Method and system for optimizing performance of bake-hardening steel automobile sheet

Abstract

The invention discloses a bake-hardening steel automobile sheet performance optimization method and system, and relates to the field of metal material machining, and the method comprises the steps: inputting production historical data, a target thickness and a target bake-hardening value into a target parameter optimization model, so as to obtain optimized target parameters, the target parameter optimization model is obtained based on a bake hardening value prediction model established based on production historical data, and optimization is carried out through a particle swarm optimization algorithm based on the corresponding relation between the finishing elongation and the process and component as a constraint condition. And controlling the production process of the bake-hardening steel automobile sheet according to the optimized target parameters. According to the method, the optimized component process of the target bake-hardening value performance is rapidly obtained based on the machine learning method by utilizing the production historical data of the bake-hardening steel, a large number of experiments are not needed, the time cost and the economic cost of product optimization are reduced, the steel plate produced by utilizing the method has no orange peel defect after being stamped, and the product quality is improved. And the requirements of the automobile outer plate can be met.

Description

Technical Field

[0001] The present application relates to the technical field of metal material processing, and in particular to a method and system for optimizing the performance of bake-hardened steel automobile plates. Background Art

[0002] In recent years, with the production of automobile outer panels, the demand for hot-dip galvanized bake-hardened steel sheets with good corrosion resistance has been increasing. The bake hardening of bake-hardened steel refers to the process of improving the yield strength through painting and baking to bring high impact resistance. The bake hardening value is generally measured by measuring the difference between the flow stress at 2% strain and the lower yield strength after heat treatment at 170℃ for 20 minutes. In addition, automobile outer panels have very high requirements for appearance quality. If there is uneven deformation on the surface during the stamping process, it will produce surface orange peel after painting, affecting the surface quality.

[0003] However, different automobile factories have different painting processes and vehicle exterior designs, resulting in different requirements for bake hardening values ​​of bake hardened steel plates. The bake hardening value of hot-dip galvanized bake hardened steel plates is affected by many factors such as chemical composition, hot rolling process, cold rolling process and hot-dip galvanizing process. The pinning effect of the solid solution carbon on dislocations in bake hardened steel plates affects whether there are orange peel defects on the surface after stamping. If you want to design steel plates with different bake hardening values ​​and ensure that there are no orange peel defects on the surface of the steel plates after stamping, you need to go through a lot of experiments, and both time cost and economic cost become bottlenecks that restrict the production rhythm.

[0004] With regard to the above-mentioned related technologies, no effective solution has been proposed so far as to the problem of how to quickly optimize the bake hardening value of bake hardened steel automobile sheets and ensure good surface quality after stamping. Summary of the invention

[0005] The technical problem to be solved by the present invention is to quickly optimize the composition process of bake-hardened steel automobile plates according to a specific bake-hardening value target, and ensure that there is no orange peel defect on the surface after stamping.

[0006] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0007] In a first aspect, the present application proposes a method for optimizing the performance of a bake-hardened steel automobile sheet, comprising:

[0008] Obtain production history data;

[0009] The production history data, target thickness and target bake hardening value are input into the target parameter optimization model to obtain the optimized target parameters; wherein the target parameter optimization model is obtained by a bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on a random forest algorithm; the target parameter optimization model is obtained by optimizing the corresponding relationship between the skin-pass elongation and the process and composition as a constraint condition through a particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-pass elongation;

[0010] The production process of bake-hardened steel automotive sheets is controlled based on the optimized target parameters.

[0011] In a feasible implementation manner, the production history data, the target thickness and the target bake hardening value are input into the target parameter optimization model to obtain the optimized target parameters, and further comprising:

[0012] The absolute value of the difference between the target bake hardening value and the predicted bake hardening value is set as an objective function;

[0013] Optimizing the objective function until the objective function reaches a minimum value;

[0014] The lower limit of the thickness search range is set to the difference between the target thickness and the thickness tolerance, and the upper limit of the thickness search range is set to the sum of the target thickness and the thickness tolerance;

[0015] The search ranges of the excess carbon content, the hot rolling coiling temperature, the annealing temperature and the skin-pass elongation are consistent with the ranges of the parameters in the production history data.

