Method for determination of the amount of a model input data for predicting membrane fouling in reverse osmosis process and device using the same

摘要

One embodiment of the present invention provides a method for determining the amount of sample input data of a reverse osmosis membrane contamination prediction model. The method comprises the steps of: establishing a database of monitoring data collected from sensors of a reverse osmosis process; constructing a contamination prediction model of the reverse osmosis membrane using the database; calculating prediction accuracy by changing the amount of input data according to a future prediction time and a type of input variable using the prediction model; and determining the amount of input data when having the best prediction accuracy among the prediction accuracies. By predicting the exact degree of membrane contamination, the method can contribute to determining the timing of reverse osmosis membrane cleaning and replacement.