Controlled cooling method and device for fine-grained steel, electronic device, storage medium

Abstract

The application provides a controlled cooling method and device of fine-grained steel, electronic equipment and storage medium, and belongs to the technical field of automatic control. The method comprises the following steps: obtaining a plurality of target controlled cooling parameters of the fine-grained steel; the plurality of target controlled cooling parameters comprise a target final rolling temperature, a target pre-cooling speed, a target pre-cooling end temperature, a target main cooling speed, a target main cooling end temperature, a target slow cooling temperature and a target slow cooling time; and cooling control of the fine-grained steel is performed based on the plurality of target controlled cooling parameters. The controlled cooling method and device of fine-grained steel, electronic equipment and storage medium provided by the application can improve the product quality and production efficiency of the fine-grained steel.

Description

Technical Field

[0001] This application belongs to the field of controlled cooling technology for fine-grained steel, and more specifically, relates to a controlled cooling method and apparatus, electronic equipment, and storage medium for fine-grained steel. Background Technology

[0002] Fine-grained steel (such as S355JR steel) is a type of low-alloy high-strength steel that improves its overall mechanical properties by refining the grain size. Its ferrite-pearlite grain size is typically controlled at 5~15μm, much smaller than that of ordinary steel (20~50μm). Due to its good strength, toughness and weldability, fine-grained steel is widely used in construction, bridges and engineering machinery.

[0003] Rapid cooling after hot rolling of fine-grained steel can shorten the high-temperature residence time, increase the phase transformation undercooling, improve the ferrite nucleation rate, and refine the final microstructure. However, existing fine-grained steels still use the same cooling control parameters as ordinary carbon steel or low-alloy high-strength steel, resulting in insufficient austenite grain refinement and difficulty in achieving stable performance to design standards. Summary of the Invention

[0004] The purpose of this application is to provide a controlled cooling method, apparatus, electronic device, and storage medium for fine-grained steel that can improve the quality of fine-grained steel products. To achieve the above objective, the technical solutions provided by this application are as follows: Firstly, a method for controlled cooling of fine-grained steel is provided, comprising: Multiple target controlled cooling parameters for fine-grained steel are obtained; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling end temperature, target main cooling rate, target main cooling end temperature, target slow cooling temperature, and target slow cooling time; Cooling control of fine-grained steel is performed based on the aforementioned multiple target cooling parameters; The determination methods for the plurality of target cooling parameters include: Acquire multiple sets of historical data, each set of historical data including historical data of multiple controlled cooling parameters, historical data of multiple performance parameters of the corresponding fine-grained steel, and the parameter range corresponding to each of the multiple controlled cooling parameters; For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on the historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value corresponding to each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. An objective function is constructed based on the fitted values ​​corresponding to each of the multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as the plurality of objective cooling parameters.

[0005] Secondly, a controlled cooling device for fine-grained steel is provided, comprising: The data acquisition module is used to acquire multiple target controlled cooling parameters for fine-grained steel; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling endpoint temperature, target main cooling rate, target main cooling endpoint temperature, target slow cooling temperature, and target slow cooling time; A cooling control module is used to control the cooling of fine-grained steel based on the multiple target cooling parameters; The determination methods for the plurality of target cooling parameters include: Acquire multiple sets of historical data, each set of historical data including historical data of multiple controlled cooling parameters, historical data of multiple performance parameters of the corresponding fine-grained steel, and the parameter range corresponding to each of the multiple controlled cooling parameters; For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on the historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value corresponding to each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. An objective function is constructed based on the fitted values ​​corresponding to each of the multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as the plurality of objective cooling parameters.

[0006] Thirdly, embodiments of this application also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the controlled cooling method for fine-grained steel provided in any possible implementation of the first aspect.

[0007] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the controlled cooling method for fine-grained steel provided in any possible implementation of the first aspect.

[0008] The beneficial effects of the technical solution provided in this application are as follows: Compared with related technologies, the controlled cooling method, apparatus, electronic equipment, and storage medium for fine-grained steel provided in this application embodiment fit the mapping relationship between performance parameters and controlled cooling parameters based on multiple sets of historical data. On this basis, an objective function is constructed based on multiple performance parameters, and the combination of controlled cooling parameters is optimized through iteration to achieve coordinated control of each stage of pre-cooling, main cooling, and slow cooling, thereby achieving precise matching between controlled cooling parameters and the microstructure and performance requirements of fine-grained steel.

