Carbon-oxygen product control method, system and equipment based on low-carbon steelmaking and storage medium

Abstract

The invention relates to the technical field of ferrous metallurgy steelmaking, and particularly provides a carbon-oxygen product control method, system and equipment based on low-carbon steelmaking and a storage medium, and the method comprises the steps that historical smelting parameters and historical molten pool state information are obtained, a dynamic prediction model used for predicting the carbon-oxygen product change trend is constructed, and a prediction model is obtained; real-time smelting parameters and real-time molten pool state information are collected in the blowing process, the real-time smelting parameters and the real-time molten pool state information are input into the prediction model, and a prediction result of the end point carbon-oxygen product is obtained; and on the basis of the prediction result, dynamic regulation and control are executed through at least one operation of oxygen supply adjustment, bottom blowing gas flow adjustment and lance position adjustment at the blowing last stage, and the blowing state meeting the end point control condition is obtained. According to the method, real-time prediction and dynamic regulation and control of the carbon-oxygen reaction trend in the blowing process are achieved, and the control precision of the endpoint carbon content and the endpoint temperature is improved.

Description

Technical Field

[0001] This invention belongs to the field of steelmaking technology in iron and steel metallurgy, and specifically relates to a method, system, equipment and storage medium for controlling the carbon-oxygen product based on low-carbon steelmaking. Background Technology

[0002] As a core step in modern steel production, furnace steelmaking's efficiency, steel cleanliness, and energy consumption are highly dependent on the accuracy of endpoint control. Among these, the carbon-oxygen product (CO product), a crucial thermodynamic indicator reflecting the balance between carbon and oxygen content in molten steel, directly impacts the molten pool reaction state, deoxidizer dosage, inclusion formation, and metal yield. It is a key parameter for evaluating endpoint control quality. A lower CO product not only signifies weaker oxidizing power and higher steel cleanliness but also significantly reduces deoxidizer consumption and subsequent refining burden, thereby improving overall production efficiency and lowering carbon emissions.

[0003] However, the converter blowing process is highly complex. Factors such as molten iron composition, temperature, oxygen supply intensity, slag system changes, and bottom blowing agitation are constantly and dynamically changing during the blowing process, making accurate prediction and real-time adjustment of the carbon-oxygen product a technical challenge. Existing technologies for converter endpoint control mainly rely on static models and operator experience, which cannot perceive the reaction state inside the molten pool in real time. Especially in the later stages of blowing, when the reaction rate of carbon and oxygen in the molten pool changes rapidly, this experience-based adjustment method is often lagging and inaccurate. In order to hit the endpoint carbon and temperature, methods such as "high lance position" or "point blowing" are commonly used, but these operations are prone to causing over-oxidation of the molten pool, causing the carbon-oxygen product of most domestic steel mills to remain in the high range of 0.0025-0.0030 for a long time, which is significantly higher than the international advanced level. High carbon-oxygen product not only increases deoxidizer consumption, but also leads to an increase in oxide inclusions in steel, a decrease in steel cleanliness, and a decrease in metal yield, further increasing refining costs and energy consumption. The fundamental reason for the above problems is that existing technologies cannot predict the carbon-oxygen product trend in real time or make precise dynamic adjustments at the end of the blowing process. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, system, equipment and storage medium for controlling carbon-oxygen product based on low-carbon steelmaking, so as to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a method for controlling the carbon-oxygen product in low-carbon steelmaking, comprising: By acquiring historical smelting parameters and historical molten pool state information, a dynamic prediction model is constructed to predict the trend of carbon-oxygen product changes, and the prediction model is obtained. Real-time smelting parameters and real-time molten pool status information are collected during the blowing process, and the real-time smelting parameters and real-time molten pool status information are input into the prediction model to obtain the prediction result of the final carbon-oxygen product. Based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting gun position, so as to obtain the blowing state that meets the endpoint control conditions. Based on the blowing state, combined with the predicted carbon-oxygen product of the endpoint obtained by the prediction model, and based on the real-time smelting parameters and real-time molten pool status information, the endpoint carbon content and endpoint temperature are judged. When the judgment result meets the preset endpoint judgment condition, the control command to end blowing is triggered.

[0006] In an optional implementation, obtaining historical smelting parameters and historical molten pool status information includes: Based on the converter production database, historical smelting parameters and historical molten pool status information of multiple heats were collected. The historical smelting parameters include molten iron composition, molten iron temperature, scrap steel addition ratio, oxygen supply intensity during the blowing process, blowing lance position and bottom blowing gas flow rate. The historical molten pool status information includes molten pool temperature, molten pool carbon content and molten pool oxygen content at different time points during the blowing process.

