Gasholder level control based on time-series analysis and process heuristics

A novel method to control gasholder levels in an iron and steel company with accurate prediction of the future trend is presented. Although various gasholders are used to recycle by-product gases generated during the ironmaking, coke-burning, and steel-making processes, the capacities of these gasholders are insufficient to handle large amounts of gases. To overcome this problem, tight control of the gasholder level should be maintained by predicting their anticipated changes. However, the current prediction logic cannot show satisfactory results due to the lack of characterization of the relevant processes. In the proposed method, time-series modeling and heuristics from industrial operators are used to correctly reflect the process characteristics and deal with unexpected process delays. By applying the proposed method to an off-line data set, a significant reduction in the discrepancy between predicted values and actual values was observed. The method is expected to be adopted in the prediction system of POSCO.