kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Learning Flow Functions from Data with Applications to Nonlinear Oscillators
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Decision and Control Systems (Automatic Control).
Control Systems Group, Dept. of Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Decision and Control Systems (Automatic Control). (Digital Futures)ORCID iD: 0000-0001-9940-5929
2023 (English)In: 22nd IFAC World CongressYokohama, Japan, July 9-14, 2023, Elsevier BV , 2023, Vol. 56, p. 4088-4093Conference paper, Published paper (Refereed)
Abstract [en]

We describe a recurrent neural network (RNN) based architecture to learn the flow function of a causal, time-invariant and continuous-time control system from trajectory data. By restricting the class of control inputs to piecewise constant functions, we show that learning the flow function is equivalent to learning the input-to-state map of a discrete-time dynamical system. This motivates the use of an RNN together with encoder and decoder networks which map the state of the system to the hidden state of the RNN and back. We show that the proposed architecture is able to approximate the flow function by exploiting the system's causality and time-invariance. The output of the learned flow function model can be queried at any time instant. We experimentally validate the proposed method using models of the Van der Pol and FitzHugh-Nagumo oscillators. In both cases, the results demonstrate that the architecture is able to closely reproduce the trajectories of these two systems. For the Van der Pol oscillator, we further show that the trained model generalises to the system's response with a prolonged prediction time horizon as well as control inputs outside the training distribution. For the FitzHugh-Nagumo oscillator, we show that the model accurately captures the input-dependent phenomena of excitability.

Place, publisher, year, edition, pages
Elsevier BV , 2023. Vol. 56, p. 4088-4093
Series
IFAC-PapersOnLine, ISSN 2405-8963 ; 56
Keywords [en]
Excitability, Learning, Oscillator, Recurrent Neural Network
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:kth:diva-343165DOI: 10.1016/j.ifacol.2023.10.1738Scopus ID: 2-s2.0-85183634393OAI: oai:DiVA.org:kth-343165DiVA, id: diva2:1836067
Conference
22nd IFAC World Congress, Yokohama, Japan, Jul 9 2023 - Jul 14 2023
Note

QC 20240209

Part of ISBN 9781713872344

Available from: 2024-02-08 Created: 2024-02-08 Last updated: 2024-02-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Aguiar, MiguelJohansson, Karl H.

Search in DiVA

By author/editor
Aguiar, MiguelJohansson, Karl H.
By organisation
Decision and Control Systems (Automatic Control)
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 19 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf