Methods, apparatus, equipment and media for producing pickled steel with excellent phosphating properties

Abstract

This invention discloses a method, apparatus, equipment, and medium for producing pickled steel with excellent phosphating performance. The production method includes: obtaining initial production process parameters, phosphating performance requirements, and mechanical property requirements for a new pickled steel product; inputting the initial production process parameters into a pre-constructed performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product produced using the initial production process parameters; modifying the initial production process parameters when the theoretical phosphating performance or theoretical mechanical properties do not meet the requirements, until both the theoretical phosphating performance and theoretical mechanical properties meet the requirements, and then determining the modified initial production process parameters as the actual production process parameters; and producing the new pickled steel product according to the actual production process parameters. This method can achieve the production of new pickled steel products with excellent phosphating performance, and has a short development cycle.

Description

Technical Field

[0001] This invention relates to the field of pickling steel production technology, and in particular to a pickling steel production method, apparatus, equipment and medium with excellent phosphating properties. Background Technology

[0002] Pickled automotive steel uses high-quality hot-rolled thin sheets as raw material. After being pickled to remove iron oxide scale, trimmed, and finished, it becomes a finished product with broad application prospects. However, due to its susceptibility to oxidation and poor corrosion resistance, pickled automotive steel requires phosphating and other coating processes before use. Phosphating, as an important pre-coating treatment method, is widely used in the automotive manufacturing industry. The quality of phosphating directly affects the appearance and corrosion resistance of the steel sheet.

[0003] In existing technologies, the phosphating performance of pickled automotive steel is improved by adjusting its chemical composition and production process. This method requires redesigning the steel grade. While the new steel grade may meet the phosphating performance requirements due to the change in chemical composition, it may also alter its mechanical properties, making it unsuitable for the original steel strength requirements. Furthermore, the time required for prototyping the new steel grade and adjusting the process is lengthy, resulting in an excessively long R&D cycle and high R&D costs. Summary of the Invention

[0004] In view of the above problems, this invention is proposed to provide a method, apparatus, equipment, and medium for producing pickled steel with excellent phosphating performance that overcomes or at least partially solves the above problems. By constructing a performance prediction model, the actual production process parameters of the new pickled steel product that meet the predicted theoretical phosphating performance and theoretical mechanical properties can be quickly obtained, thereby realizing the production of new pickled steel products with excellent phosphating performance. This method not only has a wide range of applications but also a short research and development cycle, which can greatly save research and development costs.

[0005] In a first aspect, the present invention provides a method for producing pickled steel with excellent phosphating properties, the method comprising:

[0006] Obtain the initial production process parameters, phosphating performance requirements, and mechanical property requirements for new pickled steel products;

[0007] The initial production process parameters are input into a pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product produced using the initial production process parameters.

[0008] When the theoretical phosphating performance does not meet the phosphating performance requirements, or the theoretical mechanical properties do not meet the mechanical performance requirements, the initial production process parameters are modified until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements. The modified initial production process parameters are then determined as the actual production process parameters.

[0009] The new pickled steel product is produced according to the actual production process parameters.

[0010] Optionally, modifying the initial production process parameters until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determining the modified initial production process parameters as the actual production process parameters, includes:

[0011] Determine the steel grade for the new pickled steel products;

[0012] Based on a pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; wherein, the optimal phosphating performance database is used to store the production process parameters when the phosphating performance of pickled steel products of different steel grades is optimal.

[0013] Modify the initial production process parameters to the preferred production process parameters;

[0014] The preferred production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product;

[0015] When the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters are determined as the actual production process parameters.

[0016] Optionally, the production method further includes:

[0017] Obtain historical sample data of pickled steel, wherein the historical sample data includes at least historical production process parameters, and phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters;

[0018] From the historical sample data, historical sample data with qualified phosphating performance and mechanical properties are selected and recorded as preferred sample data;

[0019] The preferred sample data is classified according to the steel grade to obtain the preferred sample data for each steel grade;

[0020] Based on the preferred sample data for each steel grade, determine the optimal phosphating performance data for each steel grade, and the production process parameters under the optimal phosphating performance;

[0021] The optimal phosphating performance data and the corresponding production process parameters for each steel grade are stored in a database to construct the optimal phosphating performance database.

[0022] Optionally, storing the optimal phosphating performance data and corresponding production process parameters for each steel grade in a database includes:

[0023] The optimal phosphating performance data for each of the steel grades is stored in a database;

[0024] When there is only one set of production process parameters corresponding to the optimal phosphating performance, this set of production process parameters is stored in the database.

[0025] When there are multiple sets of production process parameters corresponding to the optimal phosphating performance, the set with the optimal mechanical properties among the multiple sets of production process parameters is stored in the database.

[0026] Optionally, the production method further includes:

[0027] Obtain historical sample data of pickled steel, wherein the historical sample data includes at least historical production process parameters, and phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters;

[0028] The historical sample data is classified according to steel type to obtain the historical sample data for each steel type;

[0029] A neural network model is constructed for different steel grades, with input layer neurons representing production process parameters and output layer neurons representing phosphating performance data and mechanical performance data.

