Degree Name

Doctor of Philosophy


Department of Civil and Mining Engineering


The water industry is facing increased pressure to produce higher quality treated water at a lower cost. The operation of water treatment plants is considerably different from most manufacturing industrial operations because raw water sources are often subject to natural perturbations. The efficiency of an existing treatment plant closely relates to the operating conditions of the plant, particularly to that of coagulant types and dosages. In this study, an Artificial Neural Network (ANN) model has been applied to water treatment plant data in order to predict the coagulant dosage. The ANNs provide an alternative means of computation inspired by the functioning of the human brain and nervous system and which are efficient in establishing cause-effect relationships. The objectives of this research are to evaluate the feasibility and capability of ANNs to aid in the operation of water treatment plants, to determine the correlations between the water treatment parameters and the coagulant dosage levels and hence to predict future doses. The economic benefits of using ANNs and its performance against time series models are also evaluated. The data set supplied by Wyong Shire Council, NSW is used in this study.