Abstract

In order to make data-driven models of physical systems interpretable and reliable, it is essential to include prior physical knowledge in the modeling framework. Hamiltonian Neural Networks (HNNs) implement Hamiltonian theory in deep learning and form a comprehensive framework for modeling autonomous energy-conservative systems. Despite being suitable to estimate a wide range of physical system behavior from data, classical HNNs are restricted to systems without inputs and require noiseless state measurements and information on the derivative of the state to be available. To address these challenges, this paper introduces an Output Error Hamiltonian Neural Network (OE-HNN) modeling approach to address the modeling of physical systems with inputs and noisy state measurements. Furthermore, it does not require the state derivatives to be known. Instead, the OE-HNN utilizes an ODE-solver embedded in the training process, which enables the OE-HNN to learn the dynamics from noisy state measurements. In addition, extending HNNs based on the generalized Hamiltonian theory enables to include external inputs into the framework which are important for engineering applications. We demonstrate via simulation examples that the proposed OE-HNNs results in superior modeling performance compared to classical HNNs.
Original languageEnglish
Pages (from-to)5152-5157
Number of pages6
JournalIFAC-PapersOnLine
Volume56
Issue number2
DOIs
Publication statusPublished - 1 Jul 2023
Event22nd World Congress of the International Federation of Automatic Control (IFAC 2023 World Congress) - Yokohama, Japan
Duration: 9 Jul 202314 Jul 2023
Conference number: 22
https://www.ifac2023.org/

Funding

This work is part of the DAMOCLES research project which received funding from the Eindhoven Artificial Intelligence Systems Institute, as part of the EMDAIR funding programme.

FundersFunder number
Eindhoven University of Technology

    Keywords

    • Hamiltonian Neural Networks
    • Nonlinear system identification
    • Machine learning

    Fingerprint

    Dive into the research topics of 'Physics-Informed Learning Using Hamiltonian Neural Networks with Output Error Noise Models'. Together they form a unique fingerprint.

    Cite this