Convolutional and Graph Neural Network framework for predicting critical impact velocity in heterogeneous PBX-9501

Heterogeneous energetic materials (HEM) can involve structural defects such as randomly distributed pores of varying size and shape. The unique arrangements of these defects cause initiation metrics such as pressure, temperature, and particle velocity to vary on a sample-to-sample basis. Current methods for predicting initiation rely on experiments and computational models. However, accounting for each possible pore configuration requires an extensive number of experiments and computational simulations, making them unfeasible for this problem. Machine Learning (ML) offers an attractive approach to overcome these challenges. Towards this goal, this work introduces a ML framework involving a Convolutional Neural Network (CNN), and Graph Neural Network (GNN) for predicting critical elocities in PBX-9501 samples with multiple pores of varying quantity, size, and spatial distribution. The performance of both models was evaluated across two types of pore arrangements: Cartesian grids and rotated configurations. The comparative evaluation showed that the GNN outperformed the CNN in Cartesian grid pore configurations, achieving a lower average error of 0.678 ±0.621% compared to the CNN of 0.902 ±0.799%. Conversely, for rotated pore arrangements, the CNN achieved better accuracy of 0.782 ±1.107% than the GNN of 0.967 ±1.09%. Despite these differences, both models consistently achieved average prediction errors below 1%, demonstrating strong overall performance across different pore configurations. Ultimately, this work advances the development of ML-driven models capable of rapidly and accurately predicting how complex pore structures influence shock sensitivity in HEM(s).

Recommended citation: coming soon https://doi.org/10.1130/B38196.1