Data-driven methods in control engineering
Overview
The goal of the junior research group "Data-Driven Methods in Control Engineering" is to explore the synergetic combination of model- and data-driven methods for control engineering tasks. For this purpose, model-driven methods are combined with machine learning to obtain hybrid methods and to achieve the highest possible performance in control design. The hybrid design methods developed in this way are to be combined and evaluated on various demonstrators. Industrial exploitation of the results is also planned through knowledge transfer in cooperation with the Fraunhofer Institute for Mechatronic Design IEM.
Key Facts
- Research profile area:
- Intelligent Technical Systems
- Project type:
- Research
- Project duration:
- 01/2020 - 12/2024
- Funded by:
- BMBF
More Information
Publications
Datengetriebene Modellbildung für nichtlineare mechatronische Systeme in regelungstechnisch verwertbarer Form
A. Junker, Datengetriebene Modellbildung für nichtlineare mechatronische Systeme in regelungstechnisch verwertbarer Form, Heinz Nixdorf Institut, Paderborn, 2024.
Adaptive Data‐Driven Models in Port‐Hamiltonian Form for Control Design
A. Junker, J. Timmermann, A. Tr?chtler, PAMM 25 (2024).
Online Learning With Joint State and Model Estimation
R.-S. G?tte, J. Timmermann, PAMM 25 (2024).
Autonomous Golf Putting with Data-Driven and Physics-Based Methods
A. Junker, N. Fittkau, J. Timmermann, A. Tr?chtler, in: 2022 Sixth IEEE International Conference on Robotic Computing (IRC), IEEE, 2023.
Adaptive Koopman-Based Models for Holistic Controller and Observer Design
Show all publications
A. Junker, K.E.F. Pape, J. Timmermann, A. Tr?chtler, IFAC-PapersOnLine 56 (2023) 625–630.