Skip to main content
Log in

Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: A wavelet network approach

  • Published:
International Journal of Environmental Science & Technology Aims and scope Submit manuscript

Abstract

Although traditional artificial neural networks have been an attractive topic in modeling membrane filtration, lower efficiency by trial-and-error constructing and random initializing methods often accompanies neural networks. To improve traditional neural networks, the present research used the wavelet network, a special feedforward neural network with a single hidden layer supported by the wavelet theory. Prediction performance and efficiency of the proposed network were examined with a published experimental dataset of cross-flow membrane filtration. The dataset was divided into two parts: 62 samples for training data and 329 samples for testing data. Various combinations of transmembrane pressure, filtration time, ionic strength and zeta potential were used as inputs of the wavelet network so as to predict the permeate flux. Through the orthogonal least square alogorithm, an initial network with 12 hidden neurons was obtained which offered a normalized square root of mean square of 0.103 for the training data. The initial network led to a wavelet network model after training procedures with fast convergence within 30 epochs. Futher the wavelet network model accurately depicted the positive effects of either transmembrane pressure or zeta potential on permeate flux. The wavelet network also offered accurate predictions for the testing data, 96.4 % of which deviated the measured data within the ± 10 % relative error range. Moreover, comparisons indicated the wavelet network model produced better predictability than the back-forward backpropagation neural network and the multiple regression models. Thus the wavelet network approach could be employed successfully in modeling dynamic permeate flux in cross-flow membrane filtration.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Al-Abri, M.; Hilal, N., (2008). Artificial neural network simulation of combined humic substance coagulation and membrane filtration. Chem. Eng. J., 141 (1-3), 27–34 (8 pages).

    Article  CAS  Google Scholar 

  • Aydiner, C.; Demir, I.; Yildiz, E., (2005). Modeling of flux decline in crossflow microfiltration using neural networks: The case of phosphate removal. J. Membr. Sci., 248(1–2), 53–62 (10 pages).

    Article  CAS  Google Scholar 

  • Billings, S. A.; Wei, H. L., (2005). A new class of wavelet networks for nonlinear system identification. IEEE T. Neural Networ., 16 (4), 862–874 (13 pages).

    Article  Google Scholar 

  • Bowen, W. R.; Jones, M. G.; Yousef, H. N. S., (1998). Prediction of the rate of crossflow membrane ultrafiltration of colloids: A neural network approach. Chem. Eng. Sci., 53 (22), 3793–3802 (10 pages).

    Article  CAS  Google Scholar 

  • Bowen, W. R.; Mongruel, A.; Williams, P. M., (1996). Prediction of the rate of cross-flow membrane ultrafiltration: A colloidal interaction approach. Chem. Eng. Sci., 51 (18), 4321–4333 (13 pages).

    Article  CAS  Google Scholar 

  • Brindle, K.; Stephenson, T., (1996). The application of membrane biological reactors for the treatment of wastewaters. Biotech. Bioeng., 49 (6), 601–610 (10 pages).

    Article  CAS  Google Scholar 

  • Chattopadhyay, S.; Bandyopadhyay, G., (2007). Artificial neural network with backpropagation learning to predict mean monthly total ozone in Aros, Switzerland. Int. J. Remote Sens., 28 (20), 4471–4482 (12 pages).

    Article  Google Scholar 

  • Chellam, S., (2005). Artificial neural network model for transient crossflow microfiltration of polydispersed suspensions. J. Membr. Sci., 258(1–2), 35–42 (8 pages).

    Article  CAS  Google Scholar 

  • Chen, H. Q.; Kim, A. S., (2006). Prediction of permeate flux decline in crossflow membrane filtration of colloidal suspension: a radial basis function neural network approach. Desalination, 192 (1-3), 415–428 (14 pages).

    Article  CAS  Google Scholar 

  • Cheng, L. H.; Cheng, Y. F.; Chen, J. H., (2008). Predicting effect of interparticle interactions on permeate flux decline in CMF of colloidal suspensions: An overlapped type of local neural network. J. Membr. Sci., 308(1–2), 54–65 (12 pages).

    Article  CAS  Google Scholar 

  • Cinar, O.; Hasar, H.; Kinaci, C., (2006). Modeling of submerged membrane bioreactor treating cheese whey wastewater by artificial neural network. J. Biotech., 123 (2), 204–209 (6 pages).

    Article  CAS  Google Scholar 

  • Craven, P.; Wahba, P., (1978). Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation. Numer. Math., 31 (4), 377–403 (27 pages).

    Article  Google Scholar 

  • Curcio, S.; Calabro, V.; Iorio, G., (2006). Reduction and control of flux decline in cross-flow membrane processes modeled by artificial neural networks. J. Membr. Sci., 286(1–2), 125–132 (8 pages).

    Article  CAS  Google Scholar 

  • Daubechies, I., (1992). Ten lectures on wavelets. SIAM, Philadelphia, 11–17 (7 pages).

    Book  Google Scholar 

  • Defrance, L.; Jaffrin, M. Y.; Gupta, B.; Paullier, P.; Geaugey, V., (2000). Contribution of various constituents of activated sludge to membrane bioreactor fouling. Biores. Tech., 73 (2), 105–112 (8 pages).

    Article  CAS  Google Scholar 

  • Dornier, M.; Decloux, M.; Trystram, G.; Lebert, A., (1995). Interest of neural networks for the optimization of the cross-flow filtration process. LWT. Food Sci. Tech., 28 (3), 300–309 (10 pages).

    Article  CAS  Google Scholar 

  • Elzo, D.; Huisman, I.; Middelink, E.; Gekas, V., (1998). Charge effects on inorganic membrane performance in a cross-flow microfiltration process. Colloid Surf. Physicochem. Eng. A., 138(2–3), 145–159 (15 pages).

