Neural Networks Simulation of the Filtration of Sodium Chloride and Magnesium Chloride Solutions Using Nanofiltration Membranes

Abstract Artificial neural network (ANN) simulation is used to predict the rejection of two salts (NaCl and MgCl2) at typical seawater concentrations in a cross-flow nanofiltration membrane process. Rejections are predicted as a function of feed pressure and permeate flux with the salt concentration as a parameter. ANN predictions of the two salts’ rejections are compared with experimental results obtained using three different nanofiltration membranes (NF90, NF270 and N30F) in a cross flow filtration set-up. The experimental program spans a concentration range of 5000 to 25 000 ppm for NaCl solution and of 5000 to 20 000 ppm for MgCl2 solution at pressures covering the range of 2–9 bars. The effects of the training algorithm, neural network architectures and transfer function on the ANN performance, as reflected by the percentage average absolute deviation are discussed. A network with one hidden layer comprising four neurones is found to be adequate for mapping input–output relationships and providing a good interpolative tool. Algorithms based on the conjugate gradient, regularization and quasi-Newton principles were found to outperform those based on the gradient descent and variable momentum gradient descent. The former algorithms gave an average absolute percentage deviation up to 5% whereas deviations up to 20% are obtained from the latter algorithms. For most of the cases considered, the ANN proved to be an adequate interpolation tool, where an excellent prediction was obtained for some concentration levels not represented in the training data set. For very limited cases, the ANN predictive performance was poor. However, the network's performance in these extreme cases didn’t improve even with increasing the data points in the training data set.

[1]  S. Chellam,et al.  Simplified analysis of contaminant rejection during ground- and surface water nanofiltration under the information collection rule. , 2001, Water research.

[2]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[3]  W. Richard Bowen,et al.  Prediction of the rate of crossflow membrane ultrafiltration of colloids: A neural network approach , 1998 .

[4]  Michel Cabassud,et al.  Modelling of ultrafiltration fouling by neural network , 1998 .

[5]  Nandakishore Rajagopalan,et al.  Consider nanofiltration for membrane separations , 1994 .

[6]  Oumar Sarr,et al.  A phenomenological mass transfer approach in nanofiltration of halide ions for a selective defluorination of brackish drinking water , 2003 .

[7]  W. Richard Bowen,et al.  DYNAMIC ULTRAFILTRATION OF PROTEINS-A NEURAL NETWORK APPROACH , 1998 .

[8]  J. Wesselingh,et al.  Can nanofiltration be fully predicted by a model , 2002 .

[9]  H. G. Spencer,et al.  Dye-salt separations by nanofiltration using weak acid polyelectrolyte membranes , 1997 .

[10]  C. Linder,et al.  Intermediate reverse osmosis ultrafiltration (RO UF) membranes for concentration and desalting of low molecular weight organic solutes , 1989 .

[11]  Martin T. Hagan,et al.  Neural network design , 1995 .

[12]  W. Richard Bowen,et al.  Predicting salt rejections at nanofiltration membranes using artificial neural networks , 2000 .

[13]  Nidal Hilal,et al.  CHARACTERISATION OF NANOFILTRATION MEMBRANES FOR PREDICTIVE PURPOSES - USE OF SALTS, UNCHARGED SOLUTES AND ATOMIC FORCE MICROSCOPY , 1997 .

[14]  W. Richard Bowen,et al.  Modelling the retention of ionic components for different nanofiltration membranes , 2001 .

[15]  G. Trystram,et al.  Dynamic modeling of crossflow microfiltration using neural networks , 1995 .

[16]  Michel Cabassud,et al.  Use of neural networks for LPCVD reactors modelling , 1996 .

[17]  Carlo Vandecasteele,et al.  Removal of pollutants from surface water and groundwater by nanofiltration: overview of possible applications in the drinking water industry. , 2003, Environmental pollution.

[18]  Kuo-Chen Chou,et al.  Using stacked generalization to predict membrane protein types based on pseudo-amino acid composition. , 2006, Journal of theoretical biology.

[19]  J. Laîné,et al.  Neural networks for prediction of ultrafiltration transmembrane pressure – application to drinking water production , 1998 .

[20]  Octavian Pastravanu,et al.  Neural network models for ultrafiltration and backwashing , 2000 .

[21]  Serena Bandini,et al.  Nanofiltration modeling: the role of dielectric exclusion in membrane characterization , 2003 .

[22]  P. Schirg,et al.  CHARACTERISATION OF NANOFILTRATION MEMBRANES FOR THE SEPARATION OF AQUEOUS DYE-SALT SOLUTIONS , 1992 .

[23]  Nidal Hilal,et al.  Nanofiltration of highly concentrated salt solutions up to seawater salinity , 2005 .

[24]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[25]  Ata M. Hassan,et al.  Nanofiltration as a means of achieving higher TBT of ≥ 120°C in MSF , 1998 .

[26]  W. Richard Bowen,et al.  Diafiltration by nanofiltration: Prediction and optimization , 1998 .

[27]  Nidal Hilal,et al.  A comprehensive review of nanofiltration membranes:Treatment, pretreatment, modelling, and atomic force microscopy , 2004 .

[28]  Michel Cabassud,et al.  Dynamic modelling of crossflow microfiltration of bentonite suspension using recurrent neural networks , 1999 .

[29]  Michel Cabassud,et al.  Elaboration of a neural network system for semi-batch reactor temperature control: an experimental study , 1996 .

[30]  David Hasson,et al.  Utilization of the Donnan effect for improving electrolyte separation with nanofiltration membranes , 1996 .

[31]  Eric Latrille,et al.  Application of artificial neural networks for crossflow microfiltration modelling: “black-box” and semi-physical approaches , 1997 .

[32]  J. P. Boom,et al.  Retention measurements of nanofiltration membranes with electrolyte solutions , 1998 .

[33]  K. S. Spiegler,et al.  Thermodynamics of hyperfiltration (reverse osmosis): criteria for efficient membranes , 1966 .

[34]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[35]  Pierre-Yves Pontalier,et al.  Specific model for nanofiltration , 1999 .

[36]  B. Van der Bruggen,et al.  Influence of molecular size, polarity and charge on the retention of organic molecules by nanofiltration , 1999 .

[37]  Ata M. Hassan,et al.  A new approach to membrane and thermal seawater desalination processes using nanofiltration membranes (Part 1) , 1998 .

[38]  Abhay B. Bulsari,et al.  SIMULATION OF MEMBRANE SEPARATION BY NEURAL NETWORKS , 1995 .

[39]  W. Richard Bowen,et al.  Characterisation and prediction of separation performance of nanofiltration membranes , 1996 .

[40]  Shoji Kimura,et al.  REJECTION OF INORGANIC SALTS BY CHARGED ULTRAFILTRATION MEMBRANES MADE OF SULFONATED POLYSULFONE , 1983 .