Converter steelmaking heat parameter prediction method, system and equipment and storage medium

Abstract

The invention provides a converter steelmaking heat parameter prediction method, system and equipment and a storage medium, and belongs to the technical field of converter automatic steelmaking, and the converter steelmaking heat parameter prediction method comprises the steps of obtaining target historical production data corresponding to a to-be-produced steel grade and a required slag thickness from a preset database; calculating the modulus increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced; based on the modulus increment of each heat, calculating the weight of each heat; according to the weight of each heat and the heat data corresponding to each heat, standard heat parameter data of the steel grade to be produced are calculated; and according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade, the parameter prediction value of the current heat of the to-be-produced steel grade is calculated. According to the invention, the problem of low prediction precision of converter parameter values in the prior art can be solved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of converter automatic steelmaking, and particularly relates to a converter steelmaking heat parameter prediction method, system and equipment and a storage medium. BACKGROUND

[0002] Converter steelmaking technology is undergoing a paradigm shift from experience-driven to data-driven. The current industry has realized basic process control by deploying L1-L4 level automation systems, but the end-point control of steelmaking still relies on artificial experience or static models, which is difficult to meet the dynamic regulation and control demand under complex working conditions. The current end-point carbon temperature prediction error is generally higher than ±0.03%(C) and ±12℃(T), and the cost of sub-lance detection accounts for 0.8-1.2% of the cost per ton of steel, which seriously restricts production efficiency and economic benefits.

[0003] The existing converter steelmaking heat parameter prediction technology generally adopts the parameter learning method of the traditional single heat model, so there is a vicious cycle of "data island - model failure - detection lag" for a long time, resulting in low prediction accuracy of parameters in the high converter process. SUMMARY

[0004] Based on the above existing converter steelmaking heat parameter prediction status, the application provides a converter steelmaking heat parameter prediction method, system and equipment and a storage medium to overcome at least one technical problem in the prior art.

[0005] To achieve the above-mentioned purpose, the application provides a converter steelmaking heat parameter prediction method, comprising:

[0006] obtaining target historical production data corresponding to a to-be-produced steel grade and a required slag thickness from a preset database; wherein the target historical production data includes heats and heat data corresponding to each heat; the heat data is a value corresponding to each parameter of the corresponding heat;

[0007] calculating the model increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the to-be-produced steel grade;

[0008] calculating the weight of each heat based on the model increment of each heat;

[0009] calculating standard heat parameter data of the to-be-produced steel grade according to the weight of each heat and the heat data corresponding to each heat; wherein the standard heat parameter data includes heats and standard parameter values corresponding to the heats;

[0010] calculating the parameter prediction value of the current heat of the to-be-produced steel grade according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade.

[0011] To solve the above problems, the present application also provides a converter steelmaking furnace campaign parameter prediction system, the system comprises:

[0012] A target data acquisition module is configured to acquire target historical production data corresponding to a steel grade to be produced and a required slag thickness from a preset database; wherein the target historical production data comprises furnace campaigns and furnace campaign data corresponding to each furnace campaign; and the furnace campaign data is numerical values corresponding to each parameter of a corresponding furnace campaign.

[0013] A mold increment calculation module is configured to calculate mold increments of each furnace campaign in the target historical production data based on the target historical production data and parameter requirement values of the steel grade to be produced.

[0014] A weight calculation module is configured to calculate weights of the furnace campaigns based on the mold increments of the furnace campaigns.

[0015] A standard parameter calculation module is configured to calculate standard furnace campaign parameter data of the steel grade to be produced based on the weights of the furnace campaigns and the furnace campaign data corresponding to each furnace campaign; wherein the standard furnace campaign parameter data comprises furnace campaigns and standard parameter values corresponding to the furnace campaigns.

[0016] A prediction value calculation module is configured to calculate a parameter prediction value of a current furnace campaign of the steel grade to be produced based on the standard furnace campaign parameter data and preset requirement parameter data of each furnace campaign of the steel grade to be produced.

[0017] To solve the above problems, the present application also provides an electronic device, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein

[0020] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps in the converter steelmaking furnace campaign parameter prediction method as described above.

[0021] To solve the above problems, the present application also provides a computer-readable storage medium, the computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the converter steelmaking furnace campaign parameter prediction method as described above.

[0022] The converter steelmaking furnace parameter prediction method, system and equipment and storage medium provided by the application, by obtaining target historical production data corresponding to the to-be-produced steel grade and the required slag thickness from the preset database, and based on the same type of converter big data of the to-be-produced steel grade, the vicious cycle problem of "data island - model failure - detection lag" existing in the learning mode of single-furnace calculation parameters in the prior art is solved, and the converter parameter prediction accuracy is improved from the data width direction; by calculating the mold increment of each heat of the target historical production data according to the target historical production data and the parameter requirement value of the to-be-produced steel grade, calculating the weight of each heat based on the mold increment of each heat, calculating the standard heat parameter data of the to-be-produced steel grade according to the weight of each heat and the heat data corresponding to each heat, and finally calculating the parameter prediction value of the current heat of the to-be-produced steel grade according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade, the parameter prediction value of the current heat of the converter is predicted by using the incremental algorithm, and the accuracy of the prediction learning calculation is improved from the data depth direction, which can guide the parameter demand of the upcoming production heat of the converter. In summary, by constructing a multi-source data fusion architecture, based on incremental dynamic calculation and prediction, the parameter learning bottleneck of the traditional single-heat model is effectively broken through, the cross-heat parameter reuse efficiency is improved by 10 8 times, a systematic solution to the long-standing "data island - model failure - detection lag" vicious cycle in the industry is provided, and has significant engineering application value. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 The flowchart of the converter steelmaking furnace parameter prediction method provided by an embodiment of the application;

[0025] Figure 2 The module schematic diagram of the converter steelmaking furnace parameter prediction system provided by an embodiment of the application;

[0026] Figure 3 The internal structure schematic diagram of the electronic device for realizing the converter steelmaking furnace parameter prediction method provided by an embodiment of the application.

[0027] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0028] It should be understood that the specific embodiments described herein are merely illustrative of the present application and do not limit the present application.

