%0 Generic %1 kneifl2024aphin %A Kneifl, Jonas %A Rettberg, Johannes %A Herb, Julius %D 2024 %K ubs_20002 ubs_20011 ubs_40398 ubs_40177 unibibliografie ubs_30165 ubs_10002 ubs_30024 ubs_10007 ubs_30115 ubs_20019 mult darus ubs_10021 %R 10.18419/darus-4446 %T ApHIN - Autoencoder-based port-Hamiltonian Identification Networks (Software Package) %X Software package for data-driven identification of latent port-Hamiltonian systems. Abstract Conventional physics-based modeling techniques involve high effort, e.g.~time and expert knowledge, while data-driven methods often lack interpretability, structure, and sometimes reliability. To mitigate this, we present a data-driven system identification framework that derives models in the port-Hamiltonian (pH) formulation. This formulation is suitable for multi-physical systems while guaranteeing the useful system theoretical properties of passivity and stability. Our framework combines linear and nonlinear reduction with structured, physics-motivated system identification. In this process, high-dimensional state data obtained from possibly nonlinear systems serves as the input for an autoencoder, which then performs two tasks: (i) nonlinearly transforming and (ii) reducing this data onto a low-dimensional manifold. In the resulting latent space, a pH system is identified by considering the unknown matrix entries as weights of a neural network. The matrices strongly satisfy the pH matrix properties through Cholesky factorizations. In a joint optimization process over the loss term, the pH matrices are adjusted to match the dynamics observed by the data, while defining a linear pH system in the latent space per construction. The learned, low-dimensional pH system can describe even nonlinear systems and is rapidly computable due to its small size. The method is exemplified by a parametric mass-spring-damper and a nonlinear pendulum example as well as the high-dimensional model of a disc brake with linear thermoelastic behavior. Features; This package implements neural networks that identify linear port-Hamiltonian systems from (potentially high-dimensional) data [1].Autoencoders (AEs) for dimensionality reductionp. H layer to identify system matrices that fullfill the definition of a linear pH system. pHIN: identify a (parametric) low-dimensional port-Hamiltonian system directly. ApHIN: identify a (parametric) low-dimensional latent port-Hamiltonian system based on coordinate representations found using an autoencoder. Examples for the identification of linear pH systems from data. One-dimensional mass-spring-damper chain. Pendulum. discbrake model. See documentation for more details.

@misc{kneifl2024aphin, abstract = {Software package for data-driven identification of latent port-Hamiltonian systems. Abstract Conventional physics-based modeling techniques involve high effort, e.g.~time and expert knowledge, while data-driven methods often lack interpretability, structure, and sometimes reliability. To mitigate this, we present a data-driven system identification framework that derives models in the port-Hamiltonian (pH) formulation. This formulation is suitable for multi-physical systems while guaranteeing the useful system theoretical properties of passivity and stability. Our framework combines linear and nonlinear reduction with structured, physics-motivated system identification. In this process, high-dimensional state data obtained from possibly nonlinear systems serves as the input for an autoencoder, which then performs two tasks: (i) nonlinearly transforming and (ii) reducing this data onto a low-dimensional manifold. In the resulting latent space, a pH system is identified by considering the unknown matrix entries as weights of a neural network. The matrices strongly satisfy the pH matrix properties through Cholesky factorizations. In a joint optimization process over the loss term, the pH matrices are adjusted to match the dynamics observed by the data, while defining a linear pH system in the latent space per construction. The learned, low-dimensional pH system can describe even nonlinear systems and is rapidly computable due to its small size. The method is exemplified by a parametric mass-spring-damper and a nonlinear pendulum example as well as the high-dimensional model of a disc brake with linear thermoelastic behavior. Features; This package implements neural networks that identify linear port-Hamiltonian systems from (potentially high-dimensional) data [1].Autoencoders (AEs) for dimensionality reductionp. H layer to identify system matrices that fullfill the definition of a linear pH system. pHIN: identify a (parametric) low-dimensional port-Hamiltonian system directly. ApHIN: identify a (parametric) low-dimensional latent port-Hamiltonian system based on coordinate representations found using an autoencoder. Examples for the identification of linear pH systems from data. One-dimensional mass-spring-damper chain. Pendulum. discbrake model. See documentation for more details. }, added-at = {2024-09-02T16:25:26.000+0200}, affiliation = {Kneifl, Jonas/University of Stuttgart, Rettberg, Johannes/University of Stuttgart, Herb, Julius/University of Stuttgart}, author = {Kneifl, Jonas and Rettberg, Johannes and Herb, Julius}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2de76f2e04c8fb93d2e8cc1da3defd1ee/unibiblio}, doi = {10.18419/darus-4446}, howpublished = {Software}, interhash = {47fb2fb970f5933619a1fa0cd28be2e8}, intrahash = {de76f2e04c8fb93d2e8cc1da3defd1ee}, keywords = {ubs_20002 ubs_20011 ubs_40398 ubs_40177 unibibliografie ubs_30165 ubs_10002 ubs_30024 ubs_10007 ubs_30115 ubs_20019 mult darus ubs_10021}, note = {Related to: Johannes Rettberg, Jonas Kneifl, Julius Herb, Patrick Buchfink, Jörg Fehr, and Bernard Haasdonk. Data-driven identification of latent port-Hamiltonian systems. Arxiv, 2024. arXiv: 2408.08185}, orcid-numbers = {Kneifl, Jonas/0000-0003-3934-6968, Rettberg, Johannes/0009-0008-5787-1620, Herb, Julius/0000-0003-1628-6667}, timestamp = {2024-12-10T14:47:51.000+0100}, title = {ApHIN - Autoencoder-based port-Hamiltonian Identification Networks (Software Package)}, year = 2024 }