Information System for Real-Time Prediction of the Silicon Content of Iron in a Blast Furnace

A general description of an algorithm for predicting the silicon content in the iron of a blast furnace is given. It is based on the knowledge of the processes occurring in the furnace and the general laws of transient processes. The algorithm allows real-time and 10 hour prediction of the silicon content. A linearized model of the blast furnace process and a combined full-scale/mathematical approach are used. They allow customize the model to the blast furnace conditions, taking into account changes in the composition and properties of iron ore raw materials and coke and in the blast and smelting parameters. The information/modeling system developed based on the algorithm is integrated into the information system of the MMK blast furnace shop. The architecture of the software is described and its operation is illustrated. The accuracy of predicting the silicon content in iron is assessed.