A method and device for predicting the molten bath temperature during the blowing process of converter steelmaking

Abstract

The present invention discloses a method and device for predicting the molten bath temperature during the blowing process of converter steelmaking. The method includes obtaining the regression coefficient of the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures and production process parameters through regression fitting; predicting the feeding parameters of the current heat and predicting the time parameters of the current heat based on the average converter charging time, average converter tilting time, average converter tapping time, average converter slagging time, and average converter slag splashing time; calculating the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag corresponding to the current heat in all heat expenditures based on the regression coefficient and the production process parameters of the current heat; and calculating the molten bath temperature of molten steel during the blowing process according to the heat balance based on the reaction rates of various elements in hot metal during the converter blowing process. The present invention improves the hit rate of the converter end point temperature and realizes the continuous prediction of the molten steel temperature of a converter under certain operating processes and raw material and auxiliary material conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of iron and steel metallurgy, and particularly relates to a method and device for predicting the temperature of a molten bath during the blowing process of converter steelmaking. Background Art

[0002] Converter steelmaking is one of the important links in the iron and steel production process. Its purpose is to smelt molten iron with a certain composition and temperature into molten steel whose end temperature and chemical composition meet the requirements of the steel grade by continuously blowing oxygen through an oxygen lance and adding auxiliary materials. During the blowing process of the converter, the temperature of the molten bath affects both the dephosphorization process and the splashing in the converter. If the temperature of the molten bath rises rapidly, it is necessary to appropriately add coolants to stabilize the temperature of the molten bath.

[0003] Iron and steel enterprises generally rely on the experience of on-site workers for control during converter production, often using "lagging" control and making adjustments after problems occur. Therefore, providing a method that can predict the temperature of the molten bath in real time during the blowing process can reflect the temperature status in the molten bath in real time, assist in controlling operations such as oxygen blowing and feeding, stabilize the temperature rise process of the converter, avoid problems such as splashing, improve product quality and output, and reduce production costs.

[0004] Existing converter steelmaking temperature prediction methods mainly focus on predicting the end temperature of the converter and rely more on static models based on reaction mechanisms, material balances, and thermodynamics. Such models require many assumptions and do not have the ability to adapt and adjust according to actual production conditions, resulting in limited prediction accuracy. Although artificial intelligence methods mainly based on neural networks have certain ease of implementation and relatively high prediction accuracy, due to the large fluctuations in raw materials and processes at the production sites of steelmaking enterprises, and the many and complex requirements for steel grades, they still need to be further improved in practical applications. Currently, in order to predict the temperature during the blowing process of the converter, metallurgical enterprises will use equipment such as flue gas analysis in combination with control models to calculate the temperature during the blowing process of the converter. The prediction accuracy is difficult to meet the needs of enterprises, and special equipment is required, which also has requirements for the factory space. Many small and medium-sized enterprises do not have the ability to transform. Summary of the Invention

[0005] The present invention provides a method and device for predicting the temperature of a molten bath during the blowing process of converter steelmaking to solve the technical problem that it is difficult to accurately predict the temperature during the blowing process in the prior art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides a method for predicting the temperature of a molten bath during the blowing process of converter steelmaking, including:

[0008] Statistically analyze the production process parameters in the actual production historical data and the proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the converter removing hot metal in all heat expenditures, and obtain the regression coefficient between the proportion and the production process parameters through regression fitting; wherein, the production process parameters include: steel type parameters corresponding to the end steel type, raw material parameters, feeding parameters, and time parameters;

[0009] Statistically analyze the average charging time of the converter, the average tilting time of the converter, the average tapping time of the converter, the average slagging time of the converter, and the average slag splashing time of the converter in the actual production historical data;

[0010] Predict the feeding parameters of the current heat to obtain the predicted feeding parameter values; and predict the time parameters of the current heat based on the statistically analyzed average charging time of the converter, the average tilting time of the converter, the average tapping time of the converter, the average slagging time of the converter, and the average slag splashing time of the converter to obtain the predicted time parameter values;

[0011] Based on the regression coefficient and the steel type parameters, raw material parameters, predicted feeding parameter values, and predicted time parameter values corresponding to the target steel type of the current heat, calculate the proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the converter removing hot metal in all heat expenditures corresponding to the current heat;

[0012] Based on the calculated proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the converter removing hot metal in all heat expenditures corresponding to the current heat and the reaction rates of various elements in the hot metal during the converter blowing process, calculate the molten steel temperature in the blowing process according to the heat balance to obtain the predicted molten pool temperature result.

