LiCROM: Linear-Subspace Continuous Reduced Order Modeling with Neural Fields

TL;DR

LiCROM introduces a discretization-independent reduced-order modeling approach using neural fields, enabling flexible, generalizable, and adaptive simulations across various geometries and mesh types.

Contribution

The paper proposes a novel continuous, neural field-based ROM that is independent of discretization, allowing for flexible and generalizable simulation acceleration.

Findings

Enables simulation of unseen geometries after training on a single example.

Supports modifications like cutting and mesh swapping at runtime.

Demonstrates one-shot generalization to various geometries.

Abstract

Linear reduced-order modeling (ROM) simplifies complex simulations by approximating the behavior of a system using a simplified kinematic representation. Typically, ROM is trained on input simulations created with a specific spatial discretization, and then serves to accelerate simulations with the same discretization. This discretization-dependence is restrictive. Becoming independent of a specific discretization would provide flexibility to mix and match mesh resolutions, connectivity, and type (tetrahedral, hexahedral) in training data; to accelerate simulations with novel discretizations unseen during training; and to accelerate adaptive simulations that temporally or parametrically change the discretization. We present a flexible, discretization-independent approach to reduced-order modeling. Like traditional ROM, we represent the configuration as a linear combination of displacement fields. Unlike traditional ROM, our displacement fields are continuous maps from every point on the reference domain to a corresponding displacement vector; these maps are represented as implicit neural fields. With linear continuous ROM (LiCROM), our training set can include multiple geometries undergoing multiple loading conditions, independent of their discretization. This opens the door to novel applications of reduced order modeling. We can now accelerate simulations that modify the geometry at runtime, for instance via cutting, hole punching, and even swapping the entire mesh. We can also accelerate simulations of geometries unseen during training. We demonstrate one-shot generalization, training on a single geometry and subsequently simulating various unseen geometries.