Three types of composite PDMS membranes were prepared by using PAN, CA, and PVDF as support materials and used to separate ethanol from aqueous solution by pervaporation.The experimental results evidently demonstrated...Three types of composite PDMS membranes were prepared by using PAN, CA, and PVDF as support materials and used to separate ethanol from aqueous solution by pervaporation.The experimental results evidently demonstrated that the support layer had a significant impact on the flux and selectivity of composite PDMS membranes. The effect of the average pore size of supports on the performance of composite PDMS membranes was complex, and depended on many factors such as the physico-chemical properties of skin layers or supports and the preparation methods of composite membranes. The total flux of ethanol-water mixture through each composite PDMS membrane increased with increasing temperature. In contrast, the relation between selectivity and temperature was different due to various supports. With increasing feed concentration, the flux through each composite PDMS membrane increased quickly while the selectivity decreased.All these observation would be helpful to provide a guideline for the selection of an optimum support layer.展开更多
The application of carbon dioxide(CO_(2)) in enhanced oil recovery(EOR) has increased significantly, in which CO_(2) solubility in oil is a key parameter in predicting CO_(2) flooding performance. Hydrocarbons are the...The application of carbon dioxide(CO_(2)) in enhanced oil recovery(EOR) has increased significantly, in which CO_(2) solubility in oil is a key parameter in predicting CO_(2) flooding performance. Hydrocarbons are the major constituents of oil, thus the focus of this work lies in investigating the solubility of CO_(2) in hydrocarbons. However, current experimental measurements are time-consuming, and equations of state can be computationally complex. To address these challenges, we developed an artificial intelligence-based model to predict the solubility of CO_(2) in hydrocarbons under varying conditions of temperature, pressure, molecular weight, and density. Using experimental data from previous studies,we trained and predicted the solubility using four machine learning models: support vector regression(SVR), extreme gradient boosting(XGBoost), random forest(RF), and multilayer perceptron(MLP).Among four models, the XGBoost model has the best predictive performance, with an R^(2) of 0.9838.Additionally, sensitivity analysis and evaluation of the relative impacts of each input parameter indicate that the prediction of CO_(2) solubility in hydrocarbons is most sensitive to pressure. Furthermore, our trained model was compared with existing models, demonstrating higher accuracy and applicability of our model. The developed machine learning-based model provides a more efficient and accurate approach for predicting CO_(2) solubility in hydrocarbons, which may contribute to the advancement of CO_(2)-related applications in the petroleum industry.展开更多
文摘Three types of composite PDMS membranes were prepared by using PAN, CA, and PVDF as support materials and used to separate ethanol from aqueous solution by pervaporation.The experimental results evidently demonstrated that the support layer had a significant impact on the flux and selectivity of composite PDMS membranes. The effect of the average pore size of supports on the performance of composite PDMS membranes was complex, and depended on many factors such as the physico-chemical properties of skin layers or supports and the preparation methods of composite membranes. The total flux of ethanol-water mixture through each composite PDMS membrane increased with increasing temperature. In contrast, the relation between selectivity and temperature was different due to various supports. With increasing feed concentration, the flux through each composite PDMS membrane increased quickly while the selectivity decreased.All these observation would be helpful to provide a guideline for the selection of an optimum support layer.
基金supported by the Fundamental Research Funds for the National Major Science and Technology Projects of China (No. 2017ZX05009-005)。
文摘The application of carbon dioxide(CO_(2)) in enhanced oil recovery(EOR) has increased significantly, in which CO_(2) solubility in oil is a key parameter in predicting CO_(2) flooding performance. Hydrocarbons are the major constituents of oil, thus the focus of this work lies in investigating the solubility of CO_(2) in hydrocarbons. However, current experimental measurements are time-consuming, and equations of state can be computationally complex. To address these challenges, we developed an artificial intelligence-based model to predict the solubility of CO_(2) in hydrocarbons under varying conditions of temperature, pressure, molecular weight, and density. Using experimental data from previous studies,we trained and predicted the solubility using four machine learning models: support vector regression(SVR), extreme gradient boosting(XGBoost), random forest(RF), and multilayer perceptron(MLP).Among four models, the XGBoost model has the best predictive performance, with an R^(2) of 0.9838.Additionally, sensitivity analysis and evaluation of the relative impacts of each input parameter indicate that the prediction of CO_(2) solubility in hydrocarbons is most sensitive to pressure. Furthermore, our trained model was compared with existing models, demonstrating higher accuracy and applicability of our model. The developed machine learning-based model provides a more efficient and accurate approach for predicting CO_(2) solubility in hydrocarbons, which may contribute to the advancement of CO_(2)-related applications in the petroleum industry.