[0029] Based on the problems in the prior art, the present application mainly provides a converter steelmaking furnace campaign parameter prediction method, system and equipment and a storage medium, and the main purpose is to solve the problem of low prediction accuracy of parameters in the converter process by adopting the traditional single-furnace campaign model parameter learning method, which has long existed in the vicious cycle of "data island - model failure - detection lag", so as to solve the problem of low prediction accuracy of parameters in the converter process.

[0030] Figure 1 The flowchart of the converter steelmaking furnace campaign parameter prediction method provided by an embodiment of the present application is shown. The method can be executed by a system, which can be realized by software and / or hardware.

[0031] Figure 1 The converter steelmaking furnace campaign parameter prediction method is described in its entirety. As shown in Figure 1 In this embodiment, the converter steelmaking furnace campaign parameter prediction method includes steps S110-S150.

[0032] Step S110, obtaining target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database; wherein the target historical production data includes furnace campaigns and furnace campaign data corresponding to each furnace campaign; the furnace campaign data is the numerical value corresponding to each parameter of the corresponding furnace campaign.

[0033] Specifically, the preset database collects data generated in the historical production process of each steel grade, which includes historical furnace campaigns corresponding to different steel grade production and furnace campaign data corresponding to each furnace campaign. It includes but is not limited to oxygen lance parameters, bottom blowing parameters, converter smelting parameters (hot metal information, scrap steel information, smelting rhythm and tapping information, etc.). According to the steel grade to be produced and the required slag thickness, the corresponding target historical production data is selected from the preset database as the basic data for subsequent parameter prediction. Since the preset database collects a large amount of production data, the accuracy of subsequent calculation can be improved from the data width.

[0034] As an optional embodiment of the present application, obtaining target historical production data corresponding to the steel grade to be produced and the required slag thickness from the preset database includes:

[0035] Obtaining historical production data of the steel grade to be produced from the preset database; wherein the preset database stores historical production data of different steel grades; the historical production data includes historical slag thickness values of each furnace campaign;

[0036] According to a preset screening condition formula, the historical production data meeting the required slag thickness is selected from the historical production data of the steel grade to be produced as the initial selection historical production data; wherein,

[0037] The screening condition formula is:

[0038] S aim -ΔS≤S0≤S aim +ΔS; wherein,

[0039] S0 represents the historical slag thickness value of one heat in the initial selection historical production data, S aim represents the required slag thickness of the steel to be produced, and ΔS represents the slag thickness deviation value allowed for the steel to be produced.

[0040] The initial selection historical production data is sorted according to the production time of the heats from new to old, and the first preset number of heats and the heat data corresponding to the heats are selected as the target historical production data according to the sorting result.

[0041] Specifically, the historical production data refers to the data of heats that have been smelted, including but not limited to the temperature of molten iron, the composition of molten iron, scrap steel information, furnace condition information of the heat, smelting process audio information, etc. In an optional implementation, the historical production data can be preprocessed first, and the preprocessing includes but is not limited to data elimination and data normalization; wherein the data elimination includes eliminating the heats in which the historical production data has missing values; eliminating the heats containing abnormal zero values of variables; eliminating the heats containing abnormal discrete values that are too large or too small. Data elimination is used for abnormal value detection and elimination of historical production data, to ensure the consistency and reliability of the data and provide a high-quality data basis for subsequent steps. Data normalization is used to extract key features from the data after elimination, such as the frequency components of historical slag thickness value audio, image features of video, and frequency spectrum characteristics of vibration. When the sensor collects data, there may be extremely large or extremely small values, i.e. there may be values greater than the maximum value of the range and values less than the minimum value of the range. When these situations occur, normalization processing can unify the scale of the data, making the distribution of the data more consistent and the key features more obvious.

[0042] Then, according to the preset screening condition formula, the historical production data that meets the required slag thickness is selected from the historical production data of the steel to be produced as the initial selection historical production data. Exemplarily, in the screening condition formula, S aim of ordinary steel is taken as 0.4, S aim of low-phosphorus steel is taken as 0.5, ΔS is taken as 0.15 when the converter capacity is 120 t, and ΔS is taken as 0.18 when the converter capacity is 200 t.

[0043] Finally, the initial selection historical production data is sorted according to the production time of the heats from new to old, and the first preset number of heats and the heat data corresponding to the heats are selected as the target historical production data according to the sorting result. Exemplarily, the first preset number is 6, and the first 6 heats after sorting and the heat data corresponding to each heat are selected as the target historical production data.

[0044] As an optional embodiment of the present application, the method for obtaining the historical slag thickness value of each heat includes:

[0045] The audio data, video data and vibration data in the converter production process are collected by the audio slag sensor, flame analysis camera and oxygen lance vibration sensor pre-installed on the converter respectively;

[0046] The audio data, video data and vibration data are all subjected to data cleaning processing to eliminate data noise, so as to obtain cleaned audio data, cleaned video data and cleaned vibration data;

[0047] The audio historical slag thickness value is calculated according to the cleaned audio data, the video historical slag thickness value is calculated according to the cleaned video data, and the vibration historical slag thickness value is calculated according to the cleaned vibration data;

[0048] The calculation formula of the audio historical slag thickness value is:

[0049] Wherein,

[0050] I is the noise intensity collected in real time in the steelmaking process, I0 is the noise intensity when splashing, S Y is the audio historical slag thickness value, ΔH is the height of the oxygen lance relative to the liquid surface of the molten steel, R is the diameter of the converter mouth, L is the real-time oxygen flow rate of blowing, L0 is the initial set oxygen flow rate of blowing, Y is the real-time height of the smoke hood, and Y0 is the maximum height of the smoke hood opening;

[0051] The calculation formula of the video historical slag thickness value is:

[0052]

[0053] else S V =S Y ; wherein,

[0054] S V is the video historical slag thickness value, G is the number of video collected converter mouth flame slag, G0 is the critical number of video collected converter mouth flame slag, and Y0 indicates the critical thickness of the converter slag thickness;

[0055] The calculation formula of the vibration historical slag thickness value is:

[0056] Wherein,

[0057] S H is the vibration historical slag thickness value, G is the acceleration collected by the oxygen lance vibration sensor, a and b are constants, F is the oxygen pressure of the oxygen lance, L H is the height of the oxygen lance, and B H is the height correction term of the converter top;

[0058] According to the audio historical slag thickness value, the video historical slag thickness value and the vibration historical slag thickness value, a preset historical slag thickness calculation formula is used to calculate the historical slag thickness value of each heat;

[0059] The preset historical slag thickness calculation formula is:

[0060]

[0061] Wherein,

[0062] S0 is the historical slag thickness value of a heat, S v is the coupling slag thickness value corresponding to the heat, Q is the total oxygen supply amount; S H is the vibration historical slag thickness value corresponding to the heat, S V is the video historical slag thickness value corresponding to the heat, S Y is the audio historical slag thickness value corresponding to the heat, S AIM is the standard slag thickness value of the steel grade to be produced, γ Y1 , γ V1 and γ H1 are weight coefficients of the audio, video and vibration slag thickness values at low slag thickness, respectively, γ Y2 , γ V2 and γ H2 are weight coefficients of the audio, video and vibration slag thickness values at high slag thickness, respectively.

[0063] Specifically, the audio slag sensor, the flame analysis camera and the oxygen lance vibration sensor pre-installed on the converter can respectively collect audio data, video data and vibration data in the converter production process. In an optional embodiment, the converter body can be equipped with 24 high-precision sensing devices, including 8 audio slag sensors, which are uniformly distributed on the walls of the converter, for real-time monitoring of the audio data of the slag layer in the furnace, obtaining the real-time noise intensity of the steelmaking process; 4 flame analysis cameras are installed at the top of the converter and aligned with the furnace mouth to capture and analyze the shape, color and temperature of the flame, thereby collecting video data of the slag layer and obtaining the amount of slag at the furnace mouth; 3 oxygen lance vibration sensors are located at the root of the oxygen lance for monitoring the vibration of the oxygen lance during blowing, obtaining acceleration information and ensuring the stability and safety of blowing; 9 thickness sensors are distributed on the inner wall of the converter for real-time monitoring of the thickness change of the converter and collecting slag thickness data, while preventing safety production hazards caused by excessive thinning of the converter. The installation positions of these devices are carefully designed to ensure the accuracy and real-time nature of the data, providing comprehensive sensing capabilities for converter steelmaking to achieve comprehensive monitoring of different production stages and different production states; and optimizing the data collection effect, further improving the accuracy of data collection and the efficiency and quality of steelmaking.

[0064] In order to make the collected data more available, the audio data, the video data and the vibration data are cleaned respectively to eliminate data noise and obtain cleaned audio data, cleaned video data and cleaned vibration data. Then, the audio historical slag thickness value is calculated according to the cleaned audio data, the video historical slag thickness value is calculated according to the cleaned video data, and the vibration historical slag thickness value is calculated according to the cleaned vibration data. In the calculation formula of the audio historical slag thickness value, I0 is the noise intensity during splashing, which is a fixed value determined by the performance of each converter, and the audio equipment will collect the sound intensity during splashing on site before use, which is taken as I0, and I is the real-time collection value during smelting of each smelted steel. In the calculation formula of the video historical slag thickness value, exemplarily, G0 is 300, and Y0 is a constant, and the reference value is 600 mm. In the calculation formula of the vibration historical slag thickness value, exemplarily, a can be 3, b can be 5, and the furnace top height correction term can be 50 cm; the specific parameter values are obtained through experiments and summary of the converter system.

[0065] Then, according to the audio historical slag thickness value, the video historical slag thickness value and the vibration historical slag thickness value, the historical slag thickness value of each heat is calculated by using a preset historical slag thickness calculation formula. In the formula,

[0066] First, the formula is used to obtain the coupling slag thickness value of the audio historical slag thickness value, the video historical slag thickness value and the vibration historical slag thickness value, i.e. the coupling value of the audio historical slag thickness value, the video historical slag thickness value and the vibration historical slag thickness value obtained according to the above conditions, and then the historical slag thickness value of one heat is calculated. Exemplarily, in the above formula, γ Y1 , γ V1 and γ H1 may be 0.8, 0.05 and 0.15 respectively; γ Y2 , γ V2 and γ H2 may be 0.05, 0.8 and 0.15 respectively; when the converter capacity is 120 t, S AIM is 0.3 m.

[0067] In step S120, the model increment of each heat in the target historical production data is calculated according to the target historical production data and the parameter requirement value of the steel to be produced.

[0068] Specifically, in the process of calculating the mold increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced, the parameters preferably but not limited to used involve raw material parameters, including the type and tonnage of scrap steel, the amount of molten iron, the composition of molten iron; molten steel quality parameters, including oxygen content, final carbon content, final oxygen content, final temperature; efficiency parameters, including smelting period; equipment parameters, including the average thickness of the converter; process control parameters, including carbon oxygen product; by in-depth analysis of the historical heat data, the degree of compliance between the actual smelting result and the process requirement is evaluated, and the mold increment of each heat is obtained.

[0069] As an optional embodiment of the present application, the mold increment of each heat in the target historical production data is calculated according to the target historical production data and the parameter requirement value of the steel grade to be produced, including:

[0070] According to the target historical production data and the parameter requirement value of the steel grade to be produced, the mold increment of each heat in the target historical production data is calculated by using a preset mold increment calculation formula; wherein,

[0071] The preset mold increment calculation formula is:

[0072] Wherein,

[0073] M i M is the mold increment of the i-th heat in the target historical production data, the value of i is 1 to N, N is the total number of heats in the target historical production data, H0 is the average thickness of the converter of the historical heat of the steel grade to be produced, H i H is the thickness of the converter of the i-th heat in the target historical production data, T0 is the average smelting period of the historical heat of the steel grade to be produced, T i T is the smelting period of the i-th heat in the target historical production data, X COAim X is the required carbon oxygen product of the steel grade to be produced, X iCO X is the carbon oxygen product of the i-th heat in the target historical production data, F 0k F is the required tonnage of the k-th scrap steel of the steel grade to be produced, n is the total number of categories of scrap steel, F ki W is the tonnage of the k-th scrap steel of the i-th heat in the target historical production data, W 0liq W is the required amount of molten iron of the steel grade to be produced, W iliq Q is the amount of molten iron of the i-th heat in the target historical production data, Q 0T Q is the required oxygen content of the steel grade to be produced, Q iT x is the oxygen content of the i-th heat in the target historical production data, x 0I x is the required composition of molten iron of the steel grade to be produced, x Ii x is the composition of molten iron of the i-th heat in the target historical production data, x 0AC x is the final carbon content of the steel grade to be produced, xiA0 is the end carbon content of the i-th heat in the target historical production data, x 0A0 is the end oxygen content of the steel grade to be produced, x iA0 is the end oxygen content of the i-th heat in the target historical production data, T 0A is the end temperature of the steel grade to be produced, T iA is the end temperature of the i-th heat in the target historical production data, and a is an influence factor of the corresponding parameter, which is a constant value in the industry.

[0074] Specifically, the mold increment of each heat in the target historical production data can be calculated by using the above preset mold increment calculation formula, and the parameters used in the above calculation can be determined according to actual conditions, which is not particularly limited by the present application.

[0075] In step S130, the weight of each heat is calculated based on the mold increment of each heat.

[0076] Specifically, the weight of each heat is further calculated from the data depth direction based on the mold increment of each heat.

[0077] As an optional embodiment of the present application, the weight of each heat is calculated based on the mold increment of each heat, including:

[0078] According to the mold increment of each heat, the weight of each heat is calculated by using a preset weight calculation formula; wherein the preset weight calculation formula is:

[0079] wherein,

[0080] γ i is the weight of the i-th heat in the target historical production data, M i is the mold increment of the i-th heat in the target historical production data, and N is a preset number, representing the number of heats in the target historical production data. Exemplarily, N is 6.

[0081] In step S140, the standard heat parameter data of the steel grade to be produced is calculated according to the weight of each heat and the heat data corresponding to each heat; wherein the standard heat parameter data includes a heat and a standard parameter value corresponding to the heat.

[0082] Specifically, the standard heat parameter data of the to-be-produced steel grade is calculated according to the weight of each heat and the heat data corresponding to each heat. The modal information fusion of the audio data, the video data and the vibration data is performed, the mutual relationship and influence among the audio data, the video data and the vibration data are comprehensively considered in the process of calculating the standard heat parameter data, and the real-time production data and the historical data are fused and analyzed, so that the real-time performance and the adaptability of the generated standard heat parameter data are effectively improved. The new process requirements, the production conditions and the smelting technology progress and other factors are comprehensively considered, so that the representativeness and the advancement of the standard heat data are ensured.

[0083] As an optional embodiment of the present application, the standard heat parameter data of the to-be-produced steel grade is calculated according to the weight of each heat and the heat data corresponding to each heat, and includes:

[0084] The standard parameter value of each heat of the to-be-produced steel grade is calculated by using a preset standard heat parameter value calculation formula according to the weight of each heat and the heat data corresponding to each heat, so as to obtain the standard heat parameter data of the to-be-produced steel grade. The standard heat parameter value calculation formula is as follows:

[0085] Wherein,

[0086] W q is the value of the qth parameter in the standard heat parameter data, is the qth parameter of the i th heat in the target historical production data, γ i is the weight of the i th heat in the target historical production data.

[0087] In step S150, the parameter prediction value of the current heat of the to-be-produced steel grade is calculated according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade.

[0088] Specifically, the standard heat parameter data can be determined according to the parameter prediction required by the current heat, which is preferably but not limited to lime, magnesia agent, coolant, total oxygen supply amount and the like. Finally, the parameter prediction value of the current heat of the to-be-produced steel grade is calculated according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade. The heat data collected each time of steelmaking is added to the historical data of the corresponding steel grade, and the update of the historical data is completed.

[0089] As an optional embodiment of the present application, in the process of calculating the parameter prediction value of the current heat of the to-be-produced steel grade according to the standard heat parameter data and the preset requirement parameter data of each heat of the to-be-produced steel grade,

[0090] The parameter prediction value of the current heat of the to-be-produced steel grade includes: lime prediction value, magnesia agent prediction value, coolant prediction value, total oxygen supply amount prediction value, whole-process temperature prediction value and whole-process carbon prediction value.

[0091] The lime prediction value, the magnesia agent prediction value, the coolant prediction value and the total oxygen supply prediction value are calculated by using the static parameter prediction value calculation formula; the whole process temperature prediction value and the whole process carbon prediction value are calculated by using the dynamic parameter prediction value calculation formula; wherein,

[0092] The static parameter prediction value calculation formula is:

[0093] Wherein,

[0094] W q is the value of the qth item in the standard heat parameter data, W q is the parameter prediction value of the qth item of the current production heat; is the influence value of the ith parameter of the qth item, a i is the preset required parameter value of the ith parameter of the current production heat; a i_0 is the ith parameter value in the standard heat parameter data;

[0095] Specifically, wherein, W q represents the value of the qth item in the standard heat parameter data, wherein q can be lime, magnesia agent, coolant and total oxygen supply, etc. represents the influence value of the ith parameter of the qth item, such as the thickness of the converter, the smelting period, the end point temperature, the carbon oxygen product and the scrap steel, etc.

