LSTM Method for predicting location data of electrode bar in electric furnace using Long Short-Term Memory

摘要

A method for predicting electrode bar position data in an apparatus for predicting position data regarding three electrode bars installed in an electric furnace of the present invention comprises the following steps of: processing input data when data regarding the three electrode bars is input; creating a long short-term memory model (LSTM) network; proceeding learning about the processed data in the LSTM network; and predicting the position data regarding the three electrode bars using the learned data. According to the present invention, the electrode bar position data in the electric furnace is predicted using the LSTM, therefore a position of the electrode bar can be predicted more easily and accurately.