TO INVESTIGATE EFFICIENT FACTORS IN THE DOSAGE OF FeCl3 INCOAGULATION OF COLLOIDAL PARTICLES USING GMDH INWATER TREATMENT

Coagulation and flocculation are essential processes for turbidity removal from drinking water. When an unusual condition occurs, such as a heavy rain which brings high turbidity to water source, the predictable operation method can be hardly determine optimal dosage of chemical materials. Determining the optimal dosage of materials is vital since shortage dosage will result in unqualified water quality. Also it is crucial to maintain economic plant operation such as reducing man power and expensive chemical costs. Jar test in laboratory take a place on operators’own experience to determine the optimum material dosage. In this Study, Group Method of Data Handling (GMDH)-type neural networks have been used for modeling and prediction of drinking water quality in lab; using input-output data set. To validate the proposed model, a case study was carried out based on the data sets obtained from Guilan-WTP. For modeling, the experimental data obtained from the lab were divided into 70% for train and 30% for test sections. The predicted values were compared with those of experimental values in order to estimate the performance of the GMDH-neural network. The model values showed a very good regression with the experimental results.