Intelligent Predictive Control of Nonlienar Processes Using

Peter Magnus Nørgård; Paul Haase Sørensen; Niels Kjølstad Poulsen; Ole Ravn; Lars Kai Hansen

doi:10.1109/ISIC.1996.556218

Intelligent Predictive Control of Nonlienar Processes Using

Peter Magnus Nørgård, Paul Haase Sørensen, Niels Kjølstad Poulsen, Ole Ravn, Lars Kai Hansen

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

566 Downloads (Pure)

Abstract

This paper presents a novel approach to design of generalized predictive controllers (GPC) for nonlinear processes. A neural network is used for modelling the process and a gain-scheduling type of GPC is subsequently designed. The combination of neural network models and predictive control has frequently been discussed in the neural network community. This paper proposes an approximate scheme, the approximate predictive control (APC), which facilitates the implementation and gives a substantial reduction in the required amount of computations. The method is based on a technique for extracting linear models from a nonlinear neural network and using them in designing the control system. The performance of the controller is demonstrated in a simulation study of a pneumatic servo system

Original language	English
Title of host publication	Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on
Place of Publication	Dearborn, Michigan, USA
Publisher	IEEE
Publication date	1996
Pages	301-306
ISBN (Print)	0-7803-2978-3
DOIs	https://doi.org/10.1109/ISIC.1996.556218
Publication status	Published - 1996
Event	1996 IEEE International Symposium on Intelligent Control - Dearborn, United States Duration: 15 Sept 1996 → 18 Sept 1996 Conference number: 11

Conference

Conference	1996 IEEE International Symposium on Intelligent Control
Number	11
Country/Territory	United States
City	Dearborn
Period	15/09/1996 → 18/09/1996

Bibliographical note

Copyright: 1996 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/ISIC.1996.556218

N rgaardFinal published version, 503 KB

OpenUrl availability

Full text

Cite this

@inproceedings{331f55392e294391b2c25dfd444737d2,

title = "Intelligent Predictive Control of Nonlienar Processes Using",

abstract = "This paper presents a novel approach to design of generalized predictive controllers (GPC) for nonlinear processes. A neural network is used for modelling the process and a gain-scheduling type of GPC is subsequently designed. The combination of neural network models and predictive control has frequently been discussed in the neural network community. This paper proposes an approximate scheme, the approximate predictive control (APC), which facilitates the implementation and gives a substantial reduction in the required amount of computations. The method is based on a technique for extracting linear models from a nonlinear neural network and using them in designing the control system. The performance of the controller is demonstrated in a simulation study of a pneumatic servo system",

author = "N{\o}rg{\aa}rd, {Peter Magnus} and S{\o}rensen, {Paul Haase} and Poulsen, {Niels Kj{\o}lstad} and Ole Ravn and Hansen, {Lars Kai}",

note = "Copyright: 1996 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; 1996 IEEE International Symposium on Intelligent Control, ISIC 1996 ; Conference date: 15-09-1996 Through 18-09-1996",

year = "1996",

doi = "10.1109/ISIC.1996.556218",

language = "English",

isbn = "0-7803-2978-3",

pages = "301--306",

booktitle = "Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on",

publisher = "IEEE",

address = "United States",

}

Nørgård, PM, Sørensen, PH, Poulsen, NK, Ravn, O & Hansen, LK 1996, Intelligent Predictive Control of Nonlienar Processes Using. in Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on. IEEE, Dearborn, Michigan, USA, pp. 301-306, 1996 IEEE International Symposium on Intelligent Control, Dearborn, Michigan, United States, 15/09/1996. https://doi.org/10.1109/ISIC.1996.556218

Intelligent Predictive Control of Nonlienar Processes Using. / Nørgård, Peter Magnus; Sørensen, Paul Haase; Poulsen, Niels Kjølstad et al.
Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on. Dearborn, Michigan, USA: IEEE, 1996. p. 301-306.

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

TY - GEN

T1 - Intelligent Predictive Control of Nonlienar Processes Using

AU - Nørgård, Peter Magnus

AU - Sørensen, Paul Haase

AU - Poulsen, Niels Kjølstad

AU - Ravn, Ole

AU - Hansen, Lars Kai

N1 - Conference code: 11

PY - 1996

Y1 - 1996

N2 - This paper presents a novel approach to design of generalized predictive controllers (GPC) for nonlinear processes. A neural network is used for modelling the process and a gain-scheduling type of GPC is subsequently designed. The combination of neural network models and predictive control has frequently been discussed in the neural network community. This paper proposes an approximate scheme, the approximate predictive control (APC), which facilitates the implementation and gives a substantial reduction in the required amount of computations. The method is based on a technique for extracting linear models from a nonlinear neural network and using them in designing the control system. The performance of the controller is demonstrated in a simulation study of a pneumatic servo system

AB - This paper presents a novel approach to design of generalized predictive controllers (GPC) for nonlinear processes. A neural network is used for modelling the process and a gain-scheduling type of GPC is subsequently designed. The combination of neural network models and predictive control has frequently been discussed in the neural network community. This paper proposes an approximate scheme, the approximate predictive control (APC), which facilitates the implementation and gives a substantial reduction in the required amount of computations. The method is based on a technique for extracting linear models from a nonlinear neural network and using them in designing the control system. The performance of the controller is demonstrated in a simulation study of a pneumatic servo system

U2 - 10.1109/ISIC.1996.556218

DO - 10.1109/ISIC.1996.556218

M3 - Article in proceedings

SN - 0-7803-2978-3

SP - 301

EP - 306

BT - Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on

PB - IEEE

CY - Dearborn, Michigan, USA

T2 - 1996 IEEE International Symposium on Intelligent Control

Y2 - 15 September 1996 through 18 September 1996

ER -

Intelligent Predictive Control of Nonlienar Processes Using

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this