Stability of a neural predictive controller scheme on a neural model

Jim Benjamin Luther; Paul Haase Sørensen

doi:10.1109/IJCNN.1999.832708

Stability of a neural predictive controller scheme on a neural model

Jim Benjamin Luther
, Paul Haase Sørensen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

399 Downloads (Orbit)

Abstract

In previous works presenting various forms of neural-network-based predictive controllers, the main emphasis has been on the implementation aspects, i.e. the development of a robust optimization algorithm for the controller, which will be able to perform in real time. However, the stability issue has not been addressed specifically for these controllers. On the other hand a number of results concerning the stability of receding horizon controllers on a nonlinear system exist. In this paper we present a proof of stability for a predictive controller controlling a neural network model. The resulting controller is tested on a nonlinear pneumatic servo system.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Volume	3
Publication date	2009
Pages	2087-2091
ISBN (Print)	0-7803-5529-6
DOIs	https://doi.org/10.1109/IJCNN.1999.832708
Publication status	Published - 2009
Event	1999 IEEE International Joint Conference on Neural Networks - Washington, United States Duration: 10 Jul 1999 → 16 Jul 1999

Conference

Conference	1999 IEEE International Joint Conference on Neural Networks
Country/Territory	United States
City	Washington
Period	10/07/1999 → 16/07/1999

Bibliographical note

Copyright: 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/IJCNN.1999.832708

Full textFinal published version, 301 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{e58e9c05971c48b8a1f78000ff0c2908,

title = "Stability of a neural predictive controller scheme on a neural model",

abstract = "In previous works presenting various forms of neural-network-based predictive controllers, the main emphasis has been on the implementation aspects, i.e. the development of a robust optimization algorithm for the controller, which will be able to perform in real time. However, the stability issue has not been addressed specifically for these controllers. On the other hand a number of results concerning the stability of receding horizon controllers on a nonlinear system exist. In this paper we present a proof of stability for a predictive controller controlling a neural network model. The resulting controller is tested on a nonlinear pneumatic servo system.",

author = "Luther, \{Jim Benjamin\} and S{\o}rensen, \{Paul Haase\}",

note = "Copyright: 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; 1999 IEEE International Joint Conference on Neural Networks, IJCNN'99 ; Conference date: 10-07-1999 Through 16-07-1999",

year = "2009",

doi = "10.1109/IJCNN.1999.832708",

language = "English",

isbn = "0-7803-5529-6",

volume = "3",

pages = "2087--2091",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Stability of a neural predictive controller scheme on a neural model

AU - Luther, Jim Benjamin

AU - Sørensen, Paul Haase

N1 - Copyright: 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

PY - 2009

Y1 - 2009

N2 - In previous works presenting various forms of neural-network-based predictive controllers, the main emphasis has been on the implementation aspects, i.e. the development of a robust optimization algorithm for the controller, which will be able to perform in real time. However, the stability issue has not been addressed specifically for these controllers. On the other hand a number of results concerning the stability of receding horizon controllers on a nonlinear system exist. In this paper we present a proof of stability for a predictive controller controlling a neural network model. The resulting controller is tested on a nonlinear pneumatic servo system.

AB - In previous works presenting various forms of neural-network-based predictive controllers, the main emphasis has been on the implementation aspects, i.e. the development of a robust optimization algorithm for the controller, which will be able to perform in real time. However, the stability issue has not been addressed specifically for these controllers. On the other hand a number of results concerning the stability of receding horizon controllers on a nonlinear system exist. In this paper we present a proof of stability for a predictive controller controlling a neural network model. The resulting controller is tested on a nonlinear pneumatic servo system.

U2 - 10.1109/IJCNN.1999.832708

DO - 10.1109/IJCNN.1999.832708

M3 - Article in proceedings

SN - 0-7803-5529-6

VL - 3

SP - 2087

EP - 2091

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - 1999 IEEE International Joint Conference on Neural Networks

Y2 - 10 July 1999 through 16 July 1999

ER -

Stability of a neural predictive controller scheme on a neural model

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this