[0013] Furthermore, the steel type parameters include: molten steel temperature, molten steel carbon content, molten steel manganese content, and molten steel phosphorus content;

[0014] The feeding parameters include: lime addition amount, dolomite addition amount, iron ore addition amount, and magnesium ball addition amount;

[0015] The raw material parameters include: scrap steel weight, hot metal weight, hot metal temperature, hot metal silicon content, hot metal manganese content, hot metal phosphorus content, and hot metal sulfur content;

[0016] The time parameters include: converter smelting time and converter oxygen blowing time.

[0017] Furthermore, predicting the feeding parameters of the current heat to obtain the predicted feeding parameter values includes:

[0018] Calculate the feeding parameters of the current heat according to the preset static model as the predicted feeding parameter values.

[0019] Furthermore, the expression of the regression coefficient is:

[0020] ε = a×W steel + b×W scrap + c1×t steel + c2×w Si,steel + c3×w Mn,steel + c4×w P,steel + c5

[0021] ×w S,steel + d1×τ yl + d2×τ cy + e1×t metal + e2×w C,metal + e3×w Mn,metal

[0022] + e4×w P,metal + f1×W sh + f2×W bys + f3×W tks + f4×W mq + g

[0023] Among them, ε is the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated from hot metal in all heat expenditures. a, b, c1, c2, c3, c4, c5, d1, d2, e1, e2, e3, e4, f1, f2, f3, f4 are regression fitting coefficients, W steel is the weight of hot metal, W scrap is the weight of scrap steel, t steel is the temperature of hot metal, w Si,steel 、w Mn,steel 、w P,steel 、w S,steel are the silicon content, manganese content, phosphorus content and sulfur content of hot metal respectively, τ yl is the converter smelting time, τ cy is the converter oxygen blowing time, t metal is the temperature of molten steel, w C,metal 、w Mn,metal 、w P,metal are the carbon content, manganese content and phosphorus content of molten steel respectively, W sh 、W bys 、W tks 、W mq are the weights of lime, dolomite, iron ore and magnesia balls respectively, and g is a constant.

[0024] Furthermore, the average converter charging time, average converter tapping time, average converter tapping time, average converter slagging time and average converter slag splashing time based on statistics are used to predict the time parameters of the current heat, and the predicted values of the time parameters are obtained, including:

[0025] The converter oxygen blowing time of the current batch is predicted by the following formula to obtain the predicted value of the converter oxygen blowing time:

[0026]

[0027] in, is the oxygen blowing amount of the current furnace calculated by the static model, Oxygen flow rate for oxygen lance;

[0028] The converter smelting time of the current heat is predicted by the following formula to obtain the predicted value of converter smelting time:

[0029] τ yyl =τ pzl +τ ycy +τ pdl +τ pcg +τ pdz +τ pjz

[0030] Among them, τ yyl is the predicted value of converter smelting time, τ pzl is the average converter charging time, τ ycy is the predicted value of converter oxygen blowing time, τ pdl is the average converter pouring time, τ pcg is the average converter tapping time, τ pdz is the average converter slag dumping time, τ pjz is the average converter slag splashing time.

[0031] Furthermore, based on the regression coefficient and the steel grade parameters, raw material parameters, charging parameter prediction values and time parameter prediction values corresponding to the target steel grade of the current heat, the proportion of the heat expenditure of the converter corresponding to the current heat, excluding the physical heat of molten steel generated by molten iron and the physical heat of slag, in all heat expenditures is calculated. The formula is: ε = a × W steel +b×W scrap +c1×t steel +c2×w Si,steel +c3×w Mn,steel +c4

[0032] ×w P,steel +c5×w S,steel +d1×τ yyl +d2×τ ycy +e1×t metal,m +e2

[0033] ×w C,metal,m +e3×w Mn,metal,m +e4×w P,metal,m +f1×W ysh

[0034] + f2 × W ybys + f3 × W ytks + f4 × W ymq + g

[0035] Among them, t metal,m is the molten steel temperature corresponding to the target steel grade, w C,metal,m , w Mn,metal,m , w P,metal,m are respectively the molten steel carbon content, molten steel manganese content and molten steel phosphorus content corresponding to the target steel grade, W ysh , W ybys , W ytks , W ymq are respectively the predicted values of the lime addition amount, dolomite addition amount, iron ore addition amount and magnesia ball addition amount, τ yyl is the predicted value of the converter smelting time, τ ycy is the predicted value of the converter oxygen blowing time.

