Optimal operation strategy extraction for blast furnace ironmaking process based on fuzzy C-means clustering

Abstract

Two key variables in blast furnace ironmaking - silicon content in hot metal ([Si]) and hot metal temperature (FeW) are considered and used to represent the thermal state in hot metal, while hourly output of hot metal (Fe/H) is used to represent the efficiency of ironmaking. The data is preprocessed by wavelet analysis to denoise and remove outliers. Fuzzy C-means clustering (FCM) is then used to identify the relation between efficiency of ironmaking and smelting intensity by using the processed data. Simulation based on data collected from No.7 blast furnace of Handan Steel show that the mean value of historical data (0.45) is not the stable thermal state of blast furnace. The system is more stable and has higher smelting intensity when silicon content is around 0.41, which shows that “low silica smelting practice” attempt in the steel industry can lower the energy consumption while keeping the smelting intensity and smooth production. It is proved that appropriate level of silicon content will lead to safe, smooth production with lower energy consumption and higher production.