[0016] In a feasible implementation manner, the corresponding relationship between the polishing elongation and the process and the composition is a parameter corresponding relationship between the polishing elongation and the thickness and the excess carbon content.

[0017] In a feasible implementation, it also includes:

[0018] Screening the production history data to obtain data with a yield point elongation less than 0.5% of the critical yield point elongation for not causing orange peel after stamping of the steel plate;

[0019] In the data obtained after screening, the skin-finishing elongation is used as the output variable, the thickness and the excess carbon content are used as the input variables, and a polynomial regression algorithm is used to establish a corresponding relationship between the skin-finishing elongation and the process and composition.

[0020] In a feasible implementation manner, the corresponding relationship between the finishing elongation and the process and composition is specifically:

[0021] SPE% = a 0 +a 1 *Th+a 2 *C%+a 3 *Th 2 +a 4 *Th*C%+a 5 * C%;

[0022] Among them, SPE% is the percentage of skin-clearing elongation; Th is the thickness of the steel plate, in mm; C% is the mass percentage of excess carbon content; a 0 、a 1 、a 2 、a 3 、a 4 、a 5 is the weight coefficient.

[0023] In a feasible implementation, it also includes:

[0024] The production history data is preprocessed; the preprocessing includes removing null values, zero values ​​and abnormal values ​​in the data; the abnormal values ​​are values ​​of the bake hardening values ​​exceeding the range of 3 standard deviations.

[0025] In a feasible implementation, it also includes:

[0026] Optimizing the preset parameters in the random forest algorithm by a K-fold cross validation method to obtain the bake hardening value prediction model;

[0027] The preset parameters include the number of trees in the forest, the number of features for each tree, the maximum depth of the tree, and the number of samples for the minimum split of a tree node.

[0028] In a feasible implementation, it also includes:

[0029] The sample data which are not sampled in each sampling in the production history data are obtained, and the bake hardening value prediction model is tested by using the sample data.

[0030] In a feasible implementation manner, the calculation formula for the excess carbon content is:

[0031] C%=Ct%-Nb%*12 / 93-Ti%*12 / 48+N%12 / 14;

[0032] Among them, C% is the mass percentage of excess carbon content; Ct% is the mass percentage of total carbon content in steel; Nb% is the mass percentage of Nb content in steel; Ti% is the mass percentage of Ti content in steel; N% is the mass percentage of N content in steel.

[0033] In a second aspect, the present application proposes a bake-hardened steel automobile sheet performance optimization system, which is applied to the bake-hardened steel automobile sheet performance optimization method described in any of the above feasible embodiments, comprising:

[0034] Data collection module, used to obtain historical production data;

[0035] A data processing module, for inputting the production history data, target thickness and target bake hardening value into a target parameter optimization model to obtain optimized target parameters; wherein the target parameter optimization model is obtained by a bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on a random forest algorithm; the target parameter optimization model is obtained by optimizing the corresponding relationship between the skin-pass elongation and the process and composition as a constraint condition through a particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-pass elongation;

[0036] A parameter optimization module is used to control the production process of bake-hardened steel automobile sheets based on the optimized target parameters.

[0037] In summary, the performance optimization method of bake-hardened steel automobile plates in an embodiment of the present application includes: obtaining production history data; inputting the above-mentioned production history data, target thickness and target bake-hardening value into a target parameter optimization model to obtain optimized target parameters; wherein the above-mentioned target parameter optimization model is obtained based on a bake-hardening value prediction model established based on the above-mentioned production history data; the above-mentioned bake-hardening value prediction model is constructed based on a random forest algorithm; the above-mentioned target parameter optimization model is based on the corresponding relationship between the smoothing elongation and the process and composition as constraints, and is obtained by optimizing the particle swarm optimization algorithm; the above-mentioned production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, smoothing elongation, yield point elongation and bake-hardening value; the above-mentioned target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and smoothing elongation; and the production process of bake-hardened steel automobile plates is controlled based on the above-mentioned optimized target parameters.

