Centralized direct and indirect neural control of distributed parameter systems

Ieroham S. Baruch; Rosalba Galvan-Guerra

doi:10.1007/978-3-642-04514-1_5

Centralized direct and indirect neural control of distributed parameter systems

Ieroham S. Baruch, Rosalba Galvan-Guerra

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

2 Scopus citations

Abstract

The paper proposed to use a Recurrent Neural Network Model (RNNM) for centralized modeling, identification and direct adaptive control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points plus the recirculation tank. The RNNM learning algorithm is the dynamic backpropagation one. The graphical simulation results of the distributed plant direct and indirect adaptive neural control system, exhibited good convergence and precise reference tracking, outperforming the optimal control.

Original language	English
Title of host publication	Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control
Editors	Oscar Castillo, Witold Pedrycz, Janusz Kacprzyk
Pages	63-81
Number of pages	19
DOIs	https://doi.org/10.1007/978-3-642-04514-1_5
State	Published - 2009
Externally published	Yes

Publication series

Name	Studies in Computational Intelligence
Volume	257
ISSN (Print)	1860-949X

Keywords

Anaerobic digestion bioprocess
Backpropagation learning
Direct and indirect adaptive neural control
Distributed parameter system
Recurrent neural network model
System identification
Wastewater treatment bioreactor

Access to Document

10.1007/978-3-642-04514-1_5

Cite this

@inbook{7d9bd7657fc84cc5996771e93360c441,

title = "Centralized direct and indirect neural control of distributed parameter systems",

abstract = "The paper proposed to use a Recurrent Neural Network Model (RNNM) for centralized modeling, identification and direct adaptive control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points plus the recirculation tank. The RNNM learning algorithm is the dynamic backpropagation one. The graphical simulation results of the distributed plant direct and indirect adaptive neural control system, exhibited good convergence and precise reference tracking, outperforming the optimal control.",

keywords = "Anaerobic digestion bioprocess, Backpropagation learning, Direct and indirect adaptive neural control, Distributed parameter system, Recurrent neural network model, System identification, Wastewater treatment bioreactor",

author = "Baruch, {Ieroham S.} and Rosalba Galvan-Guerra",

year = "2009",

doi = "10.1007/978-3-642-04514-1_5",

language = "Ingl{\'e}s",

isbn = "9783642045134",

series = "Studies in Computational Intelligence",

pages = "63--81",

editor = "Oscar Castillo and Witold Pedrycz and Janusz Kacprzyk",

booktitle = "Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control",

}

Centralized direct and indirect neural control of distributed parameter systems. / Baruch, Ieroham S.; Galvan-Guerra, Rosalba.
Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control. ed. / Oscar Castillo; Witold Pedrycz; Janusz Kacprzyk. 2009. p. 63-81 (Studies in Computational Intelligence; Vol. 257).

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

TY - CHAP

T1 - Centralized direct and indirect neural control of distributed parameter systems

AU - Baruch, Ieroham S.

AU - Galvan-Guerra, Rosalba

PY - 2009

Y1 - 2009

N2 - The paper proposed to use a Recurrent Neural Network Model (RNNM) for centralized modeling, identification and direct adaptive control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points plus the recirculation tank. The RNNM learning algorithm is the dynamic backpropagation one. The graphical simulation results of the distributed plant direct and indirect adaptive neural control system, exhibited good convergence and precise reference tracking, outperforming the optimal control.

AB - The paper proposed to use a Recurrent Neural Network Model (RNNM) for centralized modeling, identification and direct adaptive control of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system. The analytical model of the digestion bioprocess represented a distributed parameter system, which is reduced to a lumped system using the orthogonal collocation method, applied in three collocation points plus the recirculation tank. The RNNM learning algorithm is the dynamic backpropagation one. The graphical simulation results of the distributed plant direct and indirect adaptive neural control system, exhibited good convergence and precise reference tracking, outperforming the optimal control.

KW - Anaerobic digestion bioprocess

KW - Backpropagation learning

KW - Direct and indirect adaptive neural control

KW - Distributed parameter system

KW - Recurrent neural network model

KW - System identification

KW - Wastewater treatment bioreactor

UR - http://www.scopus.com/inward/record.url?scp=70350151409&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-04514-1_5

DO - 10.1007/978-3-642-04514-1_5

M3 - Capítulo

AN - SCOPUS:70350151409

SN - 9783642045134

T3 - Studies in Computational Intelligence

SP - 63

EP - 81

BT - Evolutionary Design of Intelligent Systems in Modeling, Simulation and Control

A2 - Castillo, Oscar

A2 - Pedrycz, Witold

A2 - Kacprzyk, Janusz

ER -

Centralized direct and indirect neural control of distributed parameter systems

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this