Quantitative structure relative volatility relationship model for extractive distillation of ethylbenzene/ p -xylene mixtures

Young Mook Kang, Yukwon Jeon, Gicheon Lee, Hyoungjun Son, Sung Wook Row, Seonghwan Choi, Young Jong Seo, Young Hwan Chu, Jae Min Shin, Yong Gun Shul, Kyoung Tai No

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Extractive distillation is a highly effective process for the separation of compound pairs having low relative volatility values, such as ethylbenzene (EB) and p-xylene (PX) mixtures. Many solvents or solvent mixtures have been screened experimentally to identify a suitable extraction agent for EB/PX mixtures. Because the number of possible solvent and solvent mixture candidates is high, it is necessary to introduce a computer-aided extraction performance prediction technique. In this study, a knowledge-based quantitative structure relative volatility relationship (QSRVR) model was developed using multiple linear regression (MLR) and artificial neural network (ANN) models, with each model having five descriptors. The root-mean-square errors (RMSE) of the training and test sets for the MLR model were calculated as 0.01486 and 0.00905, while their squared correlation coefficients (R2) were 0.867 and 0.941, respectively. The R2 and RMSE values of the total data set for the MLR model were 0.878 and 0.01408, and for the ANN model the values were 0.949 and 0.00929, respectively. The predictive ability of both models is sufficient for identifying suitable extractive distillation solvents for the separation of EB/PX mixtures.

Original languageEnglish
Pages (from-to)11159-11166
Number of pages8
JournalIndustrial and Engineering Chemistry Research
Volume53
Issue number27
DOIs
Publication statusPublished - 2014 Jul 9

Fingerprint

Ethylbenzene
Xylene
Distillation
Linear regression
Mean square error
Neural networks
4-xylene
ethylbenzene

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Chemical Engineering(all)
  • Industrial and Manufacturing Engineering

Cite this

Kang, Young Mook ; Jeon, Yukwon ; Lee, Gicheon ; Son, Hyoungjun ; Row, Sung Wook ; Choi, Seonghwan ; Seo, Young Jong ; Chu, Young Hwan ; Shin, Jae Min ; Shul, Yong Gun ; No, Kyoung Tai. / Quantitative structure relative volatility relationship model for extractive distillation of ethylbenzene/ p -xylene mixtures. In: Industrial and Engineering Chemistry Research. 2014 ; Vol. 53, No. 27. pp. 11159-11166.
@article{70b0cd835d5845678e906cb12a867f09,
title = "Quantitative structure relative volatility relationship model for extractive distillation of ethylbenzene/ p -xylene mixtures",
abstract = "Extractive distillation is a highly effective process for the separation of compound pairs having low relative volatility values, such as ethylbenzene (EB) and p-xylene (PX) mixtures. Many solvents or solvent mixtures have been screened experimentally to identify a suitable extraction agent for EB/PX mixtures. Because the number of possible solvent and solvent mixture candidates is high, it is necessary to introduce a computer-aided extraction performance prediction technique. In this study, a knowledge-based quantitative structure relative volatility relationship (QSRVR) model was developed using multiple linear regression (MLR) and artificial neural network (ANN) models, with each model having five descriptors. The root-mean-square errors (RMSE) of the training and test sets for the MLR model were calculated as 0.01486 and 0.00905, while their squared correlation coefficients (R2) were 0.867 and 0.941, respectively. The R2 and RMSE values of the total data set for the MLR model were 0.878 and 0.01408, and for the ANN model the values were 0.949 and 0.00929, respectively. The predictive ability of both models is sufficient for identifying suitable extractive distillation solvents for the separation of EB/PX mixtures.",
author = "Kang, {Young Mook} and Yukwon Jeon and Gicheon Lee and Hyoungjun Son and Row, {Sung Wook} and Seonghwan Choi and Seo, {Young Jong} and Chu, {Young Hwan} and Shin, {Jae Min} and Shul, {Yong Gun} and No, {Kyoung Tai}",
year = "2014",
month = "7",
day = "9",
doi = "10.1021/ie403235r",
language = "English",
volume = "53",
pages = "11159--11166",
journal = "Industrial and Engineering Chemistry Research",
issn = "0888-5885",
number = "27",

