Method and device for predicting plate shape quality of thick steel plate guided by forward process
By using a forward process-guided approach and integrating the characteristics of each process in thick plate production with convolutional neural networks and collaborative attention mechanisms, the problem of insufficient accuracy in the thick plate shape quality prediction model was solved, achieving higher prediction accuracy and production guidance effect.
Patent Information
- Application Number
- CN202410852764.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-06-28
AI Technical Summary
Existing technologies cannot adequately consider the interrelationships between various processes in thick plate production from a holistic perspective, resulting in insufficient accuracy of thick plate shape quality prediction models.
The forward process-guided approach is adopted. By acquiring multi-source heterogeneous data from the entire thick plate production process, and after data cleaning, interpolation and dimensionality reduction, process features are extracted using a convolutional neural network, and feature fusion is performed using a collaborative attention mechanism. Finally, the data is input into a pre-trained prediction model to predict plate shape quality.
It improves the accuracy of thick plate shape quality prediction, better assists on-site production decision-making, and fully considers the interaction and influence between various processes.
Smart Images

Figure CN118917454A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of intelligent modeling of complex industrial processes, and in particular relates to a method and device for predicting the shape quality of a steel thick plate guided by a forward process. Background Art
[0002] As one of the important products of the steel industry, thick plates have the characteristics of diverse product types, stable quality, different performances and a wide range of applications. Therefore, countries around the world attach great importance to the product quality of thick plates. Improving the quality of thick plate products can not only ensure safety in subsequent use, but also reduce the loss of thick plate manufacturing companies, and further promote the steel manufacturing industry to move towards intelligence and digitalization.
[0003] The thick plate production process is very complex and is a typical process industry process. Its production goal is to obtain products with superior performance, qualified quality and standard plate shape. In order to achieve this goal, the thick plate production process must be monitored in real time and effectively controlled. Thick plate production consists of a series of processes, and the output of the previous process is the input of the next process, which mainly includes heating process, rolling process and cooling process. Regarding whether the quality of the final thick plate product is qualified, the company currently evaluates it mainly from five aspects, namely, the size, shape, performance, surface and internal quality of the thick plate product. Among them, the relationship between the quality of the thick plate shape and the production process is very close, requiring the most stringent control of the entire production process. In addition, the thick plate shape, as one of the key indicators for evaluating the quality of thick plate products, will directly affect the final yield rate of the thick plate. Thick plate manufacturing companies should improve the quality of products as much as possible with low production costs and low energy losses. Therefore, finding the relationship between the production process and the final thick plate shape quality and establishing an accurate thick plate shape quality prediction model are important issues that need to be solved urgently. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present application proposes a forward process-guided steel thick plate shape quality prediction method and device.
[0005] In a first aspect, the present application proposes a forward process-guided steel plate shape quality prediction method, comprising:
[0006] Acquire multi-source heterogeneous data of the entire thick plate production process;
[0007] Preprocessing multi-source heterogeneous data of the entire thick plate production process;
[0008] According to different processes, feature extraction is performed on the pre-processed multi-source heterogeneous data of the entire thick plate production process to obtain the features corresponding to different processes;
[0009] Input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fused features;
[0010] The fusion features are input into a pre-trained prediction model to obtain a prediction result of the shape quality of the steel thick plate.
[0011] The preprocessing of multi-source heterogeneous data of the entire thick plate production process includes:
[0012] Performing data cleaning on multi-source heterogeneous data of the entire thick plate production process;
[0013] Interpolate the multi-source heterogeneous data of the entire thick plate production process after data cleaning to obtain multi-source heterogeneous data of equal length;
[0014] The high-dimensional data in the multi-source heterogeneous data of the entire thick plate production process is reduced in dimension to obtain the source heterogeneous data after dimension reduction.
[0015] The feature extraction is performed on the pre-processed multi-source heterogeneous data of the entire thick plate production process according to different processes to obtain features corresponding to different processes, including:
[0016] According to different processes, multi-source heterogeneous data of equal length and source heterogeneous data after dimensionality reduction are divided into variables;
[0017] According to the time sequence of different processes, the multi-source heterogeneous data of equal length after the variables are divided and the source heterogeneous data after dimensionality reduction are spliced;
[0018] Normalize the spliced multi-source heterogeneous data;
[0019] The normalized multi-source heterogeneous data are input into different convolutional neural networks corresponding to different processes for feature extraction to obtain the features corresponding to different processes.
[0020] The different convolutional neural networks include: a convolutional layer, an attenuation layer, a flattening layer and a fully connected layer.
[0021] The different processes include: a heating process, a rolling process and a cooling process.
[0022] The pre-trained collaborative attention mechanism model includes:
[0023] A first collaborative attention layer and a second collaborative attention layer; the first collaborative attention layer includes: a first query vector, a first key vector and a first value vector; the second collaborative attention layer includes: a second query vector, a second key vector and a second value vector; the characteristics of the heating process are superimposed in the first query vector as the input of the first collaborative attention layer, the characteristics of the rolling process are superimposed in the first key vector and the first value vector respectively as the attention weight of the first collaborative attention layer, the output of the first collaborative attention layer is superimposed in the second query vector as the input of the second collaborative attention layer, the cooling process is superimposed in the second key vector and the second value vector respectively as the attention weight of the second collaborative attention layer, and the output of the second collaborative attention layer is used as the fusion feature.
