A novel approach to modelling and exploiting uncertainty in stochastic control systems

Randa Herzallah; David Lowe

doi:10.1007/3-540-46084-5_130

A novel approach to modelling and exploiting uncertainty in stochastic control systems

Randa Herzallah, David Lowe

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

We consider an inversion-based neurocontroller for solving control problems of uncertain nonlinear systems. Classical approaches do not use uncertainty information in the neural network models. In this paper we show how we can exploit knowledge of this uncertainty to our advantage by developing a novel robust inverse control method. Simulations on a nonlinear uncertain second order system illustrate the approach.

Original language	English
Title of host publication	Artificial neural networks — ICANN 2002
Subtitle of host publication	international conference Madrid, Spain, August 28–30, 2002 Proceedings
Editors	José R. Dorronsoro
Place of Publication	Berlin (DE)
Publisher	Springer
Pages	801-806
Number of pages	6
ISBN (Print)	978-3-540-44074-1
DOIs	https://doi.org/10.1007/3-540-46084-5_130
Publication status	Published - 1 Jan 2002
Event	Artificial Neural Networks 2002 - Madrid, Spain Duration: 28 Aug 2002 → 30 Aug 2002

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	2415
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Artificial Neural Networks 2002
Abbreviated title	ICANN 2002
Country/Territory	Spain
City	Madrid
Period	28/08/02 → 30/08/02

Keywords

neurocontroller
nonlinear systems
neural network models
inverse control method
Simulations

Access to Document

10.1007/3-540-46084-5_130

Cite this

Herzallah, R., & Lowe, D. (2002). A novel approach to modelling and exploiting uncertainty in stochastic control systems. In J. R. Dorronsoro (Ed.), Artificial neural networks — ICANN 2002: international conference Madrid, Spain, August 28–30, 2002 Proceedings (pp. 801-806). (Lecture notes in computer science; Vol. 2415). Springer. https://doi.org/10.1007/3-540-46084-5_130

@inproceedings{b47da9ba49664f9ca2a4452d49a0aa0e,

title = "A novel approach to modelling and exploiting uncertainty in stochastic control systems",

abstract = "We consider an inversion-based neurocontroller for solving control problems of uncertain nonlinear systems. Classical approaches do not use uncertainty information in the neural network models. In this paper we show how we can exploit knowledge of this uncertainty to our advantage by developing a novel robust inverse control method. Simulations on a nonlinear uncertain second order system illustrate the approach.",

keywords = "neurocontroller, nonlinear systems, neural network models, inverse control method, Simulations",

author = "Randa Herzallah and David Lowe",

year = "2002",

month = jan,

day = "1",

doi = "10.1007/3-540-46084-5_130",

language = "English",

isbn = "978-3-540-44074-1",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "801--806",

editor = "Dorronsoro, {Jos{\'e} R.}",

booktitle = "Artificial neural networks — ICANN 2002",

address = "Germany",

note = "Artificial Neural Networks 2002, ICANN 2002 ; Conference date: 28-08-2002 Through 30-08-2002",

}

Herzallah, R & Lowe, D 2002, A novel approach to modelling and exploiting uncertainty in stochastic control systems. in JR Dorronsoro (ed.), Artificial neural networks — ICANN 2002: international conference Madrid, Spain, August 28–30, 2002 Proceedings. Lecture notes in computer science, vol. 2415, Springer, Berlin (DE), pp. 801-806, Artificial Neural Networks 2002, Madrid, Spain, 28/08/02. https://doi.org/10.1007/3-540-46084-5_130

A novel approach to modelling and exploiting uncertainty in stochastic control systems. / Herzallah, Randa; Lowe, David.
Artificial neural networks — ICANN 2002: international conference Madrid, Spain, August 28–30, 2002 Proceedings. ed. / José R. Dorronsoro. Berlin (DE): Springer, 2002. p. 801-806 (Lecture notes in computer science; Vol. 2415).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - A novel approach to modelling and exploiting uncertainty in stochastic control systems

AU - Herzallah, Randa

AU - Lowe, David

PY - 2002/1/1

Y1 - 2002/1/1

N2 - We consider an inversion-based neurocontroller for solving control problems of uncertain nonlinear systems. Classical approaches do not use uncertainty information in the neural network models. In this paper we show how we can exploit knowledge of this uncertainty to our advantage by developing a novel robust inverse control method. Simulations on a nonlinear uncertain second order system illustrate the approach.

AB - We consider an inversion-based neurocontroller for solving control problems of uncertain nonlinear systems. Classical approaches do not use uncertainty information in the neural network models. In this paper we show how we can exploit knowledge of this uncertainty to our advantage by developing a novel robust inverse control method. Simulations on a nonlinear uncertain second order system illustrate the approach.

KW - neurocontroller

KW - nonlinear systems

KW - neural network models

KW - inverse control method

KW - Simulations

UR - http://www.scopus.com/inward/record.url?scp=84902178195&partnerID=8YFLogxK

UR - http://www.springerlink.com/content/y9d4wjgt2w4jk45v/

U2 - 10.1007/3-540-46084-5_130

DO - 10.1007/3-540-46084-5_130

M3 - Conference publication

SN - 978-3-540-44074-1

T3 - Lecture notes in computer science

SP - 801

EP - 806

BT - Artificial neural networks — ICANN 2002

A2 - Dorronsoro, José R.

PB - Springer

CY - Berlin (DE)

T2 - Artificial Neural Networks 2002

Y2 - 28 August 2002 through 30 August 2002

ER -

A novel approach to modelling and exploiting uncertainty in stochastic control systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this