[0007] In an optional implementation, a dynamic prediction model is constructed to predict the trend of carbon-oxygen product changes, resulting in a prediction model including: Based on historical smelting parameters and historical molten pool state information, a time series sample of the blowing process is constructed according to the blowing time sequence. The iron composition, oxygen supply intensity, blowing lance position, bottom blowing gas flow rate, and corresponding molten pool temperature, molten pool carbon content and molten pool oxygen content in the time series sample are organized as the input features of the smelting feature input layer. The input features of the smelting feature input layer are formed by a staged feature extraction layer consisting of multiple nonlinear transformation units connected in series. The staged feature extraction layer generates a staged feature vector that reflects the change in carbon-oxygen reaction intensity by weighted combination according to time steps. The stage feature vector output by the stage feature extraction layer is input into the carbon-oxygen product prediction output layer. The carbon-oxygen product prediction output layer includes multiple output units for outputting the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value, resulting in a prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value. After comparing the prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value with the actual carbon-oxygen product of historical furnaces and iteratively adjusting the weight parameters in the smelting feature input layer, the stage feature extraction layer and the carbon-oxygen product prediction output layer, the trained dynamic prediction model is used as the prediction model when the carbon-oxygen product prediction error of the dynamic prediction model in the verification furnace meets the preset threshold.

[0008] In an optional implementation, based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting nozzle position, to obtain a blowing state that meets the endpoint control conditions, including: When the predicted result is higher than the preset endpoint carbon-oxygen product upper limit, the oxygen supply is adjusted to reduce the top-blown oxygen flow rate and the oxygen supply intensity, in order to reduce the energy of the top-blown oxygen flow and slow down the oxidation reaction rate above the molten pool. When the predicted result is lower than the preset endpoint carbon-oxygen product lower limit, the oxygen supply is adjusted to increase the top-blown oxygen flow rate and increase the oxygen supply intensity, so as to increase the amount of oxygen flow into the surface area of ​​the molten pool and enhance 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 bottom blowing gas flow rate is adjusted to increase the stirring intensity of the molten pool, thereby increasing the circulation speed of the molten metal in the molten pool and improving the uniformity of oxygen distribution in the molten pool. If the predicted results still do not meet the endpoint control conditions after adjusting the bottom-blown gas flow rate to increase the stirring intensity of the molten pool, the gun position is adjusted to change the oxygen flow impact position and control the injection depth of the oxygen flow in the molten pool. This is used to reduce excessive oxygen reaction in local areas and bring the carbon-oxygen product closer to the target range.

[0009] In one optional implementation, based on the blowing state, combined with the endpoint carbon-oxygen product prediction results obtained from the prediction model, and according to real-time smelting parameters and real-time molten pool state information, the endpoint carbon content and endpoint temperature are determined, including: Based on the comparison of real-time smelting parameters with the oxygen supply intensity, oxygen supply time and bottom blowing gas flow rate at the end of the blowing process, the matching relationship between the current oxygen supply conditions at the end of the blowing process and the oxygen supply conditions of the corresponding blowing stages in the historical furnace is determined. By comparing the measured value of the molten pool temperature, the rate of change of the molten pool temperature, the measured value of the carbon content of the molten pool, and the rate of decrease of the carbon content of the molten pool with the reaction rate of the current carbon-oxygen reaction rate of the molten pool and the reaction rate of the corresponding blowing stage in the historical furnace, the matching relationship between the current carbon-oxygen reaction rate of the molten pool and the reaction rate of the corresponding blowing stage in the historical furnace is determined. The matching relationship between oxygen supply conditions and the matching relationship between the carbon-oxygen reaction rate in the molten pool are correlated with the predicted results of the endpoint carbon-oxygen product obtained from the prediction model to determine whether the endpoint carbon content is within the preset endpoint carbon content range. After determining the endpoint carbon content, the temperature of the endpoint is determined by comparing the temperature distribution of the historical furnace at the corresponding blowing stage with the real-time molten pool temperature. When the final carbon content is within the preset final carbon content range and the final temperature is within the preset final temperature range, the blowing state is confirmed to have met the final control conditions.

[0010] In an optional implementation, when the judgment result meets the preset endpoint determination condition, a control command to end the blowing process is triggered, including: Based on the judgment result, a termination blowing trigger signal is generated and input into the converter control system; After the converter control system receives the end blowing trigger signal, it closes the top blowing oxygen valve to terminate the top blowing oxygen supply. After the top-blown oxygen supply is terminated, the bottom-blown gas flow rate is reduced to the set flow rate for the shutdown stage through the converter control system. After the bottom blowing gas flow rate is reduced to the set flow rate of the stop blowing stage, the blowing lance position is raised to the exit position through the converter control system; After the blowing lance is raised to the exit position, the converter control system outputs a blowing end status signal, and the blowing process enters the end stage.

[0011] Secondly, the present invention provides a carbon-oxygen product control system based on low-carbon steelmaking, comprising: The prediction model building module is used to obtain historical smelting parameters and historical molten pool state information, and to build a dynamic prediction model for predicting the trend of carbon-oxygen product changes, thus obtaining the prediction model. The prediction result generation module is used to collect real-time smelting parameters and real-time molten pool state information during the blowing process, and input the real-time smelting parameters and real-time molten pool state information into the prediction model to obtain the prediction result of the endpoint carbon-oxygen product. The dynamic control execution module is used to perform dynamic control at the end of the blowing process by adjusting oxygen supply, adjusting bottom blowing gas flow rate and adjusting gun position based on the prediction results, so as to obtain the blowing state that meets the endpoint control conditions. The result judgment control module is used to judge the endpoint carbon-oxygen product prediction result obtained by combining the blowing state with the prediction model, and to judge the endpoint carbon content and endpoint temperature according to the real-time smelting parameters and real-time molten pool status information. When the judgment result meets the preset endpoint judgment condition, the control command to end blowing is triggered.

