Case Study | 10.10.2021

Fragment Field Modeling Using Digital Twins and Generative Adversarial Networks (GAN)

connect with us


Machine Learning

Data Science

Key Technologies

Deep Learning

Digital Twin

PEC and SwRI have teamed to support development of novel weapons capabilities through advancements in digital engineering. To employ emerging weapon technologies faster, PEC is developing an accurate and effective machine-learning (ML) technique for characterizing asymmetric weapon fragment fields. The traditional approach to weapon testing, diagnostics, and fragment modeling will not work for asymmetric weapons since the fragment field differs around their azimuth. At best, asymmetric weapon testing will result in a patchwork of data collection at relatively few carefully chosen zones leaving the bulk of the fragment field uncharacterized.

Digital engineered data will be the cornerstone of a new paradigm for hypersonic asymmetric weapon characterization. The ability to synthesize digital twin fragment fields with patchwork experimental measurements will be a transformative outcome of this effort.  Arena test and digital twin model data will be fused within the ML framework using: 1) a Generative Adversarial Network (GAN) to synthesis physical and digital twin data, and 2) a Bayesian Neural Network (BNN) to stochastically model fragment fields. GAN-based data synthesis will address the issue of limited experimental measurements, while BNN-based models will address the uncertainties involved.

For more information on our progress and broad range of services contact Dr. Eddie O’Hare at


connect with us

Other Case Studies

Pulsed Laser Measurement for Materials at Extreme Loading Rates

Assessment, Design, and Construction Support to Mitigate Hostile Vehicle Ramming Threats

FragTrack and ParticleTrack: Computer Vision Applications to Track & Quantify Test Video Data