Journal of Water Supply: Research and Technology—AQUA Vol 57 No 1 pp 23–34 © IWA Publishing 2008 doi:10.2166/aqua.2008.008
Neural networks and genetic algorithms in membrane technology modelling
S. Strugholtz, S. Panglisch, R. Gimbel and J. Gebhardt
University of Duisburg-Essen, Institute for Energy and Environmental Engineering, Bismarckstrasse 90, 47057, Duisburg, Germany silke.strugholtz@uni-due.de
IWW Rhenish-Westfalian Institute for Water Research, Moritzstrasse 24, 45476, Mülheim an der Ruhr, Germany
aquatune – Dr Gebhardt & Co. GmbH, Untig Mühl, 65326, Aarbergen, Germany
ABSTRACT
For the operation of many drinking water treatment processes influences of raw water quality and operational settings on process performance are unknown. Therefore black box models such as neural networks are a promising way to model drinking water treatment processes. The combination of neural networks with genetic algorithms also enables fast process optimization. The application of neural networks and genetic algorithms in drinking water treatment will be shown for a ceramic membrane microfiltration plant. First, neural networks were applied for prediction of the course of transmembrane pressure (TMP) over several cycles with high precision. In a second step these models were applied for operational costs optimization by genetic algorithms. Based on Darwin's idea of the survival of the fittest, settings for filtration time, flux and aluminium dosage were optimized, leading to minimized operational costs with a costs reduction of about 15%. The study proved the effectiveness of genetic algorithms and the applicability for online optimization being planned for further studies.
Keywords: ceramic membranes; drinking water; genetic algorithms; neural networks; optimization
Full article (PDF Format)
PAY-PER-VIEW: Buy this article for £20.00 (IWA MEMBER PRICE: £15.00)
|
