Input-to-state stability for system identification with continuous-time Runge–Kutta neural networks

DOI10.1080/00207179.2021.1978555MaRDI QIDQ6040951zbMATH OpenOpenAlexFDO

Authors Michael Deflorian

Publication date 25 May 2023

Published in International Journal of Control (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1080/00207179.2021.1978555

zbMATH Keywords

continuous-time neural networksdiscrete-time neural networksinput-to-state stabilitynonlinear identificationRunge-Kutta neural networksstate space models

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) System identification (93B30) Control/observation systems involving computers (process control, etc.) (93C83) Asymptotic stability in control theory (93D20) Input-output approaches in control theory (93D25)

Recommendations

• A Runge-Kutta neural network-based control method for nonlinear MIMO systems
• Generalization of an input-to-state stability preserving Runge-Kutta method for nonlinear control systems
• scientific article; zbMATH DE number 2201211
• Continuous-time system identification with neural networks: model structures and fitting criteria
• Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms.

Cites work

• A flexible state-space model for learning nonlinear dynamical systems
• A Generalization of Algebraic Stability for Runge--Kutta Methods
• An Interior Point Algorithm for Large-Scale Nonlinear Programming
• Continuous-time system identification with neural networks: model structures and fitting criteria
• Generalization of an input-to-state stability preserving Runge-Kutta method for nonlinear control systems
• Global stability of a class of continuous-time recurrent neural networks
• Global stability of a class of discrete-time recurrent neural networks
• scientific article; zbMATH DE number 1573291 (Why is no real title available?)
• scientific article; zbMATH DE number 5347321 (Why is no real title available?)
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• Identification and control of electro-mechanical systems using state-dependent parameter estimation
• Input-to-state stability (ISS) analysis for dynamic neural networks
• Input-to-state stability for discrete-time nonlinear systems
• Non-linear system identification using neural networks
• Nonlinear black-box modeling in system identification: A unified overview
• Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms.
• Nonlinear systems.
• Numerical Methods for Ordinary Differential Equations
• Sufficient and necessary conditions for global exponential stability of discrete-time recurrent neural networks

Cited in

(4)

• Classification with Runge-Kutta networks and feature space augmentation
• A Runge-Kutta neural network-based control method for nonlinear MIMO systems
• Input-to-state stability (ISS) analysis for dynamic neural networks
• On the normalization of gray-box state-space neural networks

This page was built for publication: Input-to-state stability for system identification with continuous-time Runge–Kutta neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6040951)