Modeling and optimization of turbidity removal from produced water using response surface methodology and artificial neural network

In this study, results of parametric effects and optimization turbidity removal from produced water using response surface methodology (RSM) artificial neural network (ANN) based on a statistically designed experimentation via the Box–Behnken design (BBD) are reported. A three-level, three-factor BBD was employed dosage (x1), time (x2) temperature (x3) as process variables. quadratic polynomial model obtained to predict efficiency. The RSM predicted an optimal efficiency 83% at conditions x1 (1 g/L), x2 (16.5 min) x3 (45 °C) validated experimentally 82.73% with low lack fit F value 0.6 CV 8.22%. ANN 83.01% 82.98%. Both models showed be effective in describing effect considered operating variables water. However, described more accurately when compared model, smaller PRE (percentage relative error) AAD (absolute average deviation) ±0.0241% ±0.0139%, respectively.