Representation/Prediction of Solubilities of Pure Compounds in Water Using Artificial Neural Network−Group Contribution Method

Gharagheizi, Farhad; Eslamimanesh, Ali; Mohammadi, Amir H.; Richon, Dominique

doi:10.1021/je101061t

Cited by 54 publications

(55 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mendez-Teja -0.00001000 -0.00001000 0.00050000 --- 4 Kumar-Johnston 0.00000100 0.02500000 -0.00100000 --- 5 Garlapati-Madras 0.00000000 0.00117374 0.41996382 0.00000000 0.31953855 - 6 Bian 0.00100000 -0.00125600 0.00000000 0.34070671 8.70164889 -7…”

Section: Sl Nomentioning

confidence: 99%

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Srinidhi¹,

Patel²,

A³

2020

Preprint

View full text Add to dashboard Cite

The research on dye solubility modeling in supercritical carbon dioxide is gaining prominence over the past few decades. A simple and ubiquitous model that is capable of accurately predicting the solubility in supercritical carbon dioxide would be invaluable for industrial and research applications. In this study, we present such a model for predicting dye solubility in supercritical carbon dioxide with ethanol as the co-solvent for a qualitatively diverse sample of eight dyes. A feed forward back propagation -artificial neural network model based on Levenberg-Marquardt algorithm was constructed with seven input parameters for solubility prediction, the network architecture was optimized to be [7-7-1] with mean absolute error, mean square error, root mean square error and Nash-Sutcliffe coefficient to be 0.026, 0.0016, 0.04 and 0.9588 respectively. Further, Pearson-product moment correlation analysis was performed to assess the relative importance of the parameters considered in the ANN model. A total of twelve prevalent semiempirical equations were also studied to analyze their efficiency in correlating to the solubility of the prepared sample. Mendez-Teja model was found to be relatively efficient with root mean square error and mean absolute error to be 0.094 and 0.0088 respectively. Furthermore, Grey relational analysis was performed and the optimum regime of temperature and pressure were identified with dye solubility as the higher the better performance characteristic. Finally, the dye specific crossover ranges were identified by analysis of isotherms and a strategy for class specific selective dye extraction using supercritical CO2 extraction process is proposed.

show abstract

Section: Sl Nomentioning

confidence: 99%

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Srinidhi¹,

Patel²,

A³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Pearson product-moment correlation coefficient (r x,y ) was computed to estimate the extent and nature of inter variable correlation using the equation (6).…”

Section: Assessment Of Relative Variable Importance Pearson Product-moment Correlation Analysismentioning

confidence: 99%

“…Therefore, research focused on modeling the solubility of dyestuff using supercritical fluid extraction process using empirical data is being pursued at an accelerating pace over the past few decades. Although cubic equations of state are widely used to calculate solubilities of solutes in supercritical CO2, they are highly disadvantageous for application in industries for the various reasons explained by Gharagheizi et al [6]. Further, Semi-empirical models, models involving mass transfer phenomenon, and Black box approaches like wavelet neural network modeling, artificial neural networks, Fuzzy logic technology, Response surface methodology, have also been studied for general solubility modeling purposes for the supercritical CO2 extraction process.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network (FFBP-ANN) Based Grey’s Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Srinidhi

Patel²,

Vk³

2020

Preprint

View full text Add to dashboard Cite

The research on dye solubility modeling in supercritical carbon dioxide is gaining prominence over the past few decades. A simple and ubiquitous model that is capable of accurately predicting the solubility in supercritical carbon dioxide would be invaluable for industrial and research applications. In this study, we present such a model for predicting dye solubility in supercritical carbon dioxide with ethanol as the co-solvent for a qualitatively diverse sample of eight dyes. A feed forward back propagation - artificial neural network model based on Levenberg-Marquardt algorithm was constructed with seven input parameters for solubility prediction, the network architecture was optimized to be [7-7-1] with mean absolute error, mean square error, root mean square error and Nash-Sutcliffe coefficient to be 0.026, 0.0016, 0.04 and 0.9588 respectively. Further, Pearson-product moment correlation analysis was performed to assess the relative importance of the parameters considered in the ANN model. A total of twelve prevalent semiempirical equations were also studied to analyze their efficiency in correlating to the solubility of the prepared sample. Mendez-Teja model was found to be relatively efficient with root mean square error and mean absolute error to be 0.094 and 0.0088 respectively. Furthermore, Grey’s relational analysis was performed and the optimum regime of temperature and pressure were identified with dye solubility as the higher the better performance characteristic. Finally, the dye specific crossover ranges were identified by analysis of isotherms and a strategy for class specific selective dye extraction using supercritical CO2 extraction process is proposed.

show abstract

“…Therefore, research focused on modeling dyestuff solubility using supercritical fluid extraction process using empirical data is being pursued at an accelerating pace over the past few decades. Although cubic equations of state are widely used to calculate solubilities of solutes in supercritical CO 2 , they are highly disadvantageous for application in industries for the various reasons explained by Gharagheizi et al [6]. Further, Semiempirical models, models involving mass transfer phenomenon, and Black box approaches like wavelet neural networks, artificial neural networks, Fuzzy logic technology, Response surface methodology, have also been studied for general solubility modeling purposes of the supercritical CO 2 extraction process.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Srinidhi¹

2021

Preprint

View full text Add to dashboard Cite

The research on dye solubility modeling in supercritical carbon dioxide is gaining prominence over the past few decades. A simple and ubiquitous model that is capable of accurately predicting the solubility in supercritical carbon dioxide would be invaluable for industrial and research applications. In this study, we present such a model for predicting dye solubility in supercritical carbon dioxide with ethanol as the co-solvent for a qualitatively diverse sample of eight dyes. A feed forward back propagation - artificial neural network model based on Levenberg-Marquardt algorithm was constructed with seven input parameters for solubility prediction, the network architecture was optimized to be [7-7-1] with mean absolute error, mean square error, root mean square error and Nash-Sutcliffe coefficient to be 0.026, 0.0016, 0.04 and 0.9588 respectively. Further, Pearson-product moment correlation analysis was performed to assess the relative importance of the parameters considered in the ANN model. A total of twelve prevalent semiempirical equations were also studied to analyze their efficiency in correlating to the solubility of the prepared sample. Mendez-Teja model was found to be relatively efficient with root mean square error and mean absolute error to be 0.094 and 0.0088 respectively. Furthermore, Grey relational analysis was performed and the optimum regime of temperature and pressure were identified with dye solubility as the higher the better performance characteristic. Finally, the dye specific crossover ranges were identified by analysis of isotherms and a strategy for class specific selective dye extraction using supercritical CO2 extraction process is proposed.

show abstract

Representation/Prediction of Solubilities of Pure Compounds in Water Using Artificial Neural Network−Group Contribution Method

Cited by 54 publications

References 73 publications

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Artificial Neural Network (FFBP-ANN) Based Grey’s Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

Contact Info

Product

Resources

About