[0030] The historical sample data of each steel grade is input into the corresponding neural network model of the steel grade for training and testing to obtain the performance prediction model of different steel grades.

[0031] Optional,

[0032] The step of inputting the historical sample data of each steel grade into the corresponding neural network model of the steel grade for training and testing to obtain the performance prediction model of different steel grades includes:

[0033] The historical sample data for each steel grade is divided into training sample data and test sample data according to a set ratio;

[0034] The training sample data of each steel grade is input into the neural network model of the corresponding steel grade for training. The training process is optimized by a pre-set algorithm until the model converges to obtain the optimized initial performance prediction model of the corresponding steel grade.

[0035] The test sample data of each steel grade is input into the initial performance prediction model of the corresponding steel grade, and the test phosphating performance and test mechanical properties are output.

[0036] When the tested phosphating performance and the tested mechanical properties meet the modeling requirements, the initial performance prediction model of the steel grade is used as the performance prediction model of the steel grade.

[0037] Optionally, the production process parameters include hot rolling process parameters and pickling process parameters.

[0038] Secondly, the present invention provides a pickling steel production apparatus with excellent phosphating performance, the production apparatus comprising:

[0039] The acquisition module is used to acquire the initial production process parameters, phosphating performance requirements, and mechanical property requirements of new pickled steel products.

[0040] The theoretical performance prediction module is used to input the initial production process parameters into a pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product produced using the initial production process parameters.

[0041] The actual production process parameter determination module is used to modify the initial production process parameters when the theoretical phosphating performance does not meet the phosphating performance requirements or the theoretical mechanical properties do not meet the mechanical performance requirements, until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determine the modified initial production process parameters as the actual production process parameters.

[0042] The production module is used to produce the new pickled steel product according to the actual production process parameters.

[0043] Optionally, the actual production process parameter determination module is also used for:

[0044] Determine the steel grade for the new pickled steel products;

[0045] Based on a pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; wherein, the optimal phosphating performance database is used to store the production process parameters when the phosphating performance of pickled steel products of different steel grades is optimal.

[0046] Modify the initial production process parameters to the preferred production process parameters;

[0047] The preferred production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product;

[0048] When the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters are determined as the actual production process parameters.

[0049] Optionally, the production apparatus further includes:

[0050] The first acquisition module is used to acquire historical sample data of pickled steel. The historical sample data includes at least historical production process parameters, as well as phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters.

[0051] The preferred sample data screening module is used to screen out historical sample data from the historical sample data that have qualified phosphating performance and mechanical properties, and record them as preferred sample data;

[0052] The first sample classification module is used to classify the preferred sample data according to the steel grade to obtain the preferred sample data for each steel grade;

[0053] The determining module is used to determine the optimal phosphating performance data for each steel grade, and the production process parameters under the optimal phosphating performance, based on the preferred sample data for each steel grade.

[0054] The optimal phosphating performance database construction module is used to store the optimal phosphating performance data and the corresponding production process parameters of each steel grade into the database to construct the optimal phosphating performance database.

[0055] Optionally, the optimal phosphating performance database building module is also used for:

[0056] The optimal phosphating performance data for each of the steel grades is stored in a database;

[0057] When there is only one set of production process parameters corresponding to the optimal phosphating performance, this set of production process parameters is stored in the database.

[0058] When there are multiple sets of production process parameters corresponding to the optimal phosphating performance, the set with the optimal mechanical properties among the multiple sets of production process parameters is stored in the database.

[0059] Optionally, the production apparatus further includes:

[0060] The second acquisition module is used to acquire historical sample data of pickled steel. The historical sample data includes at least historical production process parameters, as well as phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters.

[0061] The second sample classification module is used to classify the historical sample data according to steel type to obtain the historical sample data for each steel type.

[0062] The neural network model construction module is used to construct neural network models for different steel grades with production process parameters as input layer neurons and phosphating performance data and mechanical performance data as output layer neurons.

[0063] The performance prediction model construction module is used to input the historical sample data of each steel grade into the corresponding neural network model of the steel grade for training and testing, so as to obtain the performance prediction model of different steel grades.

[0064] Optionally, the performance prediction model building module is also used for:

[0065] The historical sample data for each steel grade is divided into training sample data and test sample data according to a set ratio;

[0066] The training sample data of each steel grade is input into the neural network model of the corresponding steel grade for training. The training process is optimized by a pre-set algorithm until the model converges to obtain the optimized initial performance prediction model of the corresponding steel grade.

[0067] The test sample data of each steel grade is input into the initial performance prediction model of the corresponding steel grade, and the test phosphating performance and test mechanical properties are output.

[0068] When the tested phosphating performance and the tested mechanical properties meet the modeling requirements, the initial performance prediction model of the steel grade is used as the performance prediction model of the steel grade.

[0069] Optionally, the production process parameters include hot rolling process parameters and pickling process parameters.

[0070] Thirdly, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the production method as described in the first aspect.

[0071] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing the computer to perform the production method as described in the first aspect.