[0036] Furthermore, based on the proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the converter for the current heat in all heat expenditures and the reaction rates of each element in the hot metal during the converter blowing process, the molten steel temperature in the blowing process is calculated according to the heat balance to obtain the predicted result of the molten pool temperature. The formula is:

[0037]

[0038] Among them, t metal，j is the molten pool temperature at the blowing time j. The blowing time is equally divided into multiple time periods, and the time of each time period is Δt, v C,i , v Si,i , v Mn,i , v P,i , v Fe,i are respectively the reaction rates of carbon, silicon, manganese, phosphorus and iron elements in the i-th time period, Q yc,j is the heat release amount of dust oxidation at the blowing time j, W Slag,j and W Metal,j are respectively the slag weight and the molten steel weight generated by the hot metal at the blowing time j, t m,j is the melting point of the molten steel at the blowing time j, C m , C s are respectively the specific heat capacities of the molten steel and the slag; ε is the proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the hot metal in all heat expenditures.

[0039] On the other hand, the present invention also provides a molten pool temperature prediction device for the converter steelmaking blowing process, including:

[0040] A regression fitting module, which is used to statistically analyze the production process parameters in the actual production historical data, as well as the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures, and obtain the regression coefficient between the proportion and the production process parameters through regression fitting; wherein, the production process parameters include steel grade parameters corresponding to the end steel grade, raw material parameters, feeding parameters and time parameters;

[0041] A time statistics module, which is used to statistically analyze the average converter charging time, average converter tilting time, average converter tapping time, average converter slag discharging time and average converter slag splashing time in the actual production historical data;

[0042] A current heat expenditure proportion calculation module, which is used to calculate the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures for the current heat expenditure, based on the regression coefficient calculated by the regression fitting module, the steel grade parameters corresponding to the target steel grade of the current heat expenditure, the raw material parameters, and the feeding parameter prediction value and time parameter prediction value calculated by the current heat expenditure proportion calculation module;

[0043] A current heat expenditure proportion calculation module, which is used to calculate the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures for the current heat expenditure, based on the regression coefficient calculated by the regression fitting module, the steel grade parameters corresponding to the target steel grade of the current heat expenditure, the raw material parameters, and the feeding parameter prediction value and time parameter prediction value calculated by the current heat expenditure proportion calculation module;

[0044] A molten bath temperature prediction module for blowing process, which is used to calculate the molten bath temperature of the molten steel during the blowing process and obtain the molten bath temperature prediction result according to the heat balance, based on the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures for the current heat expenditure calculated by the current heat expenditure proportion calculation module and the reaction rates of various elements in the hot metal during the converter blowing process.

[0045] On the other hand, the present invention further provides an electronic device, which includes a processor and a memory; wherein, at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the above method.

[0046] On another hand, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by the processor to implement the above method.

[0047] The beneficial effects brought by the technical solution provided by the present invention at least include:

[0048] The molten bath temperature prediction method during the converter steelmaking blowing process provided by the present invention obtains the regression coefficient between the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures and the production process parameters through regression fitting; predicts the charging parameters of the current heat, and based on the statistically averaged converter charging time, converter tilting time, converter tapping time, converter slagging time, and converter slag splashing time, predicts the time parameters of the current heat; calculates the proportion of heat expenditure other than the physical heat of molten steel and the physical heat of slag corresponding to the current heat in all heat expenditures based on the regression coefficient and the production process parameters of the current heat; calculates the molten bath temperature of molten steel during the blowing process according to the heat balance based on the reaction rates of various elements in hot metal during the converter blowing process. Thereby, the hit rate of the converter end-point temperature prediction is improved, and the continuous prediction of the molten steel temperature of the converter under the determined operation process and raw and auxiliary material conditions is realized. Furthermore, it is convenient to adjust the converter operation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0050] Figure 1 It is a flowchart of the molten bath temperature prediction method during the converter steelmaking blowing process provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will further describe the embodiments of the present invention in detail in conjunction with the drawings.

