LiCROM: Linear-Subspace Continuous Reduced Order Modeling with Neural Fields
Chang Yue, Peter Yichen Chen, Zhecheng Wang, Maurizio M. Chiaramonte, Kevin Carlberg, Eitan Grinspun
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.
Topics & Concepts
DiscretizationSubspace topologyComputer scienceRepresentation (politics)KinematicsDiscretization errorAlgorithmApplied mathematicsControl theory (sociology)MathematicsArtificial intelligenceMathematical analysisPhysicsControl (management)LawPoliticsPolitical scienceClassical mechanicsModel Reduction and Neural NetworksProbabilistic and Robust Engineering DesignHydraulic and Pneumatic Systems