[0072] The technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0073] This invention provides a method, apparatus, equipment, and medium for producing pickled steel with excellent phosphating performance. The initial production process parameters of the newly acquired pickled steel product can be input into a pre-constructed performance prediction model to quickly predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product. When the predicted theoretical phosphating performance or theoretical mechanical properties do not meet the requirements, the initial production process parameters need to be modified until they do. The initial production process parameters at which the requirements are met are then used as the actual production process parameters for the new pickled steel product. This method, through the constructed performance prediction model, can quickly verify the actual production process parameters of the new pickled steel product that meet the phosphating performance and mechanical property requirements, thus achieving the production of new pickled steel products with excellent phosphating performance. This method not only has a wide range of applications but also a short development cycle, significantly saving research and development costs.

[0074] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0075] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0076] Figure 1 This is a flowchart of a pickling steel production method with excellent phosphating performance provided by an embodiment of the present invention;

[0077] Figure 2 This is a flowchart of a method for constructing a performance prediction model provided by an embodiment of the present invention;

[0078] Figure 3 This is a structural block diagram of a pickling steel production apparatus with excellent phosphating performance provided in an embodiment of the present invention. Detailed Implementation

[0079] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0080] First, a brief introduction to the application scenarios involved in the embodiments of the present invention will be given:

[0081] In the automotive industry, pickled automotive steel, made from high-quality hot-rolled sheet metal, undergoes pickling to remove iron oxide scale, edge trimming, and finishing before becoming a finished product, and has broad application prospects. With the rapid development of the automotive industry in recent years, the market demand for hot-rolled automotive steel has been continuously increasing due to its good surface quality and excellent mechanical and processing properties. However, because pickled automotive steel is prone to oxidation and has poor corrosion resistance, it requires phosphating or other coating processes before use.

[0082] Phosphating is an important pretreatment process for cathodic electrophoretic coating. The phosphate film formed after phosphating has a uniform and dense appearance, which can reduce electrochemical corrosion on the material surface and improve the material's corrosion resistance. At the same time, as the film layer between the substrate material and the electrophoretic paint film, the phosphate film plays a crucial role in connecting the two. The quality of the phosphate film directly affects the adhesion between the electrophoretic paint film and the material surface, the corrosion resistance of the material surface, and the overall coating effect on the vehicle body surface.

[0083] In existing technologies, the phosphating performance of pickled automotive steel can be improved by adjusting its chemical composition and production process. Therefore, to achieve good phosphating performance, many engineers specializing in pickled automotive steel focus on composition design to ensure that the phosphating performance of pickled automotive steel for different applications meets requirements. This approach requires redesigning the steel grade. While the newly designed steel grade may meet the phosphating performance requirements due to changes in chemical composition, it may also alter its mechanical properties, making it unsuitable for the original steel strength requirements. Furthermore, the time required for prototyping and process adjustments for the new steel grade is lengthy, resulting in excessively long R&D cycles and high R&D costs.

[0084] Therefore, to address the above problems, this invention provides a method for producing pickled steel with excellent phosphating performance. By constructing a performance prediction model and an optimal phosphating performance database, the actual production process parameters of the new pickled steel product that meet the predicted theoretical phosphating performance and theoretical mechanical properties can be quickly obtained, thereby realizing the production of a new pickled steel product with excellent phosphating performance. This method not only has a wide range of applications but also a short research and development cycle, which can greatly save research and development costs.

[0085] Next, the pickling steel production method with excellent phosphating performance provided by the embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0086] Figure 1 This is a flowchart of a pickling steel production method with excellent phosphating performance provided by an embodiment of the present invention, such as... Figure 1 As shown, the production method includes:

[0087] Step S110: Obtain the initial production process parameters, phosphating performance requirements, and mechanical property requirements for the new pickled steel products.

[0088] In this embodiment, the phosphating performance and mechanical property requirements for new pickled steel products can be obtained from sales contracts or new product design schemes. Initial production process parameters can also be obtained from new product design schemes. These new product design schemes can be based on the requirements in the sales contract or be new product design schemes independently developed by the enterprise.

[0089] Step S120: Input the initial production process parameters into the pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel products produced using the initial production process parameters.

[0090] Optionally, a performance prediction model can be built using the following steps:

[0091] The first step is to obtain historical sample data of pickled steel.

[0092] The historical sample data includes at least historical production process parameters, as well as phosphate performance data and mechanical property data of pickled steel products produced under historical production process parameters.

[0093] In this embodiment, the historical sample data may also include information on the steel type and thickness of the pickled steel products.

[0094] The mechanical property data may include yield strength, tensile strength, hardness, and elongation; the phosphating film performance data may include film weight data, P ratio measurement data, and microscopic morphology images under an electron microscope. The microscopic morphology images under the electron microscope can be analyzed using intelligent image analysis techniques to extract the phosphating film coverage and size as the final data.

[0095] Optionally, the production process parameters include hot rolling process parameters and pickling process parameters.

