The possibilities of modelling the membrane separation processes using artificial neural networks

• Autorzy: Kabsch-Korbutowicz M. , Kutyłowska M.

Warianty tytułu

PL

Możliwości modelowania procesów separacji membranowej z wykorzystaniem sztucznych sieci neuronowych

• Języki publikacji: EN

Abstrakty

EN

Despite the substantial progress observed in last years in membrane science, many initial problems associated with membrane processes have not been solved, including limitations in ability to control and predict membrane fouling and selectivity. That is why a suitable method for process optimization should be developed which will allow the most important membrane parameters to be modelled. The paper describes the possibilities of forecasting the parameters of the membrane processes using artificial neural network (ANN). The modelled parameters vary in their properties, so different ANN may be used for their testing and forecasting.

PL

Pomimo znaczącego w ostatnich latach rozwoju technik membranowych pozostało jeszcze wiele problemów związanych z procesami separacji, a także ograniczeń w kontrolowaniu foulingu i selektywności membran. Dlatego konieczny jest rozwój metod optymalizacji, które umożliwiają zamodelowanie najważniejszych parametrów procesów membranowych. W artykule opisano możliwości prognozowania parametrów procesów membranowych z użyciem sztucznych sieci neuronowych. Właściwości modelowanych parametrów są zmienne, dlatego do testowania i prognozowania użyto różnych typów sieci neuronowych.

Słowa kluczowe

EN

neural networks; biological membranes; membrane process; optimization

PL

sieci neuronowe; membrany biologiczne; procesy membranowe; optymalizacja

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Environment Protection Engineering
• Rocznik: 2008
• Tom: Vol. 34, nr 1
• Strony: 15--35
• Opis fizyczny: bibliogr. 26 poz.

Twórcy

autor

Kabsch-Korbutowicz M.

autor

Kutyłowska M.

• Institute of Environmental Protection Engineering, Wroclaw University of Technology, 50-370 Wroclaw,

Bibliografia

• [1] KOŁTUNIEWICZ A., The history and state of arts in membrane technologies, VIII Spring Membrane School “Membrane, membrane processes and their application”, Opole-Turawa, 23–26 April 2006.
• [2] NORGAARD M., Neural Network Based System Identification TOOLBOX for use with MATLAB.
• [3] MCCULLOCH W.S, PITTS W., A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 1943, Vol. 5, 115–133.
• [4] RAZAVI S.M.A., MOUSAVI S.M., MORTAZAVI S.A., Dynamic prediction of milk ultrafiltration performance: a neural network approach, Chemical Engineering Science, 2003, Vol. 58, 4185–4195.
• [5] PIRON E., LATRILE E., RENE F., Application of artificial neural networks for crossflow microfiltration modelling: black box and semi physical approach, Computers Chem. Engng., 1997, Vol. 21(9), 1021–1030.
• [6] DORNIER M., DECLOUX M., TRYSTRAM G., LEBERT A., Dynamic modelling of crossflow microfiltration using neural networks, Journal of Membrane Science, 1996, Vol. 98, 263–273.
• [7] BOWEN W.R., JONES M.J., YOUSEF H.N.S., Dynamic ultrafiltration of proteins – a neural network approach, Journal of Membrane Science, 1998, Vol. 146, 225–235.
• [8] RAI P., MAJUMDAR G.C., DASGUPTA S., DE S., Modelling the performance of batch ultrafiltration of synthetic fruit juice and mosambi juice using artificial neural network, Journal of Food Engineering, 2005, Vol. 71, 273–281.
• [9] HAMACHI M., CABASSUD M., DAVIN A., MIETTON PEUCHOT M., Dynamic modelling of crossflow microfiltration of bentonite suspension using recurrent neural network, Chemical Engineering and Processing, 1998, Vol. 38, 203–210.
• [10] DELGRANGE N., CABASSUD C., DURAND-BOURLIER L., LAINE J.M., Modelling of ultrafiltration fouling by neural network, Desalination, 1998, Vol. 118, 213–227.
• [11] DELGRANGE-VINCENT N., CABASSUD C., CABASSUD M., DURAND-BOURLIER L., LAINE J.M., Neural networks for long term prediction of fouling and backwash efficiency in ultrafiltration for drinking water production, Desalination, 2000, Vol. 131, 353–362.
• [12] DELGRANGE N., CABASSUD C., CABASSUD M., DURAND-BOURLIER L., LAINE J.M., Neural networks for prediction of ultrafiltration transmembrane pressure: application to drinking water production, Journal of Membrane Science, 1998, Vol. 150, 111–123.
• [13] CABASSUD M., DELGRANGE-VINCENT N., CABASSUD C., DURAND-BOURLIER L., LAINE J.M., Neural networks: a tool to improve UF plant productivity, Desalination, 2002, Vol. 145, 223–231.
• [14] SAHOO G.B., RAY C., Predicting flux decline in cross-flow membranes using artificial neural networks and genetic algorithms, Journal of Membrane Science, 2006, Vol. 283, 147–157.
• [15] SHETTY G.R., CHELLAM S., Predicting membrane fouling during municipal drinking water nanofiltration using artificial neural networks, Journal of Membrane Science, 2003, Vol. 217, 69–86.
• [16] SHETTY G.R., MALKI H., CHELLAM S., Predicting contaminant removal during municipal drinking water nanofiltration using artificial neural networks, Journal of Membrane Science, 2003, Vol. 212, 99–112.
• [17] BOWEN W.R., JONES M.G., WELFOOT J.S., HAITHAM Y., Predicting salt rejections at nanofiltration membranes using artificial neural networks, Desalination, 2000, Vol. 129, 147–162.
• [18] BOWEN W.R., JONES M.G., HAITHAM Y., Prediction of the rate of crossflow membrane ultrafiltration of colloids: a neural network approach, Chemical Engineering Science, 1998, Vol. 53, 3793–3802.
• [19] CHEN H., KIM A.S., Prediction of permeate flux decline in cross-flow membrane filtration of colloidal suspension: a radial basis function neural network approach, Desalination, 2006, Vol. 192, 415–428.
• [20] CURCIO S., CALABRO V., IORIO G., Reduction and control of flux decline in cross-flow membrane processes modelled by artificial neural networks, Journal of Membrane Science, 2006, Vol. 286, 125–132.
• [21] CHELLAM S., Artificial neural network model for transient crossflow microfiltration of polydispersed suspensions, Journal of Membrane Science, 2005, Vol. 258, 35–42.
• [22] ZHAO YU., TAYLOR J.S., SHANKAR CHELLAM., Predicting RO/NF water quality by modified solution diffusion model and artificial neural networks, Journal of Membrane Science, 2005, Vol. 263, 38–46.
• [23] NIEMI H., BULSARI A., PALOSAARI S., Simulation of membrane separation by neural networks, Journal of Membrane Science, 1995, Vol. 102, 185–191.
• [24] AYDINER C., DEMIR I., YILDIZ E., Modeling flux decline in crossflow microfiltration using neural networks: the case of phosphate removal, Journal of Membrane Science, 2005, Vol. 248, 53–62.
• [25] TEODOSIU C., PASTRAVANU O., MACOVEANU M., Neural network models for ultrafiltration and backwashing, Water Research, 2000, Vol. 34, 4371–4380.
• [26] SHAHSAVAND A., POURAFSHARI CHENAR M., Neural networks modelling of hollow fibre membrane processes, Journal of Membrane Science, 2007, Vol. 297, 59–73.