Method for assessing integral states of furnace conditions by aid of pattern recognition technology

Abstract

The invention discloses a method for assessing integral states of furnace conditions by the aid of a pattern recognition technology. The method sequentially includes steps of 1), acquiring various required data of blast furnaces; 2), dividing furnace top gas flow distribution patterns into A categories, dividing furnace profile variation patterns into B categories, dividing furnace temperature variation patterns into C categories and dividing furnace hearth working state patterns into D categories; 4), confirming current furnace conditions; 5), selecting discharging indexes, melting loss reaction carbon quantities, blast furnace utilization coefficients and fuel ratios and judging current furnace top gas flow distribution conditions, furnace profile variation conditions, furnace temperature conditions and furnace hearth conditions which are acquired in the step 4). The method for assessing the integral states of the furnace conditions has the advantages that the running states of the blast furnaces can be integrally reflected, furnace condition assessing results are accurate and are high in instantaneity, the accuracy of the blast furnace maintenance basis can be improved, and the possibility of abnormal running of the blast furnaces can be reduced.

Description

technical field [0001] The invention relates to the technical field of iron and steel smelting control, in particular to a method for evaluating the overall state of a furnace by using pattern recognition technology. technical background [0002] At present, China's steel production capacity is more than 700 million tons. Most of China uses blast furnace ironmaking. Each blast furnace is equipped with a sintering plant and a coking plant. Sintering, coking, and ironmaking together constitute an ironmaking system. A series of huge pollution sources produce a large amount of dust, noise, sulfur dioxide and other pollutants every year. Once the blast furnace system is out of order, the emissions will be even more alarming. The overall state of the blast furnace is stable and controllable, which has become the main goal of the majority of blast furnace workers. [0003] At present, the blast furnace is gradually becoming large-scale, and the inner volume of each blast furnace is...

AI Technical Summary

Problems solved by technology

[0003] At present, the blast furnace is gradually becoming large-scale, and the inner volume of each blast furnace is 1000m 3 to 5500m 3 Varies, with a volume of 3200m 3 Taking the blast furnace as an example, it can produce about 9,000 tons of pig iron per day and produce about 15,000 tons of CO 2 Once the overall condition of the blast furnace is abnormal, the output will drop, but the consumption will rise sharply. For example, the output of pig iron will drop to 5,000 tons, but the consumption will be almost the same. Huge damage was caused, and ensuring the stability of the overall condition of the blast furnace and smooth operation became the first task of the blast furnace operation

[0004] Although the blast furnace itself is a multi-variable, large-lag, and nonlinear huge system, there are huge material flows, energy flows, and information flows in the blast furnace smelting process. 3 The large-scale blast furnaces in China have several overall abnormalities every year due to operational reasons. Once the judgment is wrong, it will cause huge losses. However, due to the huge volume of the blast furnace and the large amount of monitoring information, each large-scale blast furnace has more than 500 points of detection Content, different personnel will come to different views on the same furnace condition due to differences in experience and skills, and will take different adjustment measures. Over the years, blast furnace workers at home and abroad have conducted decades of exploration in the development of blast furnace mathematical models, the design and application of blast furnace expert systems, etc. Although some achievements have been made, they are still far from the practical requirements. Far away, the document "Chu Mansheng, Overview of Blast Furnace Mathematical Model Based on Reaction Kinetics, Henan Metallurgy, June 2009" summarizes Japan's achievements in blast furnace mathematical model development in recent decades, and most of the practical mathematical models The model only focuses on the local problems of the blast furnace, such as material distribution simulation, furnace type management, hearth balance, piping, sliding materials, etc. The mathematical model of the whole furnace only has a demonstration function, and it is far from the actual evaluation and control of the blast furnace process. Chen Lingkun et al., "Development and Research of Expert System for Blast Furnace Smelting, Iron and Steel, January 2006". Balance calculation, etc.) to combine various objectives into a whole of blast furnace process evaluation, but the optimization of individual objectives does not represent the overall optimization

There is currently no way to use computer technology to assess the overall condition of a blast furnace in real time

Images