A coupled model tree (MT) genetic algorithm (GA) scheme for biofouling assessment in pipelines.

A computerized learning algorithm was developed for assessing the extent of biofouling formations on the inner surfaces of water supply pipelines. Four identical pipeline experimental systems with four different types of inlet waters were set up as part of a large cooperative project between academia and industry in Israel on biofouling modeling, prediction, and prevention in pipeline systems. Samples were taken periodically for hydraulic, chemical, and biological analyses. Biofilm sampling was done using Robbins devices, carrying stainless steel coupons. An MT-GA, a hybrid model combining model trees (MTs) and genetic algorithms (GAs) in which the sampled input data are selected by the proposed methodology, was developed. The method outcome is a set of empirical linear rules which form a model tree, iteratively optimized by a GA and verified using the dataset resulting from the empirical field studies. Good correlations were achieved between modeled and observed cell coverage area within the biofilm. Sensitivity analysis was conducted by testing the model's response to changes in: (1) the biofilm measure used as output (target) variable; (2) variability of GA parameters; and (3) input attributes. The proposed methodology provides a new tool for biofouling assessment in pipelines.

[1]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[2]  Ho,et al.  A Combined Pore Blockage and Cake Filtration Model for Protein Fouling during Microfiltration. , 2000, Journal of colloid and interface science.

[3]  P Stoodley,et al.  Influence of hydrodynamics and nutrients on biofilm structure , 1998, Journal of applied microbiology.

[4]  M. Vieira,et al.  Drinking water biofilm assessment of total and culturable bacteria under different operating conditions , 2006, Biofouling.

[5]  T. E. Cloete Biofouling control in industrial water systems: What we know and what we need to know , 2003 .

[6]  A. Camper,et al.  Development and structure of drinking water biofilms and techniques for their study , 1998, Journal of applied microbiology.

[7]  G. Amy,et al.  Predicting membrane flux decline from complex mixtures using flow-field flow fractionation measurements and semi-empirical theory. , 2005, Water Science and Technology.

[8]  Albert S Kim,et al.  EPS biofouling in membrane filtration: an analytic modeling study. , 2006, Journal of colloid and interface science.

[9]  Randy L. Haupt,et al.  Practical Genetic Algorithms , 1998 .

[10]  Avi Ostfeld,et al.  A coupled model tree-genetic algorithm scheme for flow and water quality predictions in watersheds , 2008 .

[11]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[12]  W. Sand,et al.  Extracellular polymeric substances mediate bioleaching/biocorrosion via interfacial processes involving iron(III) ions and acidophilic bacteria. , 2006, Research in microbiology.

[13]  Paul Stoodley,et al.  A model of fluid–biofilm interaction using a Burger material law , 2007, Biotechnology and bioengineering.

[14]  D. Johnson,et al.  Sulfidogenesis and selective precipitation of metals at low pH mediated by Acidithiobacillus spp. and acidophilic sulfate-reducing bacteria , 2010 .

[15]  B. Kintz,et al.  Computational Handbook of Statistics , 1968 .

[16]  Y K Choi,et al.  Modeling of extracellular polymeric substances and soluble microbial products production in a submerged membrane bioreactor at various SRTs. , 2006, Water science and technology : a journal of the International Association on Water Pollution Research.

[17]  Quan J. Wang,et al.  Using genetic algorithms to optimise model parameters , 1997 .

[18]  E. Friedler,et al.  A preliminary coupled MT-GA model for the prediction of highway runoff quality. , 2009, The Science of the total environment.

[19]  Ralf Kuriyel,et al.  Combined models of membrane fouling: Development and application to microfiltration and ultrafiltration of biological fluids , 2006 .

[20]  Hong Men,et al.  Microbial Growth Model and Stability Analysis , 2009, 2009 First International Workshop on Education Technology and Computer Science.

[21]  Weiyi Li,et al.  A three mechanism model to describe fouling of microfiltration membranes , 2006 .

[22]  Fenglin Yang,et al.  Application of fractal permeation model to investigate membrane fouling in membrane bioreactor , 2005 .

[23]  E. Friedler,et al.  Modeling highway runoff pollutant levels using a data driven model. , 2009, Water science and technology : a journal of the International Association on Water Pollution Research.