Multi-Fidelity Predictive Model for Shock Response of Energetic Materials Using Conditional U-Net

TL;DR

This paper introduces MISTnet2, a conditional neural network that predicts shock-induced temperature fields in energetic materials across various microstructures and shock strengths, advancing the understanding of detonation initiation.

Contribution

The paper presents a novel multi-fidelity conditional U-Net model that extends prior work by handling multiple shock strengths, microstructure types, and simulation methods.

Findings

MISTnet2 accurately predicts temperature fields across diverse microstructures.

The model bridges atomistic and coarse-grain simulations.

It enables first-principles predictions of detonation safety.

Abstract

Mapping microstructure to properties is central to materials science. Perhaps most famously, the Hall-Petch relationship relates average grain size to strength. More challenging has been deriving relationships for properties that depend on subtle microstructural features and not average properties. One such example is the initiation of energetic materials under dynamical loading, dominated by energy localization on microstructural features such as pores, cracks, and interfaces. We propose a conditional convolutional neural network to predict the shock-induced temperature field as a function of shock strength, for a wide range of microstructures, and obtained via two different simulation methods. The proposed model, denoted MISTnet2, significantly extends prior work that was limited to a single shock strength, model, and type of microstructure. MISTnet2 can contribute to bridging atomistics with coarse-grain simulations and enable first principles predictions of detonation initiation and safety of this class of materials.