[0009] This application's embodiments, through data-driven parameter optimization logic, overcome the limitations of traditional controlled cooling processes that rely on empirical formulas and general parameter frameworks. This enables the synergistic goals of grain refinement, performance stability, and energy consumption reduction, thereby improving the quality and production efficiency of fine-grained steel products. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0011] Figure 1 A schematic flowchart illustrating the controlled cooling method for fine-grained steel provided in this application embodiment; Figure 2 A structural block diagram of the controlled cooling device for fine-grained steel provided in the embodiments of this application; Figure 3 A schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0013] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.” When describing multiple (two or more) items, if the relationship between the multiple items is not explicitly defined, the multiple items can refer to one, several or all of the multiple items. For example, the description of "parameter A includes A1, A2, A3" can be implemented as parameter A includes A1 or A2 or A3, or it can be implemented as parameter A includes at least two of the three items A1, A2 and A3.

[0014] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0015] This application provides a controlled cooling method for fine-grained steel, which can be executed by electronic equipment, such as... Figure 1 As shown, the method may include: S101: Obtain multiple target controlled cooling parameters for fine-grained steel; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling endpoint temperature, target main cooling rate, target main cooling endpoint temperature, target slow cooling temperature, and target slow cooling time.

[0016] The methods for determining multiple target cooling parameters include: Acquire multiple sets of historical data. Each set of historical data includes historical data for multiple controlled cooling parameters, historical data for multiple performance parameters of the corresponding fine-grained steel, and parameter ranges for each of the multiple controlled cooling parameters. For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value of each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. The objective function is constructed based on the fitted values ​​of multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as multiple objective cooling parameters.

[0017] In this embodiment, a three-stage controlled cooling method consisting of a pre-cooling section, a main cooling section, and a slow cooling section can be used to cool fine-grained steel. The pre-cooling section begins after final rolling, where a laminar flow cooling system is activated to cool the fine-grained steel slab to the target pre-cooling endpoint temperature at a target pre-cooling rate, inhibiting austenite grain growth. In the main cooling section, the slab is rapidly cooled to the target main cooling endpoint temperature at a target main cooling rate. In the slow cooling section, the fine-grained steel slab is moved into a heat-holding slow cooling device and held at the target slow cooling temperature for the target slow cooling time to promote uniform carbide precipitation and reduce internal stress.

[0018] Among them, the target final rolling temperature, target precooling rate, target precooling endpoint temperature, target main cooling rate, target main cooling endpoint temperature, target slow cooling temperature, and target slow cooling time, etc., can be obtained based on historical data analysis. The specific steps are as follows: (1) Historical data collection: Taking S355JR steel as an example, 2000 sets of rolling-cooling data for S355JR steel over the past three years can be collected, including controlled cooling parameters and corresponding product performance parameters. Controlled cooling parameters include the final rolling temperature. (820-860℃), precooling rate v1, precooling endpoint temperature T1, main cooling rate v2, main cooling endpoint temperature T2, slow cooling temperature And cooling time t, performance parameters including grain size d, yield strength fluctuation Impact energy at -20℃ Akv, energy consumption E, and plate shape qualification rate R.

[0019] Each cooling control parameter and product performance parameter has a corresponding parameter range, for example: , ,and , , , , .

[0020] (2) Data fitting: In this embodiment, for each performance parameter, the performance parameter can be used as the dependent variable, and the corresponding cooling control parameters can be used as independent variables. A second-order multiple regression model (specifically a second-order response surface model) is used to fit the mapping relationship between the performance parameter and the cooling control parameters. The specific formula is as follows:

[0021] in: y represents a single performance parameter (such as grain size d, yield strength fluctuation). wait); Indicates cooling control parameters, , , , , , , ; a0 is a constant term, a i b is the coefficient of the linear term. i The coefficients are quadratic terms (obtained by fitting 2000 sets of historical data).

[0022] (3) Parameter optimization: (3-1) The median value of the refrigeration control parameter range can be taken first. (e.g., v1=10℃ / s, T1=775℃, etc.) are used as initial parameter combinations; (3-2) Substitute the initial parameters into the mapping model corresponding to each performance parameter, and calculate d, Given E, Akv, and R, calculate the initial value of the objective function F; (3-3) Fine-tune the parameters in small steps (e.g., adjust v2 from 27℃ / s to 28℃ / s), recalculate the F value, and retain the cooling parameter combination with smaller F.

[0023] Repeat steps (3-3) above until all combinations of cooling parameters are traversed. Select the combination of cooling parameters with the smallest corresponding objective function value as multiple target cooling parameters. For example, multiple target cooling parameters could be: [ , , , , , , [840℃, 10℃ / s, 775℃, 28℃ / s, 530℃, 500℃, 20s]. Other methods can also be used to determine the combination of cooling parameters, as detailed in the following examples.