    Article  CAS  Google Scholar 

  • Faibish, R. S.; Elimelech, M.; Cohen, Y., (1998). Effect of interparticle electrostatic double layer interactions on permeate flux decline in cross-flow membrane filtration of colloidal suspensions: An experimental investigation. J. Colloid Interf. Sci., 204 (1), 77–86 (10 pages).

    Article  CAS  Google Scholar 

  • Haykin, S., (1999). Neural networks: A Comprehensive Foundation. 2nd. Ed., Prentice Hall, 183-197.

  • Huisman, I. H.; Dutre, B.; Persson, K. M.; Tragardh, G., (1997). Water permeability in ultrafiltration and microfiltration: Viscous and electroviscous effects. Desalination, 113 (1), 95–103 (9 pages).

    Article  CAS  Google Scholar 

  • Li, Q. L.; Elimelech, M., (2004). Organic fouling and chemical cleaning of nanofiltration membranes: Measurements and mechanisms. Environ. Sci. Tech., 38 (17), 4683–4693 (11 pages).

    Article  CAS  Google Scholar 

  • Liao, B. Q.; Kraemer, J. T.; Bagley, D. M., (2006). Anaerobic membrane bioreactors: Applications and research directions. Crit. Rev. Environ. Sci. Tech., 36 (6), 489–530 (42 pages).

    Article  CAS  Google Scholar 

  • McDonogh, R. M.; Fane, A. G.; Fell, C. J. D., (1989). Charge effects in the cross-flow filtration of colloids and particulates. J. Membr. Sci., 43 (1), 69–85 (17 pages).

    Article  CAS  Google Scholar 

  • Ni Mhurchu, J.; Foley, G., (2006). Dead-end filtration of yeast suspensions: Correlating specific resistance and flux data using artificial neural networks. J. Membr. Sci., 281(1–2), 325–333 (9 pages).

    Article  CAS  Google Scholar 

  • Oussar, Y.; Dreyfus, G., (2000) Initialization by selection for wavelet network training. Neurocomputing, 34 (1), 131–143 (13 pages).

    Article  Google Scholar 

  • Oussar, Y.; Rivals, I.; Personnaz, L.; Dreyfus, G., (1998). Training wavelet networks for nonlinear dynamic input-output modeling. Neurocomputing, 20 (1-3), 173–188 (16 pages).

    Article  Google Scholar 

  • Priddy, K. L.; Keller, P. E., (2005). Artificial neural networks: An introduction. SPIE Press, 15-16 (2 pages).

  • Sahoo, G. B.; Ray, C., (2006). Predicting flux decline in cross-flow membranes using artificial neural networks and genetic algorithms. J. Membr. Sci., 283(1–2), 147–157 (11 pages).

    Article  CAS  Google Scholar 

  • Sanner, R. M.; Slotine, J. J. E., (1998). Structurally dynamic wavelet networks for adaptive control of robotic systems. Int. J. Contr., 70 (3), 405–421 (17 pages).

    Article  Google Scholar 

  • Sjoberg, J.; Zhang, Q., H.; Ljung, L.; Benveniste, A.; Delyon, B.; Glorennec, P. Y; Hjalmarsson, H.; Juditsky, A., (1995). Nonlinear black-box modeling in system identification: A unified overview. Automatica, 31 (12), 1691–1724 (34 pages).

    Article  Google Scholar 

  • Song, L. F., (1998). Flux decline in cross-flow microfiltration and ultrafiltration: mechanisms and modeling of membrane fouling. J. Membr. Sci., 139 (2), 183–200 (18 pages).

    Article  CAS  Google Scholar 

  • Tarleton, E. S.; Wakeman, R. J., (1993). Understanding flux decline in cross-flow microfiltration. I: Effects of particle and pore-size. Chem. Eng. Res. Des., 71 (4), 399–410 (12 pages).

    CAS  Google Scholar 

  • Visvanathan, C.; Ben Aim, R.; Parameshwaran, K., (2000). Membrane separation bioreactors for wastewater treatment. Crit. Rev. Environ. Sci. Tech., 30 (1), 1–48 (48 pages).

    Article  CAS  Google Scholar 

  • Zhang, M. M.; Song, L. F., (2000). Mechanisms and parameters affecting flux decline in cross-flow microfiltration and ultrafiltration of colloids, Environ. Sci. Tech., 34 (17), 3767–3773 (7 pages).

    Article  CAS  Google Scholar 

  • Zhang, Q. H., (1992). Wavelet network: The radial structure and an efficient initialization procedure, technical report of Linkoping University, LiTH-ISY-I1423. October.

  • Zhang, Q. H., (1997). Using wavelet network in nonparametric estimation. IEEE T. Neural Network, 8 (2), 227–236 (10 pages).

    Article  CAS  Google Scholar 

  • Zhang, Q. H.; Benveniste, A., (1992). Wavelet networks, IEEE T. Neural Network, 3 (6), 889–898 (10 pages).

    Article  CAS  Google Scholar 

  • Zhang, X. Y.; Qi, J. H.; Zhang, R. S.; Liu, M. C.; Xue, H. F.; Fan, B. T., (2001). Prediction of programmed-temperature retention values of naphthas by wavelet neural networks. Comput. Chem., 25 (2), 125–133 (9 pages).

    Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to G. M. Zeng Ph.D..

Rights and permissions

Reprints and permissions

About this article

Cite this article

Wei, A.L., Zeng, G.M., Huang, G.H. et al. Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: A wavelet network approach. Int. J. Environ. Sci. Technol. 6, 395–406 (2009). https://doi.org/10.1007/BF03326078

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03326078

Keywords

Navigation