[0038] The method for optimizing the performance of bake-hardened steel automobile plates proposed in the embodiment of the present application uses the historical data of bake-hardened steel production, and quickly designs the optimized component process scheme corresponding to the required bake-hardening value based on the random forest algorithm and the particle swarm optimization algorithm, without a large number of experiments, reducing the time cost and economic cost of product optimization. The present application uses the corresponding relationship formula of the smoothing elongation and thickness and excess carbon content of the historical data of the yield point elongation less than 0.5% as a constraint condition to optimize the component process, ensuring that the yield point elongation of the optimized product is less than 0.5%, avoiding the orange peel defect in the stamping process of the automobile plate. The present application uses the random forest algorithm to establish a bake-hardening value prediction model. The random forest algorithm is insensitive to abnormal values ​​and outliers, has no special requirements for the variable dimension, does not require standardization, and its accuracy and stability are often better than traditional algorithms. The present invention uses the established target parameter optimization model, takes the absolute value of the difference between the required bake-hardening value and the predicted bake-hardening value as the objective function, and uses the particle swarm optimization algorithm to optimize the process parameters of each component, combines the machine learning algorithm with the optimization theory, improves the convergence speed, reduces the number of parameters, and makes the algorithm simple and easy to implement.

[0039] The method for optimizing the performance of bake-hardened steel automobile plates proposed in this application, and other advantages, objectives and features of this application will be partially reflected through the following description, and will also be partially understood by technicians in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0041] Figure 1 A schematic diagram of a method for optimizing the performance of a bake-hardened steel automobile sheet provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of functional modules of a bake-hardened steel automobile plate performance optimization system provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of an electronic device for optimizing the performance of bake-hardened steel automobile plates provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0045] In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0046] See also Figure 1 , which is a schematic diagram of a process for optimizing the performance of a bake-hardened steel automobile sheet provided in an embodiment of the present application, and may specifically include:

[0047] S110. Obtain production history data.

[0048] Exemplarily, the above production history data include parameters such as thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin pass elongation, yield point elongation and bake hardening value corresponding to the produced hardened steel automobile sheet.

[0049] S120. Input the production history data, target thickness and target bake hardening value into the target parameter optimization model to obtain the optimized target parameters; wherein, the target parameter optimization model is obtained based on the bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on the random forest algorithm; the target parameter optimization model is based on the corresponding relationship between the skin-finishing elongation and the process and composition as constraints, and is obtained by optimizing the particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-finishing elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-finishing elongation.

[0050] Exemplarily, in this embodiment, the bake hardening value prediction model is used as the above-mentioned target parameter optimization model. First, the production history data of bake hardening steel is obtained, including: thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; secondly, the bake hardening value is used as the output variable, and the thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, and skin-pass elongation are used as input variables. The bake hardening value prediction model (i.e., the above-mentioned target parameter optimization model) is established using the random forest algorithm, and the corresponding relationship formula between the skin-pass elongation and the process and composition is established; finally, the established bake hardening value prediction model is used to optimize the process parameters of each component using the particle swarm optimization algorithm. In the process of optimization using the particle swarm optimization algorithm, the corresponding relationship formula between the skin-pass elongation and the process and composition is used as a constraint condition. By inputting the above-mentioned real-time production data into the model, the bake hardening value required for the bake hardening steel can be obtained, so as to further obtain the corresponding optimized component process plan.

[0051] S130. Controlling the production process of bake-hardened steel automobile sheets based on the optimized target parameters.