[0024] In step (3-2), the calculation process of the objective function includes: ①Performance parameter normalization (eliminating dimensional differences and mapping all indicators to the [0,1] interval): Normalized value of grain size (d) : (12μm is the theoretical minimum grain size, and 25μm is the maximum size using traditional processes.) Smaller is better); Yield strength fluctuation ( normalized value : (5MPa is the theoretical minimum fluctuation, and 15MPa is the fluctuation value of the traditional process.) Smaller is better); Normalized value of energy consumption per unit (E) : (70kWh / t is the theoretical minimum energy consumption, and 85kWh / t is the energy consumption of traditional processes.) Smaller is better); Normalized value of impact energy (AkV) at -20℃ : (45J is the theoretical maximum impact energy, and 34J is the standard lower limit). Normalized value of plate shape pass rate (R) : (99% is the theoretical maximum pass rate, and 90% is the pass rate of traditional processes). ② Weight allocation: The performance indicators are weighted according to the core process requirements (grain refinement > performance stability > energy consumption reduction > impact energy improvement > plate shape qualification), ensuring that the total weight is 1. The specific weight allocation is as follows: , , , , .

[0025] ③ Multi-target conversion to single-target: In this embodiment, an objective function can be constructed based on multiple performance parameters, taking into account grain size (d), yield strength fluctuation ( The optimization objective for performance parameters such as energy consumption per unit (E) is to minimize their values, that is, the smaller the value of such performance parameters, the better; the optimization objective for parameters such as -20℃ impact energy (Akv) and plate shape qualification rate (R) is to maximize their values, that is, the larger the value of such performance parameters, the better.

[0026] To construct a unified objective function F, this embodiment first considers the grain size (d), yield strength fluctuation (d), and other parameters. Performance parameters such as energy consumption per unit (E) are classified into two categories: -20℃ impact energy (AkV) and plate shape qualification rate (R). Then, an equivalent evaluation value is determined for each category II performance parameter based on its normalized value. The equivalent evaluation value of each category II performance parameter is negatively correlated with its normalized value. The objective function is obtained by weighted summing of the normalized values ​​of all category I performance parameters and the equivalent evaluation values ​​of all category II performance parameters.

[0027] Through the above process, a unified "minimization objective function F" is constructed, and the calculation formula is as follows: ; Constraints: , , , , , , ,and , , , , .

[0028] S102: Cooling control of fine-grained steel based on multiple target cooling parameters.

[0029] In this embodiment, based on obtaining multiple target cooling parameters, a three-stage cooling method can be adopted, and the cooling of fine-grained steel can be controlled according to the multiple target cooling parameters. Specifically, the cooling can be based on the target precooling rate. The initial number of nozzles to be opened is determined by the correspondence between the number of nozzles and the number of nozzles: 3 sets of nozzles correspond to a low precooling rate of 8-9℃ / s, 5 sets of nozzles correspond to a high precooling rate of 11-12℃ / s, and 4 sets of nozzles correspond to a medium rate of 9-11℃ / s. The initial number of nozzles to be opened is determined based on this correspondence.

[0030] Simultaneously, during the precooling process, the cooling rate of the slab is monitored using an infrared thermometer (1Hz sampling). If the actual rate is lower than the target... If the actual rate is higher than the target, gradually increase the number of nozzles (up to a maximum of 5 sets); To ensure the slab is accurately cooled to T1 (770-780℃), reduce the number of nozzles (to a minimum of 3 sets).

[0031] As can be seen from the above, this embodiment fits the mapping relationship between performance parameters and controlled cooling parameters based on multiple sets of historical data. On this basis, an objective function is constructed based on multiple performance parameters, and the combination of controlled cooling parameters is optimized to achieve coordinated control of each stage of pre-cooling, main cooling and slow cooling, thereby achieving precise matching between controlled cooling parameters and the performance requirements of fine-grained steel.

[0032] This embodiment, through data-driven parameter optimization logic, overcomes the limitations of traditional controlled cooling processes that rely on empirical formulas and general parameter frameworks. It can achieve the synergistic goals of grain refinement, performance stability, and energy consumption reduction, thereby improving the quality and production efficiency of fine-grained steel products.

[0033] In one embodiment of this application, within the parameter range of each cooling control parameter, different combinations of multiple cooling control parameters are traversed to obtain multiple cooling control parameter combinations, including: For each cooling control parameter, calculate the correlation strength between that cooling control parameter and multiple performance parameters; Cooling parameters with a correlation strength greater than or equal to a preset strength threshold are designated as first-class cooling parameters, and cooling parameters with a correlation strength less than a preset strength threshold are designated as second-class cooling parameters. For each type of cooling control parameter, the parameter range of the type of cooling control parameter is divided based on the preset first interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​of the type of cooling control parameter. For each type of second-class cooling control parameter, the parameter range of the second-class cooling control parameter is divided based on a preset second interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​for the second-class cooling control parameter. The second interval length is greater than the first interval length. By iterating through multiple parameter values ​​of each first-class cooling parameter and different combinations of multiple parameter values ​​of each second-class cooling parameter, multiple cooling parameter combinations are obtained.

