Converter automatic slag splashing control method, device, computer equipment and storage medium

Abstract

The present invention relates to a method, device, computer equipment and storage medium for automatic slag splashing control of a converter, which belongs to the technical field of converter steelmaking. The method comprises: collecting relevant information of the current heat and historical heats, establishing and classifying a database of historical heats, and obtaining corresponding slag splashing and furnace protection gun position control curves; fitting various slag splashing gun position control curves and performing stepwise regression calculations on various slag compositions and weights to form a curve fitting database and an optimal stepwise regression database; combining the condition information of the current heat, obtaining a recommended slag splashing gun position control curve and recommended slag composition and weight values; calculating the calculated values ​​of the slag composition and weight of the current heat according to material balance; obtaining predicted values ​​of the slag composition and weight of the current heat through recurrent neural network calculations; and finally obtaining the slag splashing mode of the current heat and performing automatic slag splashing operations. The present invention can accurately control the slag splashing gun position, improve the slag splashing and furnace protection effect and converter operation rate, and reduce process production costs.

Description

Technical Field

[0001] The present invention relates to a converter automatic slag splashing control method, device, computer equipment and storage medium, belonging to the technical field of converter steelmaking. Background Art

[0002] The converter slag splashing technology utilizes steelmaking end-point slag with a saturated or supersaturated MgO content after tapping. Appropriate modifiers are added to adjust the slag viscosity and composition to an appropriate range. High-pressure nitrogen is then blown into the furnace via an oxygen lance to splash the slag, creating a coating of slag with a defined viscosity, refractoriness, and corrosion resistance. The slag cools and solidifies on the lining, forming a high-melting-point molten slag layer that protects the lining. This layer offers excellent corrosion resistance, inhibits oxidation and decarburization of the lining bricks, and mitigates erosion and erosion caused by high-temperature slag. This protects the lining bricks, reduces refractory wear, and reduces the consumption of gunning materials. It also reduces labor intensity, extends the service life of the lining, increases converter availability, and reduces production costs.

[0003] Optimizing the main process parameters of converter slag splashing and adopting a suitable oxygen lance nozzle structure will help improve the comprehensive level of slag splashing and protection: (1) Appropriate slag amount in the molten pool: According to the practice and effect of slag splashing, the slag amount is generally 100kg / t. (2) Slag properties: An important measure to reduce lining erosion is to increase the MgO content in the slag. When the MgO in the slag reaches saturation, the amount of MgO dissolved in the lining will decrease, thereby increasing the life of the lining. The MgO content in the slag is related to the slag basicity. Generally, the final slag basicity (%CaO / SiO2) is about 3, and the MgO content is 8% to 12%. The FeO content in the slag has a great influence on the lining erosion and slag splashing effect. The mineral composition of FeO in the slag is mostly various low-melting-point ferrites, with a melting point far lower than the tapping temperature. Moreover, the higher the FeO content, the more ferrites there are, the better the slag fluidity is, the greater the erosion effect on the lining is, and it is not easy to adhere to the lining. If the FeO content in the slag is too low, it will make it difficult to make slag and remove P and S in the converter. Therefore, the FeO content in the slag must be strictly controlled during operation; if the slag viscosity is high, the slag is thick and difficult to splash, and the adhesion to the furnace lining is poor; if the slag viscosity is low, the slag is thin, and the splash slag is easy to cover, but the covering layer is thin, and there will be slag hanging and falling, which requires adding slag material to adjust. (3) By adding slag conditioning agents, the slag is modified, the melting temperature is increased, and the bonding ability of the slag and the furnace lining is improved, thereby improving the dynamic conditions of the splash slag and the anti-corrosion ability of the splash slag layer. (4) Nitrogen pressure and flow, oxygen lance process parameters and oxygen lance position control, combined blown converter bottom blowing, slag splashing time, steel grade endpoint control target requirements, as well as each plant's process equipment, furnace charge results, technical operation level, management requirements, etc. all have a direct impact on the slag splashing furnace protection effect and need to be highly valued and comprehensively considered.

[0004] Slag splashing is a significant advancement in converter protection technology, significantly increasing converter lifespan and reducing refractory consumption. It demonstrates broad prospects for widespread adoption in my country. However, given the differences in process equipment, charge requirements, operational expertise, steel grade endpoint control targets, and management requirements across various enterprises, efficient and low-cost automated slag splashing technology is urgently needed. Therefore, this application proposes a method for automated converter slag splashing control. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes a method, device, computer equipment and storage medium for automatic slag splashing control of a converter, which can achieve precise control of the slag splashing gun position, improve the slag splashing furnace protection effect and converter operation rate, and reduce the process production cost.

