A physics-aware deep learning model for shear band formation around collapsing pores in shocked reactive materials

2025-10-08

AI Summary

This study addresses the early-stage hot-spot formation mechanisms in crystalline energetic materials under weak-to-moderate shock loading—a regime less explored than strong-shock conditions. Focusing on porous reactive materials, it systematically investigates the coupled dynamics of shear-band localization and plastic heating as drivers of hot-spot nucleation. To model these highly nonlinear spatiotemporal processes, we propose Physics-Aware Recurrent Convolutional Neural Network v2 (PARCv2), which integrates physical priors with recurrent convolutional architecture, markedly improving prediction accuracy and generalizability over conventional deep learning models. Benchmarking against Fourier neural operators and neural ordinary differential equations confirms PARCv2’s superior predictive fidelity and robustness, while also delineating failure boundaries of purely data-driven approaches for complex nonequilibrium dynamics. The work advances fundamental understanding of safety-relevant response mechanisms in energetic materials and establishes an interpretable, transferable AI-augmented paradigm for high-fidelity multiscale simulation.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Modeling shock-to-detonation phenomena in energetic materials (EMs) requires capturing complex physical processes such as strong shocks, rapid changes in microstructural morphology, and nonlinear dynamics of chemical reaction fronts. These processes participate in energy localization at hotspots, which initiate chemical energy release leading to detonation. This study addresses the formation of hotspots in crystalline EMs subjected to weak-to-moderate shock loading, which, despite its critical relevance to the safe storage and handling of EMs, remains underexplored compared to the well-studied strong shock conditions. To overcome the computational challenges associated with direct numerical simulations, we advance the Physics-Aware Recurrent Convolutional Neural Network (PARCv2), which has been shown to be capable of predicting strong shock responses in EMs. We improved the architecture of PARCv2 to rapidly predict shear localizations and plastic heating, which play important roles in the weak-to-moderate shock regime. PARCv2 is benchmarked against two widely used physics-informed models, namely, Fourier neural operator and neural ordinary differential equation; we demonstrate its superior performance in capturing the spatiotemporal dynamics of shear band formation. While all models exhibit certain failure modes, our findings underscore the importance of domain-specific considerations in developing robust AI-accelerated simulation tools for reactive materials.

Problem

• Predicting shear band formation in shocked energetic materials
• Modeling hotspot initiation under weak-to-moderate shock loading
• Overcoming computational challenges in reactive material simulations

Innovation

• Improved PARCv2 architecture for shear band prediction
• Physics-aware recurrent convolutional neural network approach
• Benchmarked against Fourier neural operator and neural ODE