Practical stability analysis for DNN observation

I. Chairez, A. Poznyak, T. Poznyak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The most important fact for differential neural networks dynamics is related to its weights time evolution. This is a consequence for the higher nonlinear structure describing the matrix differential equations, which are associated with the adaptive capability for this kind of neural networks. However, as we know, there is no any analytical demonstration of the weights stability. In fact, this is the main inconvenient to design real applications of differential neural network observers, especially for control uncertain nonlinear systems. This paper deals with the stability proof for the weights dynamics using an adaptive procedure to adjust the weights ODE. A new dynamic neuro-observer, using the classical Luenberger structure based on practical stability theory, is suggested This methodology aviods the averaged convergence for the state estimation and provides an upper bound for the weights trajectories. A numerical example dealing with the ozonization process state estimation is presented to illustrate the effectiveness of the suggested approach.

Original languageEnglish
Title of host publicationProceedings of the 47th IEEE Conference on Decision and Control, CDC 2008
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2551-2556
Number of pages6
ISBN (Print)9781424431243
DOIs
StatePublished - 2008
Event47th IEEE Conference on Decision and Control, CDC 2008 - Cancun, Mexico
Duration: 9 Dec 200811 Dec 2008

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370

Conference

Conference47th IEEE Conference on Decision and Control, CDC 2008
Country/TerritoryMexico
CityCancun
Period9/12/0811/12/08

Fingerprint

Dive into the research topics of 'Practical stability analysis for DNN observation'. Together they form a unique fingerprint.

Cite this