Water Quality Assessment in Distribution System Using Artificial Intelligence

Abstract

In this study various artificial intelligence techniques have been compared for assessment and prediction of water quality in various zones of municipal distribution system using six physico-chemical characteristics viz. pH, alkalinity, hardness, dissolved oxygen (DO), total solids (TS) and most probable number (MPN). Fuzzy expert system, artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) were used for the comparative study. The proposed expert system includes a fuzzy model consisting of IF-THEN rules to determine WQI based on water quality characteristics. The fuzzy models are developed using triangular and trapezoidal membership functions with centroid, bisector and mean of maxima (MOM) methods for defuzzification. In ANN method the cascade feed forward back propagation (CFBP) and feed forward back propagation (FFBP) algorithms were compared for prediction of water quality in the municipal distribution system. The comparative study was carried out by varying the number of neuron (1-10) in the hidden layer, by changing length of training dataset and by changing transfer function. ANFIS models are developed by using triangular, trapezoidal, bell and Gaussian membership function. Further, these artificial intelligence techniques are compared with multiple linear regression technique, which is the commonly used statistical technique for modelling water quality variables. The study revealed that artificial neural network (ANN) outperforms other modelling techniques and is a robust tool for understanding the poorly defined relations between water quality variables and water quality index (WQI) in municipal distribution system. This tool could be of great help to the distribution system operator and manager to find change in WQI with changes in water quality varibles.