A Neural Network Model for Prediction of Tri-Halo-Methane Concentration in Drinking Water

In this study a neural network model is proposed for modeling tri-halo-methane concentration in drinking water. After training, the neural network model predicts tri-halo-methane concentration based on input data. Parameters such as pH, Temperature, free chlorine residue and TOC were used as input data. To validate the proposed method, a case study was carried out, based on the data obtained from Guilan grand treatment plant (Sangar). The Levenberg-Marquardt algorithm was selected as the best of thirteen back-propagation algorithms. The optimal neuron number for Levenberg Marquardt algorithm is 8 neurons. The performance of modeling was determined. The trends of the forecast and measured data were in good agreement.