Identification of the Optimal Control Center for Blast Furnace Thermal State Based on the Fuzzy C-means Clustering

Abstract

It is required to maintain silicon content in hot metal ([Si]) at a stable level to ensure smooth operation of the blast furnace ironmaking process. However, current blast furnace control strategy always leads to frequent fluctuation of silicon content in hot metal. To stabilize blast furnace operation, this article attempts to identify the optimum control centre of silicon content through exploring the operational data of blast furnace ironmaking process. A quantitative analysis of the impact of thermal state on the smelting efficiency and intensity is presented by combining wavelet denoising and fuzzy c-means (FCM) clustering. Simulation results show that the commonly adopted mean value of historical data is not necessarily the optimum state of blast furnace operation. There exists some optimum state lower than the mean value, under which higher smelting efficiency and intensity can be achieved. It is also proved that the "low silica smelting practice" attempt in the steel industry is feasible and meaningful.KEY WORDS: fuzzy C-means clustering; wavelet denoising; stability; silicon content in hot metal; hourly hot metal output.

Discovering Categorical Main and Interaction Effects Based on Association Rule Mining

“…For BF-a, silicon content lower than 0.3736 will be regarded as low, higher than 0.8059 will be seen as high, otherwise is proper. Similarly, the corresponding thresholds for BF-b are 0.4132 and 0.8251 [33]. The target is to predict whether the silicon content of hot metal is low, high or proper.…”

Support algorithm for blast furnace operation with optimal fuel consumption

“…Apart from the usual monitoring of real BF processes [1,2] and mathematical and numerical models [3][4][5][6][7], which can be supported by physical cold models [8][9][10][11], the common use of neural networks for controlling hot metal quality and temperature [12][13][14][15][16][17] should be mentioned. Advanced methods such as genetic algorithms [18,19], subspace methods [20][21][22], or fuzzy clustering [23] are also reported.…”