[0052] First Embodiment

[0053] This embodiment provides a molten bath temperature prediction method during the converter steelmaking blowing process, which can be implemented by an electronic device. The execution process of this method is as Figure 1 shown and includes the following steps:

[0054] S1. Statistically analyze the production process parameters in the actual production historical data and the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures in the converter, and through regression fitting, obtain the regression coefficient between the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures and the production process parameters.

[0055] It should be noted that in this embodiment, the production process parameters include: end steel grade parameters, raw material parameters, feeding parameters, and time parameters; among them, the end steel grade parameters include: tapping temperature of the smelted steel grade, molten steel carbon content, molten steel manganese content, and molten steel phosphorus content; the raw material parameters include: scrap steel weight, hot metal weight, hot metal temperature, hot metal silicon content, hot metal manganese content, hot metal phosphorus content, and hot metal sulfur content; the feeding parameters include: lime addition amount, dolomite addition amount, iron ore addition amount, and magnesium ball addition amount; the time parameters include: converter smelting time and converter oxygen blowing time.

[0056] Based on the above, the expression of the regression coefficient is:

[0057] ε = a×W steel + b×W scrap + c1×t steel + c2×w Si,steel + c3×w Mn,steel + c4×w P,steel + c5

[0058] ×w S,steel + d1×τ yl + d2×τ cy + e1×t metal + e2×w C,metal + e3×w Mn,metal

[0059] + e4×w P,metal + f1×W sh + f2×W bys + f3×W tks + f4×W mq + g

[0060] Among them, ε is the proportion of the heat expenditure other than the physical heat of the molten steel produced from hot metal and the physical heat of the slag in all heat expenditures, a, b, c1, c2, c3, c4, c5, d1, d2, e1, e2, e3, e4, f1, f2, f3, f4 are regression fitting coefficients, W steel is the hot metal weight, W scrap is the scrap steel weight, t steel is the hot metal temperature, w Si,steel 、w Mn,steel 、w P,steel 、w S,steel are the hot metal silicon content, hot metal manganese content, hot metal phosphorus content, and hot metal sulfur content respectively, τ yl is the converter smelting time, τ cy is the converter oxygen blowing time, t metal is the molten steel temperature, w C,metal 、w Mn,metal 、w P,metalare the carbon content, manganese content and phosphorus content of molten steel respectively, W sh 、W bys 、W tks 、W mq are the weights of lime, dolomite, iron ore and magnesium balls respectively, and g is a constant.

[0061] S2, collect actual production history data to obtain the average converter charging time, average converter pouring time, average converter tapping time, average converter slag pouring time and average converter slag splashing time.

[0062] S3, predict the charging parameters of the current heat to obtain the expected charging parameters; and based on the statistical average converter charging time, average converter pouring time, average converter tapping time, average converter slag pouring time and average converter slag splashing time, predict the time parameters of the current heat to obtain the expected time parameters.

[0063] It should be noted that, in this embodiment, the estimated charging parameters include the amount of lime added, the amount of dolomite added, the amount of iron ore added, and the amount of magnesium balls added for this batch calculated based on the static model.

[0064] The estimated time parameters include estimated converter smelting time and estimated oxygen blowing time.

[0065] The estimated time parameter can be calculated by the following formula:

[0066] τ yyl =τ pzl +τ ycy +τ pdl +τ pcg +τ pdz +τ pjz

[0067] Among them, τ yyl is the predicted value of converter smelting time, τ pzl is the average converter charging time, τ ycy is the predicted value of converter oxygen blowing time, τ pdl is the average converter pouring time, τ pcg is the average converter tapping time, τ pdz is the average converter slag dumping time, τ pjz is the average converter slag splashing time.

[0068]

[0069] in, is the oxygen blowing amount of the current furnace calculated by the static model, The oxygen flow rate for the oxygen lance.

[0070] S4. Calculate the proportion of the heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in the converter corresponding to the current heat in all heat expenditures based on the regression coefficients, the target steel grade parameters, raw material parameters, predicted charging parameters, and predicted time parameters of the current heat.

[0071] It should be noted that in this embodiment, the target steel grade parameters include the target steel grade temperature, the target carbon content of molten steel, the target manganese content of molten steel, and the target phosphorus content of molten steel.

