Neural Stress Fields for Reduced-order Elastoplasticity and Fracture
SessionNeural Physics
DescriptionThe material point method (MPM) is a versatile simulation framework for large-deformation elastoplasticity and fracture. However, MPM's long runtime and large memory consumptions render it unsuitable for applications constrained by computation time and memory usage, e.g., virtual reality. To overcome these barriers, we propose a reduced-order MPM framework. Our key innovation is training a low-dimensional manifold for the Kirchhoff stress field via an implicit neural representation. This low-dimensional neural stress field (NSF) enables efficient evaluations of stress values and, correspondingly, internal forces at arbitrary spatial locations. In addition, we also train neural deformation and affine fields to build low-dimensional manifolds for the deformation and affine momentum fields. These neural stress, deformation, and affine fields share the same low-dimensional latent space, which uniquely embeds the high-dimensional MPM simulation state. After training, we run new simulations by evolving in this single latent space, which drastically reduces the computation time and memory consumption. Our general continuum-mechanics-based reduced-order framework is applicable to any phenomena governed by the elastodynamics equation. To showcase the versatility of our framework, we simulate a wide range of material behaviors, including elastica, sand, metal, non-Newtonian fluids, fracture, contact, and collision. We demonstrate dimension reduction by up to 100,000X and time savings by up to 10X.
Authors
Event Type
Technical Papers
TimeThursday, 14 December 20232:35pm - 2:45pm 
LocationMeeting Room C4.8, Level 4 (Convention Centre)
