Artificial neural network model for transient crossflow microfiltration of polydispersed suspensions

Robust artificial neural network (ANN) models for membrane fouling induced by polydispersed feed suspensions during crossflow microfiltration were derived and validated. ANNs performed highly accurate simulations of time-variant specific fluxes for several feed suspensions under a wide range of hydrodynamic parameters. Hence, ANNs incorporate the integral effects of complex colloidal transport and deposition mechanisms as well as changes in cake morphology and resistance with hydrodynamics better than mathematically complicated mechanistic models. An important contribution of this research is that it is demonstrated that ANNs need not be used simply as black boxes and cause-effect information can be quantitatively extracted from network connection weights to assist in model development and experimental design. Such an analysis revealed that the initial permeate flux is the most important operational variable influencing membrane fouling. However, in contrast to crossflow filtration of monodispersed suspensions, the shear rate was found to only weakly influence specific flux.

[1]  E. Leonard,et al.  THE DEPOSITION OF REJECTED MATTER IN MEMBRANE SEPARATION PROCESSES , 1984 .

[2]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[3]  Donald A. Jackson,et al.  Fish–Habitat Relationships in Lakes: Gaining Predictive and Explanatory Insight by Using Artificial Neural Networks , 2001 .

[4]  Robert H. Davis,et al.  Experimental verification of the shear-induced hydrodynamic diffusion model of crossflow microfiltration , 1991 .

[5]  Robert H. Davis,et al.  The behavior of suspensions and macromolecular solutions in crossflow microfiltration , 1994 .

[6]  V. Tarabara,et al.  Morphology of Deposits Formed from Chemically Heterogeneous Suspensions: Application to Membrane Filtration , 2002 .

[7]  R. Field,et al.  Critical flux concept for microfiltration fouling , 1995 .

[8]  M. Elimelech,et al.  Kinetics of Permeate Flux Decline in Crossflow Membrane Filtration of Colloidal Suspensions. , 1997, Journal of colloid and interface science.

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[11]  Richard J. Wakeman,et al.  Understanding flux decline in crossflow microfiltration. I: Effects of particle and pore size : Particle processing , 1993 .

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

[13]  Shankararaman Chellam,et al.  Effect of pretreatment on surface water nanofiltration , 1997 .

[14]  Michel Y. Jaffrin,et al.  Effect of cake thickness and particle polydispersity on prediction of permeate flux in microfiltration of particulate suspensions by a hydrodynamic diffusion model , 2000 .

[15]  Wei-Ming Lu,et al.  Selective Particle Deposition in Crossflow Filtration , 1989 .

[16]  Mark M. Clark,et al.  Modeling of flux decline during crossflow ultrafiltration of colloidal suspensions , 1998 .

[17]  G. Foley,et al.  Membrane Fouling during Constant Flux Crossflow Microfiltration of Dilute Suspensions of Active Dry Yeast , 1995 .

[18]  A. Fane.  Ultrafiltration: factors influencing flux and rejection , 1986 .

[19]  R. J. Hunter.  Foundations of Colloid Science , 1987 .

[20]  Mark R. Wiesner,et al.  Particle back-transport and permeate flux behavior in crossflow membrane filters , 1997 .

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

[22]  R. Wakeman,et al.  Understanding flux decline in crossflow microfiltration. Part 2 - Effects of process parameters , 1994 .

[23]  Mark R. Wiesner,et al.  Evaluation of crossflow filtration models based on shear-induced diffusion and particle adhesion: Complications induced by feed suspension polydispersivity , 1998 .

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

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

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

[27]  A. Goh.  Seismic liquefaction potential assessed by neural networks , 1994 .