Artificial Neural Network (ANN) for Optimization of Palm Oil Mill Effluent (POME) Treatment using Reverse Osmosis Membrane

Abstract

The treatment of palm oil mill effluent (POME) by Reverse Osmosis (RO) membrane was achieved experimentally. The biological oxygen demand (BOD), chemical oxygen demand (COD) and Color as final response of POME treatment process were selected. However, main influence factors on POME treatment process as concentration, transmembrane pressure and pH were tested on responses. The experimental results of responses were compared to the prediction by applying of Artificial Neural Network (ANN) as a simulation technique to create model of the process. Higher validation of ANN model was found for COD, BOD and Color which the prediction values very close compared to experimental result. The COD removal was investigated as a major affect factor in experiments. The best removal of COD was obtained at lower of POME concentration, pH, transmembrane pressure and time of contact. Therefore, these results showed that appreciate model created by ANN for POME treatment process which contributed easily to apply in industrial filed as future application.