Application of support vector machine modeling on phase distribution in the riser of an LSCFB reactor

Shaikh A. Razzak; Muhammad I. Hossain; Syed M. Rahman; Mohammad M. Hossain

doi:10.1515/ijcre-2013-0122

Application of support vector machine modeling on phase distribution in the riser of an LSCFB reactor

Shaikh A. Razzak, Muhammad I. Hossain, Syed M. Rahman, Mohammad M. Hossain^*

^*Corresponding author for this work

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

5 Scopus citations

Abstract

Support vector machine (SVM) modeling approach is applied to predict the solids holdups distribution of a liquid-solid circulating fluidized bed (LSCFB) riser. The SVM model is developed/trained using experimental data collected from a pilot-scale LSCFB reactor. Two different size glass bead particles (500 μm (GB-500) and 1,290 μm (GB-1290)) are used as solid phase, and water is used as liquid phase. The trained model successfully predicted the experimental solids holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The goodness of the model prediction is verified by using different statistical performance indicators. For the both sizes of particles, the mean absolute error is found to be less than 5%. The correlation coefficients (0.998 for GB-500 and 0.994 for GB-1290) also show favorable indications of the suitability of SVM approach in predicting the solids holdup of the LSCFB system.

Original language	English
Pages (from-to)	123-134
Number of pages	12
Journal	International Journal of Chemical Reactor Engineering
Volume	12
Issue number	1
DOIs	https://doi.org/10.1515/ijcre-2013-0122
State	Published - 1 Jan 2014

Bibliographical note

Funding Information:
Acknowledgments: The authors would like to gratefully acknowledge the support provided by King Abdulaziz City for Science and Technology (KACST) through the Science & Technology Unit at King Fahd University of Petroleum & Minerals for funding this work through project no. KACST # T-K-11-0431. The author also gratefully acknowledges the contributions of Powder Technology Research Center and University of Western Ontario for the experimental part of this work.

Publisher Copyright:
© 2014 by De Gruyter 2014.

Keywords

fluidization
hydrodynamics
normalized superficial liquid velocity
solids holdups
support vector machine
terminal settling velocity

ASJC Scopus subject areas

Chemical Engineering (all)

Access to Document

10.1515/ijcre-2013-0122

Cite this

@article{04a6a06ff92243e8952f497b50f9da98,

title = "Application of support vector machine modeling on phase distribution in the riser of an LSCFB reactor",

abstract = "Support vector machine (SVM) modeling approach is applied to predict the solids holdups distribution of a liquid-solid circulating fluidized bed (LSCFB) riser. The SVM model is developed/trained using experimental data collected from a pilot-scale LSCFB reactor. Two different size glass bead particles (500 μm (GB-500) and 1,290 μm (GB-1290)) are used as solid phase, and water is used as liquid phase. The trained model successfully predicted the experimental solids holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The goodness of the model prediction is verified by using different statistical performance indicators. For the both sizes of particles, the mean absolute error is found to be less than 5%. The correlation coefficients (0.998 for GB-500 and 0.994 for GB-1290) also show favorable indications of the suitability of SVM approach in predicting the solids holdup of the LSCFB system.",

keywords = "fluidization, hydrodynamics, normalized superficial liquid velocity, solids holdups, support vector machine, terminal settling velocity",

author = "Razzak, {Shaikh A.} and Hossain, {Muhammad I.} and Rahman, {Syed M.} and Hossain, {Mohammad M.}",

note = "Funding Information: Acknowledgments: The authors would like to gratefully acknowledge the support provided by King Abdulaziz City for Science and Technology (KACST) through the Science & Technology Unit at King Fahd University of Petroleum & Minerals for funding this work through project no. KACST # T-K-11-0431. The author also gratefully acknowledges the contributions of Powder Technology Research Center and University of Western Ontario for the experimental part of this work. Publisher Copyright: {\textcopyright} 2014 by De Gruyter 2014.",

year = "2014",

month = jan,

day = "1",

doi = "10.1515/ijcre-2013-0122",

language = "English",

volume = "12",

pages = "123--134",

journal = "International Journal of Chemical Reactor Engineering",

issn = "1542-6580",

publisher = "Walter de Gruyter GmbH",

number = "1",

}

TY - JOUR

T1 - Application of support vector machine modeling on phase distribution in the riser of an LSCFB reactor

AU - Razzak, Shaikh A.

AU - Hossain, Muhammad I.

AU - Rahman, Syed M.

AU - Hossain, Mohammad M.

N1 - Funding Information: Acknowledgments: The authors would like to gratefully acknowledge the support provided by King Abdulaziz City for Science and Technology (KACST) through the Science & Technology Unit at King Fahd University of Petroleum & Minerals for funding this work through project no. KACST # T-K-11-0431. The author also gratefully acknowledges the contributions of Powder Technology Research Center and University of Western Ontario for the experimental part of this work. Publisher Copyright: © 2014 by De Gruyter 2014.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Support vector machine (SVM) modeling approach is applied to predict the solids holdups distribution of a liquid-solid circulating fluidized bed (LSCFB) riser. The SVM model is developed/trained using experimental data collected from a pilot-scale LSCFB reactor. Two different size glass bead particles (500 μm (GB-500) and 1,290 μm (GB-1290)) are used as solid phase, and water is used as liquid phase. The trained model successfully predicted the experimental solids holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The goodness of the model prediction is verified by using different statistical performance indicators. For the both sizes of particles, the mean absolute error is found to be less than 5%. The correlation coefficients (0.998 for GB-500 and 0.994 for GB-1290) also show favorable indications of the suitability of SVM approach in predicting the solids holdup of the LSCFB system.

AB - Support vector machine (SVM) modeling approach is applied to predict the solids holdups distribution of a liquid-solid circulating fluidized bed (LSCFB) riser. The SVM model is developed/trained using experimental data collected from a pilot-scale LSCFB reactor. Two different size glass bead particles (500 μm (GB-500) and 1,290 μm (GB-1290)) are used as solid phase, and water is used as liquid phase. The trained model successfully predicted the experimental solids holdups of the LSCFB riser under different operating parameters. It is observed that the model predicted cross-sectional average of solids holdups in the axial directions and radial flow structure are well agreement with the experimental values. The goodness of the model prediction is verified by using different statistical performance indicators. For the both sizes of particles, the mean absolute error is found to be less than 5%. The correlation coefficients (0.998 for GB-500 and 0.994 for GB-1290) also show favorable indications of the suitability of SVM approach in predicting the solids holdup of the LSCFB system.

KW - fluidization

KW - hydrodynamics

KW - normalized superficial liquid velocity

KW - solids holdups

KW - support vector machine

KW - terminal settling velocity

UR - http://www.scopus.com/inward/record.url?scp=84907775885&partnerID=8YFLogxK

U2 - 10.1515/ijcre-2013-0122

DO - 10.1515/ijcre-2013-0122

M3 - Article

AN - SCOPUS:84907775885

SN - 1542-6580

VL - 12

SP - 123

EP - 134

JO - International Journal of Chemical Reactor Engineering

JF - International Journal of Chemical Reactor Engineering

IS - 1

ER -

Application of support vector machine modeling on phase distribution in the riser of an LSCFB reactor

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this