[0052] Exemplarily, the optimized target parameters obtained through the above steps, that is, the optimized process method corresponding to the bake hardening value and other parameters required for the current bake hardening steel, are used to control the production process of bake hardening steel automobile plates in real time.

[0053] In summary, the method for optimizing the performance of bake-hardened steel automobile plates proposed in the embodiment of the present application utilizes the historical production data of bake-hardened steel, and based on the random forest algorithm and the particle swarm optimization algorithm, quickly designs the optimized composition process scheme corresponding to the required bake-hardening value, without the need for a large number of experiments, thereby reducing the time cost and economic cost of product optimization. The present application uses the random forest algorithm to establish a bake-hardening value prediction model. The random forest algorithm is insensitive to abnormal values ​​and outliers, has no special requirements for the variable dimension, does not require standardization, and is often better in accuracy and stability than traditional algorithms.

[0054] The present invention utilizes the established target parameter optimization model, takes the absolute value of the difference between the required bake hardening value and the predicted bake hardening value as the objective function, adopts the particle swarm optimization algorithm to optimize the process parameters of each component, combines the machine learning algorithm with the optimization theory, improves the convergence speed, reduces the number of parameters, and makes the algorithm simple and easy to implement.

[0055] In some examples, the production history data, the target thickness, and the target bake hardening value are input into a target parameter optimization model to obtain optimized target parameters, further comprising:

[0056] The absolute value of the difference between the target bake hardening value and the predicted bake hardening value is set as an objective function;

[0057] Optimizing the objective function until the objective function reaches a minimum value;

[0058] The lower limit of the thickness search range is set to the difference between the target thickness and the thickness tolerance, and the upper limit of the thickness search range is set to the sum of the target thickness and the thickness tolerance;

[0059] The search ranges of the excess carbon content, the hot rolling coiling temperature, the annealing temperature and the skin-pass elongation are consistent with the ranges of the parameters in the production history data.

[0060] For example, the required bake hardening value, i.e., the absolute value of the difference between the target bake hardening value and the predicted bake hardening value, is used as the objective function, and optimization is performed to minimize the objective function. In this way, the optimization direction can be minimized to improve the optimization efficiency and facilitate convergence.

[0061] In some examples, the corresponding relationship between the finishing elongation and the process and the composition is a parameter corresponding relationship between the finishing elongation and the thickness and the excess carbon content.

[0062] For example, the corresponding relationship formula of the skin-clearing elongation, process and composition is the corresponding relationship formula of the skin-clearing elongation, thickness and excess carbon content. The appropriate skin-clearing elongation can avoid the appearance of orange peel after steel plate stamping, and the setting of the skin-clearing elongation is related to the thickness and excess carbon content.

[0063] In some examples, this also includes:

[0064] Screening the production history data to obtain data with a yield point elongation less than 0.5% of the critical yield point elongation for not causing orange peel after stamping of the steel plate;

[0065] In the data obtained after screening, the skin-finishing elongation is used as the output variable, the thickness and the excess carbon content are used as the input variables, and a polynomial regression algorithm is used to establish a corresponding relationship between the skin-finishing elongation and the process and composition.

[0066] For example, the data with yield point elongation less than 0.5% in the processed data are screened out, the skin-pass elongation is used as the output variable, the thickness and excess carbon content are used as the input variables, and the polynomial regression algorithm is used to establish the corresponding relationship formula between skin-pass elongation and thickness and excess carbon content. When steel plates with yield point elongation less than 0.5% are used in the production of automobile outer panel parts, it can ensure that there will be no orange peel defects after stamping.

[0067] The embodiment of the present application optimizes the composition process by using the corresponding relationship formula of the smoothing elongation of historical data with a yield point elongation of less than 0.5% and thickness, excess carbon content as a constraint condition, thereby ensuring that the yield point elongation of the optimized product is less than 0.5%, thereby avoiding orange peel defects in the stamping process of automobile plates.

