Dynamic prediction of milk ultrafiltration performance: A neural network approach

Neural network models were tested in connection with the dynamic prediction of permeate flux (JP), total hydraulic resistance (RT) and the solutes rejection for the crossflow ultrafiltration of milk at different transmembrane pressure (TMP) and temperature (T). This process has complex non-linear dependencies on the operating conditions. Thus it provides demanding test of the neural network approach to the process variables prediction. Two neural network models with single hidden layer were constructed to predict the time dependent rate of JP/RT and rejections from a limited number of training data. The modelling results showed that there is an excellent agreement between the experimental data and predicted values, with average errors less than 1%. The experimental results showed that the RT and solutes rejection (except for protein) increased greatly with time at each value of TMP and T, whereas the JP decreased significantly for the same conditions. Increasing TMP at constant T led to an increase in the JP, RT and solutes rejection, but increasing T at constant TMP had no significant effect on the JP, RT and rejection of components.

[1]  E. A. Zottola,et al.  Modeling Flux of Skim Milk as a Function of pH, Acidulant, and Temperature , 1992 .

[2]  Michael J. Lewis,et al.  Hydrodynamic factors affecting flux and fouling during ultrafiltration of skimmed milk , 2000 .

[3]  Munir Cheryan,et al.  Modelling of hollow-fibre ultrafiltration of skimmilk under mass-transfer limiting conditions , 1987 .

[4]  Munir Cheryan,et al.  Ultrafiltration and Microfiltration Handbook , 1998 .

[5]  M. Lewis,et al.  Flux pattern and fouling of membranes during ultrafiltration of some dairy products , 1994 .

[6]  Gun Trägårdh,et al.  Predicting limiting flux of skim milk in crossflow microfiltration , 1997 .

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

[8]  C. Heath,et al.  Ultrafiltration of skim milk in flat-plate and spiral-wound modules , 1997 .

[9]  M. Caric,et al.  The effect of turbulence promoter on cross-flow microfiltration of skim milk , 2002 .

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

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

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

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

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