[0034] In this embodiment, for each cooling control parameter, the correlation strength between it and multiple performance parameters can be calculated, quantifying the influence weight of the cooling control parameter on the performance parameters. The higher the correlation strength, the greater the influence of the cooling control parameter on the performance parameters. Accordingly, cooling control parameters can be divided into first-class cooling control parameters (key parameters with a significant impact on performance parameters) and second-class cooling control parameters (minor parameters with a smaller impact on performance parameters) based on the correlation strength. Specifically, a strength threshold (e.g., the average correlation strength corresponding to each cooling control parameter) can be preset. Cooling control parameters with a correlation strength greater than or equal to the strength threshold are classified as first-class cooling control parameters, and cooling control parameters with a correlation strength less than the strength threshold are classified as second-class cooling control parameters.

[0035] Based on this, for the first type of cooling control parameters, a smaller first interval length (e.g., 5%) can be used to divide the parameter interval. One parameter value is randomly selected from each sub-interval as multiple parameter values ​​for this type of cooling control parameter. This achieves fine-grained division of the parameter interval for the first type of cooling control parameters, avoiding missing the optimal solution due to excessively large step sizes. For the second type of cooling control parameters, a larger second interval length (e.g., 10%) can be used to divide the parameter interval. One parameter value is randomly selected from each sub-interval as multiple parameter values ​​for this type of cooling control parameter. This achieves coarse-grained division of the parameter interval for the second type of cooling control parameters. Since this type of cooling control parameter has a smaller impact on performance parameters, coarse-grained interval division will not significantly affect the value of the objective function and can greatly reduce the number of samples. Finally, all combinations of multiple parameter values ​​for the first type of cooling control parameters and multiple parameter values ​​for the second type of cooling control parameters are traversed to obtain multiple cooling control parameter combinations for subsequent objective function optimization.

[0036] As can be seen from the above, this embodiment classifies multiple cooling parameters based on the correlation strength between each cooling control parameter and performance parameter. Fine-grained division of the parameter range of the first type of cooling control parameters with a large correlation strength can avoid missing the optimal solution due to excessive step size. Coarse-grained division of the parameter range of the second type of cooling control parameters with a small correlation strength can reduce the amount of calculation and thus improve the optimization speed.

[0037] In one embodiment of this application, the step of calculating the correlation strength between each cooling control parameter and multiple performance parameters includes: For each performance parameter, calculate the partial derivative of that performance parameter with respect to each cooling control parameter, and use it as the influence coefficient of each cooling control parameter on that performance parameter; For each cooling control parameter, the correlation strength between the cooling control parameter and multiple performance parameters is calculated based on the influence coefficient of the cooling control parameter on each performance parameter.

[0038] In this embodiment, for each performance parameter, the partial derivative of that performance parameter with respect to each cooling control parameter can be calculated, which serves as the influence coefficient of each cooling control parameter on that performance parameter. The partial derivative of the i-th performance parameter with respect to the j-th cooling control parameter... This represents the j-th cooling parameter when all other cooling parameters are kept constant. A change of 1 unit will affect the i-th performance parameter. The absolute amount of change. For example, d is the grain size (in μm). The main cooling rate is v2 (unit: °C / s). This means that for every 1℃ / s increase in v2, the grain size d decreases by 0.05μm.

[0039] Furthermore, considering the different dimensions of cooling control parameters and performance parameters, it is impossible to directly compare the influence coefficients of different parameters using partial derivatives. To solve this problem, this embodiment converts the absolute changes of cooling control parameters and performance parameters into relative rates of change to obtain the influence coefficients. The following calculation formula:

[0040] The above formula represents the j-th cooling control parameter. When a relative change of 1% occurs, the i-th performance parameter The percentage of relative change that occurred.

[0041] Based on this, for each cooling control parameter By considering its impact on all performance parameters, the correlation strength between this cooling control parameter and multiple performance parameters can be obtained. For example, it can be calculated using the following formula. The strength of the correlation with multiple performance parameters:

[0042] in, Indicates the strength of the association. This represents the weighting coefficients corresponding to each performance parameter, for example... , , , , .

[0043] As can be seen from the above, this embodiment uses the partial derivatives of the performance parameters with respect to the cooling control parameters as influence coefficients, which can directly characterize the degree of influence of each cooling control parameter on the performance parameters. Based on this, for each cooling control parameter, the influence coefficients of its influence on all performance parameters are integrated to obtain the correlation strength, which can comprehensively evaluate the importance of the cooling control parameter to the performance parameters.

[0044] In one embodiment of this application, the controlled cooling method for fine-grained steel further includes: For each set of historical data, determine the sub-interval where the historical data of each cooling control parameter in the set of historical data is located, and concatenate the endpoints of the sub-interval where the historical data of each cooling control parameter is located to obtain the first sub-interval vector corresponding to the set of historical data. Specifically, for each combination of cooling control parameters, a fitted value for each performance parameter is calculated based on that combination of cooling control parameters and the mapping relationship corresponding to each performance parameter, including: Determine the sub-interval where each parameter value in the cooling control parameter combination is located, and concatenate the endpoints of the sub-intervals where each parameter value is located to obtain the second sub-interval vector corresponding to the cooling control parameter combination; If there exists a first sub-interval vector that is equal to the second sub-interval vector, then the historical data of each performance parameter in the historical data corresponding to the first sub-interval vector is taken as the fitted value corresponding to each performance parameter. Otherwise, the fitted value for each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter.

