Back propagation Neural network modeling approach in the anaerobic digestion of wastewater treatment

In this paper, the use of back propagation neural network for modeling is investigated from the experimental values obtained in a laboratory scale system of anaerobic tapered fluidized bed reactor. The input parameters considered for modeling are four inputs, flow of influent, COD_in, pH_in, hydraulic retention time and two outputs viz., COD_out, CH₄ gas yield. Back propagation neural network has great adaptability to the variations of system configuration and operation condition and the prediction results are found to be closer to the experimental results.