Physics-informed Data-driven Cavitation Model for a Specific MG EOS

TL;DR

This paper introduces a physics-informed neural network model for cavitation based on a specific Mie-Gr"uneisen EOS, effectively integrating experimental data and physics constraints to improve multi-phase flow simulations.

Contribution

The paper develops a novel neural network-based cavitation model that embeds physics and experimental data for the polynomial EOS, enhancing simulation accuracy.

Findings

Model accurately predicts cavitation pressure regions.

Effective in simulating complex multi-phase flows.

Good agreement with experimental data across dimensions.

Abstract

We present a novel one-fluid cavitation model of a specific Mie-Gr\"uneisen equation of state(EOS), named polynomial EOS, based on an artificial neural network. Not only the physics-informed equation but also the experimental data are embedded into the proposed model by an optimization problem. The physics-informed data-driven model provides the concerned pressure within the cavitation region, where the density tends to zero when the pressure falls below the saturated pressure. The present model is then applied to computing the challenging compressible multi-phase flow simulation, such as nuclear and underwater explosions. Numerical simulations show that our model in application agrees well with the corresponding experimental data, ranging from one dimension to three dimensions with the $h-$adaptive mesh refinement algorithm and load balance techniques in the structured and unstructured grid.