Nonlinear port-Hamiltonian system identification from input-state-output data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cherifi, Karim, Messaoudi, Achraf El, Gernandt, Hannes, Roschkowski, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929716900921344
author Cherifi, Karim
Messaoudi, Achraf El
Gernandt, Hannes
Roschkowski, Marco
author_facet Cherifi, Karim
Messaoudi, Achraf El
Gernandt, Hannes
Roschkowski, Marco
contents A framework for identifying nonlinear port-Hamiltonian systems using input-state-output data is introduced. The framework utilizes neural networks' universal approximation capacity to effectively represent complex dynamics in a structured way. We show that using the structure helps to make long-term predictions compared to baselines that do not incorporate physics. We also explore different architectures based on MLPs, KANs, and using prior information. The technique is validated through examples featuring nonlinearities in either the skew-symmetric terms, the dissipative terms, or the Hamiltonian.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonlinear port-Hamiltonian system identification from input-state-output data
Cherifi, Karim
Messaoudi, Achraf El
Gernandt, Hannes
Roschkowski, Marco
Systems and Control
Dynamical Systems
Optimization and Control
Chaotic Dynamics
93B30, 93B15, 93C10, 68T07, 93B99
A framework for identifying nonlinear port-Hamiltonian systems using input-state-output data is introduced. The framework utilizes neural networks' universal approximation capacity to effectively represent complex dynamics in a structured way. We show that using the structure helps to make long-term predictions compared to baselines that do not incorporate physics. We also explore different architectures based on MLPs, KANs, and using prior information. The technique is validated through examples featuring nonlinearities in either the skew-symmetric terms, the dissipative terms, or the Hamiltonian.
title Nonlinear port-Hamiltonian system identification from input-state-output data
topic Systems and Control
Dynamical Systems
Optimization and Control
Chaotic Dynamics
93B30, 93B15, 93C10, 68T07, 93B99
url https://arxiv.org/abs/2501.06118