Modeling fouling in a large RO system with artificial neural networks

Artificial neural network (ANN) models were developed from a six-year process database to quantify causes of membrane fouling in the first stage of a full-scale, three-stage reverse osmosis (RO) system. The data comprised 59 hydraulic and water quality parameters, representing 190 runs between membrane cleanings. The runs were segmented into a Phase 1 period of initial particle deposition followed by a Phase 2 period of gradual biofilm and scale growth. The phases were modeled separately. Rather than specific flux, a fouling indicator P-foul' was calculated from RO system pressures which are normally modulated in part to compensate for fouling. The ANN modeling found that the best predictors of Phase 1 fouling were total chlorine, electrical conductance, TDS, ammonia, and the cartridge filter pressure drop. The best predictors of Phase 2 fouling were turbidity, nitrate, organic nitrogen, nitrite, and total chlorine. These results are consistent with known Phase 1 and 2 fouling mechanisms. The predictive electrical conductance, TDS, and turbidity are "bulk" water quality parameters which were found significantly correlated to sparsely measured cations, sulfates, chlorides, and alkalinity. Simulations with different chlorine concentrations demonstrate how the model could be used to reduce fouling rates.