Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems

O. Schön, R.-S. Götte, J. Timmermann, ArXiv:2204.12972 (2022).

Download
No fulltext has been uploaded.
forms.preprint.field.doi.label
Preprint
Author
Schön, Oliver; Götte, Ricarda-Samantha; Timmermann, Julia
Abstract
While trade-offs between modeling effort and model accuracy remain a major concern with system identification, resorting to data-driven methods often leads to a complete disregard for physical plausibility. To address this issue, we propose a physics-guided hybrid approach for modeling non-autonomous systems under control. Starting from a traditional physics-based model, this is extended by a recurrent neural network and trained using a sophisticated multi-objective strategy yielding physically plausible models. While purely data-driven methods fail to produce satisfying results, experiments conducted on real data reveal substantial accuracy improvements by our approach compared to a physics-based model.
Publishing Year
Journal Title
arXiv:2204.12972
LibreCat-ID

Cite this

Schön O, Götte R-S, Timmermann J. Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems. arXiv:220412972. Published online 2022. doi:10.1016/j.ifacol.2022.07.282
Schön, O., Götte, R.-S., & Timmermann, J. (2022). Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems. In arXiv:2204.12972. https://doi.org/10.1016/j.ifacol.2022.07.282
@article{Schön_Götte_Timmermann_2022, title={Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems}, DOI={10.1016/j.ifacol.2022.07.282}, journal={arXiv:2204.12972}, author={Schön, Oliver and Götte, Ricarda-Samantha and Timmermann, Julia}, year={2022} }
Schön, Oliver, Ricarda-Samantha Götte, and Julia Timmermann. “Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems.” ArXiv:2204.12972, 2022. https://doi.org/10.1016/j.ifacol.2022.07.282.
O. Schön, R.-S. Götte, and J. Timmermann, “Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems,” arXiv:2204.12972. 2022, doi: 10.1016/j.ifacol.2022.07.282.
Schön, Oliver, et al. “Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying  Non-Autonomous Dynamical Systems.” ArXiv:2204.12972, 2022, doi:10.1016/j.ifacol.2022.07.282.

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2204.12972

Search this title in

Google Scholar