Predictive control using feedback linearization based on dynamic neural models

Jiamei Deng; V. M. Becerra; R. Stobart

doi:10.1109/ICSMC.2007.4413858

Predictive control using feedback linearization based on dynamic neural models

Jiamei Deng, V. M. Becerra, R. Stobart

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a hybrid control strategy integrating dynamic neural networks and feedback linearization into a predictive control scheme. Feedback linearization is an important nonlinear control technique which transforms a nonlinear system into a linear system using nonlinear transformations and a model of the plant. In this work, empirical models based on dynamic neural networks have been employed. Dynamic neural networks are mathematical structures described by differential equations, which can be trained to approximate general nonlinear systems. A case study based on a mixing process is presented.

Original language	English
Title of host publication	IEEE International Conference on Systems, Man and Cybernetics (ISIC 2007)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2716 - 2721
ISBN (Electronic)	9781424409914
ISBN (Print)	9781424409907
DOIs	https://doi.org/10.1109/ICSMC.2007.4413858
Publication status	Published - 2007

Keywords

predictive control, neural networks, nonlinear predictive control , NETWORKS, SYSTEMS

Access to Document

10.1109/ICSMC.2007.4413858

Cite this

@inproceedings{b2428eaf10c445008eb3d334cd370663,

title = "Predictive control using feedback linearization based on dynamic neural models",

abstract = "This paper presents a hybrid control strategy integrating dynamic neural networks and feedback linearization into a predictive control scheme. Feedback linearization is an important nonlinear control technique which transforms a nonlinear system into a linear system using nonlinear transformations and a model of the plant. In this work, empirical models based on dynamic neural networks have been employed. Dynamic neural networks are mathematical structures described by differential equations, which can be trained to approximate general nonlinear systems. A case study based on a mixing process is presented.",

keywords = "predictive control, neural networks, nonlinear predictive control , NETWORKS, SYSTEMS",

author = "Jiamei Deng and Becerra, {V. M.} and R. Stobart",

year = "2007",

doi = "10.1109/ICSMC.2007.4413858",

language = "English",

isbn = "9781424409907",

pages = "2716 -- 2721",

booktitle = "IEEE International Conference on Systems, Man and Cybernetics (ISIC 2007)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Predictive control using feedback linearization based on dynamic neural models. / Deng, Jiamei; Becerra, V. M.; Stobart, R.
IEEE International Conference on Systems, Man and Cybernetics (ISIC 2007). Piscataway: Institute of Electrical and Electronics Engineers Inc., 2007. p. 2716 - 2721.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Predictive control using feedback linearization based on dynamic neural models

AU - Deng, Jiamei

AU - Becerra, V. M.

AU - Stobart, R.

PY - 2007

Y1 - 2007

N2 - This paper presents a hybrid control strategy integrating dynamic neural networks and feedback linearization into a predictive control scheme. Feedback linearization is an important nonlinear control technique which transforms a nonlinear system into a linear system using nonlinear transformations and a model of the plant. In this work, empirical models based on dynamic neural networks have been employed. Dynamic neural networks are mathematical structures described by differential equations, which can be trained to approximate general nonlinear systems. A case study based on a mixing process is presented.

AB - This paper presents a hybrid control strategy integrating dynamic neural networks and feedback linearization into a predictive control scheme. Feedback linearization is an important nonlinear control technique which transforms a nonlinear system into a linear system using nonlinear transformations and a model of the plant. In this work, empirical models based on dynamic neural networks have been employed. Dynamic neural networks are mathematical structures described by differential equations, which can be trained to approximate general nonlinear systems. A case study based on a mixing process is presented.

KW - predictive control, neural networks, nonlinear predictive control , NETWORKS, SYSTEMS

U2 - 10.1109/ICSMC.2007.4413858

DO - 10.1109/ICSMC.2007.4413858

M3 - Conference contribution

SN - 9781424409907

SP - 2716

EP - 2721

BT - IEEE International Conference on Systems, Man and Cybernetics (ISIC 2007)

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

ER -

Predictive control using feedback linearization based on dynamic neural models

Abstract

Keywords

Access to Document

Fingerprint

Cite this