[0012] Thirdly, a device is provided, comprising: Memory for storing carbon-oxygen product control programs based on low-carbon steelmaking; A processor is configured to implement the steps of the carbon-oxygen product control method for low-carbon steelmaking as provided in the first aspect when executing the carbon-oxygen product control program for low-carbon steelmaking.

[0013] Fourthly, a computer-readable storage medium is provided, on which a carbon-oxygen product control program based on low-carbon steelmaking is stored, wherein when the carbon-oxygen product control program based on low-carbon steelmaking is executed by a processor, the carbon-oxygen product control program based on low-carbon steelmaking implements the steps of the carbon-oxygen product control method based on low-carbon steelmaking provided in the first aspect.

[0014] The beneficial effects of this invention are as follows: The carbon-oxygen product control method, system, equipment, and storage medium provided by this invention for low-carbon steelmaking construct a dynamic prediction model by acquiring historical smelting parameters and historical molten pool state information. This model reflects the actual changes in carbon-oxygen reaction at different blowing stages, thereby improving the prediction accuracy of the endpoint carbon-oxygen product trend. During the blowing process, real-time smelting parameters and real-time molten pool state information are collected and input into the prediction model, enabling the model to update the endpoint carbon-oxygen product prediction results based on real-time operating conditions, improving the timeliness and reliability of endpoint prediction. Based on the prediction results, dynamic control of oxygen supply, bottom blowing gas flow rate, or lance position is implemented at the end of the blowing process, allowing the carbon-oxygen reaction intensity at the end of the blowing process to be adjusted directionally according to the prediction deviation, improving the stability of endpoint control and reducing endpoint deviation caused by operating condition fluctuations. After determining the blowing state, the endpoint carbon-oxygen product prediction results from the prediction model, along with real-time smelting parameters and real-time molten pool state information, are used to determine the endpoint carbon content and endpoint temperature, shifting endpoint control from post-event judgment to pre-event identification, improving the endpoint hit rate. When the judgment result meets the endpoint determination condition, the end blowing command is triggered, so that the blowing stop action can be executed when the reaction reaches the optimal node, thereby reducing the probability of over-blowing or under-blowing, improving the first-time hit rate of converter blowing, reducing energy and oxygen consumption, and improving the overall stability of the low-carbon steelmaking process.

[0015] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0018] Figure 2 This is a schematic block diagram of a system according to an embodiment of the present invention.

[0019] Figure 3 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0022] The carbon-oxygen product control method based on low-carbon steelmaking provided in this embodiment of the invention is executed by a computer device, and correspondingly, the carbon-oxygen product control system based on low-carbon steelmaking runs in the computer device.

[0023] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 1 The implementing entity can be a carbon-oxygen product control system based on low-carbon steelmaking. Depending on different requirements, the order of steps in this flowchart can be changed, and some can be omitted.

[0024] like Figure 1 As shown, the method includes: S1. Obtain historical smelting parameters and historical molten pool state information, construct a dynamic prediction model for predicting the trend of carbon-oxygen product changes, and obtain the prediction model.

[0025] S2. During the blowing process, real-time smelting parameters and real-time molten pool status information are collected and input into the prediction model to obtain the prediction result of the final carbon-oxygen product.

[0026] S3. Based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting gun position, so as to obtain the blowing state that meets the endpoint control conditions.

[0027] S4. Based on the blowing state, combined with the prediction results of the endpoint carbon-oxygen product obtained by the prediction model, and based on the real-time smelting parameters and real-time molten pool state information, the endpoint carbon content and endpoint temperature are judged. When the judgment result meets the preset endpoint judgment conditions, the control command to end blowing is triggered.

[0028] In one embodiment of the present invention, based on step S1, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0029] Obtaining historical smelting parameters and historical molten pool status information includes: Based on the converter production database, historical smelting parameters and historical molten pool status information of multiple heats were collected. The historical smelting parameters include molten iron composition, molten iron temperature, scrap steel addition ratio, oxygen supply intensity during the blowing process, blowing lance position and bottom blowing gas flow rate. The historical molten pool status information includes molten pool temperature, molten pool carbon content and molten pool oxygen content at different time points during the blowing process.

[0030] A dynamic prediction model is constructed to predict the trend of carbon-oxygen product changes, resulting in a prediction model including: Based on historical smelting parameters and historical molten pool state information, a time series sample of the blowing process is constructed according to the blowing time sequence. The iron composition, oxygen supply intensity, blowing lance position, bottom blowing gas flow rate, and corresponding molten pool temperature, carbon content, and oxygen content in the time series sample are organized as input features for the smelting feature input layer. The input features of the smelting feature input layer are then input into a staged feature extraction layer formed by a series of multi-level nonlinear transformation units. The staged feature extraction layer generates a staged feature vector reflecting the changes in carbon-oxygen reaction intensity through a weighted combination based on time steps. The staged feature vector output by the staged feature extraction layer is then input into... The carbon-oxygen product prediction output layer includes multiple output units for outputting the current carbon-oxygen product prediction value and the endpoint carbon-oxygen product prediction value, resulting in a prediction result sequence composed of the current carbon-oxygen product prediction value and the endpoint carbon-oxygen product prediction value. After comparing the prediction result sequence composed of the current carbon-oxygen product prediction value and the endpoint carbon-oxygen product prediction value with the actual carbon-oxygen product of historical furnaces and iteratively adjusting the weight parameters in the smelting feature input layer, the stage feature extraction layer and the carbon-oxygen product prediction output layer, the trained dynamic prediction model is used as the prediction model when the carbon-oxygen product prediction error of the dynamic prediction model in the verification furnace meets the preset threshold.

