Classification and the case matching algorithm of the blast furnace burden surface

Abstract

The relationship between the burden surface and the gas flow in blast furnace was studied in this paper using the improving k-means algorithm and graded case based matching method. An improved k-means classification algorithm was proposed based on the evaluation of effectiveness index to study the relationship between the burden surface and the gas flow in blast furnace from historical data, which proved the proposed algorithm has high accuracy according to the experimental data and different standard data sets. The paper also proposed a matching algorithm on the basis of the above clustering algorithm to obtain the most matched historical burden surface with the current burden surface. At last, compared with both of the improved grey similarity matching algorithm and Euclidean nearest neighbor matching algorithm, the results showed that the proposed method has higher efficiency and matching accuracy, and it is more suitable for the research of the relationship between burden surface and gas flow to assist the monitoring of the blast furnace to control burden surface.