Pseudo-Hamiltonian system identification

Autor:	Holmsen, Sigurd, Eidnes, Sølve, Riemer-Sørensen, Signe
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Systems and Control Computer Science - Machine Learning Mathematics - Dynamical Systems Mathematics - Numerical Analysis Primary: 34A55 37M10 Secondary: 37J99
Druh dokumentu:	Working Paper
Popis:	Identifying the underlying dynamics of physical systems can be challenging when only provided with observational data. In this work, we consider systems that can be modelled as first-order ordinary differential equations. By assuming a certain pseudo-Hamiltonian formulation, we are able to learn the analytic terms of internal dynamics even if the model is trained on data where the system is affected by unknown damping and external disturbances. In cases where it is difficult to find analytic terms for the disturbances, a hybrid model that uses a neural network to learn these can still accurately identify the dynamics of the system as if under ideal conditions. This makes the models applicable in some situations where other system identification models fail. Furthermore, we propose to use a fourth-order symmetric integration scheme in the loss function and avoid actual integration in the training, and demonstrate on varied examples how this leads to increased performance on noisy data. Comment: 33 pages, 21 figures, including the appendix; v2: restructured and modified the text, added Section 6
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.06920 Zobrazit plný text záznamu View this record from Arxiv