Learning robust parameter inference and density reconstruction in flyer plate impact experiments

2025-06-30

AI Summary

In flyer-impact experiments, conventional parameter estimation fails because radiographic imaging cannot directly observe critical state variables such as density. To address this, we propose an end-to-end inversion framework integrating generative machine learning with Bayesian inference. Our method constructs a joint radiographic–hydrodynamic surrogate model trained on observable image ensembles from both low- and high-velocity impacts, enabling direct posterior inference of equation-of-state (EoS) and pore-crush model parameters from time-resolved radiograph sequences. Innovatively, this is the first application of generative modeling to high-energy shock physics inversion, markedly enhancing robustness against out-of-distribution noise and unknown material states. Validation on synthetic data demonstrates high-accuracy parameter estimation and physically self-consistent density field reconstruction. The framework establishes a new paradigm for modeling materials under extreme conditions when only indirect observations are available.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Estimating physical parameters or material properties from experimental observations is a common objective in many areas of physics and material science. In many experiments, especially in shock physics, radiography is the primary means of observing the system of interest. However, radiography does not provide direct access to key state variables, such as density, which prevents the application of traditional parameter estimation approaches. Here we focus on flyer plate impact experiments on porous materials, and resolving the underlying parameterized equation of state (EoS) and crush porosity model parameters given radiographic observation(s). We use machine learning as a tool to demonstrate with high confidence that using only high impact velocity data does not provide sufficient information to accurately infer both EoS and crush model parameters, even with fully resolved density fields or a dynamic sequence of images. We thus propose an observable data set consisting of low and high impact velocity experiments/simulations that capture different regimes of compaction and shock propagation, and proceed to introduce a generative machine learning approach which produces a posterior distribution of physical parameters directly from radiographs. We demonstrate the effectiveness of the approach in estimating parameters from simulated flyer plate impact experiments, and show that the obtained estimates of EoS and crush model parameters can then be used in hydrodynamic simulations to obtain accurate and physically admissible density reconstructions. Finally, we examine the robustness of the approach to model mismatches, and find that the learned approach can provide useful parameter estimates in the presence of out-of-distribution radiographic noise and previously unseen physics, thereby promoting a potential breakthrough in estimating material properties from experimental radiographic images.

Problem

• Estimating material properties from radiographic observations in shock physics
• Resolving EoS and crush model parameters in flyer plate impact experiments
• Overcoming insufficient data from high-velocity impacts via machine learning

Innovation

• Machine learning for parameter inference from radiographs
• Generative approach for posterior distribution of parameters
• Robust to out-of-distribution noise and unseen physics