LiCROM: Linear-Subspace Continuous Reduced Order Modeling with Neural Fields
Name
3610548.3618158.pdf
Size
11.71 MB
Format
Adobe PDF
Checksum (MD5)
80a8efc36a87604dbb15c7305a79e1bb
Author(s)
Chang, Yue
Chen, Peter Yichen
Wang, Zhecheng
Chiaramonte, Maurizio M.
Carlberg, Kevin
Grinspun, Eitan
Date Issued
December 10, 2023
Publisher
ACM|SIGGRAPH Asia 2023 Conference Papers
Citation
Chang, Yue, Chen, Peter Yichen, Wang, Zhecheng, Chiaramonte, Maurizio M., Carlberg, Kevin et al. 2023. "LiCROM: Linear-Subspace Continuous Reduced Order Modeling with Neural Fields."
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3610548.3618158