[0024] The pre-trained prediction model is a single-layer fully connected network.
[0025] In a second aspect, the present application proposes a forward process-guided steel plate shape quality prediction device, comprising:
[0026] The data acquisition module is used to obtain multi-source heterogeneous data of the entire thick plate production process;
[0027] The data preprocessing module is used to preprocess the multi-source heterogeneous data of the entire thick plate production process;
[0028] The process feature extraction module is used to extract features from the pre-processed multi-source heterogeneous data of the entire thick plate production process according to different processes, and obtain the features corresponding to different processes;
[0029] The fusion feature extraction module is used to input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fusion features;
[0030] The quality prediction module is used to input the fusion features into the pre-trained prediction model to obtain the steel plate shape quality prediction result.
[0031] In a third aspect, the present application proposes an electronic device comprising: one or more processors, and a memory, wherein the memory is used to store instructions, and when the instructions are executed by the one or more processors, the one or more processors execute the forward process-guided steel thick plate shape quality prediction method.
[0032] In a fourth aspect, the present application proposes a computer-readable storage medium storing executable instructions, which, when executed, enable a processor to execute the forward process-guided steel thick plate shape quality prediction method.
[0033] In a fifth aspect, the present application proposes a computer program product, including a computer program or instructions, which, when executed by a processor, implements the forward process-guided steel thick plate shape quality prediction method.
[0034] Beneficial effects:
[0035] The present application proposes a forward process-guided steel thick plate shape quality prediction method and device, designs different convolutional neural networks for feature extraction according to the characteristics of different process data, and adopts a collaborative attention mechanism to fuse the three extracted process features, fully considering the connection between each process, and can better predict the shape quality of thick plates, thereby assisting on-site production decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 Flow chart of the method for predicting the shape quality of thick steel plates guided by the forward process of the embodiment of the present application;
[0037] Figure 2 Schematic diagram of a steel plate shape quality prediction training model and prediction method according to an embodiment of the present application;
[0038] Figure 3 Actual production process flow chart of steel plate in the embodiment of the present application;
[0039] Figure 4 Schematic diagram of the steel plate shape quality prediction training model and prediction process according to the embodiment of the present application;
[0040] Figure 5 Schematic diagram of the feature extraction process based on the collaborative attention mechanism fusion in the embodiment of the present application;
[0041] Figure 6 ROC curve experimental result diagram of the embodiment of the present application;
[0042] Figure 7 Confusion matrix experimental results of the embodiment of the present application;
[0043] Figure 8 Comparison diagram of the box shape results of the thick plate shape quality prediction in the embodiment of the present application;
[0044] Fig. 9 Principle block diagram of the device for predicting the shape quality of thick steel plates guided by the forward process in an embodiment of the present application. DETAILED DESCRIPTION
[0045] In the quality evaluation of thick plate products, the control of thick plate shape quality is a challenging task. The production process of thick plates involves complex physical processing and chemical reactions. Changes in any variable may affect other variables, which in turn lead to problems with the shape of the thick plates. And because thick plate production is a small-batch, multi-variety, multi-process process, it is particularly difficult to determine the specific production process variables that affect the shape of the plate. This makes it difficult to select appropriate process variables for modeling in order to accurately predict the shape when establishing a plate shape quality prediction model. At the same time, it is also impossible to deeply analyze the importance of each process variable on the shape of the thick plate.
[0046] At present, the research on the prediction of plate shape is mainly based on the production mechanism, and the various processes in the production process of thick plates are deeply analyzed. By understanding and applying the principles of physical and chemical changes that thick plates undergo during the production process, combined with expert experience, the various possible effects of the production process on the plate shape of thick plates are systematically analyzed. Finally, a prediction model is established with the production process indicators and equipment operation parameters in the thick plate production process as input and the final plate shape of the thick plate as output. However, most traditional methods are aimed at specific processes or problems, and directly use various parameters as the input of the model, and fail to solve the plate shape quality problem from the perspective of the whole process. Thick plate production is a continuous full-process process, and each process interacts and affects each other. Mechanism modeling and data-driven methods based on a single process may ignore the correlation between processes, resulting in modeling errors. In addition, data-driven prediction methods have also become a research hotspot. For example, a certain document established a random forest prediction model using historical data from the thick plate rolling stage, and used the association rule mining algorithm to analyze the important control variables in the production process. These analysis results were applied to the actual thick plate control process to improve the plate shape quality control effect. However, most of the above methods are targeted at specific processes or problems, and fail to solve the plate quality problem from the perspective of the entire process. Usually, the acquired data is directly used, and there is no need to classify and extract features from the acquired data according to the process, and the characteristics of data fusion between each process are not considered. However, thick plate production is a continuous full-process process, and each process interacts and affects each other. Mechanism modeling and data-driven methods based on a single process may ignore the correlation between processes, resulting in modeling errors.
[0047] In response to this problem, the present application proposes a forward process-guided steel thick plate shape quality prediction method and device. According to expert knowledge and production process, the method uses the full process data (including 100 one-dimensional process variables and 36 two-dimensional variables) in the thick plate production process as the initial input of the model, and then divides the process and preprocesses the data according to the actual production process of the thick plate; the convolutional neural network is used to extract the features of the three divided processes to further obtain the deep representation of the input data; and on this basis, the collaborative attention mechanism is used to fuse the extracted process features, and finally the subsequent shape quality prediction is performed. The method of the present application fully considers the influence of the interaction between the various processes of thick plate production on the final shape quality, so as to more accurately predict the shape quality of the thick plate. Practice has shown that the method of the present application is an effective method for predicting the shape quality of steel thick plates, and has good guiding significance for actual thick plate production operations.
[0048] Embodiment 1:
[0049] This embodiment proposes a forward process-guided steel plate shape quality prediction method, such as Figure 1 , Figure 2 As shown, including:
[0050] Step S1: Acquire multi-source heterogeneous data of the entire thick plate production process;
[0051] Step S2: preprocessing the multi-source heterogeneous data of the entire thick plate production process;
[0052] Step S3: extracting features from the preprocessed multi-source heterogeneous data of the entire thick plate production process according to different processes to obtain features corresponding to different processes;
[0053] Step S4: Input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fusion features;
[0054] Step S5: input the fusion features into the pre-trained prediction model to obtain the steel plate shape quality prediction result.
[0055] In this embodiment, it is preferred to obtain multi-source heterogeneous data of the entire thick plate production process, and the multi-source heterogeneous data of the entire thick plate production process includes: one-dimensional data, one-dimensional time series data and two-dimensional data. Under normal circumstances, the result of preprocessing the multi-source heterogeneous data of the entire thick plate production process is directly used as the input of the prediction model. In practice, it is found that even if the collaborative attention mechanism model is subsequently used for feature fusion, the result of preprocessing the multi-source heterogeneous data of the entire thick plate production process is used as the input of the collaborative attention mechanism model. No matter how it is adjusted, the final prediction result cannot be further improved. However, the present application extracts features from the preprocessed multi-source heterogeneous data of the entire thick plate production process according to different processes to obtain features corresponding to different processes; then the features corresponding to different processes are input into the pre-trained collaborative attention mechanism model to obtain fused features, and the fused features are input into the pre-trained prediction model to obtain the prediction result of the shape quality of the steel thick plate, and its prediction accuracy is significantly improved, breaking the inherent thinking in this field that the use of the collaborative attention mechanism model cannot further improve the prediction accuracy.
[0056] In step S1, in the specific prediction process, firstly, multi-source heterogeneous data of the whole process of thick plate production is obtained, which can be real-time data of the thick plate production process or training data of the thick plate production process, and the obtained multi-source heterogeneous data of the whole process of thick plate production is used as input data for prediction. Before making the prediction, the collaborative attention mechanism model and the prediction model need to be pre-trained. Before pre-training, the historical multi-source heterogeneous data of the whole process of thick plate production needs to be collected. The construction process of the historical multi-source heterogeneous data of the whole process of thick plate production will be described in detail in the pre-trained collaborative attention mechanism model.
[0057] In step S2, the preprocessing of multi-source heterogeneous data of the entire thick plate production process includes:
[0058] Step S2.1: performing data cleaning on multi-source heterogeneous data of the entire thick plate production process;
[0059] Step S2.2: interpolating the multi-source heterogeneous data of the entire thick plate production process after data cleaning to obtain multi-source heterogeneous data of equal length;
[0060] Step S2.3: Perform dimensionality reduction processing on the high-dimensional data in the multi-source heterogeneous data of the entire thick plate production process to obtain the source heterogeneous data after dimensionality reduction.
[0061] The different processes include: heating process, rolling process and cooling process, such as Figure 3In the actual thick plate production process, due to the different lengths of the thick plates produced, the lengths of the one-dimensional time series data in the heating process, rolling process, and cooling process are quite different based on the original sampling rates. Therefore, in order to make full use of the correlation of the data in the three processes, it is necessary to perform linear interpolation processing on the unequal length sample data in the extracted high-dimensional data to unify the dimensions of all sample data.
[0062] The multi-source heterogeneous data of the entire thick plate production process is cleaned, and the linear interpolation method is used to preprocess the input data to unify the dimensions of all sample data in view of the differences in data dimensions caused by different data sample sizes. In view of the problem of inconsistent lengths of heterogeneous data, the traditional data filling method selects the value with the largest variable length and performs subsequent zero filling operations on related variables. This method will lead to more null values in the future and does not take into account the problem of large differences in data lengths between different processes in the process industry, which is not conducive to modeling feature extraction. Another method is to perform up and down sampling and interpolate the data. Among them, the linear interpolation algorithm is easy to calculate and is the most commonly used method. Because the change trend of the actual thick plate variable data does not have an obvious functional relationship, it is impossible to use mathematical expressions to accurately describe the functional relationship. Therefore, in this case, linear interpolation is a very effective method. Finally, in order to reduce the redundancy between features and facilitate subsequent fusion with one-dimensional process data, high-dimensional data needs to be reduced in dimension.
[0063] In step S3, the pre-processed multi-source heterogeneous data of the entire thick plate production process is subjected to feature extraction according to different processes to obtain features corresponding to different processes, including:
[0064] Step S3.1: According to different processes, multi-source heterogeneous data of equal length and source heterogeneous data after dimensionality reduction are divided into variables;
[0065] Step S3.2: splicing the multi-source heterogeneous data of equal length after the variables are divided and the source heterogeneous data after dimensionality reduction according to the time sequence of different processes;
[0066] Step S3.3: normalize the spliced multi-source heterogeneous data;
[0067] Step S3.4: Input the normalized multi-source heterogeneous data into different convolutional neural networks corresponding to different processes to perform feature extraction and obtain features corresponding to different processes.
[0068] In this embodiment, the pre-processed multi-source heterogeneous data of the thick plate production process are divided into variables according to the three processes of the actual production of thick plates: heating process, rolling process, and cooling process according to different processes, and the divided one-dimensional data and the high-dimensional data after dimensionality reduction are spliced according to the three processes. In the thick plate production process, there are large differences in the distribution and range of each variable data. Therefore, before predicting and analyzing the thick plate shape quality, it is necessary to normalize each variable data in the thick plate sample. Finally, three different convolutional neural networks are used to further extract features from the normalized multi-source heterogeneous data to obtain a deeper expression of the input data of the three processes. Each convolutional neural network contains: a convolution layer (Conv layer), a dropout layer (Dropout layer), a flatten layer (Flatten layer) and a fully connected layer (Dense layer).
[0069] The pre-trained collaborative attention mechanism model includes:
[0070] A first collaborative attention layer and a second collaborative attention layer; the first collaborative attention layer includes: a first query vector, a first key vector and a first value vector; the second collaborative attention layer includes: a second query vector, a second key vector and a second value vector; the characteristics of the heating process are superimposed in the first query vector as the input of the first collaborative attention layer, the characteristics of the rolling process are superimposed in the first key vector and the first value vector respectively as the attention weight of the first collaborative attention layer, the output of the first collaborative attention layer is superimposed in the second query vector as the input of the second collaborative attention layer, the cooling process is superimposed in the second key vector and the second value vector respectively as the attention weight of the second collaborative attention layer, and the output of the second collaborative attention layer is used as the fusion feature.
[0071] The pre-trained prediction model is a single-layer fully connected network.
[0072] In this embodiment, after extracting features from each process, in order to fully consider the role and connection between variables in each process, a collaborative attention mechanism is used to fuse the features of the three processes, and then the fused features are used to perform subsequent prediction of the shape quality of the steel thick plate. In this embodiment, step S3.4 obtains features corresponding to three different processes, including: features corresponding to the heating process, features corresponding to the rolling process, and features corresponding to the cooling process. The features corresponding to the heating process, the rolling process, and the cooling process are respectively used as three input sources X heat , X roll and X cool ,in and n1, n2, n3 are the number of variables in the heating, rolling and cooling processes respectively, and d is the variable dimension. Each input source corresponds to the feature representation of the heating process, rolling process and cooling process respectively. To calculate the fused feature representation, the specific implementation steps are as follows:
[0073] First, the input source X of the heating process heat Convert it into a feature vector and add this feature vector to the input source X of the rolling process roll On, generate data X heat Based on data X roll The attention weight A' (i.e., Q1 of the first collaborative attention layer comes from the heating process, and K1 and V1 come from the rolling process) is used to achieve the purpose of the forward process (heating process) guiding the backward process (rolling process).
[0074] Similarly, X' is converted into a feature vector and this feature vector is added to the input source X of the cooling process. cool On, generate data X cool Attention weight A based on data X' (here Q2 comes from the fusion feature X' of the first two processes, and K2 and V2 come from the cooling process). In this embodiment, through the design of the query vector Q (Query), key vector K (Key) and value vector V (Value) in the collaborative attention mechanism model, it not only realizes the fusion of the three process features, but also reflects the guiding role of the forward process on the backward process, and fully considers the connection between the various processes in the actual production process.
[0075] Finally, the fused features are input into a single-layer fully connected network to extract the thick plate product quality label information implicit in the production process data from the data features. Furthermore, the extracted quality label information is spatially normalized using the Softmax function to obtain the final thick plate shape quality label prediction value.
[0076] In this embodiment, before predicting the shape quality of steel thick plates, it is necessary to collect historical multi-source heterogeneous data of the entire thick plate production process as sample data, and pre-train the collaborative attention mechanism model. The training process is as follows:
[0077] Step S100: Collect historical multi-source heterogeneous data of the entire thick plate production process, including:
[0078] Step S100.1: Collect historical full-process multi-source heterogeneous production data in actual industrial sites as sample data, and store them in a relational database;
[0079] Step S100.2: Select the required variables from all historical full-process multi-source heterogeneous production data as input, and the thick plate shape quality label as the prediction output;
[0080] In this embodiment, according to the actual process and the mechanism analysis of the thick plate production process, 100 one-dimensional process variables and 36 two-dimensional variables are selected as the input of the model, and the thick plate shape quality label is used as the prediction output of the model. The specific selected one-dimensional process variables and high-dimensional variables are shown in Table 1 and Table 2 below:
[0081] In the relational database, SQL statements are used to extract data and divide the specifications of thick plate samples, and thick plates of the same specifications are screened out and their data is stored in .csv format for the next step of data preprocessing;
[0082] Specifically, in this embodiment, a total of 5,000 production data of the same specifications from January 2019 to June 2021 are extracted from the historical database of the thick plate production process of a steel plant as input data, and the quality label data identifying the quality of the plate shape is used as output data. These data are used to establish a quality prediction model for the final plate quality prediction.
[0083] In this embodiment, since there are many types of historical data screened according to specifications, a certain specification of thick plate is extracted from the historical database of the thick plate production process of a domestic steel plant for experimental analysis. After data cleaning and finally data screening and preprocessing, 4504 thick plate shape quality sample data are obtained, including 2947 normal thick plate sample data and 1557 abnormal thick plate sample data. The sample partitioning method is used to divide the training set and the test set according to the ratio of 8:2, including 3603 groups of training data and 901 groups of test data. The training data is used for model construction, and the test data is used for model verification and finding the optimal parameters of the model.
[0084] Table 1 Selected one-dimensional process variable information (100 variables) partial statistics
[0085]
[0086]
[0087] Table 2 Selected high-dimensional variable information (36 variables) partial statistics
[0088]
[0089] Step S101: preprocessing the historical multi-source heterogeneous data of the entire thick plate production process, including:
[0090] Step S101.1: performing data cleaning on the historical multi-source heterogeneous data of the entire thick plate production process;
[0091] Step S101.2: interpolating the historical multi-source heterogeneous data of the entire thick plate production process after data cleaning to obtain historical multi-source heterogeneous data of equal length;
[0092] Step S101.3: Dimensionality reduction processing is performed on high-dimensional data in historical multi-source heterogeneous data of the entire thick plate production process to obtain historical source heterogeneous data after dimensionality reduction.
[0093] The process of preprocessing the historical multi-source heterogeneous data of the entire thick plate production process is the same as the preprocessing process in step S2, the only difference is that the input data is different. Step S101 inputs historical data, while step S2 inputs test data or real-time data. In the actual thick plate production process, due to the different lengths of the thick plates produced, the lengths of the one-dimensional time series data in the heating process, rolling process, and cooling process are quite different based on the original different sampling rates. Therefore, in order to make full use of the correlation of the data in the three processes, it is necessary to perform linear interpolation processing on the unequal length sample data in the extracted high-dimensional data to unify the dimensions of all sample data.
[0094] Specifically, this embodiment performs data cleaning and preprocessing on the selected 5000 thick plate data of the same specification, removes abnormal data samples in the process data, and obtains the remaining 4504 thick plate data. The linear interpolation method is implemented as follows:
[0095] According to the Lagrange interpolation method, the intermediate values of the adjacent data points on the left and right of the one-dimensional time series data are estimated;
[0096] If the coordinates (x0, y0) and (x1, y1) are known, calculate the value of x at a certain position in the interval [x0, y0], calculate the polynomial y = L1(x) = a0 + a1x, and satisfy L1(x0) = y0, L1(x1) = y1. From analytic geometry, we know that:
[0097]
[0098] The mathematical expression of the linear interpolation method is:
[0099]
[0100] Wherein, L(x) is the estimated value of the intermediate value, a0 and a1 are the coefficients of the difference polynomial, specifically, a0 is the intercept of the linear function, and a1 is the slope of the linear function.
[0101] In order to reduce the redundancy between features and facilitate subsequent fusion with one-dimensional process data, it is necessary to perform dimensionality reduction processing on the high-dimensional data. This embodiment adopts PCA (Principal Component Analysis) dimensionality reduction.
[0102] Step S102: extracting features from the preprocessed historical multi-source heterogeneous data according to different processes to obtain features corresponding to different processes;
[0103] Step S102.1: dividing historical multi-source heterogeneous data of equal length and historical source heterogeneous data after dimensionality reduction into variables according to different processes;
[0104] Step S102.2: splicing the historical multi-source heterogeneous data of equal length after the variables are divided and the historical source heterogeneous data after dimensionality reduction according to the time sequence of different processes;
[0105] Step S102.3: normalizing the spliced historical multi-source heterogeneous data;
[0106] Step S102.4: Input the normalized historical multi-source heterogeneous data into different convolutional neural networks corresponding to different processes to perform feature extraction to obtain features corresponding to different processes.
[0107] The process of extracting the corresponding features of different processes in this embodiment is the same as step S3, the only difference is the input data. Step S102 inputs historical data, while step S3 inputs test data or data acquired in real time. Specifically, first, according to different processes (including: heating process, rolling process, cooling process), the historical multi-source heterogeneous data of equal length and the historical source heterogeneous data after dimensionality reduction are divided into variables; secondly, the historical multi-source heterogeneous data of equal length after variable division and the historical source heterogeneous data after dimensionality reduction are spliced according to the process. Furthermore, the spliced historical multi-source heterogeneous data are normalized; in the thick plate production process, there are large differences in the distribution and range of each variable data. Therefore, before predicting and analyzing the thick plate shape quality, it is necessary to normalize each variable data in the thick plate sample. The normalization calculation formula is as follows:
[0108]
[0109] Among them, x np represents the pth variable data in the nth data sample, and x min represents the minimum value of the variable in all data samples, x max Indicates the maximum value of the variable in all data samples.
[0110] In a specific implementation, the normalized historical multi-source heterogeneous data can be divided into a training set and a test set in a ratio of 8:2, wherein the training set sample data is used to train the parameters of the model, while the test set sample data does not participate in the training and is used for the final evaluation of the model performance after the model training is completed. Finally, the normalized historical multi-source heterogeneous data is input into different convolutional neural networks corresponding to different processes for feature extraction to obtain features corresponding to different processes. This embodiment uses three convolutional neural networks to further extract features from the normalized historical multi-source heterogeneous data to obtain a deeper expression of the input data of the three processes. Each feature extraction network includes a convolutional layer (Conv layer), a dropout layer (Dropout layer), a flattening layer (Flatten layer) and a fully connected layer (Dense layer).
[0111] In step S102.4, the normalized historical multi-source heterogeneous data is input into different convolutional neural networks corresponding to different processes to perform feature extraction to obtain features corresponding to different processes, including:
[0112] Step S102.4.1: Input the normalized historical multi-source heterogeneous data into a convolution layer with different convolution kernels and the same filter;
[0113] In this embodiment, the convolution layer is used to extract features from the input data. The convolution layer in each network is set with different sizes of convolution kernels (the convolution kernel of the convolution layer of the heating process is 5×5, the convolution kernel of the convolution layer of the rolling process is 9×9, and the convolution kernel of the convolution layer of the cooling process is 7×7) and the same number of filters (32) according to different input data. The convolution layer operation process is as follows:
[0114]
[0115] Among them, x(i,j) represents the pixel value of the i-th row and j-th column of the input X; K represents the convolution kernel size, W(m,n) represents the weight of the m-th row and n-th column, and W b represents the bias term of the convolution kernel, X is the normalized historical multi-source heterogeneous data, and u CNN,i is the output of the i-th convolutional layer.
[0116] Step S102.4.2: Use the output of each convolutional layer as the input of the attenuation layer;
[0117] In this example, a Dropout layer is applied after each convolutional layer, where the dropout rate parameter is set to 0.2 to prevent overfitting during training. The output after Dropout is calculated as follows:
[0118]
[0119] Among them, ⊙ represents the Hadamard product, that is, element-wise multiplication, and M is the same as the input u CNN,i The binary mask matrix of the same size, Y is the output of the attenuation layer, and p is the discard rate.
[0120] Step S102.4.3: Use the output of the attenuation layer as the input of the flattening layer;
[0121] Step S102.4.4: Convert the output of the flattening layer into a one-dimensional vector, and input the one-dimensional vector into the fully connected layer to obtain features corresponding to different processes;
[0122] In this example, after the Dropout layer, the output is flattened, converting the multi-dimensional output into a one-dimensional vector that can be input into the fully connected layer. After each Flatten layer, a fully connected layer with 32 neurons is applied, which helps learn complex patterns in the data. The calculation formula of the fully connected layer is as follows:
[0123] y flatten =W T x+b
[0124] Among them, x is the input data of the fully connected layer, W represents the weight, b represents the bias, and y flatten is the output of the fully connected layer.
[0125] Among them, both the convolutional layer and the fully connected layer use Relu as the activation function:
[0126] f Relu (x r )=max(0,x r )
[0127] Among them, x r Represents the activation function input data, f Relu (x r ) is the activation function.
[0128] Compared with other activation functions such as Sigmoid and Tanh, Relu is easier to optimize and can effectively avoid the problem of gradient disappearance during gradient descent, thereby reducing the risk of information loss.
[0129] Step S103: using features corresponding to different processes as input to train the collaborative attention mechanism model;
[0130] Step S104: Adopting Adam (Adaptive Moment Estimation) to optimize the loss function of the collaborative attention mechanism model to obtain a pre-trained collaborative attention mechanism model;
[0131] In this embodiment, after extracting features from each process, in order to fully consider the role and connection between variables in each process, a collaborative attention mechanism is used to fuse the features of the three processes, and then the fused features are used for subsequent plate quality prediction. In this embodiment, step S102 obtains features corresponding to three different processes, including: features corresponding to the heating process, features corresponding to the rolling process, and features corresponding to the cooling process. The features corresponding to the heating process, the rolling process, and the cooling process are respectively used as three input sources X heat , X roll and X cool ,in and n1, n2, n3 are the number of variables in the heating, rolling and cooling processes respectively, and d is the variable dimension. Each input source corresponds to the feature representation of the heating process, rolling process and cooling process respectively. To calculate the fused feature representation, the specific implementation steps are as follows:
[0132] First, the input source X of the heating process heat Convert it into a feature vector and add this feature vector to the input source X of the rolling process roll On, generate data X heat Based on data X roll The attention weight A' (that is, Q1 of the first collaborative attention layer comes from the heating process, K1 and V1 come from the rolling process) is used to achieve the purpose of the forward process (heating process) guiding the backward process (rolling process).
[0133] Specifically, and The collaborative attention weight is calculated as follows:
[0134]
[0135] in, is the learned projection matrix, d k is the dimension of the key-value set (also the dimension of the query set), f o is a linear layer X' that projects the output weights to the target channel dimension, represents the dot product calculation result of the query vector Q1 and the key vector, represents the value calculated by querying vector Q1, represents the result of weighted summation of the value vector V1 using the attention weight A', It represents the final attention output result of all the above steps. Attn(·) represents the operation function of the attention mechanism, which specifically refers to the whole process of calculating the query, key, and value vectors through the attention mechanism.
[0136] Similarly, X' is converted into a feature vector and this feature vector is added to the input source X of the cooling process. cool On, generate data X cool Based on the attention weight A of data X' (where Q2 comes from the fusion feature X' of the first two processes, K2 and V2 are used to cool the process), the specific calculation formula is the same as above. The collaborative attention fusion module structure is as follows Figure 5 shown.
[0137] The above process not only realizes the fusion of the three process features, but also reflects the guiding role of the forward process on the backward process, and fully considers the connection between the various processes in the actual production process through the design of the attention mechanism query vector Q (Query), key vector K (Key) and value vector V (Value). Compared with the current research methods, this embodiment pays more attention to how to integrate the multi-source heterogeneous data in the thick plate production process, that is, to perform feature fusion of thick plate data of different dimensions (including one-dimensional data and two-dimensional data in the thick plate production process) to achieve plate shape quality prediction. This article, on the basis of considering the characteristics of multi-source heterogeneous data of thick plates, further considers the characteristics of multiple processes and strong coupling in the actual production process of thick plates (that is, there are interactions and influences between the front and rear processes of thick plate production). Through the collaborative attention mechanism, the Q, K, and V of the three processes are cross-designed to explore the influence of the interaction between the variables of each process on the final thick plate shape quality.
[0138] Finally, during the training process of the entire network, Adam is used to optimize the loss function to adapt to the update speed of different parameters. The network weight and bias update calculation formula is as follows:
[0139] (1) Update the momentum and bias estimates of the loss function. The specific calculation formula is as follows:
[0140]
[0141] Among them, S t and R t They represent the first-order and second-order moment estimates of the gradient of the loss function; β1 and β2 are the decay rates, g t represents the gradient value at time step t.
[0142] (2) Correct the deviation. The specific calculation formula is as follows:
[0143]
[0144] in, and represents the corrected first-order and second-order moment estimates.
[0145] (3) Update the parameters of the entire network. The specific update calculation formula is as follows:
[0146]
[0147] Among them, θ t is the parameter at the tth iteration, θ t+1 is the parameter updated after the tth iteration, η represents the learning rate, ε represents the smoothing term, which is set to 10-8 to prevent division by zero.
[0148] In order to further illustrate the effect of this embodiment, the experimental process is described in detail as follows:
[0149] 1. Experimental environment configuration and parameter setting
[0150] This experiment uses Python to extract and normalize the preliminary data, merge and resample multi-source heterogeneous data, and use the PyTorch framework to establish a steel plate shape quality prediction model based on the forward process guided attention mechanism feature fusion. The activation function uses the Relu function, and Softmax is used for thick plate shape classification. Figure 4 , Figure 5 The algorithm is designed based on the feature fusion model structure shown in the figure, and the network is trained using the cross entropy loss function. In the back propagation, the Adam optimization algorithm is used to learn the network parameters. During the training process, after many experiments, the optimal learning rate is selected as 0.001, the random seed number random_state is set to 42, the batch_size is set to 512, and the number of epochs of the entire model is set to 50. The network training is run on a computer with an Intel(R) Xeon(R) W-2123, 3.60GHz 8-core CPU, 32GB memory, and a graphics card of Quadro P2000.
[0151] 2. Evaluation Metrics
[0152] In this embodiment, the accuracy, F1 score and the area under the receiver operating characteristic curve (AUC), referred to as AUC-ROC, are used to evaluate the prediction performance of the method of the present invention, wherein the larger the value of AUC-ROC, the better the prediction performance of the model. The calculation formulas for each evaluation index are as follows:
[0153] (1) Accuracy
[0154]
[0155] (2) F1-Score
[0156]
[0157] in, represents the accuracy, Represents recall rate. TP represents the number of samples correctly identified as positive by the model, FP represents the number of samples that are incorrectly labeled as positive but actually belong to the negative category, TN represents the number of samples correctly identified as negative, and FN represents the number of samples that are incorrectly classified as negative but actually belong to the positive category.
[0158] 3. Experimental results
[0159] Experiments were conducted on the above sample data and the above parameters were set. The ROC curve and confusion matrix results of the obtained model are as follows: Figure 6 and Figure 7 shown.
[0160] In addition, in order to more fully illustrate the effectiveness of the forward process-guided steel thick plate shape quality prediction method proposed in this embodiment, the results of the prediction method of this embodiment are compared with other common algorithms. The comparative experimental results are shown in Table 3 below.
[0161] Table 3 Comparison of prediction results between the prediction method of the present invention and common algorithms
[0162]
[0163]
[0164] It can be seen from Table 3 that the forward process-guided steel thick plate shape quality prediction method (i.e., Co-Attention Fusion) of this embodiment has the highest accuracy, and the AUC value of the area enclosed under the ROC curve is also closer to 1, indicating that the forward process-guided steel thick plate shape quality prediction method proposed in this embodiment has better classification performance.
