Neuro-observer based on backstepping technique for distributed parameters systems

Rita Q. Fuentes, Isaac Chairez, Alexander Poznyak

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

The aim of this manuscript is to present an observer design for partially known distributed parameters systems described by Partial Differential Equations (PDE) using Differential Neural Networks (DNN) methodology and backstepping-like procedure. A Volterra-like integral transformation is used to change the coordinates of the error dynamics into exponentially stable target system. This gives as a result the output injection functions of the observer which are obtained by solving a PDE system. DNN are used to find an explicit solution to the PDE system and to make the observer gains to be discontinuous which have well known advantages. Theoretical results were proved using the Lyapunov theory. A numerical example demonstrates the proposed method effectiveness. © 2012 IEEE.

Conference

ConferenceCCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control
Period1/12/12 → …

Fingerprint

Backstepping
Partial differential equations
Neural networks

Cite this

Fuentes, R. Q., Chairez, I., & Poznyak, A. (2012). Neuro-observer based on backstepping technique for distributed parameters systems. Paper presented at CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control, . https://doi.org/10.1109/ICEEE.2012.6421213
Fuentes, Rita Q. ; Chairez, Isaac ; Poznyak, Alexander. / Neuro-observer based on backstepping technique for distributed parameters systems. Paper presented at CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control, .
@conference{08e14046a0fb40b6ac197ebdd7a3623a,
title = "Neuro-observer based on backstepping technique for distributed parameters systems",
abstract = "The aim of this manuscript is to present an observer design for partially known distributed parameters systems described by Partial Differential Equations (PDE) using Differential Neural Networks (DNN) methodology and backstepping-like procedure. A Volterra-like integral transformation is used to change the coordinates of the error dynamics into exponentially stable target system. This gives as a result the output injection functions of the observer which are obtained by solving a PDE system. DNN are used to find an explicit solution to the PDE system and to make the observer gains to be discontinuous which have well known advantages. Theoretical results were proved using the Lyapunov theory. A numerical example demonstrates the proposed method effectiveness. {\circledC} 2012 IEEE.",
author = "Fuentes, {Rita Q.} and Isaac Chairez and Alexander Poznyak",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ICEEE.2012.6421213",
language = "American English",
note = "CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control ; Conference date: 01-12-2012",

}

Fuentes, RQ, Chairez, I & Poznyak, A 2012, 'Neuro-observer based on backstepping technique for distributed parameters systems', Paper presented at CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control, 1/12/12. https://doi.org/10.1109/ICEEE.2012.6421213

Neuro-observer based on backstepping technique for distributed parameters systems. / Fuentes, Rita Q.; Chairez, Isaac; Poznyak, Alexander.

2012. Paper presented at CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Neuro-observer based on backstepping technique for distributed parameters systems

AU - Fuentes, Rita Q.

AU - Chairez, Isaac

AU - Poznyak, Alexander

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The aim of this manuscript is to present an observer design for partially known distributed parameters systems described by Partial Differential Equations (PDE) using Differential Neural Networks (DNN) methodology and backstepping-like procedure. A Volterra-like integral transformation is used to change the coordinates of the error dynamics into exponentially stable target system. This gives as a result the output injection functions of the observer which are obtained by solving a PDE system. DNN are used to find an explicit solution to the PDE system and to make the observer gains to be discontinuous which have well known advantages. Theoretical results were proved using the Lyapunov theory. A numerical example demonstrates the proposed method effectiveness. © 2012 IEEE.

AB - The aim of this manuscript is to present an observer design for partially known distributed parameters systems described by Partial Differential Equations (PDE) using Differential Neural Networks (DNN) methodology and backstepping-like procedure. A Volterra-like integral transformation is used to change the coordinates of the error dynamics into exponentially stable target system. This gives as a result the output injection functions of the observer which are obtained by solving a PDE system. DNN are used to find an explicit solution to the PDE system and to make the observer gains to be discontinuous which have well known advantages. Theoretical results were proved using the Lyapunov theory. A numerical example demonstrates the proposed method effectiveness. © 2012 IEEE.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84874447128&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84874447128&origin=inward

U2 - 10.1109/ICEEE.2012.6421213

DO - 10.1109/ICEEE.2012.6421213

M3 - Paper

ER -

Fuentes RQ, Chairez I, Poznyak A. Neuro-observer based on backstepping technique for distributed parameters systems. 2012. Paper presented at CCE 2012 - 2012 9th International Conference on Electrical Engineering, Computing Science and Automatic Control, . https://doi.org/10.1109/ICEEE.2012.6421213