A dynamic soft-sensing system and method for silicon content in molten iron during blast furnace ironmaking

Abstract

The invention provides a dynamic soft measurement system and method for the silicon content of molten iron during the blast furnace ironmaking process. The system includes: actual data acquisition unit, normalized preprocessing unit, and dynamic soft measurement unit; the method includes: obtaining the parameters required for dynamic soft measurement of silicon content in blast furnace molten iron: the working condition parameters of the current heat, the working conditions of the previous heat Parameters and the silicon content of molten iron in the previous heat; perform normalization preprocessing on the parameters required for dynamic soft measurement of silicon content in blast furnace molten iron; use the dynamic soft measurement model of silicon content in molten iron during the blast furnace ironmaking process to perform dynamic soft measurement of silicon content in molten iron . Compared with the existing manual measurement or testing of the silicon content of molten iron, the present invention reduces the operator's workload, reduces the measurement uncertainty introduced by manual operation, improves the timeliness and accuracy of the measurement, and has high credibility. . The method of the invention has universality for predicting the silicon content of molten iron in the blast furnace smelting process, and is helpful to realize closed-loop integrated control and optimized operation of the quality of molten iron in the blast furnace.

Description

technical field [0001] The invention relates to the technical field of automatic control of blast furnace smelting, in particular to a dynamic soft measurement system and method for silicon content in molten iron during the blast furnace ironmaking process. Background technique [0002] Blast furnace production is a continuous dynamic time-varying nonlinear multi-variable coupling system carried out under airtight conditions where high temperature, high pressure, multi-physical fields coexist, and chemical reactions and transfer phenomena occur simultaneously. The key factor of high yield, high quality and low consumption. During the smelting process, the quality of furnace temperature control directly affects the fluctuation of furnace conditions, and the fluctuation of furnace conditions determines the control mode of furnace temperature. "Too high" or "too low" furnace temperature can easily induce abnormal furnace conditions. In actual production, the key technology to ...

AI Technical Summary

Problems solved by technology

[0006] Most of the methods of the above-mentioned patents and related documents use all relevant variables collected by the blast furnace as input variables, making full use of the rich data features, but also introducing more noise and time-consuming problems.

In addition, in the actual production process, due to the failure of detection instruments and transmitters and other devices and the influence of complex electromagnetic interference, there are many unknown interferences in the measurement data, and its actual industrial background has a high impact on the robustness of the algorithm itself. However, the method reported in the above-mentioned patent has not considered the robustness issue. In view of changes in smelting conditions and abnormal jitter, the generalization ability of the silicon content prediction model in molten iron will be greatly reduced.

In addition, the above method does not consider the input-output timing and process time-delay relationship, so it cannot capture the inherent dynamic characteristics of the smelting process well

Images