
author Nguyen, Phong C. H.
Nguyen, Yen-Thi
Choi, Joseph B.
Seshadri, Pradeep K.
Udaykumar, H. S.
Baek, Stephen S.
author_facet Nguyen, Phong C. H.
Nguyen, Yen-Thi
Choi, Joseph B.
Seshadri, Pradeep K.
Udaykumar, H. S.
Baek, Stephen S.
author_sort Nguyen, Phong C. H.
collection PubMed
description The thermo-mechanical response of shock-initiated energetic materials (EMs) is highly influenced by their microstructures, presenting an opportunity to engineer EM microstructures in a “materials-by-design” framework. However, the current design practice is limited, as a large ensemble of simulations is required to construct the complex EM structure-property-performance linkages. We present the physics-aware recurrent convolutional (PARC) neural network, a deep learning algorithm capable of learning the mesoscale thermo-mechanics of EM from a modest number of high-resolution direct numerical simulations (DNS). Validation results demonstrated that PARC could predict the themo-mechanical response of shocked EMs with comparable accuracy to DNS but with notably less computation time. The physics-awareness of PARC enhances its modeling capabilities and generalizability, especially when challenged in unseen prediction scenarios. We also demonstrate that visualizing the artificial neurons at PARC can shed light on important aspects of EM thermos-mechanics and provide an additional lens for conceptualizing EM.
format Online
Article
Text
id pubmed-10146890
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Association for the Advancement of Science
record_format MEDLINE/PubMed
spelling pubmed-101468902023-04-29 PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials Nguyen, Phong C. H. Nguyen, Yen-Thi Choi, Joseph B. Seshadri, Pradeep K. Udaykumar, H. S. Baek, Stephen S. Sci Adv Physical and Materials Sciences The thermo-mechanical response of shock-initiated energetic materials (EMs) is highly influenced by their microstructures, presenting an opportunity to engineer EM microstructures in a “materials-by-design” framework. However, the current design practice is limited, as a large ensemble of simulations is required to construct the complex EM structure-property-performance linkages. We present the physics-aware recurrent convolutional (PARC) neural network, a deep learning algorithm capable of learning the mesoscale thermo-mechanics of EM from a modest number of high-resolution direct numerical simulations (DNS). Validation results demonstrated that PARC could predict the themo-mechanical response of shocked EMs with comparable accuracy to DNS but with notably less computation time. The physics-awareness of PARC enhances its modeling capabilities and generalizability, especially when challenged in unseen prediction scenarios. We also demonstrate that visualizing the artificial neurons at PARC can shed light on important aspects of EM thermos-mechanics and provide an additional lens for conceptualizing EM. American Association for the Advancement of Science 2023-04-28 /pmc/articles/PMC10146890/ /pubmed/37115927 http://dx.doi.org/10.1126/sciadv.add6868 Text en Copyright © 2023 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY). https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Physical and Materials Sciences
Nguyen, Phong C. H.
Nguyen, Yen-Thi
Choi, Joseph B.
Seshadri, Pradeep K.
Udaykumar, H. S.
Baek, Stephen S.
PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title_full PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title_fullStr PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title_full_unstemmed PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title_short PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
title_sort parc: physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
topic Physical and Materials Sciences
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10146890/
https://www.ncbi.nlm.nih.gov/pubmed/37115927
http://dx.doi.org/10.1126/sciadv.add6868
work_keys_str_mv AT nguyenphongch parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials
AT nguyenyenthi parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials
AT choijosephb parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials
AT seshadripradeepk parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials
AT udaykumarhs parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials
AT baekstephens parcphysicsawarerecurrentconvolutionalneuralnetworkstoassimilatemesoscalereactivemechanicsofenergeticmaterials