[0068] In some examples, the corresponding relationship between the finishing elongation and the process and composition is specifically the following formula (1):

[0069] SPE% = a 0 +a 1 *Th+a 2 *C%+a 3 *Th 2 +a 4 *Th*C%+a 5 *C%(1);

[0070] Among them, SPE% is the percentage of skin-clearing elongation; Th is the thickness of the steel plate, in mm; C% is the mass percentage of excess carbon content; a 0 、a 1 、a 2 、a 3 、a 4 、a 5 is the weight coefficient.

[0071] Exemplarily, the above formula (1) adopts the form of a binary quadratic function and does not include a constant term, which can reduce the complexity of the equation and avoid non-convergence during the optimization process.

[0072] In some examples, this also includes:

[0073] The production history data is preprocessed; the preprocessing includes removing null values, zero values ​​and abnormal values ​​in the data; the abnormal values ​​are values ​​of the bake hardening values ​​exceeding the range of 3 standard deviations.

[0074] For example, in the data processing process, an abnormal value is a value whose bake hardening value exceeds the range of 3 standard deviations. Removing values ​​outside the range of 3 standard deviations can avoid the influence of the measurement error of the bake hardening value on the calculation result.

[0075] In some examples, this also includes:

[0076] Optimizing the preset parameters in the random forest algorithm by a K-fold cross validation method to obtain the bake hardening value prediction model;

[0077] The preset parameters include the number of trees in the forest, the number of features for each tree, the maximum depth of the tree, and the number of samples for the minimum split of a tree node.

[0078] For example, in the process of establishing the bake hardening value prediction model using the random forest algorithm, the four parameters of the number of trees in the forest, the number of features of each tree, the maximum depth of the tree, and the number of samples for the minimum split of the tree node are optimized using the K-fold cross validation method. This step debugs and optimizes the main parameters of the random forest algorithm and improves the accuracy of the model.

[0079] In some examples, this also includes:

[0080] The sample data which are not sampled in each sampling in the production history data are obtained, and the bake hardening value prediction model is tested by using the sample data.

[0081] For example, in the process of establishing a bake hardening value prediction model using the random forest algorithm, the sample data that is not drawn in each sampling is used to test the model. This can make full use of the sample data that is not drawn, avoid dividing the data into training sets and test sets, and improve data utilization.

[0082] In some examples, the excess carbon content is calculated as follows:

[0083] C%=Ct%-Nb%*12 / 93-Ti%*12 / 48+N%12 / 14(2);

[0084] Among them, C% is the mass percentage of excess carbon content; Ct% is the mass percentage of total carbon content in steel; Nb% is the mass percentage of Nb content in steel; Ti% is the mass percentage of Ti content in steel; N% is the mass percentage of N content in steel.

[0085] For example, in the above formula (2), the present application considers adding a small amount of Ti or Nb to the ultra-low carbon steel to stabilize part of the carbon.

[0086] The technical solution of the present application is further described in detail below through specific embodiments.

[0087] The bake-hardened galvanized steel plate to be designed in this embodiment is HC180BD+Z, the target thickness is 0.8 mm, the target bake-hardening value is 40 MPa, and the bake-hardening value is measured according to BH2 in the standard GB / T 24174-2022. 1931 samples of production history data of HC180BD+Z were obtained, and the main parameter data were sorted out: thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation, and bake-hardening value. The excess carbon content is calculated by the above formula (2).

[0088] Furthermore, the data were processed to remove null values, zero values, and outliers whose bake hardening values ​​exceeded 3 standard deviations. After processing, 1811 samples were obtained, and the data of 10 samples are shown in Table 1 below.

[0089]

[0090] Table 1

[0091] The bake hardening value is used as the output variable, and the thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, and skin-pass elongation are used as input variables. The bake hardening value prediction model is established using the random forest algorithm. The four parameters of the number of trees in the forest, the number of features of each tree, the maximum depth of the tree, and the number of samples with the minimum split of the tree node are optimized using the K-fold cross validation method. The model is tested on the sample data that was not drawn in each sampling.

