Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems
arXiv:2204.12972 · doi:10.1016/j.ifacol.2022.07.282
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.
arXiv comment6 pages, 6 figures, accepted to IFAC for publication under a Creative Commons Licence CC-BY-NC-ND
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
- Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling
- Neurosymbolic AI: The 3rd Wave
- Sparse Identification of Nonlinear Dynamics with Control (SINDYc)
- Training neural networks under physical constraints using a stochastic augmented Lagrangian approach
- Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering