Rolling force prediction model construction method, rolling force prediction method and device and medium
By constructing a rolling force prediction model, using the neuron network model to accurately predict and self-optimize the rolling force, the shortcomings of traditional models in adapting to product differentiation and operating conditions are solved, and the production efficiency and intelligence level are improved.
Patent Information
- Application Number
- CN202411035967.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-08
AI Technical Summary
The traditional rolling force budget model is difficult to adapt to product differentiated control needs and changes in working conditions, and lacks self-learning and adaptability, resulting in instability and inefficiency of the production process.
A rolling force prediction model is constructed, and a feature parameter data is extracted by obtaining historical rolling source data, a feature parameter data set is constructed, and a neuronal network model is used for training and optimization, so as to achieve accurate prediction and self-optimization of rolling force.
It improves the accuracy and production efficiency of rolling force, meets customer personalized needs, reduces production costs and the complexity of manual intervention, and improves the level of production intelligence.
Smart Images

Figure CN118904935A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of rolling technology, and in particular to a rolling force prediction model construction method, a rolling force prediction method and device, and a medium. Background Art
[0002] In the cold rolling and tempering process of the steel industry, accurate budgeting and control of rolling force is essential to ensure product quality, improve production efficiency and meet customer needs. However, in the actual production process, due to the complexity of product differentiation control requirements and the frequent changes in working conditions and customer needs, the traditional rolling force budgeting model faces severe challenges.
[0003] Specifically, even for the same type of steel, the rolling force requirements vary significantly due to different control objectives, working conditions and customer needs. Traditional control schemes often lack sufficient consideration of these changing factors, resulting in a serious lag in the pre-calculation of rolling force in terms of adaptability and intelligence. This not only affects the stability and controllability of the production process, but may also lead to unstable product quality and fail to meet the personalized needs of customers.
[0004] In addition, traditional rolling force budget models are often based on fixed mathematical models and empirical formulas, which are difficult to effectively deal with uncertainties and changes in the production process. They lack self-learning and adaptive capabilities and can only rely on continuous manual optimization and control. This not only increases the complexity and cost of manual intervention, but also limits the level of intelligence and efficiency of the production process. Summary of the invention
[0005] In view of the above problems, the present invention is proposed to provide a rolling force prediction model construction method, rolling force prediction method and device, and medium that overcome the above problems or at least partially solve the above problems. By constructing a rolling force prediction model, the budget strategy of rolling force can be automatically adjusted according to different products, equipment and customer needs to adapt to various changes in the production process. At the same time, the model also has self-learning and self-adaptive capabilities, and can use the latest production data for self-optimization and improvement, improve the accuracy and reliability of the model, and thus help improve production efficiency and intelligence level.
[0006] In a first aspect, a rolling force prediction model construction method is provided for predicting the rolling force of a skin pass mill, the method comprising:
[0007] Acquire historical rolling source data of the skin-pass mill, extract characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data, wherein the characteristic parameter data at least includes the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness;
[0008] Constructing a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force;
[0009] The pre-constructed rolling force neural network model is trained, evaluated and optimized according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
[0010] Optionally, constructing a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force includes:
[0011] The characteristic parameter data is used as input data, and the rolling force corresponding to the characteristic parameter is used as target output data, so as to construct a characteristic parameter data set including the input data and the target output data.
[0012] Optionally, the pre-built rolling force neural network model is a deep neural network model, comprising five input layers, a hidden layer and an output layer, wherein the input features of the input layer are the characteristic parameter data, and the output result of the output layer is the predicted rolling force.
[0013] Optionally, the pre-built rolling force neural network model is trained, evaluated and optimized according to the characteristic parameter data set to obtain an optimized rolling force prediction model, including:
[0014] Dividing the characteristic parameter data set into a training set and a test set;
[0015] Based on the training set, training the pre-built rolling force neural network model;
[0016] Based on the test set, evaluating the stability and prediction accuracy of the trained rolling force neural network model to obtain an evaluation result;
[0017] When the evaluation result shows that the rolling force neural network model does not meet the standard, the rolling force neural network model is optimized according to a set optimization strategy to obtain an optimized rolling force prediction model.
[0018] Optionally, based on the test set, the prediction accuracy of the trained rolling force neural network model is evaluated, including:
[0019] Inputting the characteristic parameter data in the test set into the trained rolling force neural network model to obtain the predicted rolling force output by the rolling force neural network model;
[0020] Determining a difference between the predicted rolling force and a target rolling force, wherein the target rolling force is a rolling force corresponding to the input characteristic parameter data in the test set;
[0021] When the difference is within a preset difference threshold range, outputting the rolling force neural network model as meeting the standard;
[0022] When the difference is outside the preset difference threshold range, the output of the rolling force neural network model does not meet the standard.
[0023] Optionally, when the evaluation result is that the rolling force prediction model does not meet the standard, optimizing the rolling force prediction model according to a set optimization strategy includes:
[0024] When the evaluation result is that the rolling force prediction model does not meet the standard, determining that the rolling product type corresponding to the characteristic parameter data input into the rolling force prediction model is a target product;
[0025] Acquire historical rolling source data when the skin-pass mill rolls the target product, extract characteristic parameter data and corresponding rolling force corresponding to the target product from the historical rolling source data, and construct an optimization set;
[0026] Based on the optimization set, the rolling force neural network model is optimized by using an incremental self-learning method.
[0027] In a second aspect, a rolling force prediction model construction device is provided for predicting the rolling force of a skin pass mill, the device comprising:
[0028] A parameter extraction module, used to obtain historical rolling source data of the skin-pass mill, and extract characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data, wherein the characteristic parameter data at least includes the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness;
[0029] A data set building module, used to build a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force;
[0030] The model building module is used to train, evaluate and optimize the pre-built rolling force neural network model according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
[0031] In a third aspect, a rolling force prediction method is provided for predicting the rolling force of a skin pass mill, the method comprising:
[0032] Extracting target characteristic parameter data from the material properties and process requirements of the product to be rolled, wherein the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements;
[0033] The target characteristic parameters are input into the rolling force prediction model constructed according to the method described in the first aspect to obtain the predicted rolling force.
[0034] In a fourth aspect, a rolling force prediction device is provided for predicting the rolling force of a skin pass mill, the device comprising:
[0035] A parameter extraction module is used to extract target characteristic parameter data from the material properties and process requirements of the product to be rolled, wherein the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements;
[0036] A rolling force prediction module is used to input the target characteristic parameters into the rolling force prediction model constructed according to the method described in the first aspect to obtain a predicted rolling force.
[0037] In a fifth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the rolling force prediction model construction method as described in the first aspect.
[0038] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:
[0039] The embodiment of the present invention provides a rolling force prediction model construction method, rolling force prediction method and device, and medium. By extracting characteristic parameter data affecting the rolling force, including the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness, and the rolling force corresponding to the characteristic parameter data, a characteristic parameter data set is constructed, and then the pre-constructed rolling force neural network model is trained, evaluated and optimized according to the constructed characteristic parameter data set to obtain an optimized rolling force prediction model for predicting the rolling force of the leveling mill. The model establishment process integrates the rolling process technology, product characteristics, model training and optimization of the leveling mill and other key fields of technology, aiming to achieve accurate budgeting and self-learning of rolling force. Therefore, the model can automatically adjust the budget and control strategy of the rolling force according to different products, equipment and customer needs to adapt to various changes in the production process. At the same time, the model also has self-learning and self-adaptive capabilities, and can use the latest production data for self-optimization and improvement, improve the accuracy and reliability of the model, thereby facilitating the improvement of production efficiency and intelligence level, and is of great significance for meeting the personalized needs of customers, reducing production costs and improving the competitiveness of enterprises.
[0040] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] 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 invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0042] Figure 1 It is a flow chart of a rolling force prediction model construction method provided by an embodiment of the present invention;
[0043] Figure 2 is a structural schematic diagram of a neural network model provided by an embodiment of the present invention;
[0044] Figure 3 is a schematic diagram of a loss function used in a model training process provided by an embodiment of the present invention;
[0045] Figure 4 is a schematic diagram of the difference between a predicted rolling force and a target rolling force provided by an embodiment of the present invention;
[0046] Figure 5 is a flow chart of a model incremental self-learning process provided by an embodiment of the present invention;
[0047] Figure 6 It is a structural block diagram of a rolling force prediction model building device provided by an embodiment of the present invention;
[0048] Figure 7 is a flow chart of a rolling force prediction method provided by an embodiment of the present invention;
[0049] Figure 8 It is a structural block diagram of a rolling force prediction device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0050] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.
[0051] Various structural schematic diagrams according to embodiments of the present disclosure are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may further design regions / layers with different shapes, sizes, and relative positions according to actual needs.
[0052] In order to better understand the above-mentioned technical scheme, the above-mentioned technical scheme will be described in detail below in combination with specific implementation methods. It should be understood that the embodiments of the present disclosure and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.
[0053] Figure 1 is a flow chart of a rolling force prediction model construction method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes steps S110 to S130, which are specifically as follows:
[0054] Step S110, obtaining historical rolling source data of the leveling mill, extracting characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data, wherein the characteristic parameter data at least includes the yield strength of the rolled material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness.
[0055] Specifically, historical rolling source data within a set number or a set time period can be obtained according to different product types. For example, for Class A products, the first X1 source data of historical rolling of the same Class A product, or all source data within the historical time period t1 (t can be several months or several years, etc., without limitation) can be obtained, and each source data includes the above-mentioned characteristic parameter data and the rolling force corresponding to the characteristic parameter data; for Class B products, the first X2 source data of historical rolling of the same Class B product, or all source data within the historical time period t2 can be obtained. Specifically, it can be obtained according to actual needs, and this embodiment does not limit this.
[0056] In this embodiment, the differentiated control requirements of products are taken into consideration: that is, the control targets of the same type of steel are very different. Moreover, with the changes in working conditions and customer needs, the control focus of the same product is different, which leads to different requirements for its rolling force. In the process of realizing the present invention, it is found that the differentiated requirements of products, equipment and customers are mainly related to the parameters such as the yield strength of the material, rolling speed, rolling temperature, diameter of the roll and surface roughness. Therefore, the present invention extracts the above parameters as characteristic parameter data to construct a rolling force prediction model to meet the differentiated control requirements of products, working conditions and customers as much as possible, and improve the adaptability and budget accuracy of the model.
[0057] Optionally, before executing step S120, the method may further include:
[0058] Preprocess the extracted characteristic parameter data.
[0059] Specifically, this can include removing noise, outliers, missing values, etc. from the data to ensure the quality and consistency of the data. Perform necessary transformations on the data, such as scaling and normalization, so that the model can better process the data.
[0060] Step S120: construct a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force.
[0061] Specifically, the characteristic parameter data is used as input data, and the rolling force corresponding to the characteristic parameter is used as target output data, so as to construct a characteristic parameter data set including the input data and the target output data.
[0062] Step S130: training, evaluating and optimizing the pre-constructed rolling force neural network model according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
[0063] Optional, pre-built rolling force neural network model as a deep neural network model, Figure 2 is a schematic diagram of the structure of a neural network model provided by an embodiment of the present invention, such as Figure 2As shown in the figure, the deep neural network model includes an input layer (x1~xn), a hidden layer (h11~h1n, ..., hm1~hmn), and an output layer (y1~yn). The input layer is the beginning of the neural network, which receives raw data or features. The number of neurons in the input layer usually matches the number of features of the input data. There can be one or more hidden layers between the input layer and the output layer. The number of hidden layers and the number of neurons in each layer can be adjusted according to the complexity of the problem and the required learning ability. The layers are fully connected, that is, each neuron in each layer is connected to each neuron in the next layer. In each hidden layer, the neurons perform a weighted sum of the inputs and apply an activation function (such as ReLU, Sigmoid, or tanh) to produce outputs. These outputs will serve as inputs to the next layer.
[0064] In this embodiment, the pre-built rolling force neural network model includes five input layers, a hidden layer and an output layer, wherein the input features of the input layer are feature parameter data, and the output result of the output layer is the predicted rolling force. The rolling force budget model is constructed by adopting a deep neural network model to achieve accurate prediction and intelligent control of the rolling force.
[0065] Optionally, step S130 includes:
[0066] The first step is to divide the feature parameter data set into a training set and a test set;
[0067] The second step is to train the pre-built rolling force neural network model based on the training set;
[0068] In this embodiment, the trained rolling force neural network model can be stored to facilitate subsequent evaluation and optimization of the model.
[0069] The third step is to evaluate the stability and prediction accuracy of the trained rolling force neural network model based on the test set and obtain the evaluation results;
[0070] Since the training process of the model is to find the minimum value of the loss function. This can usually be achieved by using the back propagation algorithm, gradient descent algorithm (SGD) or Adam algorithm, and adjusted according to the actual situation. At the same time, in order to prevent overfitting and improve the generalization ability of the model, some regularization techniques such as L1 regularization and L2 regularization can be used. The parameters of the model are continuously adjusted through the training set to gradually reduce the loss function. Therefore, the stability of the trained rolling force neural network model can be evaluated according to the loss function. Among them, the loss function is a function used to measure the difference between the model prediction value and the true value. Figure 3 is a schematic diagram of a loss function used in a model training process provided by an embodiment of the present invention, such as Figure 3As shown in the figure, after selecting a suitable loss function, during the model training process, each round of iteration will calculate a loss value based on the current model parameters. This loss value is a specific quantification of the difference between the model prediction value and the true value. During the training process, it is necessary to constantly monitor the change of the loss value. If the loss value gradually decreases, it means that the model is gradually learning and optimizing; if the loss value fluctuates or increases, the model parameters may need to be adjusted. In addition to monitoring the change of the loss value on the training set, the test set is also needed to evaluate the performance of the model. Calculating the loss value on the test set can more objectively reflect the generalization ability of the model. If the loss value of the model on the test set also gradually decreases, it means that the model has good generalization ability; if the loss value on the test set increases, it may be overfitting, and measures need to be taken to prevent overfitting. In order to more accurately evaluate the performance of the model, the loss value of the current model can be compared with the loss value of the benchmark model. If the loss value of the current model is significantly lower than the loss value of the benchmark model, it means that the current model has better stability.
[0071] Optionally, based on the test set, the prediction accuracy of the trained rolling force neural network model is evaluated, including:
[0072] The characteristic parameter data in the test set is input into the trained rolling force neural network model to obtain the predicted rolling force output by the rolling force neural network model; the difference between the predicted rolling force and the target rolling force is determined, and the target rolling force is the rolling force corresponding to the input characteristic parameter data in the test set; when the difference is within the preset difference threshold range, the output rolling force neural network model meets the standard; when the difference is outside the preset difference threshold range, the output rolling force neural network model does not meet the standard.
[0073] Figure 4 is a schematic diagram of the difference between a predicted rolling force and a target rolling force provided by an embodiment of the present invention, such as Figure 4 As shown, the abscissa represents the predicted rolling force F 预 , the ordinate represents the target rolling force F 目 , when the point is located on the line S, it means that the difference between the predicted rolling force and the target rolling force is 0. The preset difference threshold range can be set according to actual needs and is not limited to this.
[0074] It should be noted that in this embodiment, the model is evaluated mainly by the two indicators of loss function and prediction accuracy. In practice, other evaluation indicators may be combined, such as recall rate, F1 value, etc., which are not limited in the present invention. When the evaluation result of the model from any indicator is not up to standard, the output evaluation result is not up to standard.
[0075] Step 4: When the evaluation result shows that the rolling force neural network model does not meet the standards, the rolling force neural network model is optimized according to the set optimization strategy to obtain the optimized rolling force prediction model.
[0076] On the contrary, when the evaluation result shows that the rolling force neural network model meets the standards, there is no need to optimize the rolling force neural network model and it can be directly used as the rolling force prediction model.
[0077] In an implementation of this embodiment, when the evaluation result is that the rolling force prediction model does not meet the standard, the rolling force prediction model is optimized according to the set optimization strategy, including:
[0078] When the evaluation result is that the rolling force prediction model does not meet the standards, the rolling product type corresponding to the characteristic parameter data input into the rolling force prediction model is determined to be the target product; the historical rolling source data when the flat mill rolls the target product is obtained, and the characteristic parameter data and the corresponding rolling force corresponding to the target product are extracted from the historical rolling source data to construct an optimization set; based on the optimization set, the rolling force neural network model is optimized using an incremental self-learning method.
[0079] By optimizing the model using incremental self-learning, the model's ability to quickly learn new tasks can be enhanced, making the model able to adapt to changes in real time. When new data flows in, the model can be updated and optimized immediately to quickly adapt to changing data. Incremental self-learning can continue to learn new data based on the original model without retraining the entire model, thereby improving the generalization effect of the model and reducing the risk of overfitting. At the same time, the incremental self-learning model needs to store less data at a time, which helps save memory and storage space and achieve efficient use of resources.
[0080] It should be noted that the newly introduced data of the incremental self-learning model, that is, the data in the optimization set, can also be quality controlled and preprocessed to avoid the impact of noise data and outliers on the model. At the same time, online learning techniques such as small batch updates and learning rate decay can also be used to improve model accuracy. Ultimately, the model can adapt to changes in product characteristics and process requirements, thereby improving the model's prediction accuracy and generalization ability.
[0081] Figure 5 is a flow chart of a model incremental self-learning process provided by an embodiment of the present invention, such as Figure 5As shown, after receiving the steel coil output telegram, the Java class is loaded by executing an external process to execute the executable exe file. The executable exe file executes the online self-learning process, that is, by connecting to the Oracle database to calculate the deviation between the predicted value and the actual value, and write it to the database, and then read the historical data of similar products to evaluate the model accuracy to determine whether the model meets the standard. When the model meets the standard, the database link is ended and no incremental self-learning is performed; when the model does not meet the standard, the category (i.e., the target product) is marked and written to the database for data collection. If the incremental data collected is greater than or equal to 1000 and the production line is stopped, the model is incrementally self-learned, and then the latest model accuracy is evaluated to meet the standard. After meeting the standard, the data table is cleared, the database link is ended, and the incremental self-learning is completed; if the incremental data is not greater than or equal to 1000, or the production line is not stopped, the database link is directly ended without incremental self-learning.
[0082] In other implementations of this embodiment, the rolling force prediction model can also be optimized by adjusting model parameters and structure, or preprocessing data, so that the model can adapt to changes in different process conditions and product requirements, thereby maintaining its good prediction performance.
[0083] In this embodiment, the optimized model can be embedded into the existing production line process control database and integrated into the production line process control system to achieve real-time rolling force budgeting.
[0084] The present invention applies deep learning technology to the rolling force budget of the leveler, and realizes accurate budgeting and self-learning of rolling force by integrating technologies in multiple fields such as rolling process technology, product characteristics, data processing and analysis, and deep learning. This will help improve the prediction accuracy of rolling force setting value, production efficiency, product quality and equipment life, and bring significant economic benefits to the enterprise. And the friendly user interface enables the model to be integrated into other systems such as the secondary system of the production line, realizes the monitoring and self-learning optimization mechanism of rolling force, improves the pre-calculation accuracy of the rolling force of the leveler, expands the adaptability of the model, improves the adaptive ability of the model, reduces the maintenance difficulty of engineers, and provides pan-intelligent support for product process control in combination with the quality control needs of the market. The innovative use of rolling speed for direct pre-calculation of the rolling force of the leveler provides accurate budget data for the speed feedforward control of the rolling force of the leveler. The present invention can also provide strong support for the production decision-making of enterprises, help enterprises realize refined and intelligent production management, and improve the core competitiveness of enterprises.
[0085] Based on the same inventive concept, an embodiment of the present invention provides a device for implementing the rolling force prediction model construction method in the above embodiment. Figure 6 is a structural block diagram of a rolling force prediction model building device provided by an embodiment of the present invention, such as Figure 6As shown, the device 600 includes a parameter extraction module 610 , a data set establishment module 620 and a model establishment module 630 .
[0086] The parameter extraction module 610 is used to obtain the historical rolling source data of the leveling mill, and extract the characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data. The characteristic parameter data at least includes the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness. The data set establishment module 620 is used to construct a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force. The model establishment module 630 is used to train, evaluate and optimize the pre-constructed rolling force neural network model according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
[0087] Optionally, the data set establishing module 620 is used to:
[0088] The characteristic parameter data is taken as input data, and the rolling force corresponding to the characteristic parameter is taken as target output data, so as to construct a characteristic parameter data set including the input data and the target output data.
[0089] Optionally, the pre-built rolling force neural network model is a deep neural network model, including five input layers, a hidden layer and an output layer, wherein the input features of the input layer are feature parameter data, and the output result of the output layer is the predicted rolling force.
[0090] Optionally, the model building module 630 includes:
[0091] A data set division unit, used for dividing the feature parameter data set into a training set and a test set;
[0092] A model training unit, used for training a pre-built rolling force neural network model based on a training set;
[0093] A model evaluation unit, used to evaluate the stability and prediction accuracy of the trained rolling force neural network model based on a test set to obtain an evaluation result;
[0094] The model optimization unit is used to optimize the rolling force neural network model according to the set optimization strategy when the evaluation result shows that the rolling force neural network model does not meet the standards, so as to obtain the optimized rolling force prediction model.
[0095] Optionally, the model evaluation unit is also used to:
[0096] The characteristic parameter data in the test set is input into the trained rolling force neural network model to obtain the predicted rolling force output by the rolling force neural network model; the difference between the predicted rolling force and the target rolling force is determined, and the target rolling force is the rolling force corresponding to the input characteristic parameter data in the test set; when the difference is within the preset difference threshold range, the output rolling force neural network model meets the standard; when the difference is outside the preset difference threshold range, the output rolling force neural network model does not meet the standard.
[0097] Optionally, the model optimization unit is also used to:
[0098] When the evaluation result is that the rolling force prediction model does not meet the standards, the rolling product type corresponding to the characteristic parameter data input into the rolling force prediction model is determined to be the target product; the historical rolling source data when the flat mill rolls the target product is obtained, and the characteristic parameter data and the corresponding rolling force corresponding to the target product are extracted from the historical rolling source data to construct an optimization set; based on the optimization set, the rolling force neural network model is optimized using an incremental self-learning method.
[0099] The specific details of the rolling force prediction model construction method used in the above-mentioned device can be understood by corresponding to the relevant descriptions and effects in the above-mentioned rolling force prediction model construction method embodiment, and will not be repeated here.
[0100] Based on the same inventive concept, an embodiment of the present invention provides a rolling force prediction method, which uses the rolling force prediction model constructed in the above embodiment to predict the rolling force of the skin pass mill. Figure 7 is a flow chart of a rolling force prediction method provided by an embodiment of the present invention, such as Figure 7 As shown, the method includes:
[0101] Step S710, extracting target characteristic parameter data from the material properties and process requirements of the product to be rolled, wherein the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements.
[0102] Step S720: input the target characteristic parameters into a pre-built rolling force prediction model to obtain a predicted rolling force.
[0103] The rolling force prediction model pre-constructed in step S720 is composed of Figure 1The rolling force prediction model construction method described in the corresponding embodiment is constructed. The specific details of the rolling force prediction model construction method can be understood by corresponding to the relevant descriptions and effects in the above-mentioned rolling force prediction model construction method embodiment, which will not be repeated here. The model has been applied to the rolling force prediction of the 1-5# galvanizing, 8# galvanizing, 1# continuous annealing, and 2# continuous annealing of Shougang Jingtang United Iron and Steel Co., Ltd. in the form of a database link in the secondary process control system.
[0104] Based on the same inventive concept, an embodiment of the present invention further provides a device for implementing the rolling force prediction method in the above embodiment. Figure 8 is a structural block diagram of a rolling force prediction device provided by an embodiment of the present invention, such as Figure 8 As shown, the device 800 includes a parameter extraction module 810 and a rolling force prediction module 820 .
[0105] The parameter extraction module 810 is used to extract target characteristic parameter data from the material properties and process requirements of the product to be rolled, and the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements. The rolling force prediction module 820 is used to input the target characteristic parameters into a pre-built rolling force prediction model to obtain the predicted rolling force.
[0106] Among them, the rolling force prediction model pre-constructed in this embodiment is composed of Figure 1 The rolling force prediction model construction method described in the corresponding embodiment is constructed. The specific details of the rolling force prediction model construction method can be understood by corresponding related descriptions and effects in the rolling force prediction model construction method embodiment shown above, and will not be repeated here.
[0107] Optionally, the present invention also provides a computer product, which includes a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute to implement the rolling force prediction model construction method of the above method embodiment.
[0108] The technical solutions provided in the above embodiments of the present application have at least the following technical effects or advantages:
[0109] The embodiment of the present invention provides a rolling force prediction model construction method, rolling force prediction method and device, and medium. By extracting characteristic parameter data affecting the rolling force, including the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness, and the rolling force corresponding to the characteristic parameter data, a characteristic parameter data set is constructed, and then the pre-constructed rolling force neural network model is trained, evaluated and optimized according to the constructed characteristic parameter data set to obtain an optimized rolling force prediction model for predicting the rolling force of the leveling mill. The model establishment process integrates the rolling process technology, product characteristics, model training and optimization of the leveling mill and other key fields of technology, aiming to achieve accurate budgeting and self-learning of rolling force. Therefore, the model can automatically adjust the budget and control strategy of the rolling force according to different products, equipment and customer needs to adapt to various changes in the production process. At the same time, the model also has self-learning and self-adaptive capabilities, and can use the latest production data for self-optimization and improvement, improve the accuracy and reliability of the model, thereby facilitating the improvement of production efficiency and intelligence level, and is of great significance for meeting the personalized needs of customers, reducing production costs and improving the competitiveness of enterprises.
[0110] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.
[0111] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.
[0112] It should be noted that the above-mentioned embodiments illustrate rather than limit the invention and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims.
Claims
1. A method for constructing a rolling force prediction model, characterized in that: For predicting the rolling force of a skin-pass mill, the method comprises: Acquire historical rolling source data of the skin-pass mill, extract characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data, wherein the characteristic parameter data at least includes the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness; Constructing a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force; The pre-constructed rolling force neural network model is trained, evaluated and optimized according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
2. The method according to claim 1, characterized in that The step of constructing a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force includes: The characteristic parameter data is used as input data, and the rolling force corresponding to the characteristic parameter is used as target output data, so as to construct a characteristic parameter data set including the input data and the target output data.
3. The method according to claim 1, characterized in that The pre-constructed rolling force neural network model is a deep neural network model, including five input layers, a hidden layer and an output layer, wherein the input feature of the input layer is the characteristic parameter data, and the output result of the output layer is the predicted rolling force.
4. The method according to claim 1, characterized in that: The method of training, evaluating and optimizing the pre-built rolling force neural network model according to the characteristic parameter data set to obtain an optimized rolling force prediction model includes: Dividing the characteristic parameter data set into a training set and a test set; Based on the training set, training the pre-built rolling force neural network model; Based on the test set, evaluating the stability and prediction accuracy of the trained rolling force neural network model to obtain an evaluation result; When the evaluation result shows that the rolling force neural network model does not meet the standard, the rolling force neural network model is optimized according to a set optimization strategy to obtain an optimized rolling force prediction model.
5. The method according to claim 4, characterized in that Based on the test set, the prediction accuracy of the trained rolling force neural network model is evaluated, including: Inputting the characteristic parameter data in the test set into the trained rolling force neural network model to obtain the predicted rolling force output by the rolling force neural network model; Determining a difference between the predicted rolling force and a target rolling force, wherein the target rolling force is a rolling force corresponding to the input characteristic parameter data in the test set; When the difference is within a preset difference threshold range, outputting the rolling force neural network model as meeting the standard; When the difference is outside the preset difference threshold range, the output of the rolling force neural network model does not meet the standard.
6. The method according to claim 5, characterized in that When the evaluation result shows that the rolling force prediction model does not meet the standard, optimizing the rolling force prediction model according to a set optimization strategy includes: When the evaluation result is that the rolling force prediction model does not meet the standard, determining that the rolling product type corresponding to the characteristic parameter data input into the rolling force prediction model is a target product; Acquire historical rolling source data when the skin-pass mill rolls the target product, extract characteristic parameter data and corresponding rolling force corresponding to the target product from the historical rolling source data, and construct an optimization set; Based on the optimization set, the rolling force neural network model is optimized by using an incremental self-learning method.
7. A rolling force prediction model construction device, characterized in that: For predicting the rolling force of a skin-pass mill, the device comprises: A parameter extraction module, used to obtain historical rolling source data of the skin-pass mill, and extract characteristic parameter data affecting the rolling force and the rolling force corresponding to the characteristic parameter data from the historical rolling source data, wherein the characteristic parameter data at least includes the yield strength of the rolling material, the rolling speed, the rolling temperature, the diameter of the roll and the surface roughness; A data set building module, used to build a characteristic parameter data set according to the characteristic parameter data and the corresponding rolling force; The model building module is used to train, evaluate and optimize the pre-built rolling force neural network model according to the characteristic parameter data set to obtain an optimized rolling force prediction model.
8. A rolling force prediction method, characterized in that: For predicting the rolling force of a skin-pass mill, the method comprises: Extracting target characteristic parameter data from the material properties and process requirements of the product to be rolled, wherein the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements; The target characteristic parameters are input into the rolling force prediction model constructed according to the method according to any one of claims 1 to 6 to obtain the predicted rolling force.
9. A rolling force prediction device, characterized in that: For predicting the rolling force of a skin-pass mill, the device comprises: A parameter extraction module is used to extract target characteristic parameter data from the material properties and process requirements of the product to be rolled, wherein the target characteristic parameter data includes the yield strength of the product to be rolled, and the target rolling speed, target rolling temperature, target diameter of the roll and target surface roughness required in the process requirements; A rolling force prediction module is used to input the target characteristic parameters into a rolling force prediction model constructed according to the method described in any one of claims 1 to 6 to obtain a predicted rolling force.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the rolling force prediction model construction method according to any one of claims 1-6.
Citation Information
Patent Citations
Finish rolling force prediction method based on SA-SCSO-TSVR algorithm
CN116689515A
Casting blank defect online prediction method
CN116822315A
Rod and wire rolling force prediction method and device based on finite element and neural network
CN117473833A