[0072] The proportion of the heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in the converter corresponding to the current heat in all heat expenditures is calculated by the following formula:

[0073] ε = a×W steel +b×W scrap +c1×t steel +c2×w Si,steel +c3×w Mn,steel +c4

[0074] ×w P,steel +c5×w S,steel +d1×τ yyl +d2×τ ycy +e1×t metal,m +e2

[0075] ×w C,metal,m +e3×w Mn,metal,m +e4×w P,metal,m +f1×W ysh

[0076] +f2×W ybys +f3×W ytks +f4×W ymq +g

[0077] Wherein, t metal,m is the target molten steel temperature, w C,metal,m , w Mn,metal,m , w P,metal,m are respectively the carbon content of molten steel, the manganese content of molten steel, and the phosphorus content of molten steel corresponding to the target steel grade, W ysh , W ybys , W ytks , W ymq are respectively the predicted values of the lime addition amount, dolomite addition amount, iron ore addition amount, and magnesium ball addition amount calculated by the static model, τ yyl is the predicted value of the converter smelting time, τ ycy is the predicted value of the converter oxygen blowing time.

[0078] S5. Based on the proportion of the heat expenditure other than the physical heat of the molten steel and the physical heat of the slag generated by the converter removing hot metal in the current heat in all heat expenditures and the reaction rates of each element in the hot metal during the converter blowing process, calculate the molten steel temperature in the molten bath during the blowing process according to the heat balance to obtain the predicted result of the molten bath temperature.

[0079] It should be noted that in this embodiment, the molten steel temperature in the molten bath during the blowing process is calculated by the following formula:

[0080]

[0081] Among them, t metal，j is the molten bath temperature at the blowing time j. The blowing time is equally divided into several time periods, and the time of each time period is Δt. v C,i , v Si,i , v Mn,i , v P,i , v Fe,i are the reaction rates of carbon, silicon, manganese, phosphorus, and iron elements in the i-th time period respectively. Q yc,j is the heat release amount of soot oxidation at the blowing time j. W Slag,j and W Metal,j are the slag weight and the molten steel weight generated from hot metal at the blowing time j respectively. t m,j is the melting point of the molten steel at the blowing time j. C m , C s are the specific heat capacities of the molten steel and the slag respectively.

[0082] Next, taking the actual statistical data as an example to illustrate the implementation effect of the method in this embodiment; among them, the coefficients of the regression equation about ε statistically regressed according to historical data are listed in Table 1. The target parameter data of the steel grades are listed in Table 2. The raw material parameters and ε of each heat are listed in Table 3. Table 4 is the molten steel temperature predicted by implementing the method in this embodiment and the actual molten steel temperature at the end of the converter. It can be seen from Table 4 that the method provided in this embodiment can accurately and effectively predict the molten steel temperature at the end of the converter.

[0083] Table 1 Regression fitting coefficients of the regression equation about ε statistically regressed according to historical data

[0084] a 0.000308 b -0.000101 c1 0.000385 c2 0.073889 c3 0.019399 c4 0.058616 c5 -0.026129 d1 0.000033 d2 0.000325 e1 -0.000426 e2 -0.171953 e3 -0.031132 e4 0.0875582 f1 -0.000006185 f2 -0.000006182 f3 -0.00000002643 f4 -0.000005424 g 0.470496

[0085] Table 2 Target parameters of steel grades

[0086]

[0087]

[0088] Table 3 Raw material parameters and ε

[0089]

[0090] Table 4 Predicted molten steel temperature and actual molten steel temperature at the end of converter

[0091]

[0092]

[0093] In summary, for the molten bath temperature prediction method provided in this embodiment, the regression coefficient of the proportion of heat expenditure other than the physical heat of molten steel produced by hot metal and the physical heat of slag in all heat expenditures and the production process parameters is obtained through regression fitting; the feeding parameters of the current heat are predicted, and based on the statistically average converter charging time, average converter tilting time, average converter tapping time, average converter slag tapping time, and average converter slag splashing time, the time parameters of the current heat are predicted; based on the regression coefficient and the production process parameters of the current heat, the proportion of heat expenditure other than the physical heat of molten steel and the physical heat of slag corresponding to the current heat in all heat expenditures is calculated; based on the reaction rates of various elements in hot metal during the converter blowing process, the molten bath temperature of molten steel during the blowing process is calculated according to the heat balance. Thereby, the hit rate of predicting the end-point temperature of the converter is improved, and the continuous prediction of the molten steel temperature of the converter under the determined operating process and raw and auxiliary material conditions is realized. Furthermore, it is convenient to adjust the converter operating process.