[0006] The technical solution adopted by the present invention to solve its technical problems is:

[0007] In a first aspect, an embodiment of the present invention provides a method for automatically controlling slag splashing in a converter, comprising the following steps:

[0008] Collect relevant information of the current heat and historical heats, and establish a historical heat database, wherein the relevant information includes furnace entry condition information, slag-making auxiliary material information, oxygen consumption, and end-point condition information. The furnace entry condition information includes the composition, temperature, and weight of the molten iron, and the type and weight of the scrap steel; the slag-making auxiliary material information includes the composition and addition amount of various slag-making auxiliary materials; the end-point condition information includes the end-point temperature, end-point carbon content, end-point molten pool level, end-slag composition, and a slag splashing gun position control curve;

[0009] The historical furnace database is classified according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and the corresponding slag splashing furnace protection gun position control curve is obtained;

[0010] Fitting various slag splashing gun position control curves corresponding to each group of identical or similar furnace-entry conditions respectively, forming a curve fitting database of various slag splashing gun position control curves corresponding to identical or similar furnace-entry conditions;

[0011] Combined with the condition information of this heat, the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as this heat is obtained in the curve fitting database;

[0012] Based on the classification results of the historical heat database, the various slag compositions and weights corresponding to the same or similar furnace feeding conditions are subjected to stepwise regression calculations to obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions;

[0013] Combined with the condition information of this heat, the recommended values ​​of slag composition and weight for the same or similar charging conditions as this heat are obtained in the optimal stepwise regression database;

[0014] The composition and weight of the slag of this heat are calculated based on the material balance using the molten iron and scrap steel income items in the converter.

[0015] The calculated values ​​of slag composition and weight of the current heat and the recommended values ​​of slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into the recurrent neural network to obtain the predicted values ​​of slag composition and weight of the current heat;

[0016] Based on the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat, it is decided whether to dump part of the slag or whether to add slag conditioning agents for modification. The slag splashing pattern of this heat is obtained by combining the recommended curve for slag splashing gun position control under the same or similar furnace feeding conditions as this heat.

[0017] Automatic slag splashing operation is performed using the slag splashing mode of this furnace.

[0018] As a possible implementation of this embodiment, the fitting of various slag splashing gun position control curves corresponding to each group of identical or similar furnace feeding conditions includes:

[0019] The corresponding slag-splashing gun position control height curve on the time axis of each furnace is fitted, and the fitting function command is: H0=polyval(a,t), a=polyfit(tdata,Hdata,n), n represents the highest order of the polynomial, tdata and Hdata are the data to be fitted, and it is input in the form of an array; by fitting various slag-splashing gun position control curves corresponding to the same or similar furnace entry conditions in the database, the control accuracy of the slag-splashing gun position at any moment on the time axis under these conditions is further improved.

[0020] As a possible implementation of this embodiment, the stepwise regression calculation of various slag compositions and weights corresponding to the same or similar furnace feeding conditions is performed to obtain an optimal stepwise regression database of slag compositions and weights corresponding to various conditions, including:

[0021] Taking each group of identical or similar furnace conditions as the independent variable and the corresponding slag composition as the dependent variable, a stepwise regression is performed to obtain the optimal slag composition value database under the conditions;

[0022] Similarly, each group of identical or similar furnace conditions is used as the independent variable, and the corresponding slag weight is used as the dependent variable, and stepwise regression is performed to obtain the optimal slag weight value database under these conditions.

[0023] As a possible implementation of this embodiment, the calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into a recurrent neural network for calculation to obtain the predicted values ​​of the slag composition and weight of the current heat, including:

[0024] Taking "the calculated values ​​of slag composition and weight of this heat according to material balance" and "the recommended values ​​of slag composition and weight of this heat with the same or similar furnace feeding conditions" as the input of the recurrent neural network, the recurrent neural network calculation is performed to output the predicted values ​​of slag composition and weight of this heat.

[0025] As a possible implementation of this embodiment, the TSO measurement results at the blowing endpoint of this heat include C content, temperature T and molten pool liquid level h; the specific conditions of the heat include slag basicity, C content and slag amount; the slag splashing mode of this heat includes the slag splashing gun position control curve, slag splashing time and the amount of slag regulating agent added.

[0026] As a possible implementation of this embodiment, the calculated values, recommended values, predicted values, recommended curves and blowing end point TSO measurement results are all fed back to a related database for self-learning correction.

[0027] In a second aspect, an embodiment of the present invention provides a converter automatic slag splashing control device, comprising:

[0028] A database establishment module is used to collect relevant information of the current heat and historical heats and establish a historical heat database. The relevant information includes furnace entry condition information, slag auxiliary material information, oxygen consumption and end point information. The furnace entry condition information includes the composition, temperature and weight of the molten iron, and the type and weight of the scrap steel; the slag auxiliary material information includes the composition and addition amount of various slag auxiliary materials; the end point information includes the end point temperature, end point carbon content, end point molten pool level, end slag composition and the slag splashing furnace protection gun position control curve;

[0029] The database classification module is used to classify the historical furnace database according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and obtain the corresponding slag splashing furnace protection gun position control curve diagram;

[0030] The control curve fitting module is used to fit various slag splashing gun position control curves corresponding to each group of the same or similar furnace entry conditions, thereby forming a curve fitting database of various slag splashing gun position control curves corresponding to the same or similar furnace entry conditions;

