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

Phong C H Nguyen; Yen-Thi Nguyen; Joseph B Choi; Pradeep K Seshadri; H S Udaykumar; Stephen S Baek

doi:10.1126/sciadv.add6868

Back

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

Journal article

Open access

Peer reviewed

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

Phong C H Nguyen, Yen-Thi Nguyen, Joseph B Choi, Pradeep K Seshadri, H S Udaykumar and Stephen S Baek

Science advances, Vol.9(17), eadd6868

04/28/2023

DOI: 10.1126/sciadv.add6868

PMCID: PMC10146890

PMID: 37115927

Files and links (1)

url

https://doi.org/10.1126/sciadv.add6868View

Published (Version of record) Open Access

Abstract

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.

Details

Title: Subtitle: PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
Creators: Phong C H Nguyen - University of Virginia
Yen-Thi Nguyen - Department of Mechanical Engineering, University of Iowa, Iowa City, IA 52242, USA
Joseph B Choi - University of Virginia
Pradeep K Seshadri - University of Iowa
H S Udaykumar - Department of Mechanical Engineering, University of Iowa, Iowa City, IA 52242, USA
Stephen S Baek - University of Virginia
Resource Type: Journal article
Publication Details: Science advances, Vol.9(17), eadd6868
DOI: 10.1126/sciadv.add6868
PMID: 37115927
PMCID: PMC10146890
NLM abbreviation: Sci Adv
ISSN: 2375-2548
eISSN: 2375-2548
Language: English
Date published: 04/28/2023
Academic Unit: IIHR--Hydroscience and Engineering; Injury Prevention Research Center; Mechanical Engineering
Record Identifier: 9984399641702771

Metrics

99 Record Views

21 Times Cited - Web of Science