[0031] Specifically, firstly, historical smelting parameters and molten pool status information from multiple heats are collected based on the converter production database. The historical smelting parameters include the composition of the molten iron (including the content of silicon, manganese, phosphorus, and sulfur) at the time of iron input, the molten iron temperature, the proportion of scrap steel added, the oxygen supply intensity at different stages of the blowing process, the blowing lance position, and the bottom-blown gas flow rate. The historical molten pool status information includes the molten pool temperature, molten pool carbon content, and molten pool oxygen content at different time points during the blowing process. After collecting historical data from multiple heats, a time series sample of the blowing process is constructed according to the time sequence from the start to the end of each heat. The molten iron composition, oxygen supply intensity, blowing lance position, bottom-blown gas flow rate, and the corresponding molten pool temperature, molten pool carbon content, and molten pool oxygen content in the time series sample are organized into input features for the smelting feature input layer by time step.

[0032] The second step involves inputting the input features of the smelting feature input layer into a stage feature extraction layer composed of multiple nonlinear transformation units connected in series. The multiple nonlinear transformation units perform nonlinear mapping on the input features layer by layer and perform weighted combination according to weights within each time step to generate a stage feature vector that can characterize the change in carbon-oxygen reaction intensity at that stage.

[0033] For example, the first level of nonlinear transformation:

[0034] No. Layer nonlinear transformation:

[0035] in, l=2,3,…,L， For the first l The weight matrix of the layer, Let l be the bias vector of the l-th layer. This is the output vector of the l-th layer at time step t.

[0036] Obtain the eigenvector at time step t:

[0037] A weighted combination based on time steps is used to form a stage-specific feature vector:

[0038] in, This is the starting time step for a certain refining stage; The smelting feature input vector at the t-th time step contains real-time smelting and molten pool status information such as oxygen supply intensity, lance position, bottom blowing gas flow rate, molten pool temperature, molten pool carbon content, and molten pool oxygen content. The weighting coefficients for time step t. .

[0039] The third step involves inputting the staged feature vectors generated by the staged feature extraction layer into the carbon-oxygen product (C-O-V) prediction output layer. This layer contains multiple output units, capable of outputting the predicted C-O-V value for the current time step and the predicted C-O-V value for the corresponding furnace's final stage, thus forming a prediction result sequence composed of the current and final C-O-V prediction values. After obtaining the prediction result sequence, it is compared with the actual C-O-V records of the corresponding historical furnaces. Based on the comparison deviation, the weight parameters in the smelting feature input layer, staged feature extraction layer, and C-O-V prediction output layer are iteratively adjusted. Through multiple iterations of training, the prediction error of the dynamic prediction model across multiple furnaces is gradually reduced. When the C-O-V prediction error of the dynamic prediction model in the verification furnace reaches a preset error threshold, the trained and stable prediction model is solidified into a prediction model usable in actual production. In actual production applications, real-time smelting parameters (including oxygen supply intensity, blowing lance position, and bottom-blown gas flow rate) and real-time molten pool status information (including molten pool temperature, molten pool carbon content, and molten pool oxygen content) are collected during the blowing process. These real-time smelting parameters and molten pool status information are then input into the prediction model using the same input method as the training data. The prediction model outputs the current predicted carbon-oxygen product (C-O-product) and the final predicted C-O-product. The final predicted C-O-product is used to determine the current carbon-oxygen reaction trend. If the prediction result deviates from the target final C-O-product range, corresponding process controls are implemented at the end of the blowing process according to the direction of the predicted deviation. These controls include reducing or increasing the top-blown oxygen flow rate, adjusting the bottom-blown gas flow rate, and changing the blowing lance position to adjust the intensity of the carbon-oxygen reaction within the molten pool towards the target direction. After dynamic adjustment, the predicted value of the endpoint carbon-oxygen product is obtained by re-deduction of the prediction model. Combined with the actual changes in the molten pool temperature and carbon content, it is determined whether the endpoint carbon content and endpoint temperature meet the endpoint determination conditions. When both the endpoint carbon content and endpoint temperature are within the control range, it is determined that the blowing has reached the endpoint conditions. The control command to end the blowing is triggered through the converter control system, including closing the top blowing oxygen valve, reducing the bottom blowing gas flow rate to the set flow rate of the stop blowing stage, and raising the blowing lance position, so that the blowing process can be successfully completed and enter the steel tapping preparation stage.

