Modeling and identification of heat exchanger process using least squares support vector machines

Mujahed Al-Dhaifallah; Kottakkaran Sooppy Nisar; Praveen Agarwal; Alaa Elsayyad

doi:10.2298/tsci151026204a

Modeling and identification of heat exchanger process using least squares support vector machines

Mujahed Al-Dhaifallah^*, Kottakkaran Sooppy Nisar, Praveen Agarwal, Alaa Elsayyad

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

17 Scopus citations

Abstract

In this paper, Hammerstein model and non-linear autoregressive with eXogene-ous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system with-out requiring any a priori assumptions regarding its structure. The results indi-cate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.

Original language	English
Pages (from-to)	2859-2869
Number of pages	11
Journal	Thermal Science
Volume	21
Issue number	6
DOIs	https://doi.org/10.2298/tsci151026204a
State	Published - 2017

Bibliographical note

Publisher Copyright:
© 2017 Society of Thermal Engineers of Serbia.

Keywords

Hammerstein model
Heat exchanger
Identification
Support vector machine

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment

Access to Document

10.2298/tsci151026204a

Cite this

@article{540fd9de029b4ae38eaf86df614425a9,

title = "Modeling and identification of heat exchanger process using least squares support vector machines",

abstract = "In this paper, Hammerstein model and non-linear autoregressive with eXogene-ous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system with-out requiring any a priori assumptions regarding its structure. The results indi-cate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.",

keywords = "Hammerstein model, Heat exchanger, Identification, Support vector machine",

author = "Mujahed Al-Dhaifallah and Nisar, {Kottakkaran Sooppy} and Praveen Agarwal and Alaa Elsayyad",

note = "Publisher Copyright: {\textcopyright} 2017 Society of Thermal Engineers of Serbia.",

year = "2017",

doi = "10.2298/tsci151026204a",

language = "English",

volume = "21",

pages = "2859--2869",

journal = "Thermal Science",

issn = "0354-9836",

number = "6",

}

TY - JOUR

T1 - Modeling and identification of heat exchanger process using least squares support vector machines

AU - Al-Dhaifallah, Mujahed

AU - Nisar, Kottakkaran Sooppy

AU - Agarwal, Praveen

AU - Elsayyad, Alaa

PY - 2017

Y1 - 2017

N2 - In this paper, Hammerstein model and non-linear autoregressive with eXogene-ous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system with-out requiring any a priori assumptions regarding its structure. The results indi-cate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.

AB - In this paper, Hammerstein model and non-linear autoregressive with eXogene-ous inputs (NARX) model are used to represent tubular heat exchanger. Both models have been identified using least squares support vector machines based algorithms. Both algorithms were able to model the heat exchanger system with-out requiring any a priori assumptions regarding its structure. The results indi-cate that the blackbox NARX model outperforms the NARX Hammerstein model in terms of accuracy and precision.

KW - Hammerstein model

KW - Heat exchanger

KW - Identification

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85041632145&partnerID=8YFLogxK

U2 - 10.2298/tsci151026204a

DO - 10.2298/tsci151026204a

M3 - Article

AN - SCOPUS:85041632145

SN - 0354-9836

VL - 21

SP - 2859

EP - 2869

JO - Thermal Science

JF - Thermal Science

IS - 6

ER -

Modeling and identification of heat exchanger process using least squares support vector machines

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this