[0094] Second Embodiment

[0095] This embodiment provides a molten bath temperature prediction device for converter steelmaking blowing process, and the device includes:

[0096] A regression fitting module, configured to statistically analyze the production process parameters in the actual production historical data and the proportion of heat expenditure other than the physical heat of molten steel produced by hot metal and the physical heat of slag in all heat expenditures, and obtain the regression coefficient of the proportion and the production process parameters through regression fitting; wherein, the production process parameters include steel type parameters, raw material parameters, feeding parameters, and time parameters corresponding to the end steel type;

[0097] A time statistics module, configured to statistically analyze the average converter charging time, average converter tilting time, average converter tapping time, average converter slag tapping time, and average converter slag splashing time in the actual production historical data;

[0098] A current heat parameter prediction module, configured to predict the feeding parameters of the current heat to obtain a predicted value of the feeding parameters; and based on the average converter charging time, average converter tilting time, average converter tapping time, average converter slag tapping time, and average converter slag splashing time statistically analyzed by the time statistics module, predict the time parameters of the current heat to obtain a predicted value of the time parameters;

[0099] The current heat expenditure ratio calculation module for the current heat treatment is used to calculate the ratio of the heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in the converter corresponding to the current heat treatment to all heat expenditures based on the regression coefficients calculated by the regression fitting module, the steel type parameters corresponding to the target steel type of the current heat treatment, the raw material parameters, and the predicted values of the charging parameters and the predicted values of the time parameters calculated by the current heat treatment parameter prediction module;

[0100] The molten bath temperature prediction module for the blowing process is used to calculate the molten bath temperature of the molten steel during the blowing process and obtain the prediction result of the molten bath temperature based on the ratio of the heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in the converter corresponding to the current heat treatment calculated by the current heat treatment heat expenditure ratio calculation module and the reaction rates of various elements in the hot metal during the converter blowing process according to the heat balance.

[0101] The method for predicting the molten bath temperature during the converter steelmaking blowing process in this embodiment corresponds to the device for predicting the molten bath temperature during the converter steelmaking blowing process in the above first embodiment; among them, the functions implemented by the functional modules in the method for predicting the molten bath temperature during the converter steelmaking blowing process in this embodiment correspond one by one to the process steps in the device for predicting the molten bath temperature during the converter steelmaking blowing process in the above first embodiment; therefore, it will not be elaborated here.

[0102] The third embodiment

[0103] This embodiment provides an electronic device, which includes a processor and a memory; among them, at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the method of the first embodiment.

[0104] This electronic device may have relatively large differences due to configuration or performance, and may include one or more processors (central processing units, CPUs) and one or more memories. Among them, at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the above method.

[0105] The fourth embodiment

[0106] This embodiment provides a computer-readable storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by the processor to implement the method of the above first embodiment. Among them, this computer-readable storage medium may be a ROM, a random access memory, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc. The instructions stored therein can be loaded and executed by the processor in the terminal to implement the above method.

[0107] In addition, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, the embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0108] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows 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 the processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks Figure 1 or multiple flows and / or blocks Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in

