Learning networked dynamical system models with weak form and graph neural networks

Y Yu, D Huang, S Park, HC Pangborn - arxiv preprint arxiv:2407.16779, 2024 - arxiv.org
This paper presents a sequence of two approaches for the data-driven control-oriented
modeling of networked systems, ie, the systems that involve many interacting dynamical …

Multi-Timescale System Separation via Data-Driven Identification Within a Singular Perturbation Framework

S Park, HC Pangborn - 2024 American Control Conference …, 2024 - ieeexplore.ieee.org
This paper presents a timescale separation method for realization-preserving reduced-order
modeling of dynamic systems. While classical singular perturbation theory can be used to …

Global Description of Flutter Dynamics via Koopman Theory

J Song, D Huang - AIAA SCITECH 2025 Forum, 2025 - arc.aiaa.org
We introduce a data-driven method for flutter analysis and prediction based on Koopman
theory. The Koopman formalism enables the representation of nonlinear dynamics in a …

Parametrized Global Linearization Models for Flutter Prediction

J Song, Y Yu, D Huang - AIAA SCITECH 2024 Forum, 2024 - arc.aiaa.org
We present a data-driven flutter analysis and prediction method based on the Koopman
theory. The Koopman formalism represents nonlinear dynamics in a higher-dimensional …