Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant

Yancho Todorov; Sevil Ahmed; Michail Petrov; Vasilliy Chitanov

doi:10.1109/IS.2012.6335154

Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant

Yancho Todorov^*
, Sevil Ahmed
, Michail Petrov
, Vasilliy Chitanov

^*Corresponding author for this work

Not published at VTT

Institute of Cryobiology and Food Technologies
Technical University of Sofia
Bulgarian Academy of Sciences

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

5 Citations (Scopus)

Abstract

This paper describes two methodologies for implementation of Hammerstein model by using different input-output representations into model predictive control schemes. The model nonlinearity is easily approximated using a simple Takagi-Sugeno inference, while the linear parts are flexibly introduced. As optimization procedures for predictive control are used a standard gradient optimization method and an implementation of Hildreth Quadratic Programming. A comparison between the proposed control strategies is made by simulation experiments for control of nonlinear lyophilization plant.

Original language	English
Title of host publication	2012 6th IEEE International Conference Intelligent Systems
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	316-321
ISBN (Electronic)	978-1-4673-2278-2, 978-1-4673-2277-5
ISBN (Print)	978-1-4673-2276-8
DOIs	https://doi.org/10.1109/IS.2012.6335154
Publication status	Published - 28 Nov 2012
MoE publication type	A4 Article in a conference publication
Event	2012 6th IEEE International Conference Intelligent Systems, IS 2012 - Sofia, Bulgaria Duration: 6 Sept 2012 → 8 Sept 2012

Conference

Conference	2012 6th IEEE International Conference Intelligent Systems, IS 2012
Country/Territory	Bulgaria
City	Sofia
Period	6/09/12 → 8/09/12

Keywords

fuzzy-neural models
gradient descent
Hildreth quadratic programming
lyophilization
optimization
predictive control

Access to Document

10.1109/IS.2012.6335154

Cite this

@inproceedings{abf2b0c109594281afa9eb2f0eba7956,

title = "Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant",

abstract = "This paper describes two methodologies for implementation of Hammerstein model by using different input-output representations into model predictive control schemes. The model nonlinearity is easily approximated using a simple Takagi-Sugeno inference, while the linear parts are flexibly introduced. As optimization procedures for predictive control are used a standard gradient optimization method and an implementation of Hildreth Quadratic Programming. A comparison between the proposed control strategies is made by simulation experiments for control of nonlinear lyophilization plant.",

keywords = "fuzzy-neural models, gradient descent, Hildreth quadratic programming, lyophilization, optimization, predictive control",

author = "Yancho Todorov and Sevil Ahmed and Michail Petrov and Vasilliy Chitanov",

year = "2012",

month = nov,

day = "28",

doi = "10.1109/IS.2012.6335154",

language = "English",

isbn = "978-1-4673-2276-8",

pages = "316--321",

booktitle = "2012 6th IEEE International Conference Intelligent Systems",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

note = "2012 6th IEEE International Conference Intelligent Systems, IS 2012 ; Conference date: 06-09-2012 Through 08-09-2012",

}

Todorov, Y, Ahmed, S, Petrov, M & Chitanov, V 2012, Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant. in 2012 6th IEEE International Conference Intelligent Systems., 6335154, IEEE Institute of Electrical and Electronic Engineers, pp. 316-321, 2012 6th IEEE International Conference Intelligent Systems, IS 2012, Sofia, Bulgaria, 6/09/12. https://doi.org/10.1109/IS.2012.6335154

Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant. / Todorov, Yancho; Ahmed, Sevil; Petrov, Michail et al.
2012 6th IEEE International Conference Intelligent Systems. IEEE Institute of Electrical and Electronic Engineers, 2012. p. 316-321 6335154.

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

TY - GEN

T1 - Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant

AU - Todorov, Yancho

AU - Ahmed, Sevil

AU - Petrov, Michail

AU - Chitanov, Vasilliy

PY - 2012/11/28

Y1 - 2012/11/28

N2 - This paper describes two methodologies for implementation of Hammerstein model by using different input-output representations into model predictive control schemes. The model nonlinearity is easily approximated using a simple Takagi-Sugeno inference, while the linear parts are flexibly introduced. As optimization procedures for predictive control are used a standard gradient optimization method and an implementation of Hildreth Quadratic Programming. A comparison between the proposed control strategies is made by simulation experiments for control of nonlinear lyophilization plant.

AB - This paper describes two methodologies for implementation of Hammerstein model by using different input-output representations into model predictive control schemes. The model nonlinearity is easily approximated using a simple Takagi-Sugeno inference, while the linear parts are flexibly introduced. As optimization procedures for predictive control are used a standard gradient optimization method and an implementation of Hildreth Quadratic Programming. A comparison between the proposed control strategies is made by simulation experiments for control of nonlinear lyophilization plant.

KW - fuzzy-neural models

KW - gradient descent

KW - Hildreth quadratic programming

KW - lyophilization

KW - optimization

KW - predictive control

UR - https://www.scopus.com/pages/publications/84869748115

U2 - 10.1109/IS.2012.6335154

DO - 10.1109/IS.2012.6335154

M3 - Conference article in proceedings

AN - SCOPUS:84869748115

SN - 978-1-4673-2276-8

SP - 316

EP - 321

BT - 2012 6th IEEE International Conference Intelligent Systems

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 2012 6th IEEE International Conference Intelligent Systems, IS 2012

Y2 - 6 September 2012 through 8 September 2012

ER -

Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this