CN-122012846-A - Carbon-oxygen accumulation control method, system, equipment and storage medium based on low-carbon steelmaking

CN122012846ACN 122012846 ACN122012846 ACN 122012846ACN-122012846-A

Abstract

The invention relates to the technical field of ferrous metallurgy steelmaking, and particularly provides a carbon-oxygen product control method, a system, equipment and a storage medium based on low-carbon steelmaking, which comprise the steps of obtaining historical smelting parameters and historical molten pool state information, constructing a dynamic prediction model for predicting the change trend of carbon-oxygen product, and obtaining a prediction model; and based on the prediction result, performing dynamic regulation and control by at least one operation of adjusting oxygen supply, adjusting bottom blowing gas flow and adjusting gun position at the end of blowing to obtain the blowing state meeting the end control condition. The invention realizes the real-time prediction and dynamic regulation of the carbon-oxygen reaction trend in the converting process, and improves the control precision of the endpoint carbon content and the endpoint temperature.

Inventors

XU WEIKANG
WANG XUEXIN
CAO YUNTAO
LIU JIANWEI

Assignees

山东钢铁集团日照有限公司

Dates

Publication Date: 20260512
Application Date: 20251212

Claims (10)

1. A carbon-oxygen accumulation control method based on low-carbon steelmaking is characterized by comprising the following steps: acquiring historical smelting parameters and historical molten pool state information, and constructing a dynamic prediction model for predicting the change trend of the carbon-oxygen product to obtain a prediction model; Collecting real-time smelting parameters and real-time molten pool state information in the blowing process, and inputting the real-time smelting parameters and the real-time molten pool state information into a prediction model to obtain a prediction result of the endpoint carbon oxygen accumulation; Based on the prediction result, performing dynamic regulation and control by at least one of adjusting oxygen supply, adjusting bottom blowing gas flow and adjusting gun position at the end of converting to obtain converting state meeting end point control conditions; Based on the converting state, the end point carbon oxygen volume prediction result obtained by combining the prediction model is combined, the end point carbon content and the end point temperature are judged according to the real-time smelting parameters and the real-time molten pool state information, and when the judgment result meets the preset end point judgment condition, a control instruction for ending converting is triggered.
2. The method of claim 1, wherein obtaining historical smelting parameters and historical bath status information comprises: The method comprises the steps of collecting historical smelting parameters and historical bath state information of a plurality of furnace heats based on a converter production database, wherein the historical smelting parameters comprise molten iron components, molten iron temperature, scrap steel adding proportion, oxygen supply strength in a converting process, converting gun positions and bottom blowing gas flow, and the historical bath state information comprises bath temperature, bath carbon content and bath oxygen content at different time points in the converting process.
3. The method of claim 2, wherein constructing a dynamic prediction model for predicting a trend of carbon oxygen product variation to obtain the prediction model comprises: Constructing a time sequence sample of a blowing process according to a blowing time sequence based on historical smelting parameters and historical bath state information, and organizing molten iron components, oxygen supply strength, blowing gun positions, bottom blowing gas flow and corresponding bath temperature, bath carbon content and bath oxygen content in the time sequence sample as input characteristics of a smelting characteristic input layer; inputting the input characteristics of the smelting characteristic input layer into a staged characteristic extraction layer formed by connecting multiple stages of nonlinear transformation units in series, and generating staged characteristic vectors reflecting the change of the carbon-oxygen reaction intensity by the staged characteristic extraction layer in a time step weighted combination mode; Inputting the staged feature vector output by the staged feature extraction layer into a carbon-oxygen product prediction output layer, wherein the carbon-oxygen product prediction output layer comprises a plurality of output units for outputting a current carbon-oxygen product predicted value and an end carbon-oxygen product predicted value, and a predicted result sequence consisting of the current carbon-oxygen product predicted value and the end carbon-oxygen product predicted value is obtained; And comparing a predicted result sequence consisting of the current carbon volume predicted value and the end point carbon volume predicted value with the actual carbon volume of the historical heat, iteratively adjusting weight parameters in a smelting characteristic input layer, a staged characteristic extraction layer and a carbon volume predicted output layer, and taking the trained dynamic prediction model as a prediction model when the carbon volume predicted error of the dynamic prediction model on the verification heat meets a preset threshold value.
4. The method according to claim 1, wherein the performing of dynamic regulation by at least one of adjusting oxygen supply, adjusting a bottom blowing gas flow rate, and adjusting a gun position at the end of converting based on the prediction result, to obtain a converting state satisfying the end point control condition, comprises: when the predicted result is higher than the upper limit of the carbon oxygen accumulation of the preset end point, adjusting the oxygen supply to enable the adjusted oxygen supply to reduce the top-blown oxygen flow and the oxygen supply intensity, and reducing the acting energy of the top-blown oxygen flow and slowing down the oxidation reaction rate above a molten pool; When the predicted result is lower than the preset endpoint carbon oxygen accumulation lower limit, adjusting oxygen supply, so that the oxygen supply is adjusted to improve the top-blown oxygen flow and increase the oxygen supply intensity, and the oxygen supply intensity is used for improving the amount of oxygen flowing into the surface layer area of the molten pool and enhancing the carbon-oxygen reaction activity of the molten pool; when the predicted result is between the upper limit of the preset endpoint carbon oxygen product and the lower limit of the preset endpoint carbon oxygen product, the flow of the bottom blowing gas is regulated, so that the flow of the bottom blowing gas is regulated to improve the stirring intensity of the molten pool, and the stirring intensity is used for improving the circulation speed of molten metal in the molten pool and improving the distribution uniformity of oxygen in the molten pool; When the predicted result still does not meet the end point control condition after the bottom blowing gas flow is adjusted to improve the stirring intensity of the molten pool, the gun position is adjusted, so that the oxygen flow striking position is changed by the gun position, the incidence depth of the oxygen flow in the molten pool is controlled, and the oxygen flow is used for reducing the over-strong oxygen reaction in the local area and enabling the carbon-oxygen product to be close to the target range.
5. The method of claim 1, wherein the determining the endpoint carbon content and the endpoint temperature based on the converting state, the endpoint carbon volume prediction result obtained by combining the prediction model, and the real-time smelting parameters and the real-time bath state information comprises: According to the real-time smelting parameters, comparing the oxygen supply intensity, the oxygen supply time and the bottom blowing gas flow rate at the end of converting, and determining the matching relation between the current oxygen supply working condition at the end of converting and the oxygen supply working condition of the history heat in the corresponding converting stage; according to the real-time molten pool state information, comparing the measured value of the molten pool temperature, the change rate of the molten pool temperature, the measured value of the molten pool carbon content and the reduction rate of the molten pool carbon content, determining the matching relation between the current molten pool carbon oxygen reaction rate and the reaction rate of the historical heat in the corresponding converting stage; Performing association analysis on the matching relation between the oxygen supply working condition and the carbon-oxygen reaction rate of the molten pool and the end point carbon-oxygen product prediction result obtained by the prediction model, and determining whether the end point carbon content is in a preset end point carbon content range; After the terminal carbon content is determined, determining whether the terminal temperature is in a preset terminal temperature range or not according to the temperature distribution of the real-time molten pool temperature comparison historical heat in the corresponding converting stage; And when the end point carbon content is in a preset end point carbon content range and the end point temperature is in a preset end point temperature range, confirming that the converting state reaches the end point control condition.
6. The method according to claim 1, wherein triggering a control instruction to end converting when the judgment result satisfies a preset end point judgment condition, comprises: generating a blowing ending trigger signal based on the judging result, and inputting the blowing ending trigger signal into a converter control system; after receiving the blowing completion trigger signal, the converter control system closes the top-blown oxygen valve to terminate the top-blown oxygen supply; After the top-blown oxygen supply is terminated, regulating the bottom-blown gas flow to the set flow in the blowing stopping stage through a converter control system; After the flow of the bottom blowing gas is reduced to the set flow in the blowing stopping stage, lifting the converting gun position to an exit position through a converter control system; after the converting gun position is lifted to the exit position, a converter control system outputs a converting ending state signal, and the converting process enters an ending stage.
7. A carbon oxygen product control system based on low carbon steelmaking, comprising: The prediction model construction module is used for acquiring historical smelting parameters and historical molten pool state information, constructing a dynamic prediction model for predicting the change trend of the carbon-oxygen product, and obtaining a prediction model; The prediction result generation module is used for collecting real-time smelting parameters and real-time molten pool state information in the blowing process, inputting the real-time smelting parameters and the real-time molten pool state information into the prediction model, and obtaining a prediction result of the endpoint carbon oxygen accumulation; The dynamic regulation and control execution module is used for executing dynamic regulation and control by at least one operation of adjusting oxygen supply, adjusting bottom blowing gas flow and adjusting gun position at the end of converting based on the prediction result to obtain converting state meeting the end point control condition; The result judging control module is used for judging the end point carbon content and the end point temperature according to the real-time smelting parameters and the real-time molten pool state information based on the converting state and combining the end point carbon oxygen product prediction result obtained by the prediction model, and triggering a control instruction for ending converting when the judging result meets the preset end point judging condition.
8. The system of claim 7, wherein the predictive model construction module comprises: The input characteristic construction unit is used for constructing a time sequence sample of the converting process according to the converting time sequence based on the historical smelting parameters and the historical molten pool state information, and organizing molten iron components, oxygen supply strength, converting gun positions, bottom blowing gas flow and corresponding molten pool temperature, molten pool carbon content and molten pool oxygen content in the time sequence sample into input characteristics of a smelting characteristic input layer; The characteristic vector generation unit is used for inputting the input characteristics of the smelting characteristic input layer into the staged characteristic extraction layer formed by the series connection of the multistage nonlinear transformation units, and the staged characteristic extraction layer generates staged characteristic vectors reflecting the change of the carbon-oxygen reaction intensity in a time step weighted combination mode; The prediction result sequence generation unit is used for inputting the staged feature vector output by the staged feature extraction layer into the carbon-oxygen product prediction output layer, wherein the carbon-oxygen product prediction output layer comprises a plurality of output units for outputting a current carbon-oxygen product predicted value and an end-point carbon-oxygen product predicted value, and a prediction result sequence formed by the current carbon-oxygen product predicted value and the end-point carbon-oxygen product predicted value is obtained; And the prediction model generation unit is used for comparing a prediction result sequence formed by the current carbon volume predicted value and the end point carbon volume predicted value with the actual carbon volume of the historical heat and iteratively adjusting weight parameters in the smelting characteristic input layer, the staged characteristic extraction layer and the carbon volume predicted output layer, and taking the trained dynamic prediction model as a prediction model when the carbon volume predicted error of the dynamic prediction model on the verification heat meets a preset threshold value.
9. An apparatus, comprising: A memory for storing a carbon oxygen product control program based on low carbon steelmaking; A processor for implementing the steps of the carbon-oxygen control method based on low-carbon steelmaking according to any one of claims 1 to 6 when executing the carbon-oxygen control program based on low-carbon steelmaking.
10. A computer readable storage medium storing a computer program, characterized in that the readable storage medium stores a carbon-oxygen-deposition control program based on low-carbon steel making, which when executed by a processor, implements the steps of the carbon-oxygen-deposition control method based on low-carbon steel making as claimed in any one of claims 1 to 6.