[0096] The dynamic parameter prediction value calculation formula includes the following formula:

[0097]

[0098] Wherein, Q o Dvn Tot is the dynamic calculation oxygen, C0 is a constant, the value is 0.0103, α is a constant, the value is 9.2, β is a constant, the value is 13.7, γ is a constant, the value is 12.5, [C] 铁水 is the starting assay carbon of the hot metal, the value is 4.8%, [C] Aim is the target carbon corresponding to the steel grade, the value is 0.08%, [C] M is the process carbon content, the reference value is 0.35%, W Tot is the metallurgical charge, the unit is t, the reference value is 150 t;

[0099]

[0100] Wherein, T 实时 is the real-time temperature of the current heat, T 铁水 is the hot metal temperature of the current heat, T 废钢 is the scrap steel influence temperature of the current heat, This represents the cumulative amount of lime added in the current batch over time. This represents the cumulative amount of magnesium additive added over time in the current furnace batch. Q represents the cumulative amount of coolant added over time in the current furnace cycle. * α represents the cumulative amount of oxygen supplied to the current furnace over time. coo_lim Let α be the coefficient of influence of lime on temperature. coo_mag α is the coefficient of influence of magnesium additive on temperature. coo_coo α is the coefficient of influence of coolant on temperature. coo_oxy′ γ is the coefficient representing the effect of oxygen on temperature over time, and γ is the temperature conversion coefficient, with units of °C·t / Nm. 3 The reference value is 12.5, Q o Dyn Tot To dynamically calculate oxygen levels, Here, represents the temperature compensation coefficient in °C, with a reference value of 25. ε is a constant with a value of 0.05. [C] M The carbon content is for the process; the reference value is 0.35%, [C]. Aim The target carbon content for the corresponding steel grade is 0.08%.

[0101]

[0102] Among them, [C] 实时 The carbon composition of the molten steel in the current heat is [C]. 铁水 The carbon composition of the molten iron in the current furnace is [C]. 废钢 This represents the carbon composition of the scrap steel in the current heat. This represents the cumulative amount of lime added in the current batch over time. This represents the cumulative amount of magnesium additive added over time in the current furnace batch. Q represents the cumulative amount of coolant added over time in the current furnace cycle. * α represents the cumulative amount of oxygen supplied to the current furnace over time. c_lim Let α be the coefficient of influence of lime on carbon. c_mag α is the coefficient of influence of magnesium on carbon. c_coo α is the coefficient of influence of coolant on carbon. c_oxy， The coefficient representing the effect of oxygen on carbon over time.

[0103] Specifically, the static calculation includes the calculation of the amounts of lime, magnesium oxide, and coolant, as well as the total oxygen supply. The specific calculation method is as follows:

[0104]

[0105] Among them, W 石灰 W represents the amount of lime required for the current batch, in kg. 石灰_0 This indicates the amount of lime used in the overall standard batch of historical data, expressed in kg; W 镁质剂Mg represents the magnesium-based agent dosage required for the current heat, kg; W 镁质剂_0 Mg represents the magnesium-based agent dosage used for the overall standard heat in the historical data, kg; W 冷却剂 Q represents the coolant dosage required for the current heat, kg; W 冷却剂_0 Q represents the coolant dosage used for the overall standard heat in the historical data, kg; Q 总供氧量 Q represents the oxygen supply required for the current heat, m 3 ; Q 总供氧量_0 Q represents the coolant dosage used for the overall standard heat in the historical data, m 3 ; a i_lim a represents the influence coefficient of the i-th standard heat corresponding parameter on lime; a i_mag a represents the influence coefficient of the i-th standard heat corresponding parameter on magnesium-based agent; a i_coo a represents the influence coefficient of the i-th standard heat corresponding parameter on coolant; a i_oxy a represents the influence coefficient of the i-th standard heat corresponding parameter on total oxygen. Dynamic calculation includes: whole-process temperature and carbon calculation.

[0106] In the calculation of the parameter prediction value of the current production heat, the dynamic changes of the real-time production conditions such as raw material composition, temperature, charging amount, etc. are fully considered, and the static and dynamic calculation results are adjusted in real time, so as to ensure that the static calculation result is highly consistent with the actual production condition, and to accurately output the parameter prediction for the converter steelmaking process.

[0107] Further, according to the prediction value of each parameter, accurate initial setting is provided for the converter steelmaking process, and then the steelmaking process of the current heat is started. The parameters involved include: raw material parameters, covering the types and tonnage of scrap steel, the amount and composition of molten iron; molten steel quality parameters, such as oxygen content, final carbon content, final oxygen content, final temperature; efficiency parameters, such as smelting period; equipment parameters, such as the average thickness of the converter; process control parameters, represented by carbon-oxygen product.

[0108] The present application deeply mines the historical data of the converter steelmaking, and the parameters used include raw material parameters, molten steel quality parameters, efficiency parameters, process control parameters and equipment parameters. Through multivariate collaborative analysis of each parameter, the internal relationship between the parameters is deeply analyzed, the model increment of each heat in the self-learning library is obtained, the weight of each heat is further determined, and the standard heat data of the steel grade to be produced is obtained. In combination with the process requirements of the current production heat, the new process requirements, production conditions and the progress of smelting technology and other factors are comprehensively considered, and finally the predicted value of each parameter in the current production heat is accurately derived, which significantly improves the parameter prediction accuracy. In addition, by applying multi-modal calculation, the mutual relationship and influence among audio, video and vibration data are comprehensively considered, and multiple process parameters of the converter are integrated into the self-learning process, the self-learning data is optimized, the learning quality is improved, the converter endpoint hit rate is effectively improved, the production cost caused by trial and error is reduced, the converter steelmaking cycle is shortened, and the standard heat data is ensured to be representative, advanced and applicable. In addition, the big data of the converter smelting is applied to the automatic steelmaking of the converter, and the original self-learning library is expanded by 10 6 times (usually 6 heats), which greatly improves the self-learning heat number, significantly improves the accuracy of the static calculation of the converter, effectively optimizes the operation of the converter, reduces the accident rate, and improves the production automation level.

[0109] As Figure 2 shown, the present application provides a converter steelmaking heat parameter prediction system 200, which can be installed in an electronic device. According to the realized function, the converter steelmaking heat parameter prediction system 200 can include a target data acquisition module 210, a model increment calculation module 220, a weight calculation module 230, a standard parameter calculation module 240 and a predicted value calculation module 250. The units of the present application can also be referred to as modules, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0110] In this embodiment, the functions of each module / unit are as follows:

[0111] The target data acquisition module 210 is used to acquire target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database; wherein the target historical production data includes heats and heat data corresponding to each heat; the heat data is the numerical value corresponding to each parameter of the corresponding heat;

[0112] The model increment calculation module 220 is used to calculate the model increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced;

[0113] The weight calculation module 230 is used to calculate the weight of each heat based on the model increment of each heat;

[0114] The standard parameter calculation module 240 is configured to calculate standard heat parameter data of the steel grade to be produced according to the weight of each heat and the heat data corresponding to each heat.

