ANN Model of Wastewater Treatment Process

Abstract

In this work, total solids reduction process was numerically modeled with response surface methodology (RSM) and Artificial neural network (ANN) models. The experimental data was used for training these models. Amplitude of the ultrasonic waves, time of ultrasonication and total solids present in the sludge are input to the model. These factors are varied to five levels and by conducting design of experiments, the actual values were measured. The response surface methodology was used to determine the relation between the factors and total reduction in solids. To overcome the flaws in the response surface methodology, an artificial neural network model is developed and the results of the ANN models are compared with RSM models and experimentally measured values.