[0045] In this embodiment, for each set of historical data, the sub-interval to which the historical value of each controlled cooling parameter belongs can be determined sequentially in the order of final rolling temperature -> precooling speed -> precooling end temperature -> main cooling speed -> main cooling end temperature -> slow cooling temperature -> slow cooling time. By concatenating the upper and lower endpoints of all the sub-intervals to which the controlled cooling parameters belong in sequence, the first sub-interval vector corresponding to the set of historical data can be obtained.

[0046] For example, the historical data for multiple cooling control parameters in a certain set of historical data are as follows: The final rolling temperature is 832℃, and the corresponding sub-interval is [832, 833). The precooling rate is 8.3℃ / s, corresponding to the sub-interval [8.2, 8.4). The pre-cooling endpoint temperature is 772℃, and the corresponding sub-interval is [772, 773). The main cooling rate is 25℃ / s, and the corresponding sub-interval is [25, 25.25). The main cold endpoint temperature is 523℃, and the corresponding sub-interval is [522, 524); The slow cooling temperature is 486℃, and the corresponding sub-interval is [484, 488). The slow cooling time is 16s, and the corresponding sub-interval is [16, 17); By concatenating the upper and lower endpoints of the above sub-intervals in sequence, the first sub-interval vector is obtained as [832, 833, 8.2, 8.4, 772, 773, 25, 25.25, 522, 524, 484, 488, 16, 17].

[0047] Based on this, for each cooling parameter combination, when calculating the fitted value of each performance parameter based on the cooling parameter combination and the mapping relationship corresponding to each performance parameter, the same processing method as for historical data can be used first to determine the sub-interval where each parameter value in the cooling parameter combination is located. The endpoints of the sub-intervals where each parameter value is located are concatenated to obtain the second sub-interval vector corresponding to the cooling parameter combination. If a first sub-interval vector that is completely equal to the second sub-interval vector exists in the historical data, the historical performance parameter data (such as grain size, yield strength, and impact energy) corresponding to the first sub-interval vector is directly retrieved as the fitted value of the performance parameter for the current parameter combination, thereby reducing the amount of calculation; if a first sub-interval vector that is completely equal to the second sub-interval vector does not exist in the historical data, the fitted value of each performance parameter is calculated based on the cooling parameter combination and the mapping relationship corresponding to each performance parameter.

[0048] As can be seen from the above, this embodiment reduces the amount of computation by prioritizing the use of performance parameter values ​​in historical data through the comparison of sub-intervals. At the same time, historical data is a real record of actual production, and the performance parameter values ​​in it are closer to the actual production situation, which is conducive to improving the accuracy of subsequent objective function optimization.

[0049] In one embodiment of this application, cooling control of fine-grained steel is performed based on multiple target cooling parameters, including: To obtain the actual final rolling temperature of fine-grained steel; Calculate the temperature difference between the actual final rolling temperature and the target final rolling temperature; If the temperature difference is greater than the first temperature difference threshold, the target pre-cooling temperature is increased by the preset first step length to obtain multiple target cooling control parameters after adjustment. If the temperature difference is less than the second temperature difference threshold, the target main cooling speed is reduced by a preset second step size, and the target slow cooling temperature is increased by a preset third step size, to obtain multiple adjusted target cooling control parameters; wherein, the second temperature threshold is less than the first temperature threshold. Cooling control of fine-grained steel is based on multiple adjusted target cooling parameters.

[0050] In this embodiment, the actual final rolling temperature was found from 2000 sets of historical rolling-cooling data of S355JR steel. Fluctuations occur because of the microscopic segregation of alloying elements such as Mn and Si in S355JR steel. Different billets or different parts of the same billet exhibit variations in thermal conductivity and phase transformation characteristics. During heating, the inconsistent heating rates in the segregated regions lead to uneven billet exit temperatures, resulting in fluctuations in the final rolling temperature.

[0051] when At this time, v1 can be increased (e.g., by 2℃ / s) to prevent the slab from remaining in the higher temperature range for too long, which could lead to abnormal austenite grain growth; when At that time, v2 can be reduced (e.g., reduced by 3℃ / s) and increased. (For example, increase the temperature by 20°C) to avoid the slab from cooling too much and causing brittle phase precipitation.