[0096] In this embodiment, the phosphating performance of pickled steel is closely related to the surface morphology of the steel plate. Moreover, the inventors found that the production process parameters of pickled steel products directly affect the surface morphology of pickled steel. Among various production process parameters, the hot rolling process parameters and pickling process parameters have the greatest impact on the surface morphology of pickled steel. Therefore, the hot rolling process parameters and pickling process parameters can be the focus of research.

[0097] In this embodiment, the hot rolling process parameters may include furnace exit temperature, initial rolling temperature, final rolling temperature, coiling temperature, and reduction per pass; the pickling process parameters may include pickling temperature, acid concentration, pickling speed, rinsing water temperature, rinsing water conductivity, and drying temperature. All the above data can be categorized according to the coil number, with each coil number corresponding to a historical sample data point. Each historical sample data point is then stored in a sample database, thereby constructing a sample database indexed by the coil number to facilitate the retrieval of required data.

[0098] Specifically, pickling steel production data within a certain historical time period can be collected as initial historical sample data. This initial historical sample data can be preprocessed to obtain the final sample historical data. The frequency of collecting the initial historical samples can be based on the data detection frequency of pickling steel production.

[0099] The purpose of preprocessing the initial historical sample data is to remove outlier data. Specifically, filtering conditions are set for each data point to identify outlier data that does not meet the criteria. The corresponding set of initial sample data is then deleted, thus eliminating invalid or missing outlier data. For example, the filtering conditions can be thresholds for each data point.

[0100] The second step is to classify the historical sample data according to the steel type, thus obtaining the historical sample data for each steel type.

[0101] The third step is to construct a neural network model for different steel grades, with the input layer neurons representing production process parameters and the output layer neurons representing phosphating performance data and mechanical performance data.

[0102] In this embodiment, hot rolling process parameters and pickling process parameters can be used as input layer neurons.

[0103] In this embodiment, parameters such as neuron activation functions, hidden layer activation functions, output layer activation functions, maximum number of network iterations, allowable error, and learning rate can also be set. For example, the neuron activation function can be set to f(x), the hidden layer activation function to tanh(x), and the output layer activation function to purelin(x) (a linear function). The weights and thresholds of the neural network model can be initialized using the Nguyen-Widrow algorithm, the maximum number of network iterations can be set to 1000, the allowable error can be set to 0.001, and the learning rate can be set to 0.01. Furthermore, a quasi-Newton algorithm neural network model can be established based on the optimization of hidden layer neuron values.

[0104] The third step is to input the historical sample data of each steel grade into the corresponding neural network model for training and testing, so as to obtain the performance prediction model of different steel grades.

[0105] Optional, the third step includes:

[0106] Historical sample data for each steel grade is divided into training sample data and test sample data according to a set ratio. The training sample data for each steel grade is input into the corresponding neural network model for training. The training process is optimized using a pre-set algorithm until the model converges, resulting in an optimized initial performance prediction model for the corresponding steel grade. Test sample data for each steel grade is input into the initial performance prediction model, which outputs the tested phosphating performance and tested mechanical properties. When the tested phosphating performance and tested mechanical properties meet the modeling requirements, the initial performance prediction model for each steel grade is used as the performance prediction model for that steel grade.

[0107] Of these, 80% of the historical sample data can be used as training sample data, and the remaining 20% ​​can be used as test sample data.

[0108] In this embodiment, the training sample data and test sample data can also be standardized. The purpose of standardization is to limit the historical sample data to a certain range, so that all data have the same metric. For example, the historical sample data can be restricted to the [0,1] interval by normalization, which can be performed according to the following formula:

[0109]

[0110] Where x represents historical sample data, and x' represents normalized historical sample data. min The minimum value in the historical sample data, x max This represents the maximum value in the historical sample data.

[0111] Specifically, the number of hidden layer neurons in the neural network model can be determined using empirical formulas; then, the training parameters are initialized; next, standardized training sample data is input into the neural network model, and the training process is optimized using algorithms, iteratively updating the weights of the pseudo-network based on the training sample data until the model converges, resulting in a trained initial performance prediction model; then, test sample data is input into the initial performance prediction model, outputting test phosphating performance and test mechanical performance, and the test phosphating performance data and test mechanical performance data are inversely normalized; finally, the root mean square error (RMSE) metric can be used to evaluate the trained model, that is, the square root of the expected value of the square of the difference between the inversely normalized test performance data and the true performance data in the test sample data is used to evaluate whether the model's accuracy meets the requirements. When the accuracy meets the requirements, it means that the test performance data meets the modeling requirements, and the initial performance prediction model is used as the performance prediction model. When the accuracy does not meet the requirements, the initial parameters are adjusted, and the neural network model is retrained until the test performance data meets the modeling requirements.

