실험적 모델과 인공신경망을 사용한 소독부산물 생성예측 = Prediction of Chlorination By-products Using Empirical Model and Artificial Neural Networks(ANN)

다국어 초록 (Multilingual Abstract)

Water treatment facilities face new challenges with regard to maintaining disinfectants as well as reducing disinfection by-products(DBPs). The need to control DBPs in water treatment facilities has stimulated the development of various models including empirical models, kinetic based models, and artificial neural networks (ANN). In order to evaluate the appropriate models for simulating DBPs, several attempts have been made to compare an empirical based model and ANN simulations using bench-scale experiment data. The empirical based model is considered a powerful modeling tool in simulating DBPs. ANN Simulation also provides a potential modeling tool in predicting DBP formation. The external evaluation of these models is further needed by using full-scale monitoring data.