![]() | Only 14 pages are availabe for public view |
Abstract Coagulation is the most important stage in drinking water treatment processes for the maintenance of acceptable treated water quality and economic plant operation, which involves many complex physical and chemical phenomena. Moreover, the coagulant dosing rate is non-linearly correlated to raw water characteristics such as turbidity, conductivity, pH, temperature, etc. As such, coagulation reaction is hard or even impossible to control satisfactorily by conventional methods. Traditionally, jar tests are used to determine the optimum coagulant dosage. However, this is expensive and time-consuming and does not enable responses to changes in raw water quality in real-time. Modeling can be used to overcome these limitations. In this study, an artificial neural network (ANN) was used for modeling of coagulant dosage in the drinking water treatment plant of Mariout 1, Egypt. Six on-line variables of raw water quality including pH, mixing speed (Slow) and Mixing speed (Flash), slow mixing Time, Flash mixing Time, and alum dosage were used to build the coagulant dosage model. The relative importance of each input variable on the turbidity removal efficiency. It can be demonstrated that all the input variables had strong effects on turbidity removal efficiency. However, the pH exhibited the most important factor among the input variables with a relative index of 41%. Therefore, none of the investigated variables could be excluded from this study. |