[0052] As can be seen from the above, this embodiment takes into account the deviation between the actual final rolling temperature and the target final rolling temperature, and adjusts the key parameters of the pre-cooling, main cooling and slow cooling stages in a targeted manner to offset the influence of the fluctuation of the final rolling temperature. This can ensure that a uniform and fine grain structure is obtained in the end, and reduce the batch fluctuation of performance indicators.

[0053] Based on the same principle as the controlled cooling method for fine-grained steel provided in the embodiments of this application, the embodiments of this application also provide a controlled cooling device for fine-grained steel, such as... Figure 2 As shown, the cooling control device 20 for the fine-grained steel may specifically include a data acquisition module 21 and a cooling control module 22.

[0054] The data acquisition module 21 is used to acquire multiple target controlled cooling parameters for fine-grained steel; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling endpoint temperature, target main cooling rate, target main cooling endpoint temperature, target slow cooling temperature, and target slow cooling time; Cooling control module 22 is used for cooling control of fine-grained steel based on multiple target cooling parameters; The methods for determining multiple target cooling parameters include: Acquire multiple sets of historical data. Each set of historical data includes historical data for multiple controlled cooling parameters, historical data for multiple performance parameters of the corresponding fine-grained steel, and parameter ranges for each of the multiple controlled cooling parameters. For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value of each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. The objective function is constructed based on the fitted values ​​of multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as multiple objective cooling parameters.

[0055] In one embodiment of this application, the multiple performance parameters include a first type of performance parameters and a second type of performance parameters. The optimization objective of the first type of performance parameters is to minimize their values, and the optimization objective of the second type of performance parameters is to maximize their values. The data acquisition module 21 is specifically used for: The fitted values ​​corresponding to each of the multiple performance parameters are normalized to obtain the normalized values ​​corresponding to each of the multiple performance parameters. The equivalent evaluation value of each type II performance parameter is determined based on the normalized value of each type II performance parameter; the equivalent evaluation value of each type II performance parameter is negatively correlated with the normalized value of each type II performance parameter. The objective function is obtained by weighted summing of the normalized values ​​of each first-type performance parameter and the equivalent evaluation values ​​of each second-type performance parameter.

[0056] In one embodiment of this application, the data acquisition module 21 is specifically used for: For each cooling control parameter, calculate the correlation strength between that cooling control parameter and multiple performance parameters; Cooling parameters with a correlation strength greater than or equal to a preset strength threshold are designated as first-class cooling parameters, and cooling parameters with a correlation strength less than a preset strength threshold are designated as second-class cooling parameters. For each type of cooling control parameter, the parameter range of the type of cooling control parameter is divided based on the preset first interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​of the type of cooling control parameter. For each type of second-class cooling control parameter, the parameter range of the second-class cooling control parameter is divided based on a preset second interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​for the second-class cooling control parameter. The second interval length is greater than the first interval length. By iterating through multiple parameter values ​​of each first-class cooling parameter and different combinations of multiple parameter values ​​of each second-class cooling parameter, multiple cooling parameter combinations are obtained.

[0057] In one embodiment of this application, the data acquisition module 21 is further configured to: For each performance parameter, calculate the partial derivative of that performance parameter with respect to each cooling control parameter, and use it as the influence coefficient of each cooling control parameter on that performance parameter; For each cooling control parameter, the correlation strength between the cooling control parameter and multiple performance parameters is calculated based on the influence coefficient of the cooling control parameter on each performance parameter.

[0058] In one embodiment of this application, the data acquisition module 21 is further configured to: For each set of historical data, determine the sub-interval where the historical data of each cooling control parameter in the set of historical data is located, and concatenate the endpoints of the sub-interval where the historical data of each cooling control parameter is located to obtain the first sub-interval vector corresponding to the set of historical data. Specifically, for each combination of cooling control parameters, a fitted value for each performance parameter is calculated based on that combination of cooling control parameters and the mapping relationship corresponding to each performance parameter, including: Determine the sub-interval where each parameter value in the cooling control parameter combination is located, and concatenate the endpoints of the sub-intervals where each parameter value is located to obtain the second sub-interval vector corresponding to the cooling control parameter combination; If there exists a first sub-interval vector that is equal to the second sub-interval vector, then the historical data of each performance parameter in the historical data corresponding to the first sub-interval vector is taken as the fitted value corresponding to each performance parameter. Otherwise, the fitted value for each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter.

[0059] In one embodiment of this application, the data acquisition module 21 is specifically used for: Using this performance parameter as the dependent variable and the corresponding cooling control parameters as independent variables, a second-order multiple regression model is used to fit the mapping relationship between the performance parameter and each cooling control parameter.