[0092] The data with yield point elongation less than 0.5% were screened out from the processed data, and the skin-finishing elongation was used as the output variable, and the thickness and excess carbon content were used as the input variables. The polynomial regression algorithm was used to establish the corresponding relationship between skin-finishing elongation and thickness and excess carbon content, which is specifically the above formula (1). The fitting result is:

[0093] a 0 =1.13, a 1 =0.4, a 2 =89.8, a 3 =-0.1, a 4 =-81.8, a 5 =2924;

[0094] Using the established bake hardening value prediction model, the absolute value of the difference between the bake hardening value 40MPa and the predicted bake hardening value is used as the objective function, and the particle swarm optimization algorithm is used to optimize the process parameters of each component to minimize the objective function. The lower limit of the thickness search range is set to [target thickness-thickness tolerance], that is, 0.76, and the upper limit of the thickness search range is set to [target thickness+thickness tolerance], that is, 0.84. The search range of excess carbon content, hot rolling coiling temperature, annealing temperature, and skin-finishing elongation is consistent with the range of each parameter in the production history data, so as to improve the efficiency and accuracy of optimization. In this embodiment, the lower limit of the search range of excess carbon content, hot rolling coiling temperature, annealing temperature, and skin-finishing elongation is set to [0.0008, 570, 750, 1.2], and the upper limit of the search range is set to [0.0018, 730, 830, 1.47].

[0095] In the process of optimization using the particle swarm optimization algorithm, the corresponding relationship formula between the skin-clearing elongation and the thickness and the excess carbon content is used as a constraint condition to obtain the optimized composition process plan corresponding to the bake hardening value required for the bake hardening steel, as shown in Table 2 below.

[0096]

[0097] Table 2

[0098] According to this scheme, the baking hardening value obtained is 35-44MPa, and the steel plate has good surface quality after stamping without orange peel defects during the production of automobile door outer panels.

[0099] like Figure 2 FIG. 1 is a functional module diagram of a bake-hardened steel automobile sheet performance optimization system proposed in the present application. The bake-hardened steel automobile sheet performance optimization system is applied to the bake-hardened steel automobile sheet performance optimization method described in any of the above exemplary embodiments. The system includes:

[0100] Data collection module 21, used to obtain production history data;

[0101] The data processing module 22 is used to input the production history data, target thickness and target bake hardening value into the target parameter optimization model to obtain the optimized target parameters; wherein the target parameter optimization model is obtained by a bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on a random forest algorithm; the target parameter optimization model is obtained by optimizing the corresponding relationship between the skin-pass elongation and the process and composition as a constraint condition through a particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-pass elongation;

[0102] The parameter optimization module 23 is used to control the production process of bake hardening steel automobile sheet based on the optimized target parameters.

[0103] like Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and executable on the processor, and when the processor 310 executes the computer program 321, the steps of any of the above-mentioned methods for optimizing the performance of bake-hardened steel automotive plates are implemented.

[0104] Since the electronic device introduced in this embodiment is a device used to implement a bake-hardened steel automobile plate performance optimization system in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0105] In the specific implementation process, when the computer program 321 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0106] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of a method for optimizing the performance of bake-hardened steel automobile plates.

[0112] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0113] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0117] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0118] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0119] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0120] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and variations of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and variations.

Claims

1. A method for optimizing the performance of bake-hardened steel automobile sheets, characterized in that: include: Obtain production history data; The production history data, target thickness and target bake hardening value are input into the target parameter optimization model to obtain the optimized target parameters; wherein the target parameter optimization model is obtained by a bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on a random forest algorithm; the target parameter optimization model is obtained by optimizing the corresponding relationship between the skin-pass elongation and the process and composition as a constraint condition through a particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-pass elongation; The production process of bake-hardened steel automotive sheets is controlled based on the optimized target parameters.

2. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: Inputting the production history data, target thickness and target bake hardening value into a target parameter optimization model to obtain optimized target parameters, further comprising: The absolute value of the difference between the target bake hardening value and the predicted bake hardening value is set as an objective function; Optimizing the objective function until the objective function reaches a minimum value; The lower limit of the thickness search range is set to the difference between the target thickness and the thickness tolerance, and the upper limit of the thickness search range is set to the sum of the target thickness and the thickness tolerance; The search ranges of the excess carbon content, the hot rolling coiling temperature, the annealing temperature and the skin-pass elongation are consistent with the ranges of the parameters in the production history data.

3. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: The corresponding relationship between the polishing elongation and the process and the composition is the corresponding relationship between the polishing elongation and the thickness and the excess carbon content.

4. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: Also includes: Screening the production history data to obtain data with a yield point elongation less than 0.5% of the critical yield point elongation for not causing orange peel after stamping of the steel plate; In the data obtained after screening, the skin-finishing elongation is used as the output variable, the thickness and the excess carbon content are used as the input variables, and a polynomial regression algorithm is used to establish a corresponding relationship between the skin-finishing elongation and the process and composition.

5. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 4, characterized in that: The corresponding relationship between the finishing elongation and the process and composition is specifically: SPE%=a0+a1*Th+a2*C%+a3*Th 2 +a4*Th*C%+a5*C%; Among them, SPE% is the skin-clearing elongation percentage; Th is the thickness of the steel plate, in mm; C% is the mass percentage of excess carbon content; a0, a1, a2, a3, a4, and a5 are weight coefficients.

6. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: Also includes: Preprocessing the production history data; the preprocessing includes removing null values, zero values ​​and abnormal values ​​in the data; The abnormal value is a value whose bake hardening value exceeds the range of 3 standard deviations.

7. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: Also includes: Optimizing the preset parameters in the random forest algorithm by a K-fold cross validation method to obtain the bake hardening value prediction model; The preset parameters include the number of trees in the forest, the number of features for each tree, the maximum depth of the tree, and the number of samples for the minimum split of a tree node.

8. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: Also includes: The sample data which are not sampled in each sampling in the production history data are obtained, and the bake hardening value prediction model is tested by using the sample data.

9. The method for optimizing the performance of bake-hardened steel automobile sheets according to claim 1, characterized in that: The calculation formula of the excess carbon content is: C%=Ct%-Nb%*12 / 93-Ti%*12 / 48+N%12 / 14; Among them, C% is the mass percentage of excess carbon content; Ct% is the mass percentage of total carbon content in steel; Nb% is the mass percentage of Nb content in steel; Ti% is the mass percentage of Ti content in steel; N% is the mass percentage of N content in steel.

10. A bake-hardened steel automobile sheet performance optimization system, applied to the bake-hardened steel automobile sheet performance optimization method according to any one of claims 1 to 9, characterized in that: include: Data collection module, used to obtain historical production data; A data processing module, for inputting the production history data, target thickness and target bake hardening value into a target parameter optimization model to obtain optimized target parameters; wherein the target parameter optimization model is obtained by a bake hardening value prediction model established based on the production history data; the bake hardening value prediction model is constructed based on a random forest algorithm; the target parameter optimization model is obtained by optimizing the corresponding relationship between the skin-pass elongation and the process and composition as a constraint condition through a particle swarm optimization algorithm; the production history data includes one or more of thickness, excess carbon content, hot rolling coiling temperature, annealing temperature, skin-pass elongation, yield point elongation and bake hardening value; the target parameters include one or more of excess carbon content, hot rolling coiling temperature, annealing temperature and skin-pass elongation; A parameter optimization module is used to control the production process of bake-hardened steel automobile sheets based on the optimized target parameters.

Images