[0115] The prediction value calculation module 250 is configured to calculate the parameter prediction value of the current heat of the steel grade to be produced according to the standard heat parameter data and the preset requirement parameter data of each heat of the steel grade to be produced.

[0116] The converter steelmaking heat parameter prediction system 200 provided by the application obtains target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database, and is based on the same type of converter big data of the steel grade to be produced, thereby solving the vicious cycle problem of "data island - model failure - detection lag" existing in the learning mode of calculating parameters from a single heat in the prior art, and improving the converter parameter prediction accuracy from the data width direction; by calculating the module increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced, calculating the weight of each heat based on the module increment of each heat, and then calculating the standard heat parameter data of the steel grade to be produced according to the weight of each heat and the heat data corresponding to each heat, and finally calculating the parameter prediction value of the current heat of the steel grade to be produced according to the standard heat parameter data and the preset requirement parameter data of each heat of the steel grade to be produced, the parameter prediction value of the current heat of the converter is predicted by using the incremental algorithm, and the accuracy of the prediction learning calculation is improved from the data depth direction, which can guide the parameter demand of the heat to be produced by the converter. In summary, the application builds a multi-source data fusion architecture, and effectively breaks through the parameter learning bottleneck of the traditional single heat model based on incremental dynamic calculation and prediction, improves the cross-heat parameter reuse efficiency by 10 8 times, provides a systematic solution to the long-standing "data island - model failure - detection lag" vicious cycle in the industry, and has significant engineering application value.

[0117] As shown in Figure 3 , the application provides an electronic device 3 for a converter steelmaking heat parameter prediction method.

[0118] The electronic device 3 can include a processor 30, a memory 31 and a bus, and can also include a computer program stored in the memory 31 and executable on the processor 30, such as a converter steelmaking heat parameter prediction program 32. The memory 31 can also include an internal storage unit of the converter steelmaking heat parameter prediction system and an external storage device. The memory 31 can be used not only to store installed application software and various data, such as the code of the converter steelmaking heat parameter prediction program, but also to temporarily store data that has been output or will be output.

[0119] The memory 31 comprises at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 31 can be an internal storage unit of the electronic device 3, such as a mobile hard disk of the electronic device 3. In other embodiments, the memory 31 can also be an external storage device of the electronic device 3, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 31 can comprise both an internal storage unit and an external storage device of the electronic device 3. The memory 31 can be used to store application software and various data installed in the electronic device 3, such as a converter steelmaking heat parameter prediction method code, and can also be used to temporarily store data that has been output or will be output.

[0120] The processor 30 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more combinations of a central processing unit (CPU), a microprocessor, a digital processing chip, a graphics processor, and various control chips, etc. The processor 30 is the control unit of the electronic device, which connects various components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory 31 (such as a converter steelmaking heat parameter prediction program), and calls data stored in the memory 31, to perform various functions and process data of the electronic device 3.

[0121] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 31 and at least one processor 30, etc.

[0122] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3The illustrated structure does not constitute a limitation on the electronic device 3, and can include fewer or more components than illustrated, or combine certain components, or different component arrangements.

[0123] For example, although not shown, the electronic device 3 can also include a power source (such as a battery) to power the various components. Preferably, the power source can be logically connected to the at least one processor 30 through a power management system, so that the power management system can implement functions such as charge management, discharge management, and power consumption management. The power source can also include one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components. The electronic device 3 can also include various sensors, Bluetooth modules, Wi-Fi modules, and the like, which are not described here.

[0124] Further, the electronic device 3 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is typically used to establish a communication connection between the electronic device 3 and other electronic devices.

[0125] Optionally, the electronic device 3 can also include a user interface, which can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 3 and to display a visual user interface.

[0126] It should be understood that the embodiments are for illustration only and are not limited in scope by the structure.

[0127] The converter steelmaking heat parameter prediction program 32 stored in the memory 31 in the electronic device 3 is a combination of a plurality of instructions, which, when executed in the processor 30, can implement:

[0128] Step S110, obtaining target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database; wherein the target historical production data includes heats and heat data corresponding to each heat; the heat data is the numerical value corresponding to each parameter of the corresponding heat;

[0129] Step S120, calculating the mode increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced;

[0130] Step S130, based on the modulus increment of each heat, the weight of each heat is calculated;

[0131] Step S140, according to the weight of each heat and the heat data corresponding to each heat, the standard heat parameter data of the steel grade to be produced is calculated; wherein the standard heat parameter data includes heat and the standard parameter value corresponding to the heat;

[0132] Step S150, according to the standard heat parameter data and the preset requirement parameter data of each heat of the steel grade to be produced, the parameter prediction value of the current heat of the steel grade to be produced is calculated.

[0133] Specifically, the specific implementation method of the processor 30 to the above instructions can refer to Figure 1 The description of the related steps in the corresponding embodiment will not be repeated here.

[0134] Further, the modules / units integrated in the electronic device 3, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. The computer readable medium can include any entity or system, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0135] The embodiment of the application also provides a computer readable storage medium, which can be non-volatile or volatile, and stores a computer program, which is executed by a processor to realize:

[0136] Step S110, obtaining target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database; wherein the target historical production data includes heat and heat data corresponding to each heat; the heat data is the numerical value corresponding to each parameter of the corresponding heat;

[0137] Step S120, calculating the modulus increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced;

[0138] Step S130, based on the modulus increment of each heat, the weight of each heat is calculated;

[0139] Step S140, according to the weight of each heat and the heat data corresponding to each heat, the standard heat parameter data of the steel grade to be produced is calculated; wherein the standard heat parameter data includes heat and the standard parameter value corresponding to the heat;

[0140] Step S150, according to the standard heat parameters data and the preset requirement parameter data of each heat of the steel grade to be produced, calculating the parameter prediction value of the current heat of the steel grade to be produced.

