Hydrates always are considered as a threat to petroleum industry due to the operational problems it can cause.These problems could result in reducing production performance or even production stoppage for a long time....Hydrates always are considered as a threat to petroleum industry due to the operational problems it can cause.These problems could result in reducing production performance or even production stoppage for a long time.In this paper, we were intended to develop a LSSVM algorithm for prognosticating hydrate formation temperature(HFT) in a wide range of natural gas mixtures. A total number of 279 experimental data points were extracted from open literature to develop the LSSVM. The input parameters were chosen based on the hydrate structure that each gas species form. The modeling resulted in a robust algorithm with the squared correlation coefficients(R^2) of 0.9918. Aside from the excellent statistical parameters of the model, comparing proposed LSSVM with some of conventional correlations showed its supremacy, particularly in the case of sour gases with high H_2S concentrations, where the model surpasses all correlations and existing thermodynamic models. For detection of the probable doubtful experimental data, and applicability of the model, the Leverage statistical approach was performed on the data sets. This algorithm showed that the proposed LSSVM model is statistically valid for HFT prediction and almost all the data points are in the applicability domain of the model.展开更多
The acid gas absorption in four potassium based amino acid salt solutions was predicted using artificial neural network(ANN). Two hundred fifty-five experimental data points for CO_2 absorption in the four potassium b...The acid gas absorption in four potassium based amino acid salt solutions was predicted using artificial neural network(ANN). Two hundred fifty-five experimental data points for CO_2 absorption in the four potassium based amino acid salt solutions containing potassium lysinate, potassium prolinate, potassium glycinate, and potassium taurate were used in this modeling. Amine salt solution's type, temperature, equilibrium partial pressure of acid gas, the molar concentration of the solution, molecular weight, and the boiling point were considered as inputs to ANN to prognosticate the capacity of amino acid salt solution to absorb acid gas. Regression analysis was employed to assess the performance of the network. Levenberg–Marquardt back-propagation algorithm was used to train the optimal ANN with 5:12:1 architecture. The model findings indicated that the proposed ANN has the capability to predict precisely the absorption of acid gases in various amino acid salt solutions with Mean Square Error(MSE) value of 0.0011, the Average Absolute Relative Deviation(AARD) percent of 5.54%,and the correlation coefficient(R^2) of 0.9828.展开更多
SAPO-34 nanocrystals(inorganic filler) were incorporated in polyurethane membranes and the permeation properties of CO_2, CH_4,and N_2 gases were explored. In this regard, the synthesized PU-SAPO-34 mixed matrix membr...SAPO-34 nanocrystals(inorganic filler) were incorporated in polyurethane membranes and the permeation properties of CO_2, CH_4,and N_2 gases were explored. In this regard, the synthesized PU-SAPO-34 mixed matrix membranes(MMMs) were characterized via SEM, AFM, TGA, XRD and FTIR analyses. Gas permeation properties of PU-SAPO-34 MMMs with SAPO-34 contents of 5 wt%, 10 wt% and 20 wt% were investigated. The permeation results revealed that the presence of 20 wt% SAPO-34 resulted in 4.45%, 18.24% and 40.2% reductions in permeability of CO_2,CH_4,and N_2, respectively, as compared to the permeability of neat polyurethane membrane. Also,the findings showed that at the pressure of 1.2 MPa, the incorporation of 20 wt% SAPO-34 into the polyurethane membranes enhanced the selectivity of CO_2/CH_4 and CO_2/N_2, 14.43 and 37.46%, respectively. In this research, PU containing 20 wt% SAPO-34 showed the best separation performance. For the first time, polynomial regression(PR) as a simple yet accurate tool yielded a mathematical equation for the prediction of permeabilities with high accuracy(R^2>99%).展开更多
Hollow fiber microfiltration(MF)and ultrafiltration(UF)membrane processes have been extensively used in water purification and biotechnology.However,complicated filtration hydrodynamics wield a negative influence on f...Hollow fiber microfiltration(MF)and ultrafiltration(UF)membrane processes have been extensively used in water purification and biotechnology.However,complicated filtration hydrodynamics wield a negative influence on fouling mitigation and stability of hollow fiber MF/UF membrane processes.Thus,establishing a mathematical model to understand the membrane processes is essential to guide the optimization of module configurations and to alleviate membrane fouling.Here,we present a comprehensive overview of the hollow fiber MF/UF membrane filtration models developed from different theories.The existing models primarily focus on membrane fouling but rarely on the interactions between the membrane fouling and local filtration hydrodynamics.Therefore,more simplified conceptual models and integrated reduced models need to be built to represent the real filtration behaviors of hollow fiber membranes.Future analyses considering practical requirements including complicated local hydrodynamics and nonuniform membrane properties are suggested to meet the accurate prediction of membrane filtration performance in practical application.This review will inspire the development of high-efficiency hollow fiber membrane modules.展开更多
文摘Hydrates always are considered as a threat to petroleum industry due to the operational problems it can cause.These problems could result in reducing production performance or even production stoppage for a long time.In this paper, we were intended to develop a LSSVM algorithm for prognosticating hydrate formation temperature(HFT) in a wide range of natural gas mixtures. A total number of 279 experimental data points were extracted from open literature to develop the LSSVM. The input parameters were chosen based on the hydrate structure that each gas species form. The modeling resulted in a robust algorithm with the squared correlation coefficients(R^2) of 0.9918. Aside from the excellent statistical parameters of the model, comparing proposed LSSVM with some of conventional correlations showed its supremacy, particularly in the case of sour gases with high H_2S concentrations, where the model surpasses all correlations and existing thermodynamic models. For detection of the probable doubtful experimental data, and applicability of the model, the Leverage statistical approach was performed on the data sets. This algorithm showed that the proposed LSSVM model is statistically valid for HFT prediction and almost all the data points are in the applicability domain of the model.