[0060] In one embodiment of this application, the cooling control module 22 is specifically used for: To obtain the actual final rolling temperature of fine-grained steel; Calculate the temperature difference between the actual final rolling temperature and the target final rolling temperature; If the temperature difference is greater than the first temperature difference threshold, the target pre-cooling temperature is increased by the preset first step length to obtain multiple target cooling control parameters after adjustment. If the temperature difference is less than the second temperature difference threshold, the target main cooling speed is reduced by a preset second step size, and the target slow cooling temperature is increased by a preset third step size, to obtain multiple adjusted target cooling control parameters; wherein, the second temperature threshold is less than the first temperature threshold. Cooling control of fine-grained steel is based on multiple adjusted target cooling parameters.

[0061] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0062] Figure 3 A schematic diagram of the structure of an electronic device to which this application embodiment applies is shown, such as... Figure 3 As shown, the electronic device can be used to implement the methods provided in any embodiment of this application.

[0063] like Figure 3As shown, the electronic device 300 may primarily include at least one processor 301. Figure 3 The diagram shows components such as a memory 302, a communication module 303, and an input / output interface 304. Optionally, these components can be connected and communicate with each other via a bus 305. It should be noted that... Figure 3 The structure of the electronic device 300 shown is merely illustrative and does not constitute a limitation on the electronic devices to which the methods provided in the embodiments of this application are applicable.

[0064] The memory 302 can be used to store operating systems and applications, etc. The applications can include computer programs that implement the methods shown in the embodiments of this application when invoked by the processor 301, and can also include programs for implementing other functions or services. The memory 302 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and computer programs, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0065] Processor 301 is connected to memory 302 via bus 305 and implements corresponding functions by calling the application programs stored in memory 302. Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0066] Electronic device 300 can connect to a network via communication module 303 (which may include, but is not limited to, components such as a network interface) to communicate with other devices (such as user terminals or servers) through the network and achieve data interaction, such as sending data to or receiving data from other devices. Communication module 303 may include wired network interfaces and / or wireless network interfaces, meaning the communication module may include at least one of wired or wireless communication modules.

[0067] The electronic device 300 can connect to necessary input / output devices, such as a keyboard and display device, via the input / output interface 304. The electronic device 300 itself may have a display device, and other display devices can also be connected externally via the interface 304. Optionally, a storage device, such as a hard drive, can also be connected via the interface 304 to store data from the electronic device 300, retrieve data from the storage device, or store data from the storage device in the memory 302. It is understood that the input / output interface 304 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to the input / output interface 304 can be a component of the electronic device 300 or an external device connected to the electronic device 300 when needed.

[0068] The bus 305 used to connect the components may include a path for transmitting information between the components. The bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Depending on its function, the bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0069] Optionally, for the solution provided in the embodiments of this application, the memory 302 can be used to store a computer program that executes the solution of this application, and the processor 301 runs the computer program. When the processor 301 runs the computer program, it implements the operation of the method or apparatus provided in the embodiments of this application.

[0070] Based on the same principle as the method provided in the embodiments of this application, the embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0071] This application also provides a computer program product, which includes a computer program that, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0072] It should be noted that the terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0073] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0074] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0075] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application without departing from the technical concept of this application also fall within the protection scope of the embodiments of this application.

Claims

1. A method for controlled cooling of fine-grained steel, characterized in that, include: Multiple target controlled cooling parameters for fine-grained steel are obtained; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling end temperature, target main cooling rate, target main cooling end temperature, target slow cooling temperature, and target slow cooling time; Cooling control of fine-grained steel is performed based on the aforementioned multiple target cooling parameters; The determination methods for the plurality of target cooling parameters include: Acquire multiple sets of historical data, each set of historical data including historical data of multiple controlled cooling parameters, historical data of multiple performance parameters of the corresponding fine-grained steel, and the parameter range corresponding to each of the multiple controlled cooling parameters; For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on the historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value corresponding to each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. An objective function is constructed based on the fitted values ​​corresponding to each of the multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as the plurality of objective cooling parameters.

2. The controlled cooling method for fine-grained steel as described in claim 1, characterized in that, The plurality of performance parameters include a first type of performance parameters and a second type of performance parameters. The optimization objective of the first type of performance parameters is to minimize their values, and the optimization objective of the second type of performance parameters is to maximize their values. The construction of the objective function based on the fitted values ​​corresponding to each of the multiple performance parameters includes: The fitted values ​​corresponding to each of the multiple performance parameters are normalized to obtain the normalized values ​​corresponding to each of the multiple performance parameters. The equivalent evaluation value of each type II performance parameter is determined based on the normalized value of each type II performance parameter; the equivalent evaluation value of each type II performance parameter is negatively correlated with the normalized value of each type II performance parameter. The objective function is obtained by weighted summing of the normalized values ​​of each first-type performance parameter and the equivalent evaluation values ​​of each second-type performance parameter.