[0031] The recommended curve acquisition module is used to obtain the recommended curve for slag splashing gun position control with the same or similar furnace entry conditions as the current heat in the curve fitting database based on the current heat condition information;

[0032] The regression calculation module is used to perform stepwise regression calculations on various slag compositions and weights corresponding to the same or similar furnace feeding conditions based on the classification results of the historical furnace database, and obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions;

[0033] The recommended value acquisition module is used to obtain the recommended values ​​of slag composition and weight for the same or similar charging conditions as the current heat in the optimal stepwise regression database based on the current heat condition information;

[0034] The material balance calculation module is used to calculate the composition and weight of the slag of this furnace according to the material balance based on the molten iron and scrap steel income items in the converter;

[0035] The predicted value calculation module is used to input the calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the same or similar furnace feeding conditions as the current heat into the recurrent neural network to obtain the predicted values ​​of the slag composition and weight of the current heat;

[0036] The slag splashing pattern acquisition module is used to determine whether to discard part of the slag or add slag conditioning agents for modification based on the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat. It also obtains the slag splashing pattern of this heat by combining the recommended slag splashing gun position control curve for the same or similar furnace feeding conditions as this heat.

[0037] The slag splashing operation module is used to perform automatic slag splashing operation using the slag splashing mode of this furnace.

[0038] In the third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of any of the above-mentioned converter automatic slag splashing control methods.

[0039] In a fourth aspect, an embodiment of the present invention provides a storage medium having a computer program stored thereon, and when the computer program is run by a processor, the steps of any of the above-mentioned converter automatic slag splashing control methods are executed.

[0040] The beneficial effects of the technical solutions of the embodiments of the present invention are as follows:

[0041] The present invention calculates the slag composition and weight of the current heat according to the material balance based on the relevant information of the current heat, and performs recurrent neural network calculation on the "recommended slag composition and weight values ​​with the same or similar furnace entry conditions as the current heat" obtained based on big data analysis of the historical heat database and historical optimization to obtain the predicted slag composition and weight values ​​of the current heat. Combined with the TSO measurement result of the blowing endpoint of the current heat and the specific conditions of the heat, it is decided whether to discard part of the slag or whether to add a slag conditioning agent for modification. Finally, combined with the "recommended curve for slag splashing gun position control with the same or similar furnace entry conditions as the current heat", the slag splashing mode of the current heat is obtained, thereby performing automatic slag splashing operation, effectively realizing precise control of the slag splashing gun position, improving the slag splashing furnace protection effect, improving the converter operation rate, and reducing the process production cost, it has significant economic benefits and broad promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a converter automatic slag splashing control method according to an exemplary embodiment;

[0043] Figure 2 is a schematic structural diagram of a recurrent neural network according to an exemplary embodiment;

[0044] Figure 3 1 is a schematic structural diagram of a converter automatic slag splashing control device according to an exemplary embodiment;

[0045] Figure 4 This is a flow chart of automatic converter slag splashing control using the converter automatic slag splashing control device of the present invention;

[0046] Figure 5 This is a comparison diagram of the slag-splashing gun position control curve recommended for Heat 1 in Example 1, which has the same or similar charging conditions as this heat, and the slag-splashing gun position control curve derived from the model for this heat;

[0047] Figure 6 This is a comparison diagram of the slag-splashing gun position control curve recommended for Heat 2 in Example 2, which has the same or similar charging conditions as this heat, and the slag-splashing gun position control curve derived from the model for this heat;

[0048] Figure 7 It is a comparative diagram of the slag-splashing gun position control curve recommended for Heat 3 in Example 3 with the same or similar charging conditions as this heat and the slag-splashing gun position control curve derived from the model for this heat. DETAILED DESCRIPTION

[0049] In order to more clearly illustrate the technical features of the present invention, the present invention is described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0050] The slag splashing protection of the converter involves various factors such as the converter slag amount, slag composition, slag splashing nitrogen pressure and flow, oxygen lance process parameters and oxygen lance position control, combined blowing converter bottom blowing, slag splashing time, whether to adjust the slag, steel grade endpoint control target requirements, and each factory's process equipment, furnace charge results, technical operation level, management requirements, etc., which require systematic and overall consideration. To this end, the present invention provides a converter automatic slag splashing control method.

[0051] like Figure 1 As shown, an embodiment of the present invention provides a converter automatic slag splashing control method, comprising the following steps:

[0052] Collect relevant information of the current heat and historical heats, and establish a historical heat database, wherein the relevant information includes furnace entry condition information, slag-making auxiliary material information, oxygen consumption, and end-point condition information. The furnace entry condition information includes the composition, temperature, and weight of the molten iron, and the type and weight of the scrap steel; the slag-making auxiliary material information includes the composition and addition amount of various slag-making auxiliary materials; the end-point condition information includes the end-point temperature, end-point carbon content, end-point molten pool level, end-slag composition, and a slag splashing gun position control curve;

[0053] The historical furnace database is classified according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and the corresponding slag splashing furnace protection gun position control curve is obtained;

[0054] Fitting various slag splashing gun position control curves corresponding to each group of identical or similar furnace-entry conditions respectively, forming a curve fitting database of various slag splashing gun position control curves corresponding to identical or similar furnace-entry conditions;

[0055] Combined with the condition information of this heat, the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as this heat is obtained in the curve fitting database;

[0056] Based on the classification results of the historical heat database, the various slag compositions and weights corresponding to the same or similar furnace feeding conditions are subjected to stepwise regression calculations to obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions;

[0057] Combined with the condition information of this heat, the recommended values ​​of slag composition and weight for the same or similar charging conditions as this heat are obtained in the optimal stepwise regression database;

[0058] The composition and weight of the slag of this heat are calculated based on the material balance using the molten iron and scrap steel income items in the converter.

