Desulphurization Control System through Locally Weighted Regression Model

A new control method is proposed for controlling sulphur concentration in impeller desulphurization process. The proposed method is based on a locally weighted regression model, which is a type of Just-In-Time models. The desulphurization control system using the proposed method was developed and has been applied to actual plants. The proposed method determines the optimal quantity of auxiliary material from the information of the pre-processes which has actual process data. Significant effects on reducing sulphur concentration deviations and model maintenance load have been achieved in commercial production. The developed system has made contributions to reducing consumption of auxiliary material.