[0040] In one embodiment of the present invention, based on step S2, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0041] Real-time smelting parameters and molten pool state information are collected during the blowing process and input into the prediction model to obtain the predicted results of the final carbon-oxygen product, including: During the converter blowing process, real-time smelting parameters and real-time molten pool status information are collected sequentially. Real-time smelting parameters include process parameters directly related to the blowing operation, such as the current oxygen supply intensity, top-blown oxygen flow rate, blowing lance position, bottom-blown gas flow rate, and scrap melting progress. Real-time molten pool status information includes data reflecting the internal reaction state of the molten pool, such as molten pool temperature, molten pool carbon content, and molten pool oxygen content, obtained through auxiliary lances or online sensors. The collected real-time smelting parameters and real-time molten pool status information are kept consistent with the input feature structure constructed during the training phase, following a chronological order. The current time step's oxygen supply intensity, blowing lance position, bottom-blown gas flow rate, and corresponding molten pool temperature, molten pool carbon content, and molten pool oxygen content are input into the smelting feature input layer of the dynamic prediction model. The smelting feature input layer converts the input data into a feature vector that the model can process and then passes it to the staged feature extraction layer. The staged feature extraction layer performs nonlinear transformation and weighted combination on the feature vector of the current time step to generate a staged feature vector that reflects the current change in carbon-oxygen reaction intensity.

[0042] The staged feature vectors are input into the carbon-oxygen product prediction output layer. Based on these feature vectors, the layer outputs the predicted value of the current carbon-oxygen product and the predicted value of the final carbon-oxygen product for the corresponding heat cycle, forming the final carbon-oxygen product prediction result. During the blowing process, real-time smelting parameters and real-time molten pool status information are repeatedly collected at fixed time intervals. Updated features are continuously input into the prediction model. The final carbon-oxygen product prediction result output by the model reflects the carbon-oxygen reaction trend of the current blowing stage in real time, providing a basis for dynamic control at the end of the blowing process.

[0043] In one embodiment of the present invention, based on step S3, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0044] Based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting lance position, to obtain a blowing state that meets the endpoint control conditions, including: When the predicted result is higher than the preset endpoint carbon-oxygen product upper limit, the oxygen supply is adjusted to reduce the top-blown oxygen flow rate and decrease the oxygen supply intensity, thereby reducing the energy of the top-blown oxygen flow and slowing down the oxidation reaction rate above the molten pool. When the predicted result is lower than the preset endpoint carbon-oxygen product lower limit, the oxygen supply is adjusted to increase the top-blown oxygen flow rate and increase the oxygen supply intensity, thereby increasing the amount of oxygen flow entering the surface area of ​​the molten pool and enhancing the carbon-oxygen reaction activity of the molten pool. When the predicted result is between the preset endpoint carbon-oxygen product upper and lower limits, the bottom-blown gas flow rate is adjusted to increase the molten pool stirring intensity, thereby increasing the circulation speed of the molten metal in the molten pool and improving the uniformity of oxygen distribution in the molten pool. When the predicted result still does not meet the endpoint control conditions after adjusting the bottom-blown gas flow rate and increasing the molten pool stirring intensity, the gun position is adjusted to change the oxygen flow impact position and control the injection depth of the oxygen flow in the molten pool, thereby reducing excessive oxygen reaction in local areas and bringing the carbon-oxygen product closer to the target range.

[0045] In one embodiment of the present invention, based on step S4, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0046] Based on the blowing conditions, combined with the predicted carbon-oxygen product of the endpoint obtained from the prediction model, and based on real-time smelting parameters and real-time molten pool state information, the endpoint carbon content and endpoint temperature are determined, including: By comparing real-time smelting parameters with the oxygen supply intensity, oxygen supply time, and bottom-blown gas flow rate at the end of the blowing process, the matching relationship between the current oxygen supply conditions at the end of the blowing process and the oxygen supply conditions of historical furnaces in the corresponding blowing stages is determined. By comparing real-time molten pool status information with the measured values ​​of molten pool temperature, the rate of change of molten pool temperature, the measured values ​​of molten pool carbon content, and the rate of decrease of molten pool carbon content, the matching relationship between the current carbon-oxygen reaction rate of the molten pool and the reaction rate of historical furnaces in the corresponding blowing stages is determined. The matching relationship between the oxygen supply conditions and the matching relationship between the carbon-oxygen reaction rate of the molten pool are correlated with the predicted results of the endpoint carbon-oxygen product obtained from the prediction model to determine whether the endpoint carbon content is within the preset endpoint carbon content range. After determining the endpoint carbon content, the temperature distribution of historical furnaces in the corresponding blowing stages is compared with the real-time molten pool temperature to determine whether the endpoint temperature is within the preset endpoint temperature range. When both the endpoint carbon content and the endpoint temperature are within the preset endpoint temperature range, the blowing state is confirmed to have met the endpoint control conditions.

[0047] When the judgment result meets the preset endpoint judgment condition, the control command to end the blowing process is triggered, including: Based on the judgment result, a blow-end trigger signal is generated and input into the converter control system. After receiving the blow-end 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, the bottom-blown gas flow rate is reduced to the set flow rate for the stop-blowing stage through the converter control system. After the bottom-blown gas flow rate is reduced to the set flow rate for the stop-blowing stage, the blowing lance position is raised to the exit position through the converter control system. After the blowing lance position is raised to the exit position, the converter control system outputs a blow-end status signal, and the blowing process enters the end stage.

