Method for predicting converter terminal point using artificial nurve network technology

Abstract

The present invention discloses artificial neural network technological method of forecasting the terminal of medium-sized and small converter. For steel-making converter system, there are many factors, such as furnace life, gun position, sputtering, etc. to affect the terminal carbon content and temperature in non-linear relation hard to describe mathematically. The present invention applies neural network technology in the control system, and can monitor and forecast the non-linearity, non-determinacy and complexity effectively to forecast the terminal temperature and terminal carbon content of converter accurately.

Description

Technical field: [0001] The invention relates to a method for predicting the end point of a small and medium-sized converter. Background technique: [0002] Since the 1960s, people began to study trying to control the end point of the converter with a computer, and successfully developed a static model and a dynamic model of converter smelting. Because the static model only considers the initial and final state conditions of smelting, blowing according to the track calculated in advance, the complex blowing process factors cannot be considered, and no correction is made in the middle, so the hit rate of the end point is low. The dynamic model requires a more complex furnace information detection system, most of which use temperature measurement and carbon determination sub-lances to continuously feed back information in the furnace to the computer, and correct the blowing track until the blowing end, so the hit rate is relatively high. However, in order to obtain accurate m...

AI Technical Summary

Problems solved by technology

Because the static model only considers the initial and final state conditions of smelting, blowing according to the track calculated in advance, the complex blowing process factors cannot be considered, and no correction is made in the middle, so the end point hit rate is low

The dynamic model requires a more complex furnace information detection system, most of which use temperature measurement and carbon determination sub-guns to continuously feed back information in the furnace to the computer, and correct the blowing track until the blowing end, so the hit rate is higher

However, in order to obtain accurate melting pool information, the sub-lance and the oxygen lance should be kept at a certain distance. If the diameter of the furnace opening is too small, the sub-lance cannot be inserted into the furnace. Therefore, dynamic control is generally suitable for large-scale converters, and it is difficult to use small and medium-sized converters. And the secondary gun system is more complicated, the cost is higher, and the actual use effect is not very ideal

In view of the above reasons, the automatic control of the end point of domestic small and medium-sized converters has been difficult to achieve, basically relying on the traditional method of seeing the flame and judging the end point of smelting based on experience

This method of judging the end point based on experience is more affected by human factors and cannot accurately and objectively reflect the actual situation of the end point of converter smelting

Images