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 backpropagation 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.
[1]
Glenn W. Ellis,et al.
Information processing coupled with expert systems for water treatment plants
,
1992
.
[2]
James L. McClelland,et al.
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
,
1986
.
[3]
David M. Skapura,et al.
Neural networks - algorithms, applications, and programming techniques
,
1991,
Computation and neural systems series.
[4]
P. J. Ossenbruggen.
Time Series Models for Treatment of Surface Waters
,
1985
.
[5]
Kenji Baba,et al.
Explicit representation of knowledge acquired from plant historical data using neural network
,
1990,
1990 IJCNN International Joint Conference on Neural Networks.