Description

Carbon-oxygen accumulation control method, system, equipment and storage medium based on low-carbon steelmaking Technical Field The invention belongs to the technical field of ferrous metallurgy steelmaking, and particularly relates to a carbon-oxygen product control method, a system, equipment and a storage medium based on low-carbon steelmaking. Background The production efficiency, the molten steel cleanliness and the energy consumption level of the furnace steelmaking are highly dependent on the accuracy of end point control as a core link of modern steel production, wherein the carbon-oxygen product is taken as an important thermodynamic index reflecting the balance relation between the carbon content and the oxygen content in the molten steel, and the reaction state of a molten pool, the deoxidizer consumption, the inclusion generation and the metal yield are directly influenced, so that the method is a key parameter for measuring the quality of end point control. The lower carbon-oxygen product not only means weaker oxidizing property in molten steel and higher molten steel cleanliness, but also can obviously reduce deoxidizer consumption and subsequent refining burden, improve the overall production efficiency and reduce carbon emission. However, the blowing process of the converter is highly complex, and factors such as molten iron components, temperature, oxygen supply strength, slag system change, bottom blowing stirring and the like continuously and dynamically change in the blowing process, so that accurate prediction and real-time adjustment of carbon-oxygen accumulation become technical difficulties. In the prior art, the internal reaction state of a molten pool cannot be perceived in real time mainly by depending on a static model and experience of an operator in the control of a converter end point, particularly, in the later period of blowing, when the reaction rate of carbon and oxygen in the molten pool is rapidly changed, the empirical adjustment mode is often lagged and inaccurate, and in order to hit the end point carbon and the temperature, the modes such as high gun position or point blowing are generally adopted, but the operation is extremely easy to cause the peroxidation of the molten pool, so that the carbon-oxygen accumulation of most domestic steel plants is maintained in a high-level range of 0.0025-0.0030 for a long period of time, which is obviously higher than the international advanced level. The high carbon-oxygen product not only increases the consumption of deoxidizer, but also increases oxide inclusion in steel, reduces the cleanliness of molten steel and the metal yield, and further increases the refining cost and energy consumption. The prior art cannot predict the carbon oxygen accumulation trend in real time and cannot conduct accurate dynamic regulation and control at the end of converting, and is a root cause for the problems. Disclosure of Invention In order to solve the above-mentioned shortcomings of the prior art, the present invention provides a carbon-oxygen product control method, system, device and storage medium based on low-carbon steelmaking, so as to solve the above-mentioned technical problems. In a first aspect, the present invention provides a carbon-oxygen product control method based on low-carbon steelmaking, comprising: acquiring historical smelting parameters and historical molten pool state information, and constructing a dynamic prediction model for predicting the change trend of the carbon-oxygen product to obtain a prediction model; Collecting real-time smelting parameters and real-time molten pool state information in the blowing process, and inputting the real-time smelting parameters and the real-time molten pool state information into a prediction model to obtain a prediction result of the endpoint carbon oxygen accumulation; Based on the prediction result, performing dynamic regulation and control by at least one of adjusting oxygen supply, adjusting bottom blowing gas flow and adjusting gun position at the end of converting to obtain converting state meeting end point control conditions; Based on the converting state, the end point carbon oxygen volume prediction result obtained by combining the prediction model is combined, the end point carbon content and the end point temperature are judged according to the real-time smelting parameters and the real-time molten pool state information, and when the judgment result meets the preset end point judgment condition, a control instruction for ending converting is triggered. In an alternative embodiment, obtaining historical smelting parameters and historical bath status information includes: The method comprises the steps of collecting historical smelting parameters and historical bath state information of a plurality of furnace heats based on a converter production database, wherein the historical smelting parameters comprise molten iron components, molten iron temperature, scrap steel