[0110] It should also be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

[0111] Finally, it should be noted that the above is the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those skilled in the art of this technology, once the basic creative concept of the present invention is known, without departing from the principle described in the present invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A method for predicting the molten bath temperature during the blowing process of converter steelmaking, characterized in that, Including: Statistically analyze the production process parameters in the actual production historical data, as well as the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures, and obtain the regression coefficient between the proportion and the production process parameters through regression fitting; wherein, the production process parameters include: steel grade parameters corresponding to the end steel grade, raw material parameters, feeding parameters, and time parameters; Statistically analyze the average converter charging time, average converter tapping time, average converter pouring time, average converter slagging time, and average converter slag splashing time in the actual production historical data; Predict the feeding parameters of the current heat to obtain the predicted feeding parameter values; and predict the time parameters of the current heat based on the statistically analyzed average converter charging time, average converter tapping time, average converter pouring time, average converter slagging time, and average converter slag splashing time to obtain the predicted time parameter values; including: calculating the feeding parameters of the current heat according to a preset static model as the predicted feeding parameter values; predicting the converter oxygen blowing time of the current heat through the following formula to obtain the predicted converter oxygen blowing time value: Among them, is the oxygen blowing amount of the current heat calculated by the static model, is the oxygen blowing flow rate of the lance. Predict the converter smelting time of the current heat through the following formula to obtain the predicted converter smelting time value: τ yyl = τ pzl + τ ycy + τ pdl + τ pcg + τ pdz + τ pjz Among them, τ yyl is the predicted value of the converter smelting time, τ pzl is the average converter charging time, τ ycy is the predicted value of the converter oxygen blowing time, τ pdl is the average converter tapping time, τ pcg is the average converter steel tapping time, τ pdz is the average converter slag dumping time, τ pjz is the average converter slag splashing time; Based on the regression coefficient and the steel grade parameters, raw material parameters, predicted feeding parameter values, and predicted time parameter values corresponding to the target steel grade of the current heat, calculate the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures corresponding to the current heat; Based on the calculated proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures corresponding to the current heat and the reaction rates of various elements in the hot metal during the converter blowing process, calculate the molten steel temperature in the molten bath according to the heat balance to obtain the predicted molten bath temperature result, and the formula is: where t metal，j is the bath temperature at the blowing time of j. The blowing time is equally divided into multiple time periods, and the time of each time period is Δt. v C,i , v Si,i , v Mn,i , v P,i , v Fe,i are the reaction rates of carbon, silicon, manganese, phosphorus, and iron elements in the i-th time period respectively. Q yc,j is the heat release amount of fume oxidation at the blowing time of j. W Slag,j and W Metal,j are the slag weight and the molten steel weight produced from hot metal at the blowing time of j respectively. t m,j is the melting point of molten steel at the blowing time of j. C m , C s are the specific heat capacities of molten steel and slag respectively; ε is the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures.

2. The method for predicting the molten bath temperature in the converter steelmaking blowing process according to claim 1, wherein The steel grade parameters include: molten steel temperature, molten steel carbon content, molten steel manganese content, and molten steel phosphorus content; The feeding parameters include: lime addition amount, dolomite addition amount, iron ore addition amount, and magnesium ball addition amount; The raw material parameters include: hot metal temperature, scrap steel weight, hot metal weight, hot metal silicon content, hot metal manganese content, hot metal phosphorus content, and hot metal sulfur content; The time parameters include: converter smelting time and converter oxygen blowing time.

3. The molten bath temperature prediction method for the converter steelmaking blowing process according to claim 2, characterized in that The expression of the regression coefficient is: ε = a×W steel + b×W scrap + c1×t steel + c2×w Si,steel + c3×w Mn,steel + c4×w P,steel + c5 ×w S,steel +d1×τ yl +d2×τ cy +e1×t metal +e2×w C,metal +e3×w Mn,metal +e4×w P,metal +f1×W sh +f2×W bys +f3×W tks +f4×W mq +g Among them, ε is the proportion of the heat expenditure other than the physical heat of the molten steel produced from the hot metal and the physical heat of the slag in all heat expenditures, and a, b, c1, c2, c3, c4, c5, d1, d2, e1, e2, e3, e4, f1, f2, f3, f4 are regression fitting coefficients, W steel is the weight of the hot metal, W scrap is the weight of the scrap steel, t steel is the temperature of the hot metal, w Si,steel 、w Mn,steel 、w P,steel 、w S,steel are the silicon content, manganese content, phosphorus content and sulfur content of the hot metal respectively, τ yl is the converter smelting time, τ cy is the converter oxygen blowing time, t metal is the temperature of the molten steel, w C,metal 、w Mn,metal 、w P,metal are the carbon content, manganese content and phosphorus content of the molten steel respectively, W sh 、W bys 、W tks 、W mq are the weights of lime, dolomite, iron ore and magnesium balls respectively, and g is a constant.