[0059] The calculated values ​​of slag composition and weight of the current heat and the recommended values ​​of slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into the recurrent neural network to obtain the predicted values ​​of slag composition and weight of the current heat;

[0060] Based on the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat, it is decided whether to dump part of the slag or whether to add slag conditioning agents for modification. The slag splashing pattern of this heat is obtained by combining the recommended curve for slag splashing gun position control under the same or similar furnace feeding conditions as this heat.

[0061] Automatic slag splashing operation is performed using the slag splashing mode of this furnace.

[0062] Figure 1 The steps of the converter automatic slag splashing control method shown are merely a list of the technical means required by the present invention, and do not limit the steps to be performed sequentially from top to bottom. For example, in a specific implementation process, the applicant performs the following three steps in parallel:

[0063] Combined with the condition information of this heat, the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as this heat is obtained in the curve fitting database;

[0064] Combined with the condition information of this heat, the recommended values ​​of slag composition and weight for the same or similar charging conditions as this heat are obtained in the optimal stepwise regression database;

[0065] The composition and weight of the slag of this furnace are calculated based on the material balance through the molten iron and scrap steel income items in the converter.

[0066] As a possible implementation of this embodiment, the fitting of various slag splashing gun position control curves corresponding to each group of identical or similar furnace feeding conditions includes:

[0067] The corresponding slag-splashing gun position control height curve on the time axis of each furnace is fitted, and the fitting function command is: H0=polyval(a,t), a=polyfit(tdata,Hdata,n), n represents the highest order of the polynomial, tdata and Hdata are the data to be fitted, and it is input in the form of an array; by fitting various slag-splashing gun position control curves corresponding to the same or similar furnace entry conditions in the database, the control accuracy of the slag-splashing gun position at any moment on the time axis under these conditions is further improved.

[0068] As a possible implementation of this embodiment, the stepwise regression calculation of various slag compositions and weights corresponding to the same or similar furnace feeding conditions is performed to obtain an optimal stepwise regression database of slag compositions and weights corresponding to various conditions, including:

[0069] Taking each group of identical or similar furnace conditions as the independent variable and the corresponding slag composition as the dependent variable, a stepwise regression is performed to obtain the optimal slag composition value database under the conditions;

[0070] Similarly, each group of identical or similar furnace conditions is used as the independent variable, and the corresponding slag weight is used as the dependent variable, and stepwise regression is performed to obtain the optimal slag weight value database under these conditions.

[0071] As a possible implementation of this embodiment, the calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into a recurrent neural network for calculation to obtain the predicted values ​​of the slag composition and weight of the current heat, including:

[0072] Taking "the calculated values ​​of slag composition and weight of this batch according to material balance" and "the recommended values ​​of slag composition and weight of this batch with the same or similar charging conditions" as the input of the recurrent neural network, the recurrent neural network calculation is performed to output the predicted values ​​of slag composition and weight of this batch, such as Figure 2 shown.

[0073] A material balance calculates the equilibrium relationship between all materials introduced into and involved in the converter steelmaking process (such as molten iron, scrap steel, oxygen, coolant, slag, alloying additives, and corroded furnace lining) and the products of the steelmaking process (such as molten steel, slag, furnace gases, and soot). This calculation, based on the principle of conservation of mass, allows for an understanding of the sources and destinations of materials in converter steelmaking.

[0074] As a possible implementation of this embodiment, the TSO measurement results at the blowing endpoint of this heat include C content, temperature T and molten pool liquid level h; the specific conditions of the heat include slag basicity, C content and slag amount; the slag splashing mode of this heat includes the slag splashing gun position control curve, slag splashing time and the amount of slag regulating agent added.

[0075] As a possible implementation of this embodiment, the calculated values, recommended values, predicted values, recommended curves and blowing end point TSO measurement results are all fed back to a related database for self-learning correction.

[0076] like Figure 3 As shown, an embodiment of the present invention provides a converter automatic slag splashing control device, comprising:

[0077] A database establishment module is used to collect relevant information of the current heat and historical heats and establish a historical heat database. The relevant information includes furnace entry condition information, slag auxiliary material information, oxygen consumption and end point information. The furnace entry condition information includes the composition, temperature and weight of the molten iron, and the type and weight of the scrap steel; the slag auxiliary material information includes the composition and addition amount of various slag auxiliary materials; the end point information includes the end point temperature, end point carbon content, end point molten pool level, end slag composition and the slag splashing furnace protection gun position control curve;

[0078] The database classification module is used to classify the historical furnace database according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and obtain the corresponding slag splashing furnace protection gun position control curve diagram;

[0079] The control curve fitting module is used to fit various slag splashing gun position control curves corresponding to each group of the same or similar furnace entry conditions, thereby forming a curve fitting database of various slag splashing gun position control curves corresponding to the same or similar furnace entry conditions;

[0080] The recommended curve acquisition module is used to obtain the recommended curve for slag splashing gun position control with the same or similar furnace entry conditions as the current heat in the curve fitting database based on the current heat condition information;

[0081] The regression calculation module is used to perform stepwise regression calculations on various slag compositions and weights corresponding to the same or similar furnace feeding conditions based on the classification results of the historical furnace database, and obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions;

[0082] The recommended value acquisition module is used to obtain the recommended values ​​of slag composition and weight for the same or similar charging conditions as the current heat in the optimal stepwise regression database based on the current heat condition information;

[0083] The material balance calculation module is used to calculate the composition and weight of the slag of this furnace according to the material balance based on the molten iron and scrap steel income items in the converter;

[0084] The predicted value calculation module is used to input the calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the same or similar furnace feeding conditions as the current heat into the recurrent neural network to obtain the predicted values ​​of the slag composition and weight of the current heat;

[0085] The slag splashing pattern acquisition module is used to determine whether to discard part of the slag or add slag conditioning agents for modification based on the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat. It also obtains the slag splashing pattern of this heat by combining the recommended slag splashing gun position control curve for the same or similar furnace feeding conditions as this heat.

[0086] The slag splashing operation module is used to perform automatic slag splashing operation using the slag splashing mode of this furnace.

[0087] like Figure 4 As shown, the specific process of performing automatic slag splashing control of a converter using the automatic slag splashing control device of the present invention is as follows.

[0088] Step 1: Collect relevant information about the current heat and historical heats to establish a historical heat database. This includes: furnace entry conditions such as molten iron composition, temperature, and weight; scrap type and weight; various slag-forming auxiliary material compositions and addition amounts; oxygen consumption; endpoint temperature, carbon content, molten pool level, final slag composition, and slag-splashing lance position control curves. The historical heat database is categorized based on similar or similar furnace entry conditions, slag-forming auxiliary material conditions, and endpoint conditions, generating corresponding slag-splashing lance position control curves for each condition.

[0089] Step 2: Fit various slag splashing gun position control curves corresponding to each group of identical or similar furnace entry conditions to form a library of fitting curves for various slag splashing gun position control curves corresponding to identical or similar furnace entry conditions.

[0090] Using MATLAB software, the corresponding slag-splashing gun position control height curve on the time axis of each furnace is fitted. The fitting function command is: H0= polyval(a,t), a=polyfit(tdata,Hdata,n), n represents the highest order of the polynomial, tdata, Hdata are the data to be fitted, and it is input in array form;

[0091] By fitting various slag splashing gun position control curves corresponding to the same or similar furnace feeding conditions in the database, the control accuracy of the slag splashing gun position at any moment on the time axis under these conditions is further improved.

[0092] Combined with the condition information of this heat, the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as this heat is obtained in the fitting database.

[0093] Step 3: Based on the classification results in step 1, perform stepwise regression calculations on the various slag compositions and weights corresponding to the same or similar furnace feeding conditions, thereby obtaining a stepwise regression database of slag compositions and weights corresponding to various conditions.

[0094] Taking each group of identical or similar furnace conditions as the independent variable and the corresponding slag composition as the dependent variable, a stepwise regression is performed to obtain the optimal slag composition value database under that condition. Similarly, taking each group of identical or similar furnace conditions as the independent variable and the corresponding slag weight as the dependent variable, a stepwise regression is performed to obtain the optimal slag weight value database under that condition.

[0095] Combined with the condition information of this heat, the recommended values ​​of slag composition and weight for the same or similar charging conditions as this heat are obtained in the stepwise regression optimal value database.

[0096] Step 4, material balance, calculates the equilibrium relationship between all materials added to and involved in the converter steelmaking process (such as molten iron, scrap, oxygen, coolant, slag, alloying additives, and corroded lining) and the products of the steelmaking process (such as molten steel, slag, furnace gases, and soot). Material balance calculates the amount of each substance generated and, based on the principle of conservation of mass, provides an understanding of the sources and destinations of materials in converter steelmaking. The material balance calculation uses the input items of molten iron, scrap, and other materials in the converter to derive the composition and weight (output item) of the slag for this heat.

[0097] Step 5: Use the "calculated values ​​of slag composition and weight of this batch calculated according to material balance" and "recommended values ​​of slag composition and weight of this batch with the same or similar furnace feeding conditions" as the input layer to perform recurrent neural network calculation, and the output layer obtains the "predicted values ​​of slag composition and weight of this batch calculated by the recurrent neural network".