}

Quantitative structure relative volatility relationship model for extractive distillation of ethylbenzene/ p -xylene mixtures. / Kang, Young Mook; Jeon, Yukwon; Lee, Gicheon; Son, Hyoungjun; Row, Sung Wook; Choi, Seonghwan; Seo, Young Jong; Chu, Young Hwan; Shin, Jae Min; Shul, Yong Gun; No, Kyoung Tai.

In: Industrial and Engineering Chemistry Research, Vol. 53, No. 27, 09.07.2014, p. 11159-11166.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quantitative structure relative volatility relationship model for extractive distillation of ethylbenzene/ p -xylene mixtures

AU - Kang, Young Mook

AU - Jeon, Yukwon

AU - Lee, Gicheon

AU - Son, Hyoungjun

AU - Row, Sung Wook

AU - Choi, Seonghwan

AU - Seo, Young Jong

AU - Chu, Young Hwan

AU - Shin, Jae Min

AU - Shul, Yong Gun

AU - No, Kyoung Tai

PY - 2014/7/9

Y1 - 2014/7/9

N2 - Extractive distillation is a highly effective process for the separation of compound pairs having low relative volatility values, such as ethylbenzene (EB) and p-xylene (PX) mixtures. Many solvents or solvent mixtures have been screened experimentally to identify a suitable extraction agent for EB/PX mixtures. Because the number of possible solvent and solvent mixture candidates is high, it is necessary to introduce a computer-aided extraction performance prediction technique. In this study, a knowledge-based quantitative structure relative volatility relationship (QSRVR) model was developed using multiple linear regression (MLR) and artificial neural network (ANN) models, with each model having five descriptors. The root-mean-square errors (RMSE) of the training and test sets for the MLR model were calculated as 0.01486 and 0.00905, while their squared correlation coefficients (R2) were 0.867 and 0.941, respectively. The R2 and RMSE values of the total data set for the MLR model were 0.878 and 0.01408, and for the ANN model the values were 0.949 and 0.00929, respectively. The predictive ability of both models is sufficient for identifying suitable extractive distillation solvents for the separation of EB/PX mixtures.

AB - Extractive distillation is a highly effective process for the separation of compound pairs having low relative volatility values, such as ethylbenzene (EB) and p-xylene (PX) mixtures. Many solvents or solvent mixtures have been screened experimentally to identify a suitable extraction agent for EB/PX mixtures. Because the number of possible solvent and solvent mixture candidates is high, it is necessary to introduce a computer-aided extraction performance prediction technique. In this study, a knowledge-based quantitative structure relative volatility relationship (QSRVR) model was developed using multiple linear regression (MLR) and artificial neural network (ANN) models, with each model having five descriptors. The root-mean-square errors (RMSE) of the training and test sets for the MLR model were calculated as 0.01486 and 0.00905, while their squared correlation coefficients (R2) were 0.867 and 0.941, respectively. The R2 and RMSE values of the total data set for the MLR model were 0.878 and 0.01408, and for the ANN model the values were 0.949 and 0.00929, respectively. The predictive ability of both models is sufficient for identifying suitable extractive distillation solvents for the separation of EB/PX mixtures.

UR - http://www.scopus.com/inward/record.url?scp=84904104149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904104149&partnerID=8YFLogxK

U2 - 10.1021/ie403235r

DO - 10.1021/ie403235r

M3 - Article

AN - SCOPUS:84904104149

VL - 53

SP - 11159

EP - 11166

JO - Industrial and Engineering Chemistry Research

JF - Industrial and Engineering Chemistry Research

SN - 0888-5885

IS - 27

ER -