4. The method for predicting the molten bath temperature in the converter steelmaking blowing process according to claim 3, characterized in that, Based on the regression coefficient and the steel grade parameters, raw material parameters, predicted feeding parameter values, and predicted time parameter values corresponding to the target steel grade of the current heat, calculate the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures corresponding to the current heat, and the formula is: ε = a×W steel + b×W scrap + c1×t steel + c2×w Si,steel + c3×w Mn,steel + c4 ×w P,steel +c5×w S,steel +d1×τ yyl +d2×τ ycy +e1×t metal,m +e2×w C,metal,m +e3×w Mn,metal,m +e4×w P,metal,m +f1×W ysh +f2×W ybys +f3×W ytks +f4×W ymq +g Among them, t metal,m is the molten steel temperature corresponding to the target steel grade, w C,metal,m , w Mn,metal,m , w P,metal,m are respectively the carbon content, manganese content and phosphorus content of the molten steel corresponding to the target steel grade, W ysh , W ybys , W ytks , W ymq are respectively the predicted values of the lime addition amount, dolomite addition amount, iron ore addition amount and magnesium ball addition amount, τ yyl is the predicted value of the converter smelting time, τ ycy is the predicted value of the converter oxygen blowing time.

5. A molten bath temperature prediction device for the converter steelmaking blowing process, characterized in that, Including: A regression fitting module, which is used to statistically analyze the production process parameters in the actual production historical data, as well as the proportion of the heat expenditure other than the physical heat of molten steel and the physical heat of slag generated by the converter removing hot metal in all heat expenditures, and obtain the regression coefficient between the proportion and the production process parameters through regression fitting; wherein, the production process parameters include the steel grade parameters, raw material parameters, feeding parameters, and time parameters corresponding to the end steel grade; A time statistics module, which is used to count the average converter charging time, average converter tapping time, average converter steel tapping time, average converter slag pouring time and average converter slag splashing time in the actual production historical data; A current heat treatment parameter prediction module, which is used to predict the charging parameters of the current heat treatment, and obtain the predicted values of the charging parameters; and based on the counted average converter charging time, average converter tapping time, average converter steel tapping time, average converter slag pouring time and average converter slag splashing time, predict the time parameters of the current heat treatment, and obtain the predicted values of the time parameters; including: calculating the charging parameters of the current heat treatment according to a preset static model as the predicted values of the charging parameters; predicting the converter oxygen blowing time of the current heat treatment through the following formula to obtain the predicted value of the converter oxygen blowing time: Among them, is the oxygen blowing amount of the current heat calculated by the static model, is the oxygen blowing flow rate of the lance; Predicting the converter smelting time of the current heat treatment through the following formula to obtain the predicted value of the converter smelting time: τ yyl = τ pzl + τ ycy + τ pdl + τ pcg + τ pdz + τ pjz Among them, τ yyl is the predicted value of the converter smelting time, τ pzl is the average converter charging time, τ ycy is the predicted value of the converter oxygen blowing time, τ pdl is the average converter tapping time, τ pcg is the average converter steelmaking time, τ pdz is the average converter slag pouring time, τ pjz is the average converter slag splashing time; A current heat treatment heat expenditure ratio calculation module, which is used to calculate the proportion of the heat expenditure other than the physical heat of the molten steel produced by the converter removing molten iron and the physical heat of the slag in all heat expenditures based on the regression coefficient, the steel grade parameters, raw material parameters, predicted values of the charging parameters and predicted values of the time parameters corresponding to the target steel grade of the current heat treatment; A molten bath temperature prediction module during the blowing process, which is used to calculate the molten bath steel temperature during the blowing process according to the heat balance based on the proportion of the heat expenditure other than the physical heat of the molten steel produced by the converter removing molten iron and the physical heat of the slag in all heat expenditures corresponding to the current heat treatment and the reaction rates of various elements in the molten iron during the converter blowing process, and obtain the predicted result of the molten bath temperature; the formula is: Among them, t metal，j is the bath temperature at the blowing time of j. The blowing time is equally divided into multiple time periods, and the time of each time period is Δt. v C,i , v Si,i , v Mn,i , v P,i , v Fe,i are the reaction rates of carbon, silicon, manganese, phosphorus, and iron elements in the i-th time period respectively. Q yc,j is the heat release of fume oxidation at the blowing time of j. W Slag,j and W Metal,j are the weight of slag and the weight of molten steel produced from hot metal at the blowing time of j respectively. t m,j is the melting point of molten steel at the blowing time of j. C m , C s are the specific heat capacities of molten steel and slag respectively; ε is the proportion of heat expenditure other than the physical heat of molten steel produced from hot metal and the physical heat of slag in all heat expenditures.

Images