[0048] Specifically, after completing the dynamic control at the end of the blowing process, real-time smelting parameters under the current blowing conditions are first collected, including the oxygen supply intensity, oxygen supply time, and bottom-blown gas flow rate at the end of the blowing process. These real-time smelting parameters are then compared with corresponding parameters from historical furnaces at the same blowing stage. This comparison determines the matching relationship between the current oxygen supply conditions at the end of the blowing process and the oxygen supply conditions from historical furnaces. Simultaneously, real-time molten pool status information is collected and analyzed, including the measured molten pool temperature, the rate of change of molten pool temperature, the measured molten pool carbon content, and the rate of decrease of molten pool carbon content. This real-time molten pool status information is then compared with the molten pool temperature distribution range and the molten pool carbon-oxygen reaction rate formed in the same blowing stage of historical furnaces to determine the matching relationship between the current molten pool carbon-oxygen reaction rate and the reaction rate from historical furnaces.

[0049] The matching relationships between oxygen supply conditions and the carbon-oxygen reaction rate in the molten pool are correlated with the predicted endpoint carbon-oxygen product output by the dynamic prediction model. Based on the correlation analysis results, it is determined whether the endpoint slag content of the current heat is within the preset endpoint carbon content control range. After determining the endpoint carbon content, the real-time molten pool temperature is compared with the temperature distribution of the corresponding blowing stage in historical heats to determine whether the current endpoint temperature is within the preset endpoint temperature range. When both the endpoint carbon content and the endpoint temperature are within the preset endpoint temperature range, the current blowing state is determined to have met the endpoint control conditions, and a blow-end trigger signal is generated and input to the converter control system. Upon receiving the end-blowing trigger signal, the converter control system executes a stop-blowing sequence control, including closing the top-blown oxygen valve to terminate the top-blown oxygen supply. After the top-blown oxygen supply is terminated, the system controls the bottom-blowing system to reduce the bottom-blown gas flow rate to the set flow rate for the stop-blowing stage. After the bottom-blown gas flow rate is reduced, the converter control system adjusts the lifting mechanism of the blowing lance to raise it to the exit position, ensuring the lance completely exits the molten pool reaction zone. Once the blowing lance is in position, the converter control system outputs a blowing end status signal, indicating the end of the blowing process, followed by the steel tapping preparation process.

[0050] In some embodiments, the carbon-oxygen product control system based on low-carbon steelmaking may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the carbon-oxygen product control system based on low-carbon steelmaking may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) Function based on carbon-oxygen product control in low-carbon steelmaking.

[0051] In this embodiment, the carbon-oxygen product control system based on low-carbon steelmaking can be divided into multiple functional modules according to its functions, such as... Figure 2 As shown. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and is stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0052] The prediction model building module is used to obtain historical smelting parameters and historical molten pool state information, and to build a dynamic prediction model for predicting the trend of carbon-oxygen product changes, thus obtaining the prediction model. The prediction result generation module is used to collect real-time smelting parameters and real-time molten pool state information during the blowing process, and input the real-time smelting parameters and real-time molten pool state information into the prediction model to obtain the prediction result of the endpoint carbon-oxygen product. The dynamic control execution module is used to perform dynamic control at the end of the blowing process by adjusting oxygen supply, adjusting bottom blowing gas flow rate and adjusting gun position based on the prediction results, so as to obtain the blowing state that meets the endpoint control conditions. The result judgment control module is used to judge the endpoint carbon-oxygen product prediction result obtained by combining the blowing state with the prediction model, and to judge the endpoint carbon content and endpoint temperature according to the real-time smelting parameters and real-time molten pool status information. When the judgment result meets the preset endpoint judgment condition, the control command to end blowing is triggered.

[0053] In one embodiment of the present invention, the prediction model building module includes: The input feature construction unit is used to construct a time series sample of the blowing process based on historical smelting parameters and historical molten pool state information in the order of blowing time. The iron composition, oxygen supply intensity, blowing lance position, bottom blowing gas flow rate and corresponding molten pool temperature, molten pool carbon content and molten pool oxygen content in the time series sample are organized as the input features of the smelting feature input layer. The feature vector generation unit is used to form a staged feature extraction layer by connecting multiple nonlinear transformation units in series with the input features of the smelting feature input layer. The staged feature extraction layer generates staged feature vectors that reflect the changes in the intensity of carbon-oxygen reaction by weighted combination according to time steps. The prediction result sequence generation unit is used to input the stage feature vector output by the stage feature extraction layer into the carbon-oxygen product prediction output layer. The carbon-oxygen product prediction output layer includes multiple output units for outputting the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value, so as to obtain a prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value. The prediction model generation unit is used to compare the prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value with the actual carbon-oxygen product of historical furnaces and iteratively adjust the weight parameters in the smelting feature input layer, the stage feature extraction layer and the carbon-oxygen product prediction output layer. When the carbon-oxygen product prediction error of the dynamic prediction model in the verification furnace meets the preset threshold, the trained dynamic prediction model is used as the prediction model.

