The influence of aeration scheme and aeration rate on the permeate flux for wastewater treatment using membrane bioreactors: Experimental and artificial neural network modeling

In this paper, the effect of time, aeration scheme, aeration rate, and mixed liquor suspended solid (MLSS) concentration on the permeate flux in membrane bioreactors have been studied. Aeration rates of 0.5, 1.0, and 1.5 LPM were tested with MLSS concentrations of 5, 10, and 15 g/L. Furthermore, a continuous and pulsed aeration scheme (5 min on and 5 min off) was tested. The experimental data were used to develop an artificial neural network (ANN) model, which showed excellent agreement (R2 = 0.9963) with the data. The average normalized flux decreased as the MLSS concentration increased from 5 to 15 g/L and increased as the aeration rate increased from 0.5 to 1.5 LPM. No clear correlation was found between the aeration schemes and the average normalized flux. ANN weights analysis revealed the order of importance was time > aeration rate > MLSS concentration > aeration scheme.