[0112] For example, firstly, through empirical formulas Determine the number of neurons in the hidden layer, where N i N represents the number of neurons in the input layer, and N0 represents the number of neurons in the output layer. s N represents the number of training samples, α represents the variable with any value, and N represents the number of samples. h This represents the number of neurons in the hidden layer. Then, the training parameters are initialized, which may include setting the allowable error and learning rate. Next, the training samples are input into the quasi-Newton algorithm neural network model, and the Adam (Adaptive Momentum) algorithm is used to optimize the training process. The weights of the quasi-Newton algorithm neural network are iteratively updated based on the training sample data until the model converges, resulting in the initial performance prediction model. Then, the test sample data is input into the initial performance prediction model, outputting the test phosphating performance and test mechanical performance. The test phosphating performance data and test mechanical performance data are then inversely normalized, specifically using the formula: y′=x min +y(x max -x min ), and perform inverse normalization, where y′ represents the actual performance value after inverse normalization, y represents the performance test value output by the model, and x min x represents the minimum value in the test sample data. max This represents the maximum value in the test sample data.

[0113] Next, the formula will be used. Calculate the root mean square error, where n represents the number of test sample data, p i y′ represents the sample value of the performance data in the test sample data.i It is the actual performance value after denormalization, where i represents the i-th performance.

[0114] In this embodiment, the smaller the root mean square error (RMSE), the closer the predicted value of the initial performance prediction model is to the true value, indicating higher model accuracy and better performance. Furthermore, the performance prediction model can be optimized at fixed time intervals to continuously update it and prevent inaccurate performance predictions. If the accuracy of the predicted performance data no longer meets requirements before the fixed update period, the performance prediction model needs to be updated in advance.

[0115] Figure 2 This is a flowchart of a method for constructing a performance prediction model provided by an embodiment of the present invention, such as... Figure 2 The performance prediction model can also be constructed according to the following steps:

[0116] Step S1: Initial historical sample data collection.

[0117] Step S2: Missing and outlier data processing. This involves removing outlier data from the initial historical sample data to obtain the final historical sample data.

[0118] Step S3: Divide the training sample data and test sample data. This involves dividing the historical sample data into training sample data and test sample data according to a set ratio.

[0119] Step S4: Data normalization. This involves normalizing the training and testing sample data.

[0120] Step S5: Determine the initial parameters. That is, determine the initialization parameters of the established neural network model.

[0121] Step S6: Model Training. This involves training the neural network model using the training sample data to obtain an initial performance prediction model.

[0122] Step S7: Determine if the RESE (Root Mean Square Error) value meets the requirements. That is, determine if the root mean square error index of the initial performance prediction model meets the requirements. If it does not meet the requirements, proceed to step S8; if it does, proceed to step S9.

[0123] Step S8: Optimize the initial parameters. Then proceed to step S6.

[0124] Step S9, Model Application. The initial performance prediction model is used as the performance prediction model to predict the performance of pickled steel.

[0125] Step S10: Determine whether the model's accuracy meets the requirements or whether the model is within the update cycle. If yes, proceed to step S9; otherwise, proceed to step S11.

[0126] Step S11: Collect recent production data to update historical sample data. Then return to step 2 to rebuild the performance prediction model.

[0127] It should be noted that historical sample data can be categorized according to steel grade, and then performance prediction models for different steel grades can be established based on the historical sample data for each steel grade. When it is necessary to produce new pickled steel products, the corresponding performance prediction model can be adopted based on the steel grade of the new pickled steel product.

[0128] Step S130: When the theoretical phosphating performance does not meet the phosphating performance requirements, or the theoretical mechanical properties do not meet the mechanical performance requirements, modify the initial production process parameters until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements. Then, determine the modified initial production process parameters as the actual production process parameters.

[0129] Optionally, step S130 includes:

[0130] The steel grade of the new pickled steel product is determined; based on the pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; the initial production process parameters are modified to the preferred production process parameters; the preferred production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product; when the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters are determined as the actual production process parameters.

[0131] Among them, the phosphate performance optimization database is used to store the production process parameters when the phosphate performance of pickled steel products of different steel grades is optimal.

[0132] In this embodiment, the optimal production process parameters for a new pickled steel product can be determined using a simulation iteration method based on a pre-built database of optimal phosphating performance. Specifically, the optimal phosphating performance parameters for the new pickled steel product are found in the pre-built database of optimal phosphating performance. These parameters are then optimized using a simulation iteration method to obtain the optimized production process parameters, which are the preferred production process parameters.

[0133] In this embodiment, when the theoretical phosphating performance does not meet the phosphating performance requirements, or the theoretical mechanical performance does not meet the mechanical performance requirements, the designer can continue to modify the initial production process parameters based on work experience or actual conditions until the theoretical phosphating performance output by the model meets the phosphating performance requirements and the theoretical mechanical performance meets the mechanical performance requirements.

[0134] Optionally, constructing a database of optimal phosphating performance may include the following steps:

[0135] The first step is to obtain historical sample data of pickled steel.

[0136] The historical sample data includes at least historical production process parameters, as well as phosphate performance data and mechanical property data of pickled steel products produced under historical production process parameters.

[0137] In this embodiment, the specific acquisition method can be found in the steps of constructing a performance prediction model, and will not be repeated here.

[0138] The second step is to select historical sample data from which both phosphating performance and mechanical properties are qualified, and record them as preferred sample data.

[0139] In this embodiment, the production process parameters of pickled automotive steel products that meet the required phosphate and mechanical properties can be collected through a secondary system according to the detection frequency of mechanical and phosphate properties. Products that meet the required phosphate and mechanical properties refer to pickled steel products that satisfy the steel plate performance standards and surface quality standards.

[0140] The third step is to classify the preferred sample data according to the steel grade to obtain the preferred sample data for each steel grade.

[0141] The fourth step is to determine the optimal phosphating performance data for each steel grade, as well as the production process parameters under the optimal phosphating performance, based on the preferred sample data for each steel grade.

[0142] This can be understood as selecting, from the preferred sample data, which specific set of production process parameters produces pickled steel with the best phosphate performance, and then selecting according to the steel grade.

[0143] The fifth step is to store the optimal phosphating performance data and corresponding production process parameters for each steel grade in the database to construct an optimal phosphating performance database.

[0144] Optional, step five includes:

[0145] The optimal phosphating performance data for each steel grade is stored in the database. When there is only one set of production process parameters corresponding to the optimal phosphating performance, this set of production process parameters is stored in the database. When there are multiple sets of production process parameters corresponding to the optimal phosphating performance, the set with the best mechanical properties among the multiple sets of production process parameters is stored in the database.

[0146] This can be understood as follows: in production, when pickled steel produced using different process parameters all exhibits optimal phosphating performance (i.e., their corresponding phosphating properties are identical), it is necessary to select the set with the best mechanical properties as the production process parameters corresponding to the optimal phosphating performance and store it in the database. This ensures that the stored production process parameters represent the optimal phosphating and mechanical properties.

[0147] In this embodiment, when the phosphating performance of the pickled automotive steel sheet produced by the new production process parameters is better than the optimal phosphating performance of the same steel grade in the optimal database, and the mechanical properties are also qualified, the new production process parameters replace the original production process parameters of the same steel grade and are stored to continuously update the optimal phosphating performance database.

[0148] Step S140: Produce new pickled steel products according to the actual production process parameters.

[0149] In this embodiment, according to the actual production process parameters, a new pickled steel product with excellent phosphating performance can be produced.

[0150] Based on the same inventive concept, this invention also provides a pickling steel production apparatus with excellent phosphating performance. Figure 3 This is a structural block diagram of a pickling steel production apparatus with excellent phosphating performance provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the production device 300 includes an acquisition module 310, a theoretical performance prediction module 320, an actual production process parameter determination module 330, and a production module 340.

[0151] Module 310 is used to acquire the initial production process parameters, phosphating performance requirements and mechanical property requirements of new pickled steel products.

[0152] The theoretical performance prediction module 320 is used to input the initial production process parameters into the pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel products produced using the initial production process parameters.

[0153] The actual production process parameter determination module 330 is used to modify the initial production process parameters when the theoretical phosphating performance does not meet the phosphating performance requirements or the theoretical mechanical properties do not meet the mechanical performance requirements, until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determine the modified initial production process parameters as the actual production process parameters.

[0154] Production module 340 is used to produce new pickled steel products according to actual production process parameters.

[0155] Optionally, the actual production process parameter determination module 330 is also used for:

[0156] Determine the steel grade for the new pickled steel products;

[0157] Based on the pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; wherein, the optimal phosphating performance database is used to store the production process parameters when the phosphating performance of pickled steel products of different steel grades is optimal.

[0158] Modify the initial production process parameters to the optimal production process parameters;

[0159] The optimized production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel products;

[0160] When the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters will be determined as the actual production process parameters.

[0161] Optionally, the production unit 300 also includes:

[0162] The first acquisition module is used to acquire historical sample data of pickled steel. The historical sample data includes at least historical production process parameters, as well as phosphating performance data and mechanical property data of pickled steel products produced under the historical production process parameters.

[0163] The preferred sample data filtering module is used to filter out historical sample data from historical sample data that have qualified phosphating performance and mechanical properties, and record them as preferred sample data;

[0164] The sample classification module is used to classify the preferred sample data according to steel grade, and obtain the preferred sample data for each steel grade;

[0165] The determination module is used to determine the optimal phosphating performance data for each steel grade, as well as the production process parameters under the optimal phosphating performance, based on the preferred sample data for each steel grade.

[0166] The optimal phosphating performance database construction module is used to store the optimal phosphating performance data and corresponding production process parameters for each steel grade into the database to construct the optimal phosphating performance database.

[0167] Optionally, the optimal phosphating performance database building module is also used for:

[0168] The optimal phosphating performance data for each steel grade is stored in the database;

[0169] When there is only one set of production process parameters corresponding to the optimal phosphating performance, this set of production process parameters is stored in the database.

[0170] When there are multiple sets of production process parameters corresponding to the optimal phosphating performance, the set with the best mechanical properties among the multiple sets of production process parameters is stored in the database.

[0171] Optionally, the production unit 300 also includes:

[0172] The second acquisition module is used to acquire historical sample data of pickled steel. The historical sample data includes at least historical production process parameters, as well as phosphating performance data and mechanical performance data of pickled steel products produced under the historical production process parameters.

[0173] The second sample classification module is used to classify historical sample data according to steel type, and obtain historical sample data for each steel type.

[0174] The neural network model building module is used to construct neural network models for different steel grades with production process parameters as input layer neurons and phosphating performance data and mechanical property data as output layer neurons.

[0175] The performance prediction model building module is used to input historical sample data of each steel grade into the corresponding neural network model for training and testing, so as to obtain performance prediction models for different steel grades.

[0176] Optionally, the performance prediction model building module is also used for:

[0177] The historical sample data for each steel grade is divided into training sample data and test sample data according to a set ratio;

[0178] The training sample data of each steel grade is input into the corresponding neural network model for training. The training process is optimized by a pre-set algorithm until the model converges, and the optimized initial performance prediction model of the corresponding steel grade is obtained.

[0179] The test sample data for each steel grade is input into the initial performance prediction model of the corresponding steel grade, and the test phosphating performance and test mechanical properties are output.

[0180] When the phosphating performance and mechanical properties test results meet the modeling requirements, the initial performance prediction model of the steel grade is used as the performance prediction model of the steel grade.

[0181] Optionally, the production process parameters include hot rolling process parameters and pickling process parameters.

[0182] It is understood that the device provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0183] This invention also provides an electronic device that may include a processor and a memory, wherein the processor and the memory may be interconnected via a bus or other means.

[0184] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0185] Memory may include mass storage for data or instructions. For example, and not limitingly, memory may include hard disk drives (HDDs), floppy disk drives, flash memory, optical disks, magneto-optical disks, magnetic tape, or Universal Serial Bus (USB) drives, or combinations of two or more of these. Where appropriate, memory may include removable or non-removable (or fixed) media. Where appropriate, memory may be internal or external to an electronic device. In a particular embodiment, memory may be non-volatile solid-state memory.

[0186] In one instance, the memory may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0187] The processor reads and executes computer program instructions stored in the memory to implement any of the pickling steel production methods with excellent phosphating performance described in the above embodiments.

[0188] In one example, the electronic device may further include a communication interface and a bus. The processor, memory, and communication interface are connected via the bus to communicate with each other. The communication interface is primarily used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. Where appropriate, the bus may include one or more buses.

[0189] Furthermore, in conjunction with the pickling steel production method with excellent phosphating performance described in the above embodiments, this invention can be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the pickling steel production methods with excellent phosphating performance described in the above embodiments.

[0190] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0191] This invention provides a method, apparatus, equipment, and medium for producing pickled steel with excellent phosphating performance. The initial production process parameters of the newly acquired pickled steel product can be input into a pre-constructed performance prediction model to quickly predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product. When the predicted theoretical phosphating performance or theoretical mechanical properties do not meet the requirements, the initial production process parameters need to be modified until they do. The initial production process parameters at which the requirements are met are then used as the actual production process parameters for the new pickled steel product. This method, through the constructed performance prediction model, can quickly verify the actual production process parameters of the new pickled steel product that meet the phosphating performance and mechanical property requirements, thus achieving the production of new pickled steel products with excellent phosphating performance. This method not only has a wide range of applications but also a short development cycle, significantly saving research and development costs.

[0192] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0193] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0194] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A method for producing pickled steel with excellent phosphating properties, characterized in that, The production method includes: Obtain the initial production process parameters, phosphating performance requirements, and mechanical property requirements for new pickled steel products; The initial production process parameters are input into a pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product produced using the initial production process parameters. When the theoretical phosphating performance does not meet the phosphating performance requirements, or the theoretical mechanical properties do not meet the mechanical performance requirements, the initial production process parameters are modified until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements. The modified initial production process parameters are then determined as the actual production process parameters. Produce the new pickled steel product according to the actual production process parameters. The process of modifying the initial production process parameters until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determining the modified initial production process parameters as the actual production process parameters, includes: Determine the steel grade for the new pickled steel products; Based on a pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; wherein, the optimal phosphating performance database is used to store the production process parameters when the phosphating performance of pickled steel products of different steel grades is optimal. Modify the initial production process parameters to the preferred production process parameters; The preferred production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product; When the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters are determined as the actual production process parameters. The production method further includes: Historical sample data of pickled steel is obtained, including at least historical production process parameters, and phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters. The mechanical property data includes yield strength, tensile strength, hardness, and elongation. The phosphating performance data includes film weight data, P ratio measurement data, and microscopic morphology images under an electron microscope. The production process parameters include hot rolling process parameters and pickling process parameters. The hot rolling process parameters include furnace exit temperature, initial rolling temperature, final rolling temperature, coiling temperature, and reduction per pass. The pickling process parameters include pickling temperature, acid concentration, pickling speed, rinsing water temperature, rinsing water conductivity, and drying temperature. From the historical sample data, historical sample data with qualified phosphating performance and mechanical properties are selected and recorded as preferred sample data; The preferred sample data is classified according to the steel grade to obtain the preferred sample data for each steel grade; Based on the preferred sample data for each steel grade, determine the optimal phosphating performance data for each steel grade, as well as the historical production process parameters under the optimal phosphating performance; The optimal phosphating performance data and the corresponding historical production process parameters for each steel grade are stored in a database to construct the optimal phosphating performance database. The step of storing the optimal phosphating performance data and the corresponding historical production process parameters for each steel grade in the database includes: The optimal phosphating performance data for each of the steel grades is stored in a database; When there is only one set of historical production process parameters corresponding to the optimal phosphating performance, this set of historical production process parameters is stored in the database. When there are multiple sets of historical production process parameters corresponding to the optimal phosphating performance, the set with the optimal mechanical properties among the multiple sets of historical production process parameters is stored in the database.