[0141] Specifically, the computer program is executed by the processor to specifically implement the method, which can refer to the description of the related steps in the embodiment of the converter steelmaking heat parameter prediction method, and details are not described here.

[0142] In several embodiments provided by the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, for example, the division of the modules is only a logical function division, and another division mode can be used in actual implementation.

[0143] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0144] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional module.

[0145] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0146] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0147] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or systems stated in the system claims can also be implemented by one unit or system through software or hardware. The second word is used to indicate the name, and does not mean any specific order.

[0148] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application.

Claims

1. A method for predicting parameters of a converter steelmaking heat, characterized in that, The method comprises the following steps: obtaining target historical production data corresponding to the steel grade to be produced and the required slag thickness from a preset database; wherein the target historical production data comprises heats and heat data corresponding to each heat; and the heat data is numerical values corresponding to each parameter of the corresponding heat; calculating the model increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced; calculating the weight of each heat based on the model increment of each heat; calculating the standard heat parameter data of the steel grade to be produced according to the weight of each heat and the heat data corresponding to each heat; wherein the standard heat parameter data comprises a heat and a standard parameter value corresponding to the heat; calculating the parameter prediction value of the current heat of the steel grade to be produced according to the standard heat parameter data and the preset requirement parameter data of each heat of the steel grade to be produced.

2. The method of claim 1, wherein the method further comprises: The method comprises the following steps: obtaining historical production data of the steel grade to be produced from the preset database; wherein the preset database stores historical production data of different steel grades; and the historical production data comprises historical slag thickness values of each heat; selecting historical production data satisfying the required slag thickness from the historical production data of the steel grade to be produced as initial selection historical production data according to a preset screening condition formula; wherein, the screening condition formula is: S aim -ΔS≤S0≤S aim +ΔS; wherein, S0 represents the historical slag thickness value of one heat in the preliminary selection historical production data, S aim represents the required slag thickness of the steel grade to be produced, and ΔS represents the slag thickness deviation value allowed for the steel grade to be produced. sorting the initial selection historical production data according to the production time of each heat from new to old, and selecting the first preset number of heats and the heat data corresponding to the heats as target historical production data according to the sorting result.

3. The method of claim 2, wherein the method further comprises: The method for obtaining the historical slag thickness value of each heat comprises: collecting audio data, video data and vibration data in the production process of the converter through an audio slag sensor, a flame analysis camera and an oxygen lance vibration sensor pre-installed on the converter; performing data cleaning processing on the audio data, the video data and the vibration data to eliminate data noise, to obtain cleaned audio data, cleaned video data and cleaned vibration data; calculating an audio historical slag thickness value according to the cleaned audio data, a video historical slag thickness value according to the cleaned video data and a vibration historical slag thickness value according to the cleaned vibration data; wherein the calculation formula of the audio historical slag thickness value is: wherein, I is the noise intensity collected in real time in the steelmaking process, I0 is the noise intensity when spattering, S Y is the audio history slag thickness value, ΔH is the relative height of the oxygen lance to the liquid surface of the molten steel, R is the diameter of the converter mouth, L is the real-time oxygen flow rate of blowing, L0 is the initial set oxygen flow rate of blowing, Y is the real-time height of the smoke hood, Y0 is the maximum height of the smoke hood opening; the calculation formula of the video historical slag thickness value is: else S V = S Y ; wherein, S V Y is the thickness of the slag, G is the number of slag collected by the video, G0 is the critical number of slag collected by the video, and Y0 represents the critical thickness of the converter slag. the calculation formula of the vibration historical slag thickness value is: wherein, S H is the vibration history slag thickness value, G is the acceleration collected by the oxygen lance vibration sensor, a and b are constants, F is the oxygen lance oxygen pressure, L H is the oxygen lance height, B H is the furnace top height correction term; calculating the historical slag thickness value of each heat by using a preset historical slag thickness calculation formula according to the audio historical slag thickness value, the video historical slag thickness value and the vibration historical slag thickness value; wherein the preset historical slag thickness calculation formula is: wherein, S0 is a historical slag thickness value of a furnace campaign, S v is a coupled slag thickness value of a corresponding furnace campaign, Q is a total oxygen supply amount; S H is a vibration historical slag thickness value of a corresponding furnace campaign, S V is a video historical slag thickness value of a corresponding furnace campaign, S Y is an audio historical slag thickness value of a corresponding furnace campaign, S AIM is a standard slag thickness value of a steel grade to be produced, γ Y1 , γ V1 , and γ H1 are weight coefficients of the audio, video, and vibration slag thickness values at a low slag thickness, γ Y2 , γ V2 , and γ H2 are weight coefficients of the audio, video, and vibration slag thickness values at a high slag thickness.

4. The method of claim 1, wherein, calculating the model increment of each heat in the target historical production data according to the target historical production data and the parameter requirement value of the steel grade to be produced, comprises: calculating the model increment of each heat in the target historical production data by using a preset model increment calculation formula according to the target historical production data and the parameter requirement value of the steel grade to be produced; wherein, The preset mold increment calculation formula is: wherein, M i is the thickness of the converter in the i-th heat in the target historical production data, T0is the average smelting period of the historical heats of the steel grade to be produced, T i is the thickness of the converter in the i-th heat in the target historical production data, T0is the average smelting period of the historical heats of the steel grade to be produced, T i is the smelting period of the i-th heat in the target historical production data, X COAim is the required carbon-oxygen product of the steel grade to be produced, X iCO is the carbon-oxygen product of the i-th heat in the target historical production data, F 0k is the k-th scrap tonnage required by the steel grade to be produced, n is the total category of scrap, F ki is the k-th scrap tonnage of the i-th heat in the target historical production data, W 0liq is the required molten iron amount of the steel grade to be produced, W iliq is the molten iron amount of the i-th heat in the target historical production data, Q 0r is the required oxygen amount of the steel grade to be produced, Q iT is the oxygen amount of the i-th heat in the target historical production data, x 0I is the required molten iron composition of the steel grade to be produced, x Ii is the molten iron composition of the i-th heat in the target historical production data, x 0AC is the end-point carbon amount of the steel grade to be produced, x iA0 is the end-point carbon amount of the i-th heat in the target historical production data, x 0A0 is the end-point oxygen amount of the steel grade to be produced, x iA0 is the end-point oxygen amount of the i-th heat in the target historical production data, T 0A is the end-point temperature of the steel grade to be produced, T iA is the end-point temperature of the i-th heat in the target historical production data, and a is an influence factor of the corresponding parameter, which is an industry- defined value.

