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-meansquare 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 (R 2 ) were 0.867 and 0.941, respectively. The R 2 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.

Extractive distillation of benzene, toluene, and xylenes from pyrolysis gasoline using methylsulfonylethane as a cosolvent

“…It can be seen that sulfolane/MSE is the best composite solvent within the scope of the experiment. Kang reported that ED process is industrially applicable when α is greater than 1.2 32 . The results showed that sulfolane/MSE composite solvent is more selective than sulfolane and can be used for BTXs recovery.…”

“…Kang reported that ED process is industrially applicable when α is greater than 1.2. 32 The results showed that sulfolane/MSE composite solvent is more selective than sulfolane and can be used for BTXs recovery. It should be pointed out that we did not find clear advantages of sulfolane/NMP composite solvent in the ED process according to α ECH/B , though it had been recommended in the literature.…”

Quantitative Structure–Relative Volatility Relationship Model for Extractive Distillation of Ethylbenzene/p‐Xylene Mixtures: Application to Binary and Ternary Mixtures as Extractive Agents

“…To predict α EB/PX for single extractive agents, we had previously developed the requisite QSRVR models . The MLR model shows good predictability; the determination coefficient ( R 2 ) and root‐mean‐square error (RMSE) values of the MLR model were calculated as 0.878 and 0.0141, respectively.…”

“…In the case of a single extractive agent for the separation of EB and PX, our research group had previously developed quantitative structure–relative volatility relationship (QSRVR) models using multiple linear regression (MLR) and artificial neural network (ANN) techniques . Both MLR and ANN models showed considerably good accuracy, yielding R 2 values of 0.878 and 0.949, respectively.…”