Forecasting method of content of sulfur in blast-furnace molten iron

Abstract

The invention provides a forecasting method of content of sulfur in blast-furnace molten iron. The forecasting method comprises the four steps of parameter selection, data pretreatment, predication algorithm design and result output. The slag basicity, the previous molten iron silicon content, the in-furnace coke S content and the in-furnace pulverized coal S content to which a sulfur content short-period mean value, a sulfur content middle-period mean value, a sulfur content long-period mean value and previous molten iron correspond serve as input variables for forecasting the content of sulfur in the molten iron; the content of sulfur in the next molten iron is forecast by using the chemical reaction process of forming the molten iron in a blast furnace in combination of RBF (Radial Based Function) neural networks; when furnace conditions slightly fluctuate, the forecasting depends on a simple moving average system; and when the furnace conditions substantially fluctuate, the slag basicity and the previous molten iron silicon content are automatically introduced, so that the influence of furnace condition fluctuation on the sulfur content is eliminated to the maximum degree by few independent variables, thus the high forecasting accuracy is achieved, the forecasting hit rate of the sulfur content of the blast-furnace molten iron is increased, the effective control on sulfur content in pig iron is realized, and the condition that the sulfur content of the in pig iron is excessively high is avoided.

Description

technical field [0001] The invention belongs to the field of automatic control of blast furnace smelting, in particular to a method for forecasting the sulfur content of molten iron in a blast furnace. Background technique [0002] The blast furnace is a closed high-temperature reaction vessel. The production process is accompanied by complex physical and chemical reactions and heat and mass transfer processes, and its internal changes cannot be directly detected. Generally, the process parameters are used to indirectly judge the working status of the blast furnace. The sulfur content in pig iron is one of the main indicators for evaluating the quality of pig iron, so ensuring the qualified sulfur content in pig iron is one of the important tasks in blast furnace smelting. Accurately predicting the sulfur content of hot metal in blast furnaces can help operators take timely measures to prevent excessive sulfur content in pig iron. [0003] In the paper "Application of Neur...

AI Technical Summary

Problems solved by technology

[0008] The above methods are either the hot metal desulfurization model realized in the steelmaking process, or the method of predicting the silicon content in the hot metal, which cannot effectively solve the problem of predicting the sulfur content in the hot metal. The hit rate is significantly reduced when

Images