5. The method of claim 1, wherein, The weight of each heat is calculated based on the mold increment of each heat, and the weight calculation formula is: The weight of each heat is calculated based on the mold increment of each heat, and the weight calculation formula is: wherein, γ i is a weight of the i-th heat in the target historical production data, M i is a mold increment of the i-th heat in the target historical production data, N is a preset number, and indicates the number of heats in the target historical production data.

6. The method of claim 1, wherein, The weight of each heat is calculated based on the mold increment of each heat, and the weight calculation formula is: The standard heat parameter data of the steel grade to be produced is calculated according to the weight of each heat and the corresponding heat data of each heat, and the standard heat parameter value calculation formula is: wherein, W q is the value of the qth parameter in the standard heat parameter data, is the qth parameter of the ith heat in the target historical production data, γ i is the weight of the ith heat in the target historical production data.

7. The method of claim 1, wherein the method further comprises: The standard heat parameter data of the steel grade to be produced is calculated according to the weight of each heat and the corresponding heat data of each heat, and the standard heat parameter value calculation formula is: In the process of calculating the parameter prediction value of the current heat of the steel grade to be produced according to the standard heat parameter data and the preset requirement parameter data of each heat of the steel grade to be produced, The parameter prediction value of the current heat of the steel grade to be produced includes lime prediction value, magnesia agent prediction value, coolant prediction value, total oxygen supply prediction value, whole process temperature prediction value and whole process carbon prediction value; The calculation method of the lime prediction value, the magnesia agent prediction value, the coolant prediction value and the total oxygen supply prediction value is calculated by using the static parameter prediction value calculation formula; the whole process temperature prediction value and the whole process carbon prediction value are calculated by using the dynamic parameter prediction value calculation formula; wherein, wherein, W q is a value of the qth item in the standard heat parameter data, W q′ is a predicted value of the qth item parameter of the current production heat; is an influence value of the ith parameter of the qth item, a i is a preset required parameter value of the ith parameter of the current production heat; a i_0 is a value of the ith parameter in the standard heat parameter data; The static parameter prediction value calculation formula is: [C] M = 0.88 x ([C] 铁水 - [C] Aim ); wherein Q o Dvn Tot is the dynamic calculation of oxygen, C0is a constant with a value of 0.0103, a is a constant with a value of 9.2, β is a constant with a value of 13.7, γ is a constant with a value of 12.5, [C] 铁水 is the initial assay carbon of the hot metal with a value of 4.8%, [C] Aim is the target carbon for the corresponding steel grade with a value of 0.08%, [C] M is the process carbon content with a reference value of 0.35%, W Tot is the metallurgical charge; Wherein, T 实时 is the real-time temperature of the current heat, T 铁水 is the molten iron temperature of the current heat, T 废钢 is the scrap steel influence temperature of the current heat, is the cumulative amount of lime added over time for the current heat, is the cumulative amount of magnesia agent added over time for the current heat; is the cumulative amount of cooling agent added over time for the current heat, Q * is the cumulative amount of oxygen supply added over time for the current heat, α coo_lim is the temperature influence coefficient of lime, α coo_mag is the temperature influence coefficient of magnesia agent, α coo_coo is the temperature influence coefficient of cooling agent, α coo_oxy′ is the temperature influence coefficient of oxygen over time, γ is the temperature conversion coefficient, Q o Dvn Tot is the dynamic calculation of oxygen amount, is the temperature compensation coefficient, ε is a constant, the value is 0.05, [C] M is the process carbon content, [C] Aim is the target carbon of the corresponding steel grade, the value is 0.08%. wherein, [C] 实时 is the composition of carbon in the real-time molten steel of the current heat, [C] 铁水 is the composition of carbon in the molten iron of the current heat, [C] 废钢 is the composition of carbon in the scrap of the current heat, is the cumulative amount of lime added over time for the current heat, is the cumulative amount of magnesia agent added over time for the current heat; is the cumulative amount of coolant added over time for the current heat, Q * is the cumulative amount of oxygen supply added over time for the current heat, a c_lim is the influence coefficient of lime on carbon, a c_mag is the influence coefficient of magnesia agent on carbon, a c_coo is the influence coefficient of coolant on carbon, a c_oxy ′ is the influence coefficient of oxygen over time on carbon.

8. A converter steelmaking heat parameter prediction system, characterized in that, The dynamic parameter prediction value calculation formula includes the following formula: The system comprises: A target data acquisition module is configured to acquire target historical production data corresponding to a steel grade to be produced and a required slag thickness from a preset database; wherein, the target historical production data includes heats and corresponding heat data of each heat; and the heat data is a value corresponding to each parameter of the corresponding heat; A mold increment calculation module is configured to calculate mold increments of each heat in the target historical production data according to the target historical production data and parameter requirement values of the steel grade to be produced; A weight calculation module is configured to calculate weights of each heat based on the mold increments of each heat; A standard parameter calculation module is configured to calculate standard heat parameter data of the steel grade to be produced according to the weights of each heat and the corresponding heat data of each heat; wherein, the standard heat parameter data includes heats and standard parameter values corresponding to the heats; 9. An electronic device, comprising: A prediction value calculation module is configured to calculate parameter prediction values of a current heat of the steel grade to be produced according to the standard heat parameter data and preset requirement parameter data of each heat of the steel grade to be produced. The electronic device comprises: At least one processor; and A memory connected in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps in the converter steelmaking heat parameter prediction method of any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one instruction, wherein the at least one instruction causes a processor to perform operations comprising: The at least one instruction, when executed by a processor in the electronic device, implements the converter steelmaking heat parameter prediction method according to any one of claims 1 to 7.

Images