[0098] In step 6, based on the TSO measurement results at the end of blowing for this heat (including carbon content, temperature T, and bath level h), and the specific conditions of the heat (such as slag basicity, carbon content, and slag volume), a decision is made as to whether to partially discard the slag or add slag conditioning agents for modification. Finally, the recommended slag spraying gun position control curve for the same or similar furnace feeding conditions as this heat is combined with the "recommended slag spraying gun position control curve for the same or similar furnace feeding conditions as this heat" to determine the slag spraying pattern for this heat (including the slag spraying gun position control curve, slag spraying time, and slag conditioning agent dosage).

[0099] In the present invention, all theoretical calculation values, historical optimal values, recurrent neural network prediction values, gun position control recommended curves, blowing end point TSO measurement results and other information are all fed back to the relevant database for self-learning correction.

[0100] Specific calculation example 1:

[0101] Heat 1: Hot metal temperature at 1352°C, composition: C: 4.26%, Si: 0.56%, Mn: 0.32%, P: 0.081%, S: 0.032%. Scrap and hot metal charge: (181 + 50) tons. Slag and alloying materials: 26 kg / t lime, 7.1 kg / t dolomite, 7 kg / t ore. Oxygen consumption: 49 m³ / t. The blowing process was smooth, with no splashing or dry-out, and the finish line was achieved in one pass. According to the material balance, the slag basicity was calculated to be 3.2, 8.1% MgO, 16.5% FeO, and weighing 20.6 tons. Historical database recommendations for similar or similar charging conditions for this heat: 3.12, 7.9% MgO, 17.5% FeO, and weighing 19.9 tons. The predicted values ​​calculated by the recurrent neural network are R: 3.16, MgO: 7.6%, FeO: 15.7%, and weight: 20.2t. The TSO results for the converter's secondary lance at the end of the converter are: [C]: 0.080%, T: 1636°C, and bath level h: 836mm. No slag dumping or slag adjustment is required. The recommended slag lance position control curve for the same or similar furnace entry conditions as this heat, as well as the slag lance position control curve derived from the model for this heat, are as follows: Figure 5 As shown in the figure, the slag test results are: slag basicity R: 3.17; MgO: 7.8%; FeO: 16.0%. It can be seen that the predicted values ​​calculated by the recurrent neural network are closer to the actual test results.

[0102] Specific calculation example 2:

[0103] Heat 2: Hot metal temperature at 1376°C, composition: C: 4.30%, Si: 0.46%, Mn: 0.36%, P: 0.075%, S: 0.030%. Scrap and hot metal charge: (180 + 51) tons. Slag and alloying materials: 28 kg / t lime, 8.1 kg / t dolomite, 7.6 kg / t ore. Oxygen consumption: 49.2 m³ / t. The blowing process was smooth, with no splashing or dry-out, and the finish line was achieved in one pass. According to the material balance, the slag basicity was R: 3.06, MgO: 8.6%, FeO: 18.3%, and the weight was 18.3 tons. Historical database recommendations for similar or similar charging conditions for this heat: R: 3.10, MgO: 8.0%, FeO: 17.3%, and the weight was 18.9 tons. The predicted values ​​calculated by the recurrent neural network are R: 3.10; MgO: 8.1%; FeO: 17.7%; and weight: 18.5t. The TSO results for the converter's secondary lance at the end of the converter are: [C]: 0.072%, T: 1646°C, and the bath level h: 831mm. No slag dumping or slag adjustment is required. The recommended slag lance position control curve for the same or similar furnace entry conditions as this heat, as recommended by the slag lance position control curve library, and the slag lance position control curve derived from this heat model are as follows: Figure 6As shown in the figure, the slag test results are: slag basicity R: 3.09; MgO: 8.1%; FeO: 17.8%. Similarly, the predicted values ​​calculated by the recurrent neural network are closer to the actual test results.

[0104] Specific calculation example 3:

[0105] Heat 3: Hot metal temperature at 1336°C, composition: C: 4.26%, Si: 0.57%, Mn: 0.45%, P: 0.091%, S: 0.028%. Scrap and hot metal charge: (176 + 55) tons. Slag and alloying materials: 27 kg / t lime, 8.3 kg / t dolomite, 7.9 kg / t ore. Oxygen consumption: 49.0 m³ / t. The blowing process was smooth, with no splashing or dry-out, and the finish line was achieved in one pass. According to the material balance, the slag basicity was calculated to be R: 3.01, MgO: 9.6%, FeO: 19.1%, and weighing 19.5 tons. Historical database recommendations for similar or similar charging conditions for this heat: R: 3.05, MgO: 9.2%, FeO: 18.8%, and weighing 19.2 tons. The predicted values ​​calculated by the recurrent neural network are R: 3.03, MgO: 9.5%, FeO: 19.0%, and weight: 19.3t. The TSO results for the converter's secondary lance at the end of the converter are: [C]: 0.078%, T: 1636°C, and bath level h: 826mm. No slag dumping or slag adjustment is required. The recommended slag lance position control curve for the same or similar furnace entry conditions as this heat, as well as the slag lance position control curve derived from the model for this heat, are as follows: Figure 7 As shown in the figure, the slag test results are: slag basicity R: 3.03; MgO: 9.4%; FeO: 18.9%. Similarly, the predicted values ​​calculated by the recurrent neural network are closer to the actual test results.