[0054] Figure 3 The carbon-oxygen product control method based on low-carbon steelmaking provided in the embodiments of this application can be applied to equipment. Those skilled in the art will understand that the equipment structure involved in the embodiments of this invention does not constitute a limitation on the equipment. The equipment may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the equipment includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0055] The device 300 may include a processor 310, a memory 320, and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0056] The memory 320 can be used to store execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 is able to perform some or all of the steps in the above method embodiments.

[0057] The processor 310 serves as the control center of the storage device, connecting various parts of the electronic device via various interfaces and lines. It executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 310 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0058] The communication unit 330 is used to establish a communication channel, enabling the storage device to communicate with other devices. It can receive user data sent by other devices or send user data to other devices.

[0059] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0060] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other medium capable of storing program code. It includes several instructions to cause a computer device (which may be a personal computer, a server, or a second device, network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0061] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0062] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0063] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0065] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A method for controlling the carbon-oxygen product in low-carbon steelmaking, characterized in that, include: By acquiring historical smelting parameters and historical molten pool state information, a dynamic prediction model is constructed to predict the trend of carbon-oxygen product changes, and the prediction model is obtained. Real-time smelting parameters and real-time molten pool status information are collected during the blowing process, and the real-time smelting parameters and real-time molten pool status information are input into the prediction model to obtain the prediction result of the final carbon-oxygen product. Based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting gun position, so as to obtain the blowing state that meets the endpoint control conditions. Based on the blowing state, combined with the predicted carbon-oxygen product of the endpoint obtained by the prediction model, and based on the real-time smelting parameters and real-time molten pool status information, the endpoint carbon content and endpoint temperature are judged. When the judgment result meets the preset endpoint judgment condition, the control command to end blowing is triggered.

2. The method according to claim 1, characterized in that, Obtaining historical smelting parameters and historical molten pool status information includes: Based on the converter production database, historical smelting parameters and historical molten pool status information of multiple heats were collected. The historical smelting parameters include molten iron composition, molten iron temperature, scrap steel addition ratio, oxygen supply intensity during the blowing process, blowing lance position and bottom blowing gas flow rate. The historical molten pool status information includes molten pool temperature, molten pool carbon content and molten pool oxygen content at different time points during the blowing process.

3. The method according to claim 2, characterized in that, A dynamic prediction model is constructed to predict the trend of carbon-oxygen product changes, resulting in a prediction model including: Based on historical smelting parameters and historical molten pool state information, a time series sample of the blowing process is constructed according to the blowing time sequence. The iron composition, oxygen supply intensity, blowing lance position, bottom blowing gas flow rate, and corresponding molten pool temperature, molten pool carbon content and molten pool oxygen content in the time series sample are organized as the input features of the smelting feature input layer. The input features of the smelting feature input layer are formed by a staged feature extraction layer consisting of multiple nonlinear transformation units connected in series. The staged feature extraction layer generates a staged feature vector that reflects the change in carbon-oxygen reaction intensity by weighted combination according to time steps. The stage feature vector output by the stage feature extraction layer is input into the carbon-oxygen product prediction output layer. The carbon-oxygen product prediction output layer includes multiple output units for outputting the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value, resulting in a prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value. After comparing the prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value with the actual carbon-oxygen product of historical furnaces and iteratively adjusting the weight parameters in the smelting feature input layer, the stage feature extraction layer and the carbon-oxygen product prediction output layer, the trained dynamic prediction model is used as the prediction model when the carbon-oxygen product prediction error of the dynamic prediction model in the verification furnace meets the preset threshold.

4. The method according to claim 1, characterized in that, Based on the prediction results, dynamic control is performed at the end of the blowing process by adjusting at least one of the following operations: adjusting oxygen supply, adjusting bottom blowing gas flow rate, and adjusting lance position, to obtain a blowing state that meets the endpoint control conditions, including: When the predicted result is higher than the preset endpoint carbon-oxygen product upper limit, the oxygen supply is adjusted to reduce the top-blown oxygen flow rate and the oxygen supply intensity, in order to reduce the energy of the top-blown oxygen flow and slow down the oxidation reaction rate above the molten pool. When the predicted result is lower than the preset endpoint carbon-oxygen product lower limit, the oxygen supply is adjusted to increase the top-blown oxygen flow rate and increase the oxygen supply intensity, so as to increase the amount of oxygen flow into the surface area of ​​the molten pool and enhance 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 bottom blowing gas flow rate is adjusted to increase the stirring intensity of the molten pool, thereby increasing the circulation speed of the molten metal in the molten pool and improving the uniformity of oxygen distribution in the molten pool. If the predicted results still do not meet the endpoint control conditions after adjusting the bottom-blown gas flow rate to increase the stirring intensity of the molten pool, the gun position is adjusted to change the oxygen flow impact position and control the injection depth of the oxygen flow in the molten pool. This is used to reduce excessive oxygen reaction in local areas and bring the carbon-oxygen product closer to the target range.

