A physics-aware deep learning model for energy localization in multiscale shock-to-detonation simulations of heterogeneous energetic materials
Preprint
Abstract
Predictive simulations of the shock-to-detonation transition (SDT) in heterogeneous energetic materials (EM) are vital to the design and control of their energy release and sensitivity. Due to the complexity of the thermo-mechanics of EM during the SDT, both macro-scale response and sub-grid mesoscale energy localization must be captured accurately. This work proposes an efficient and accurate multiscale framework for SDT simulations of EM. We employ deep learning to model the mesoscale energy localization of shock-initiated EM microstructures upon which prediction results are used to supply reaction progress rate information to the macroscale SDT simulation. The proposed multiscale modeling framework is divided into two stages. First, a physics-aware recurrent convolutional neural network (PARC) is used to model the mesoscale energy localization of shock-initiated heterogeneous EM microstructures. PARC is trained using direct numerical simulations (DNS) of hotspot ignition and growth within microstructures of pressed HMX material subjected to different input shock strengths. After training, PARC is employed to supply hotspot ignition and growth rates for macroscale SDT simulations. We show that PARC can play the role of a surrogate model in a multiscale simulation framework, while drastically reducing the computation cost and providing improved representations of the sub-grid physics. The proposed multiscale modeling approach will provide a new tool for material scientists in designing high-performance and safer energetic materials.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Structure–property–performance linkages for heterogenous energetic materials through multi-scale modelingMultiscale and Multidisciplinary Modeling, Experiments and Design, 2020
- Structure–property linkage in shocked multi-material flows using a level-set-based Eulerian image-to-computation frameworkShock Waves, 2020
- Modeling mesoscale energy localization in shocked HMX, Part II: training machine-learned surrogate models for void shape and void–void interaction effectsShock Waves, 2019
- Modeling mesoscale energy localization in shocked HMX, part I: machine-learned surrogate models for the effects of loading and void sizesShock Waves, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A numerical study of the dynamics of detonation initiated by cavity collapseShock Waves, 2015
- A model for hot spot formation in shocked energetic materialsCombustion and Flame, 2015
- Numerical modeling of shock-to-detonation transition in energetic materialsCombustion and Flame, 2012
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- A two-phase mixture theory for the deflagration-to-detonation transition (ddt) in reactive granular materialsInternational Journal of Multiphase Flow, 1986