Interconnection of port‐Hamiltonian systems with port‐Hamiltonian neural networks

Authors

Abstract

Port‐Hamiltonian neural networks can be used to capture the interactions between small interconnected port‐Hamiltonian systems from data. We now examine different composed models and check how accurate we can train the modified composed systems. The learning of the dynamics of the composed systems is investigated for cases in which the interconnection is known beforehand and also for cases without knowledge about the interconnection. In the latter cases, only small additional data is required.

Citation

Journal: PAMM
Year: 2024
Volume: 24
Issue: 2
Pages:
Publisher: Wiley
DOI: 10.1002/pamm.202400208

BibTeX

@article{Peters_2024,
  title={{Interconnection of port‐Hamiltonian systems with port‐Hamiltonian neural networks}},
  volume={24},
  ISSN={1617-7061},
  DOI={10.1002/pamm.202400208},
  number={2},
  journal={PAMM},
  publisher={Wiley},
  author={Peters, Till},
  year={2024}
}

Download the bib file

References

Duindam, V., Macchelli, A., Stramigioli, S. & Bruyninckx, H. Modeling and Control of Complex Physical Systems. (Springer Berlin Heidelberg, 2009). doi:10.1007/978-3-642-03196-0 – 10.1007/978-3-642-03196-0
Moser, T., Durmann, J., Bonauer, M. & Lohmann, B. MORpH: Model reduction of linear port-Hamiltonian systems in MATLAB. at - Automatisierungstechnik 71, 476–489 (2023) – 10.1515/auto-2022-0119
Mehrmann, V. & Unger, B. Control of port-Hamiltonian differential-algebraic systems and applications. Acta Numerica 32, 395–515 (2023) – 10.1017/s0962492922000083
Van der Schaft A., Port‐controlled Hamiltonian systems: Towards a theory for control and design of nonlinear physical systems. Journal of The Society of Instrument and Control Engineers (2000)
Gugercin, S., Polyuga, R. V., Beattie, C. & van der Schaft, A. Structure-preserving tangential interpolation for model reduction of port-Hamiltonian systems. Automatica 48, 1963–1974 (2012) – 10.1016/j.automatica.2012.05.052