5. The method according to claim 1, characterized in that, Based on the blowing conditions, combined with the predicted carbon-oxygen product at the endpoint obtained from the prediction model, and based on real-time smelting parameters and real-time molten pool state information, the endpoint carbon content and endpoint temperature are determined, including: Based on the comparison of real-time smelting parameters with the oxygen supply intensity, oxygen supply time and bottom blowing gas flow rate at the end of the blowing process, the matching relationship between the current oxygen supply conditions at the end of the blowing process and the oxygen supply conditions of the corresponding blowing stages in the historical furnace is determined. By comparing the measured value of the molten pool temperature, the rate of change of the molten pool temperature, the measured value of the carbon content of the molten pool, and the rate of decrease of the carbon content of the molten pool with the reaction rate of the current carbon-oxygen reaction rate of the molten pool and the reaction rate of the corresponding blowing stage in the historical furnace, the matching relationship between the current carbon-oxygen reaction rate of the molten pool and the reaction rate of the corresponding blowing stage in the historical furnace is determined. The matching relationship between oxygen supply conditions and the matching relationship between the carbon-oxygen reaction rate in the molten pool are correlated with the predicted results of the endpoint carbon-oxygen product obtained from the prediction model to determine whether the endpoint carbon content is within the preset endpoint carbon content range. After determining the endpoint carbon content, the temperature of the endpoint is determined by comparing the temperature distribution of the historical furnace at the corresponding blowing stage with the real-time molten pool temperature. When the final carbon content is within the preset final carbon content range and the final temperature is within the preset final temperature range, the blowing state is confirmed to have met the final control conditions.

6. The method according to claim 1, characterized in that, When the judgment result meets the preset endpoint judgment condition, the control command to end the blowing process is triggered, including: Based on the judgment result, a termination blowing trigger signal is generated and input into the converter control system; After the converter control system receives the end blowing trigger signal, it closes the top blowing oxygen valve to terminate the top blowing oxygen supply. After the top-blown oxygen supply is terminated, the bottom-blown gas flow rate is reduced to the set flow rate for the shutdown stage through the converter control system. After the bottom blowing gas flow rate is reduced to the set flow rate of the stop blowing stage, the blowing lance position is raised to the exit position through the converter control system; After the blowing lance is raised to the exit position, the converter control system outputs a blowing end status signal, and the blowing process enters the end stage.

7. A carbon-oxygen product control system based on low-carbon steelmaking, characterized in that, include: The prediction model building module is used to obtain historical smelting parameters and historical molten pool state information, and to build a dynamic prediction model for predicting the trend of carbon-oxygen product changes, thus obtaining the prediction model. The prediction result generation module is used to collect real-time smelting parameters and real-time molten pool state information during the blowing process, and input the real-time smelting parameters and real-time molten pool state information into the prediction model to obtain the prediction result of the endpoint carbon-oxygen product. The dynamic control execution module is used to perform dynamic control at the end of the blowing process by adjusting oxygen supply, adjusting bottom blowing gas flow rate and adjusting gun position based on the prediction results, so as to obtain the blowing state that meets the endpoint control conditions. The result judgment control module is used to judge the endpoint carbon-oxygen product prediction result obtained by combining the blowing state with the prediction model, and to judge the endpoint carbon content and endpoint temperature according to the real-time smelting parameters and real-time molten pool status information. When the judgment result meets the preset endpoint judgment condition, the control command to end blowing is triggered.

8. The system according to claim 7, characterized in that, The prediction model building module includes: The input feature construction unit is used to construct a time series sample of the blowing process based on historical smelting parameters and historical molten pool state information in the order of blowing time. The iron composition, oxygen supply intensity, blowing lance position, bottom blowing gas flow rate and corresponding molten pool temperature, molten pool carbon content and molten pool oxygen content in the time series sample are organized as the input features of the smelting feature input layer. The feature vector generation unit is used to form a staged feature extraction layer by connecting multiple nonlinear transformation units in series with the input features of the smelting feature input layer. The staged feature extraction layer generates staged feature vectors that reflect the changes in the intensity of carbon-oxygen reaction by weighted combination according to time steps. The prediction result sequence generation unit is used to input the stage feature vector output by the stage feature extraction layer into the carbon-oxygen product prediction output layer. The carbon-oxygen product prediction output layer includes multiple output units for outputting the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value, so as to obtain a prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value. The prediction model generation unit is used to compare the prediction result sequence composed of the current carbon-oxygen product prediction value and the final carbon-oxygen product prediction value with the actual carbon-oxygen product of historical furnaces and iteratively adjust the weight parameters in the smelting feature input layer, the stage feature extraction layer and the carbon-oxygen product prediction output layer. When the carbon-oxygen product prediction error of the dynamic prediction model in the verification furnace meets the preset threshold, the trained dynamic prediction model is used as the prediction model.

9. A device, characterized in that, include: Memory for storing carbon-oxygen product control programs based on low-carbon steelmaking; A processor, configured to implement the steps of the carbon-oxygen product control method for low-carbon steelmaking as described in any one of claims 1-6 when executing the carbon-oxygen product control program for low-carbon steelmaking.

10. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a carbon-oxygen product control program based on low-carbon steelmaking, which, when executed by a processor, implements the steps of the carbon-oxygen product control method based on low-carbon steelmaking as described in any one of claims 1-6.

Images