Enregistré dans:
Détails bibliographiques
Auteurs principaux: Frank, Daniel, Shakib, Fahim, Staab, Steffen
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.18292
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909054170824704
author Frank, Daniel
Shakib, Fahim
Staab, Steffen
author_facet Frank, Daniel
Shakib, Fahim
Staab, Steffen
contents This paper presents a method that learns a regionally stable recurrent neural network model from a set of input-output data generated by an unknown dynamical system. Relying on generalized sector conditions on the deadzone activation function, we first derive sufficient conditions that guarantee forward invariance on a compact set of the state space for any inputs from a given set. Such regional properties lead to less conservative conditions compared to variants that offer a global form of stability, and are in line with the system data that is only observed regionally. Our learning method derives conditions for regional stability using a barrier function approach, leading to models equipped with a certificate of regional stability in a subset of the state space and for a given input set. We illustrate our theoretical result with a numerical example and compare it to methods that impose a global form of stability, which fail to identify the system, and with a method that imposes no stability constraints at all, which does not guarantee a stable behavior within any state or input set.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18292
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning the dynamics of nonlinear systems with regional stability guarantees through linear matrix inequality constraints
Frank, Daniel
Shakib, Fahim
Staab, Steffen
Systems and Control
This paper presents a method that learns a regionally stable recurrent neural network model from a set of input-output data generated by an unknown dynamical system. Relying on generalized sector conditions on the deadzone activation function, we first derive sufficient conditions that guarantee forward invariance on a compact set of the state space for any inputs from a given set. Such regional properties lead to less conservative conditions compared to variants that offer a global form of stability, and are in line with the system data that is only observed regionally. Our learning method derives conditions for regional stability using a barrier function approach, leading to models equipped with a certificate of regional stability in a subset of the state space and for a given input set. We illustrate our theoretical result with a numerical example and compare it to methods that impose a global form of stability, which fail to identify the system, and with a method that imposes no stability constraints at all, which does not guarantee a stable behavior within any state or input set.
title Learning the dynamics of nonlinear systems with regional stability guarantees through linear matrix inequality constraints
topic Systems and Control
url https://arxiv.org/abs/2605.18292