[0106] The present invention calculates the slag composition and weight of the current heat according to the material balance based on the relevant information of the current heat, and performs recurrent neural network calculation on the "recommended slag composition and weight values ​​with the same or similar furnace entry conditions as the current heat" obtained based on big data analysis of the historical heat database and historical optimization to obtain the predicted slag composition and weight values ​​of the current heat. Combined with the TSO measurement result of the blowing endpoint of the current heat and the specific conditions of the heat, it is decided whether to discard part of the slag or whether to add a slag conditioning agent for modification. Finally, combined with the "recommended curve for slag splashing gun position control with the same or similar furnace entry conditions as the current heat", the slag splashing mode of the current heat is obtained, thereby performing automatic slag splashing operation, effectively realizing precise control of the slag splashing gun position, improving the slag splashing furnace protection effect, improving the converter operation rate, and reducing the process production cost, it has significant economic benefits and broad promotion prospects.

[0107] A computer device provided by an embodiment of the present invention includes a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of any of the above-mentioned converter automatic slag splashing control methods.

[0108] Specifically, the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, the above-mentioned converter automatic slag splashing control method can be executed.

[0109] Those skilled in the art will understand that the structure of the computer device does not constitute a limitation of the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently.

[0110] In some embodiments, the computer device may also include a touch screen that can be used to display a graphical user interface (e.g., an application startup interface) and receive user operations on the graphical user interface (e.g., application startup operations). Specifically, the touch screen may include a display panel and a touch panel. The display panel may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or other devices. The touch panel can detect contact or non-contact operations performed by a user on or near it and generate pre-set operation instructions. For example, a user may use a finger, a stylus, or any other suitable object or accessory to perform operations on or near the touch panel. Furthermore, the touch panel may include a touch detection device and a touch controller. The touch detection device detects the user's touch position and posture, detects signals generated by the touch operation, and transmits the signals to the touch controller. The touch controller receives the touch information from the touch detection device, converts it into information that can be processed by the processor, and then transmits it to the processor. The touch controller can also receive and execute commands from the processor. In addition, the touch panel can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave, and any technology developed in the future can also be used to implement the touch panel. Furthermore, the touch panel can cover the display panel, and the user can operate on or near the touch panel covered on the display panel according to the graphical user interface displayed on the display panel. After the touch panel detects the operation on or near it, it transmits it to the processor to determine the user input, and then the processor provides a corresponding visual output on the display panel in response to the user input. In addition, the touch panel and the display panel can be implemented as two independent components or integrated.

[0111] Corresponding to the method for starting the above-mentioned application, an embodiment of the present invention further provides a storage medium on which a computer program is stored. When the computer program is run by a processor, the steps of any of the above-mentioned converter automatic slag splashing control methods are executed.

[0112] The startup device of the application provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for any part not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0115] Modules described as separate components may or may not be physically separate, and 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 these modules may be selected to achieve the purpose of this embodiment based on actual needs.

[0116] In addition, each functional module in the embodiments provided in the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0117] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A converter automatic slag splashing control method, characterized in that: The steps include: Collect relevant information of the current heat and historical heats and establish a historical heat database. The relevant information includes furnace entry condition information, slag-making auxiliary material information, oxygen consumption, and endpoint information. The furnace entry condition information includes the composition, temperature, and weight of molten iron, and the type and weight of scrap steel; the slag-making auxiliary material information includes the composition and addition amount of various slag-making auxiliary materials; the endpoint information includes the endpoint temperature, endpoint carbon content, endpoint molten pool level, final slag composition, and a slag splashing gun position control curve; The historical furnace database is classified according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and the corresponding slag splashing furnace protection gun position control curve is obtained; Fitting various slag splashing gun position control curves corresponding to each group of identical or similar furnace-entry conditions respectively, forming a curve fitting database of various slag splashing gun position control curves corresponding to identical or similar furnace-entry conditions; Combined with the condition information of this heat, the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as this heat is obtained in the curve fitting database; Based on the classification results of the historical heat database, the various slag compositions and weights corresponding to the same or similar furnace feeding conditions are subjected to stepwise regression calculations to obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions; Combined with the condition information of this heat, the recommended values ​​of slag composition and weight for the same or similar charging conditions as this heat are obtained in the optimal stepwise regression database; The composition and weight of the slag of this heat are calculated based on the material balance using the molten iron and scrap steel income items in the converter. The calculated values ​​of slag composition and weight of the current heat and the recommended values ​​of slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into the recurrent neural network to obtain the predicted values ​​of slag composition and weight of the current heat; Combined with the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat, it is decided whether to dump part of the slag or whether to add slag conditioning agents for modification. The slag splashing pattern of this heat is obtained by combining the recommended curve for slag splashing gun position control under the same or similar furnace feeding conditions as this heat. Automatic slag splashing operation is performed using the slag splashing mode of this furnace.

