Application of artificial neural networks to the real time operation of water treatment plants

Abstract

The water industry is facing increased pressure to produce higher quality treated water at a lower cost. The efficiency of a treatment process closely relates to the operation of the plant. To improve the operating performance, an Artificial Neural Network (ANN) paradigm has been applied to a water treatment plant. An ANN which is able to learn the non-linear performance relationships of historical data of a plant, has been proved to be capable of providing operational guidance for plant operators. A back-propagation network is used to determine the alum and polymer dosages. The results show that the ANN model is most promising. The correlation coefficients (r) between the actual and predicted values for the alum and polymer dosages were both 0.97 and the average absolute percentage errors were 4.09% and 8.76% for the alum and polymer dosages respectively. The application of the ANN model is illustrated using data from Wyong Shire Council's Wyong Water Treatment Plant on the Central Coast of NSW.

Drinking water quality and treatment: the use of artificial neural networks

“…As suggested earlier, the use of ANNs in the drinking water treatment industry is also on the rise. Applications other than those discussed in subsequent sections include trihalomethane formation and speciation (Hutton et al 1996), alum and polymer dose forecasting in coagulation (Mirsepassi et al 1995), source water salinity forecasting (DeSilets et al 1992), and the prediction of residual chlorine in the distribution system (Rodriguez et al 1997).…”

Neural Networks in Process and Automation

“…Applications include sintering, flocculation, grinding, distillation, measurement calibration, valve fault diagnosis, and distillation fault diagnosis, which reveal the wide applicability for NNs within industry [8,[13][14][15][16][17][18][19]. Among thousands,…”

Developing artificial neural network models of water treatment processes: a guide for utilities

“…With respect to water quality and demand forecasting, models have been developed for trihalomethane (THM) formation and speciation (Hutton et al 1996), source water salinity forecasting (DeSilets et al 1992), raw water colour forecasting (Zhang and Stanley 1997), and water demand forecasting (Baxter et al 2001a). Process models have been developed for alum and polymer dose forecasting in coagulation (Mirsepassi et al 1995), lime dose and hardness in softening (Baxter et al 2001a), and turbidity and colour removal through enhanced coagulation and filtration (Stanley et al 2000). The control of coagulation has been demonstrated by Baxter et al (2002).…”