정수장내 약품투입량 자동연산을 위한 신경회로망의 적용 : Focusing of Liquid Coagulant = Application of Neural Network to the Automatic Calculation of Chemicals Dosing for Water Treatment Plant

다국어 초록 (Multilingual Abstract)

In this study, the applicability of artificial neural network is analyzed and evaluated to determine the ratio of chemicals dosing in water treatment.
To determine the ratio of chemicals dosing for coagulant is very important to the effective control and management of water quality in the water treatment process.
It is possible to apply the neural network to the modeling of water treatment process control due to the learning capacities of nonlinearity and the interpolation of input and output data set. The learning process Plays a role of mapping in the relationships between input and output data set, that means the estimation of optimal parameters of the system. So, the more learning continues by rule, the more accurate parameters can be estimated.
The neural network model has the function of learning the process which can be trained with the error backpropagation algorithm in two phases. First, the foaming phase permits to fed the best parameters between input and output sets. Second, the adaptive phase use the error backpropagation algorithm in order to learn provided data sets.
Turbidity, water temperature, alkalinity, pH and electrical conductivity of raw water which inflows into water treatment plant are used as major input data set of the neural network model. Also, the ratio of chemicals dosing is used as output value of the model. The model can be estimated the ratio of chemicals dosing for each different water quality as input pattern with estimated parameters.
The results of this study were compared with the historical observed data by statistical analysis and show the validities in applying to water treatment process control for the determination of chemicals dosing. Based on this study, optimal determination of the ratio of chemicals dosing can be Performed and better water can be produced by using the results with the control of water quality in the water treatment plant.