2. The production method according to claim 1, characterized in that, The production method further includes: Obtain historical sample data of pickled steel, wherein the historical sample data includes at least historical production process parameters, and phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters; The historical sample data is classified according to steel type to obtain the historical sample data for each steel type; A neural network model is constructed with input layer neurons representing the historical production process parameters and output layer neurons representing the phosphating performance data and the mechanical performance data for different steel grades. The historical sample data of each steel grade is input into the corresponding neural network model of the steel grade for training and testing to obtain the performance prediction model of different steel grades.

3. The production method according to claim 2, characterized in that, The step of inputting the historical sample data of each steel grade into the corresponding neural network model of the steel grade for training and testing to obtain the performance prediction model of different steel grades includes: The historical sample data for each steel grade is divided into training sample data and test sample data according to a set ratio; The training sample data of each steel grade is input into the neural network model of the corresponding steel grade for training. The training process is optimized by a pre-set algorithm until the model converges to obtain the optimized initial performance prediction model of the corresponding steel grade. The test sample data of each steel grade is input into the initial performance prediction model of the corresponding steel grade, and the test phosphating performance and test mechanical properties are output. When the tested phosphating performance and the tested mechanical properties meet the modeling requirements, the initial performance prediction model for each steel grade is used as the performance prediction model for each steel grade.

4. A pickling steel production apparatus with excellent phosphating performance, characterized in that, The production apparatus includes: The acquisition module is used to acquire the initial production process parameters, phosphating performance requirements, and mechanical property requirements of new pickled steel products. The theoretical performance prediction module is used to input the initial production process parameters into a pre-built performance prediction model to predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product produced using the initial production process parameters. The actual production process parameter determination module is used to modify the initial production process parameters when the theoretical phosphating performance does not meet the phosphating performance requirements or the theoretical mechanical properties do not meet the mechanical performance requirements, until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determine the modified initial production process parameters as the actual production process parameters. The production module is used to produce the new pickled steel product according to the actual production process parameters. The process of modifying the initial production process parameters until the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, and then determining the modified initial production process parameters as the actual production process parameters, includes: Determine the steel grade for the new pickled steel products; Based on a pre-constructed optimal phosphating performance database, the preferred production process parameters corresponding to the steel grade of the new pickled steel product are determined; wherein, the optimal phosphating performance database is used to store the production process parameters when the phosphating performance of pickled steel products of different steel grades is optimal. Modify the initial production process parameters to the preferred production process parameters; The preferred production process parameters are input into the performance prediction model to re-predict the theoretical phosphating performance and theoretical mechanical properties of the new pickled steel product; When the theoretical phosphating performance meets the phosphating performance requirements and the theoretical mechanical properties meet the mechanical performance requirements, the preferred production process parameters are determined as the actual production process parameters. The device further includes: The first acquisition module is used to acquire historical sample data of pickled steel. The historical sample data includes at least historical production process parameters, and phosphating performance data and mechanical property data of the pickled steel products produced under the historical production process parameters. The mechanical property data includes yield strength, tensile strength, hardness, and elongation. The phosphating performance data includes film weight data, P ratio measurement data, and microscopic morphology images under an electron microscope. The production process parameters include hot rolling process parameters and pickling process parameters. The hot rolling process parameters include furnace exit temperature, initial rolling temperature, final rolling temperature, coiling temperature, and reduction per pass. The pickling process parameters include pickling temperature, acid concentration, pickling speed, rinsing water temperature, rinsing water conductivity, and drying temperature. The preferred sample data screening module is used to screen out historical sample data from the historical sample data that have qualified phosphating performance and mechanical properties, and record them as preferred sample data; The sample classification module is used to classify the preferred sample data according to the steel grade to obtain the preferred sample data for each steel grade; The determination module is used to determine the optimal phosphating performance data for each steel grade, and the historical production process parameters under the optimal phosphating performance, based on the preferred sample data for each steel grade. The optimal phosphating performance database construction module is used to store the optimal phosphating performance data and the corresponding historical production process parameters of each steel grade into the database to construct the optimal phosphating performance database. The step of storing the optimal phosphating performance data and the corresponding historical production process parameters for each steel grade in the database includes: The optimal phosphating performance data for each of the steel grades is stored in a database; When there is only one set of historical production process parameters corresponding to the optimal phosphating performance, this set of historical production process parameters is stored in the database. When there are multiple sets of historical production process parameters corresponding to the optimal phosphating performance, the set with the optimal mechanical properties among the multiple sets of historical production process parameters is stored in the database.

5. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the production method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the production method according to any one of claims 1-3.

Images