Data from an experimental study on the use of ozone to inactivate a parvovirus in a synthetic and an actual industrial water source was analyzed using an artificial neural network (ANN). The goal of this analysis was to predict the necessary ozone dose to disinfect the water as a function of specific environmental conditions. The network consisted of six inputs (time, alkalinity, organic carbon concentration, initial virus concentration, sonication, and ozone residual) and one output (virus concentration). The network was effective in predicting the outcome of ozone disinfection under conditions not previously encountered in training. A sensitivity analysis revealed that the network learned relationships among the variables similar to accepted trends in the disinfection process. A comparison with current EPA procedures also showed the effectiveness of the ANN approach.
[1]
M. McGuire,et al.
APPLYING OZONE FOR ORGANICS CONTROL AND DISINFECTION : A UTILITY PERSPECTIVE
,
1991
.
[2]
David A. Reckhow,et al.
The Removal of Organic Halide Precursors by Preozonation and Alum Coagulation
,
1984,
Journal AWWA.
[3]
J. Staehelin,et al.
Decomposition of ozone in water in the presence of organic solutes acting as promoters and inhibitors of radical chain reactions.
,
1985,
Environmental science & technology.
[4]
R. Rice,et al.
Handbook of ozone technology and applications. Vol. 2. Ozone for drinking water treatment
,
1984
.
[5]
S. Regli,et al.
Evaluation of Ozone Disinfection Systems: Characteristic Time T
,
1992
.