Gas sorption in H2-selective mixed matrix membranes: Experimental and neural network modeling

Robust artificial neural network (ANN) was developed to forecast sorption of gases in membranes comprised of porous nanoparticles dispersed homogenously within polymer matrix. The main purpose of this study was to predict sorption of light gases (H2, CH4, CO2) within mixed matrix membranes (MMMs) as function of critical temperature, nanoparticles loading and upstream pressure. Collected data were distributed into three portions of training (70%), validation (19%), and testing (11%). The optimum network structure was determined by trial-error method (4:6:2:1) and was applied for modeling the gas sorption. The prediction results were remarkably agreed with the experimental data with MSE of 0.00005 and correlation coefficient of 0.9994.

[1]  Indranil Saha,et al.  journal homepage: www.elsevier.com/locate/neucom , 2022 .

[2]  Alan Cooper,et al.  High pressure sorption isotherms via differential pressure measurements , 2007 .

[3]  M. Rezakazemi,et al.  Hydrodynamics and mass transfer simulation of wastewater treatment in membrane reactors , 2012 .

[4]  K. Shahidi,et al.  Hydrogen separation and purification using crosslinkable PDMS/zeolite A nanoparticles mixed matrix membranes , 2012 .

[5]  G. Sarti,et al.  Solubility and Diffusivity of Gases in Mixed Matrix Membranes Containing Hydrophobic Fumed Silica: Correlations and Predictions Based on the NELF Model , 2008 .

[6]  D. Kemp,et al.  The diffusion time lag in polymer membranes containing adsorptive fillers , 2007 .

[7]  Hasan Bal,et al.  Comparing performances of backpropagation and genetic algorithms in the data classification , 2011, Expert Syst. Appl..

[8]  S. Chellam,et al.  Predicting contaminant removal during municipal drinking water nanofiltration using artificial neural networks , 2003 .

[9]  S. Silva-Martínez,et al.  Optimal performance of COD removal during aqueous treatment of alazine and gesaprim commercial herbicides by direct and inverse neural network , 2011 .

[10]  K. Shahidi,et al.  Synthesis and gas permeation properties of a single layer PDMS membrane , 2010 .

[11]  E. Drioli,et al.  Filler-polymer combination: a route to modify gas transport properties of a polymeric membrane , 2004 .

[12]  C. Vandecasteele,et al.  Zeolite-filled PDMS membranes .1. Sorption of halogenated hydrocarbons , 1997 .

[13]  A. Kim,et al.  Prediction of permeate flux decline in crossflow membrane filtration of colloidal suspension: a radial basis function neural network approach , 2006 .

[14]  E. Vasheghani-Farahani,et al.  Pure and mixed gas CH4 and n-C4H10 permeation in PDMS-fumed silica nanocomposite membranes , 2012 .

[15]  B. Schoeman,et al.  Effect of zeolite particle size on the performance of polymer–zeolite mixed matrix membranes , 2000 .

[16]  Mashallah Rezakazemi,et al.  Separation of CO2 by single and mixed aqueous amine solvents in membrane contactors: fluid flow and mass transfer modeling , 2011, Engineering with Computers.

[17]  Farouq S. Mjalli,et al.  Neural network model-based predictive control of liquid–liquid extraction contactors , 2005 .

[18]  K. Peinemann,et al.  Molecular sieving effect of the zeolite-filled silicone rubber membranes in gas permeation , 1991 .

[19]  S. Chellam,et al.  Predicting membrane fouling during municipal drinking water nanofiltration using artificial neural networks , 2003 .

[20]  Gaohong He,et al.  Prediction of the effects of preparation conditions on pervaporation performances of polydimethylsiloxane(PDMS)/ceramic composite membranes by backpropagation neural network and genetic algorithm , 2012 .

[21]  M. Rezakazemi,et al.  CFD simulation of natural gas sweetening in a gas–liquid hollow-fiber membrane contactor , 2011 .

[22]  Mashallah Rezakazemi,et al.  Numerical modeling and optimization of wastewater treatment using porous polymeric membranes , 2013 .

[23]  K. Shahidi,et al.  Sorption properties of hydrogen-selective PDMS/zeolite 4A mixed matrix membrane , 2012 .

[24]  Jason K. Ward,et al.  CO2–CH4 permeation in high zeolite 4A loading mixed matrix membranes , 2011 .

[25]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[26]  G. B. Sahoo,et al.  Predicting flux decline in crossflow membranes using artificial neural networks and genetic algorithms , 2006 .

[27]  E. Drioli,et al.  Pervaporation performance of unfilled and filled PDMS membranes and novel SBS membranes for the removal of toluene from diluted aqueous solutions , 2010 .

[28]  Ivo F J Vankelecom,et al.  Zeolite filled polydimethylsiloxane (PDMS) as an improved membrane for solvent-resistant nanofiltration (SRNF). , 2005, Chemical communications.

[29]  Mashallah Rezakazemi,et al.  Gas permeation through H2-selective mixed matrix membranes: Experimental and neural network modeling , 2013 .

[30]  M. Rezakazemi,et al.  Simulation of ammonia removal from industrial wastewater streams by means of a hollow-fiber membrane contactor , 2012 .

[31]  D. Sholl,et al.  Monte Carlo simulation of single- and binary-component adsorption of CO2, N2, and H2 in zeolite Na-4A , 2003 .

[32]  M. Rezakazemi,et al.  Pervaporation study of ethylene glycol dehydration through synthesized (PVA–4A)/polypropylene mixed matrix composite membranes , 2013 .

[33]  M. Rezakazemi,et al.  Transient computational fluid dynamics modeling of pervaporation separation of aromatic/aliphatic hydrocarbon mixtures using polymer composite membrane , 2013 .

[34]  Ali Mortazavi,et al.  Dynamic modelling of milk ultrafiltration by artificial neural network , 2003 .

[35]  A. Nazari,et al.  Simulation and determination of optimum conditions of pervaporative dehydration of isopropanol proce , 2011 .

[36]  M. Rezakazemi,et al.  CFD simulation of water removal from water/ethylene glycol mixtures by pervaporation , 2011 .

[37]  K. L. Edwards,et al.  The use of artificial neural networks in materials science based research , 2007 .

[38]  M. Peterson,et al.  Non-invasive measurement of membrane morphology via UFDR: pore-size characterization , 2004 .