AWWA MTC57563

An artificial neural network model is derived and validated for predicting contaminantremoval during nanofiltration of ground and surface waters under conditions typical of drinkingwater treatment. The network was trained using operating conditions such as permeate flux, feedwater recovery, and element recovery (crossflow velocity), and feed water quality parametersincluding pH, total dissolved solids concentration (surrogate for ionic strength), targetcontaminant concentration, and where possible the diffusion coefficient as inputs to predict thepermeate concentration. Deterministic and pseudo stochastic simulations showed that artificialneural networks closely predicted permeate concentrations of several organic and inorganiccontaminants in experiments using source waters from seven different locations by twocommercial thin film composite membranes operating in a wide range of permeate fluxes andfeed water recoveries. Hence, neural networks can predict transport of heterogeneous watertreatment contaminants such as natural organic matter and disinfection byproduct precursors,whose physicochemical properties are unknown. Includes 36 references, figure.

Product Details

Edition:

Vol. - No.

Published:

03/05/2003

Number of Pages:

8

File Size:

1 file , 220 KB