文摘The acid gas absorption in four potassium based amino acid salt solutions was predicted using artificial neural network(ANN). Two hundred fifty-five experimental data points for CO_2 absorption in the four potassium based amino acid salt solutions containing potassium lysinate, potassium prolinate, potassium glycinate, and potassium taurate were used in this modeling. Amine salt solution's type, temperature, equilibrium partial pressure of acid gas, the molar concentration of the solution, molecular weight, and the boiling point were considered as inputs to ANN to prognosticate the capacity of amino acid salt solution to absorb acid gas. Regression analysis was employed to assess the performance of the network. Levenberg–Marquardt back-propagation algorithm was used to train the optimal ANN with 5:12:1 architecture. The model findings indicated that the proposed ANN has the capability to predict precisely the absorption of acid gases in various amino acid salt solutions with Mean Square Error(MSE) value of 0.0011, the Average Absolute Relative Deviation(AARD) percent of 5.54%,and the correlation coefficient(R^2) of 0.9828.
基金Supported by the University of Kashan and the nano-organization(1393/1752)
文摘SAPO-34 nanocrystals(inorganic filler) were incorporated in polyurethane membranes and the permeation properties of CO_2, CH_4,and N_2 gases were explored. In this regard, the synthesized PU-SAPO-34 mixed matrix membranes(MMMs) were characterized via SEM, AFM, TGA, XRD and FTIR analyses. Gas permeation properties of PU-SAPO-34 MMMs with SAPO-34 contents of 5 wt%, 10 wt% and 20 wt% were investigated. The permeation results revealed that the presence of 20 wt% SAPO-34 resulted in 4.45%, 18.24% and 40.2% reductions in permeability of CO_2,CH_4,and N_2, respectively, as compared to the permeability of neat polyurethane membrane. Also,the findings showed that at the pressure of 1.2 MPa, the incorporation of 20 wt% SAPO-34 into the polyurethane membranes enhanced the selectivity of CO_2/CH_4 and CO_2/N_2, 14.43 and 37.46%, respectively. In this research, PU containing 20 wt% SAPO-34 showed the best separation performance. For the first time, polynomial regression(PR) as a simple yet accurate tool yielded a mathematical equation for the prediction of permeabilities with high accuracy(R^2>99%).
基金supported by Program for Guangdong Introducing Innovative and Entrepreneurial Teams(No.2019ZT08L213)National Key Research and Development Program of China(No.2020YFA0211003)+1 种基金Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou)(No.GML2019ZD0403)National Natural Science Foundation of China(No.21878230)。
文摘Hollow fiber microfiltration(MF)and ultrafiltration(UF)membrane processes have been extensively used in water purification and biotechnology.However,complicated filtration hydrodynamics wield a negative influence on fouling mitigation and stability of hollow fiber MF/UF membrane processes.Thus,establishing a mathematical model to understand the membrane processes is essential to guide the optimization of module configurations and to alleviate membrane fouling.Here,we present a comprehensive overview of the hollow fiber MF/UF membrane filtration models developed from different theories.The existing models primarily focus on membrane fouling but rarely on the interactions between the membrane fouling and local filtration hydrodynamics.Therefore,more simplified conceptual models and integrated reduced models need to be built to represent the real filtration behaviors of hollow fiber membranes.Future analyses considering practical requirements including complicated local hydrodynamics and nonuniform membrane properties are suggested to meet the accurate prediction of membrane filtration performance in practical application.This review will inspire the development of high-efficiency hollow fiber membrane modules.