2. The converter automatic slag splashing control method according to claim 1, characterized in that: The fitting of various slag splashing gun position control curves corresponding to each group of identical or similar furnace feeding conditions includes: Fit the slag splashing gun position control height curve corresponding to the time axis of each furnace. The fitting function command is: H0=polyval(a,t), a=polyfit(tdata,Hdata,n), n represents the highest order of the polynomial, tdata and Hdata are the data to be fitted.

3. The converter automatic slag splashing control method according to claim 1, characterized in that: The stepwise regression calculation of various slag compositions and weights corresponding to the same or similar furnace feeding conditions is performed to obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions, including: Taking each group of identical or similar furnace conditions as the independent variable and the corresponding slag composition as the dependent variable, a stepwise regression is performed to obtain the optimal slag composition value database under the conditions; Similarly, each group of identical or similar furnace conditions is used as the independent variable, and the corresponding slag weight is used as the dependent variable, and stepwise regression is performed to obtain the optimal slag weight value database under these conditions.

4. The converter automatic slag splashing control method according to claim 1, characterized in that: The calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the current heat with the same or similar furnace feeding conditions are input into the recurrent neural network for calculation to obtain the predicted values ​​of the slag composition and weight of the current heat, including: The "calculated values ​​of slag composition and weight of this heat according to material balance" and "recommended values ​​of slag composition and weight of this heat under the same or similar charging conditions" are used as inputs of the recurrent neural network. The recurrent neural network calculation is performed to output the predicted values ​​of slag composition and weight of this heat.

5. The converter automatic slag splashing control method according to claim 1, characterized in that: The TSO measurement results of the blowing endpoint of this heat include C content, temperature T and molten pool liquid level h; the specific conditions of the heat include slag basicity, C content and slag amount; the slag splashing mode of this heat includes slag splashing gun position control curve, slag splashing time and slag regulating agent addition amount.

6. The converter automatic slag splashing control method according to any one of claims 1 to 5, characterized in that: The calculated values, recommended values, predicted values, recommended curves and blowing end point TSO measurement results are all fed back to the relevant database for self-learning correction.

7. A converter automatic slag splashing control device, characterized in that: include: A database establishment module is used to collect relevant information of the current heat and historical heats and establish a historical heat database. The relevant information includes furnace entry condition information, slag auxiliary material information, oxygen consumption and end point information. The furnace entry condition information includes the composition, temperature and weight of molten iron, and the type and weight of scrap steel; the slag auxiliary material information includes the composition and addition amount of various slag auxiliary materials; the end point information includes the end point temperature, end point carbon content, end point molten pool level, end slag composition and slag splashing furnace protection gun position control curve; The database classification module is used to classify the historical furnace database according to the same or similar furnace entry conditions, slag-making auxiliary materials and end point conditions, and obtain the corresponding slag splashing furnace protection gun position control curve diagram; The control curve fitting module is used to fit various slag splashing gun position control curves corresponding to each group of the same or similar furnace entry conditions, thereby forming a curve fitting database of various slag splashing gun position control curves corresponding to the same or similar furnace entry conditions; The recommended curve acquisition module is used to obtain the recommended curve for slag splashing gun position control with the same or similar furnace feeding conditions as the current heat in the curve fitting database based on the current heat condition information; The regression calculation module is used to perform stepwise regression calculations on various slag compositions and weights corresponding to the same or similar furnace feeding conditions based on the classification results of the historical furnace database, and obtain the optimal stepwise regression database of slag compositions and weights corresponding to various conditions; The recommended value acquisition module is used to obtain the recommended values ​​of slag composition and weight for the same or similar charging conditions as the current heat in the optimal stepwise regression database based on the current heat condition information; The material balance calculation module is used to calculate the composition and weight of the slag of this furnace according to the material balance based on the molten iron and scrap steel income items in the converter; The predicted value calculation module is used to input the calculated values ​​of the slag composition and weight of the current heat and the recommended values ​​of the slag composition and weight of the same or similar furnace feeding conditions as the current heat into the recurrent neural network to obtain the predicted values ​​of the slag composition and weight of the current heat; The slag splashing pattern acquisition module is used to determine whether to discard part of the slag or add slag conditioning agents to modify the slag based on the TSO measurement results at the blowing end point of this heat and the specific conditions of the heat. It also obtains the slag splashing pattern of this heat based on the recommended slag splashing gun position control curve for the same or similar furnace feeding conditions as this heat. The slag splashing operation module is used to perform automatic slag splashing operation using the slag splashing mode of this furnace.

8. The converter automatic slag splashing control device according to claim 7, characterized in that: The TSO measurement results of the blowing endpoint of this heat include C content, temperature T and molten pool liquid level h; the specific conditions of the heat include slag basicity, C content and slag amount; the slag splashing mode of this heat includes slag splashing gun position control curve, slag splashing time and slag regulating agent addition amount.

9. A computer device, characterized in that: It includes a processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the converter automatic slag splashing control method as described in any one of claims 1-6.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, executes the steps of the converter automatic slag splashing control method according to any one of claims 1 to 6.

Images