English

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

Systems and Control 2022-08-23 v1 Machine Learning Systems and Control

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.

Keywords

Cite

@article{arxiv.2204.12972,
  title  = {Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems},
  author = {Oliver Schön and Ricarda-Samantha Götte and Julia Timmermann},
  journal= {arXiv preprint arXiv:2204.12972},
  year   = {2022}
}

Comments

6 pages, 6 figures, accepted to IFAC for publication under a Creative Commons Licence CC-BY-NC-ND

R2 v1 2026-06-24T11:00:24.883Z