Practical stability analysis for DNN observation

I. Chairez, A. Poznyak, T. Poznyak

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

5 Citas (Scopus)

Resumen

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.

Idioma originalInglés
Título de la publicación alojadaProceedings of the 47th IEEE Conference on Decision and Control, CDC 2008
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas2551-2556
Número de páginas6
ISBN (versión impresa)9781424431243
DOI
EstadoPublicada - 2008
Evento47th IEEE Conference on Decision and Control, CDC 2008 - Cancun, México
Duración: 9 dic. 200811 dic. 2008

Serie de la publicación

NombreProceedings of the IEEE Conference on Decision and Control
ISSN (versión impresa)0743-1546
ISSN (versión digital)2576-2370

Conferencia

Conferencia47th IEEE Conference on Decision and Control, CDC 2008
País/TerritorioMéxico
CiudadCancun
Período9/12/0811/12/08

Huella

Profundice en los temas de investigación de 'Practical stability analysis for DNN observation'. En conjunto forman una huella única.

Citar esto