Implementation of neural network based non-linear predictive

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

Implementation of neural network based non-linear predictive

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

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

Abstract

The paper describes a control method for non-linear systems based on generalized predictive control. Generalized predictive control (GPC) was developed to control linear systems including open loop unstable and non-minimum phase systems, but has also been proposed extended for the control of non-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi-Newton optimization algorithm. The performance is demonstrated on a pneumatic servo system.

Original language	English
Title of host publication	Proc. of the 4th International Conference on Neural Network and Their Applications (NEURAP98)
Place of Publication	Marseilles, France
Publication date	1998
Pages	69-78
Publication status	Published - 1998
Event	NEURAP'98 Fourth International Conference on Neural - Marseilles, France Duration: 1 Jan 1998 → …

Conference

Conference	NEURAP'98 Fourth International Conference on Neural
City	Marseilles, France
Period	01/01/1998 → …

OpenUrl availability

Full text

Cite this

@inproceedings{14968ea3f32d497b88f43d2ec5b607d9,

title = "Implementation of neural network based non-linear predictive",

abstract = "The paper describes a control method for non-linear systems based on generalized predictive control. Generalized predictive control (GPC) was developed to control linear systems including open loop unstable and non-minimum phase systems, but has also been proposed extended for the control of non-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi-Newton optimization algorithm. The performance is demonstrated on a pneumatic servo system.",

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

year = "1998",

language = "English",

pages = "69--78",

booktitle = "Proc. of the 4th International Conference on Neural Network and Their Applications (NEURAP98)",

note = "NEURAP'98 Fourth International Conference on Neural ; Conference date: 01-01-1998",

}

Implementation of neural network based non-linear predictive. / Sørensen, Paul Haase; Nørgård, Peter Magnus; Ravn, Ole et al.
Proc. of the 4th International Conference on Neural Network and Their Applications (NEURAP98). Marseilles, France, 1998. p. 69-78.

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

TY - GEN

T1 - Implementation of neural network based non-linear predictive

AU - Sørensen, Paul Haase

AU - Nørgård, Peter Magnus

AU - Ravn, Ole

AU - Poulsen, Niels Kjølstad

PY - 1998

Y1 - 1998

N2 - The paper describes a control method for non-linear systems based on generalized predictive control. Generalized predictive control (GPC) was developed to control linear systems including open loop unstable and non-minimum phase systems, but has also been proposed extended for the control of non-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi-Newton optimization algorithm. The performance is demonstrated on a pneumatic servo system.

AB - The paper describes a control method for non-linear systems based on generalized predictive control. Generalized predictive control (GPC) was developed to control linear systems including open loop unstable and non-minimum phase systems, but has also been proposed extended for the control of non-linear systems. GPC is model-based and in this paper we propose the use of a neural network for the modeling of the system. Based on the neural network model a controller with extended control horizon is developed and the implementation issues are discussed, with particular emphasis on an efficient Quasi-Newton optimization algorithm. The performance is demonstrated on a pneumatic servo system.

M3 - Article in proceedings

SP - 69

EP - 78

BT - Proc. of the 4th International Conference on Neural Network and Their Applications (NEURAP98)

CY - Marseilles, France

T2 - NEURAP'98 Fourth International Conference on Neural

Y2 - 1 January 1998

ER -

Implementation of neural network based non-linear predictive

Abstract

Conference

OpenUrl availability

Fingerprint

Cite this