an artificial neural network model for the prediction of pressure filters performance and determination of optimum turbidity for coli-form and total bacteria removal

one of the principles for designing and using the various units of water treatment plants is ability of assigning and predicting performance of those units in different and various conditions that could be checked by making pilot and could be modeled by means of available programs and software such as artificial neural network. at this study a model provided for predict performance of pressure filters to remove turbidity, also relationship between turbidity quantity in optimize surface loading removal of bacteria have been investigated. this targets was considerate: (1) experimental studies on performance of pressure filters for turbidity remove under different conditions, including influent turbidity, filtration rate and filter pressure, (2) extract of statistical analysis results and determine of the minimum and maximum effluent turbidity, (3) using artificial neural networks for providing the appropriate model in determining filter performance in turbidity remove, (4) determining of the desired model indicators for using in performance of same filters, (5) determining the best influent turbidity and surface loading to receive maximum removal bacteria and coli-form. appropriate pilot making, sample testing was done with 1300 of sample and then the minimum and maximum effluent turbidity was determined based on calculation and statistical analysis. finally, the best model was determined and its indicators as one of the major objectives were presented for this study in similar cases.