Neural Network-Based KKL observer for nonlinear discrete-time systems - Archive ouverte HAL
Conference Papers Year : 2022

Neural Network-Based KKL observer for nonlinear discrete-time systems

Abstract

For non-autonomous multivariable discrete-time nonlinear systems, we address the state estimation problem using a Kazantzis-Kravaris-Luenberger (KKL) observer. We aim to build a mapping that transforms a nonlinear dynamics into a stable linear system modulo an output injection and to design an asymptotic observer. However, this mapping is difficult to compute and its numerical approximation may be badly conditioned during the transient phase. We propose an algorithm based on ensemble learning techniques to improve the numerical approximation of the mapping and its extension in the transient phase. This ensures a good asymptotic convergence of the observer and avoids peaking phenomena. The algorithm demonstrates good performance in high-dimensional and multiinput-multi-output examples.
Fichier principal
Vignette du fichier
CDC_2022 (1).pdf (630.15 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04005698 , version 1 (27-02-2023)

Identifiers

Cite

Johan Peralez, Madiha Nadri, Daniele Astolfi. Neural Network-Based KKL observer for nonlinear discrete-time systems. 2022 IEEE 61st Conference on Decision and Control (CDC), Dec 2022, Cancun, Mexico. ⟨10.1109/CDC51059.2022.9992516⟩. ⟨hal-04005698⟩
64 View
182 Download

Altmetric

Share

More