3. The controlled cooling method for fine-grained steel as described in claim 1, characterized in that, Within the parameter range of each cooling control parameter, multiple combinations of cooling control parameters are traversed to obtain multiple cooling control parameter combinations, including: For each cooling control parameter, calculate the correlation strength between that cooling control parameter and multiple performance parameters; Cooling parameters with a correlation strength greater than or equal to a preset strength threshold are designated as first-class cooling parameters, and cooling parameters with a correlation strength less than a preset strength threshold are designated as second-class cooling parameters. For each type of cooling control parameter, the parameter range of the type of cooling control parameter is divided based on the preset first interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​of the type of cooling control parameter. For each type of cooling control parameter, the parameter range of the type of cooling control parameter is divided based on a preset second interval length. A parameter value is randomly selected in each sub-interval to obtain multiple parameter values ​​for the type of cooling control parameter. The second interval length is greater than the first interval length. By iterating through multiple parameter values ​​of each first-class cooling parameter and different combinations of multiple parameter values ​​of each second-class cooling parameter, multiple cooling parameter combinations are obtained.

4. The controlled cooling method for fine-grained steel as described in claim 3, characterized in that, The calculation steps for the correlation strength between each cooling control parameter and multiple performance parameters include: For each performance parameter, calculate the partial derivative of that performance parameter with respect to each cooling control parameter, and use it as the influence coefficient of each cooling control parameter on that performance parameter; For each cooling control parameter, the correlation strength between the cooling control parameter and multiple performance parameters is calculated based on the influence coefficient of the cooling control parameter on each performance parameter.

5. The controlled cooling method for fine-grained steel as described in claim 3, characterized in that, Also includes: For each set of historical data, determine the sub-interval where the historical data of each cooling control parameter in the set of historical data is located, and concatenate the endpoints of the sub-interval where the historical data of each cooling control parameter is located to obtain the first sub-interval vector corresponding to the set of historical data. Specifically, for each combination of cooling control parameters, based on that combination of cooling control parameters and the mapping relationship corresponding to each performance parameter, the fitted value corresponding to each performance parameter is calculated, including: Determine the sub-interval where each parameter value in the cooling control parameter combination is located, and concatenate the endpoints of the sub-intervals where each parameter value is located to obtain the second sub-interval vector corresponding to the cooling control parameter combination; If there exists a first sub-interval vector that is equal to the second sub-interval vector, then the historical data of each performance parameter in the historical data corresponding to the first sub-interval vector is used as the fitted value corresponding to each performance parameter. Otherwise, the fitted value for each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter.

6. The controlled cooling method for fine-grained steel as described in claim 1, characterized in that, For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on the historical data, including: Using this performance parameter as the dependent variable and the corresponding cooling control parameters as independent variables, a second-order multiple regression model is used to fit the mapping relationship between the performance parameter and each cooling control parameter.

7. The controlled cooling method for fine-grained steel as described in claim 1, characterized in that, The cooling control of fine-grained steel based on the multiple target cooling parameters includes: To obtain the actual final rolling temperature of fine-grained steel; Calculate the temperature difference between the actual final rolling temperature and the target final rolling temperature; If the temperature difference is greater than the first temperature difference threshold, the target precooling temperature is increased by a preset first step length to obtain multiple adjusted target cooling control parameters. If the temperature difference is less than the second temperature difference threshold, the target main cooling speed is reduced by a preset second step size, and the target slow cooling temperature is increased by a preset third step size, to obtain multiple adjusted target cooling control parameters; wherein, the second temperature threshold is less than the first temperature threshold. Cooling control of fine-grained steel is performed based on the adjusted target cooling parameters.

8. A controlled cooling device for fine-grained steel, characterized in that, include: The data acquisition module is used to acquire multiple target controlled cooling parameters for fine-grained steel; the multiple target controlled cooling parameters include target final rolling temperature, target precooling rate, target precooling endpoint temperature, target main cooling rate, target main cooling endpoint temperature, target slow cooling temperature, and target slow cooling time; A cooling control module is used to control the cooling of fine-grained steel based on the multiple target cooling parameters; The determination methods for the plurality of target cooling parameters include: Acquire multiple sets of historical data, each set of historical data including historical data of multiple controlled cooling parameters, historical data of multiple performance parameters of the corresponding fine-grained steel, and the parameter range corresponding to each of the multiple controlled cooling parameters; For each performance parameter, a mapping relationship between the performance parameter and each cooling control parameter is fitted based on the historical data; Within the parameter range of each cooling control parameter, traverse different combinations of multiple cooling control parameters to obtain multiple combinations of cooling control parameters; For each combination of cooling control parameters, the fitted value corresponding to each performance parameter is calculated based on the combination of cooling control parameters and the mapping relationship corresponding to each performance parameter. An objective function is constructed based on the fitted values ​​corresponding to each of the multiple performance parameters. The combination of cooling parameters that minimizes the corresponding objective function value is selected as the plurality of objective cooling parameters.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the controlled cooling method for fine-grained steel according to any one of claims 1 to 7 when running the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the controlled cooling method for fine-grained steel according to any one of claims 1 to 7.

Images