[0165] In the table of experimental results, the first five are the plate shape quality prediction comparison results with other common algorithms. The sixth and seventh (DNN-CNN Fusion and SE-CNN-Attention Fusion) are the comparison results of plate shape quality prediction by directly fusing data between different dimensions. The last one is the forward process-guided steel thick plate shape quality prediction method proposed in this embodiment. It can be seen that the relationship between the previous and next processes is taken into account, and the accuracy of thick plate shape quality prediction is higher. The prediction method of the embodiment is compared with the prediction results of the direct feature fusion methods DNN-CNN Fusion and SE-CNN-AttentionFusion, and the resulting box shape Figure 8 As shown. Figure 8 It can also be seen that the steel thick plate shape quality prediction method guided by the forward process of this embodiment has the highest accuracy and the best effect.
[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope defined by the claims of the present application.
[0167] Embodiment 2:
[0168] In the second aspect, the present application proposes a forward process-guided steel plate shape quality prediction device, such as Fig. 9 As shown, it includes: a data acquisition module, a data preprocessing module, a process feature extraction module, a fusion feature extraction module and a quality prediction module;
[0169] The data acquisition module is connected to the data preprocessing module, the data preprocessing module is connected to the process feature extraction module, the process feature extraction module is connected to the fusion feature extraction module, and the fusion feature extraction module is connected to the quality prediction module;
[0170] The data acquisition module is used to obtain multi-source heterogeneous data of the entire thick plate production process;
[0171] The data preprocessing module is used to preprocess the multi-source heterogeneous data of the entire thick plate production process;
[0172] The process feature extraction module is used to extract features from the pre-processed multi-source heterogeneous data of the entire thick plate production process according to different processes, and obtain the features corresponding to different processes;
[0173] The fusion feature extraction module is used to input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fusion features;
[0174] The quality prediction module is used to input the fusion features into the pre-trained prediction model to obtain the steel plate shape quality prediction result.
[0175] Embodiment 3:
[0176] This embodiment proposes an electronic device, including: one or more processors, and a memory, wherein the memory is used to store instructions, and when the instructions are executed by the one or more processors, the one or more processors execute the forward process-guided steel thick plate shape quality prediction method.
[0177] The electronic device may be a mobile phone, a computer or a tablet computer, etc., including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the forward process-guided steel plate shape quality prediction method as described in the embodiment is implemented. It is understood that the electronic device may also include an input / output (I / O) interface and a communication component.
[0178] The processor is used to execute all or part of the steps in the forward process guided steel plate shape quality prediction method as described in the above embodiment. The memory is used to store various types of data, which may include instructions of any application or method in the electronic device, as well as data related to the application.
[0179] The processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the forward process guided steel thick plate shape quality prediction method described in the above embodiments.
[0180] Embodiment 4:
[0181] This embodiment provides a computer-readable storage medium storing executable instructions. When the instructions are executed and implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
[0182] The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the forward process-guided steel thick plate shape quality prediction method described in each embodiment of the present application.
[0183] The aforementioned storage media include: flash memory, hard disk, multimedia card, card-type memory (for example, SD (Secure Digital Memory Card) or DX (Memory Data Register, MDR abbreviation, memory data register) memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, CD, server, APP (Application, abbreviation of application software) application store and other media that can store program verification codes, on which computer programs are stored. When the computer program is executed by the processor, the various steps of the above-mentioned forward process-guided steel thick plate shape quality prediction method can be implemented.
[0184] Embodiment 5:
[0185] This embodiment provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the forward process-guided steel thick plate shape quality prediction method.
[0186] Based on such understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a computer program product.
[0187] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0188] The protection scope of the present application is not limited to the above-mentioned embodiments. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the scope and spirit of the present disclosure. If these changes and modifications fall within the scope of the claims of the present disclosure and their equivalents, the intention of the present disclosure also includes these changes and modifications.
Claims
1. A method for predicting the shape quality of thick steel plates guided by a forward process, characterized in that: include: Acquire multi-source heterogeneous data of the entire thick plate production process; Preprocessing multi-source heterogeneous data of the entire thick plate production process; According to different processes, feature extraction is performed on the pre-processed multi-source heterogeneous data of the entire thick plate production process to obtain features corresponding to different processes; Input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fused features; The fusion features are input into a pre-trained prediction model to obtain a prediction result of the shape quality of the steel thick plate.
2. The method for predicting the shape quality of thick steel plates guided by forward process according to claim 1, characterized in that: The preprocessing of multi-source heterogeneous data of the entire thick plate production process includes: Performing data cleaning on multi-source heterogeneous data of the entire thick plate production process; The multi-source heterogeneous data of the entire thick plate production process after data cleaning are interpolated to obtain multi-source heterogeneous data of equal length; the high-dimensional data in the multi-source heterogeneous data of the entire thick plate production process are subjected to dimensionality reduction processing to obtain the source heterogeneous data after dimensionality reduction.
3. The method for predicting the shape quality of thick steel plates guided by forward process according to claim 2, characterized in that: The feature extraction is performed on the pre-processed multi-source heterogeneous data of the entire thick plate production process according to different processes to obtain features corresponding to different processes, including: According to different processes, multi-source heterogeneous data of equal length and source heterogeneous data after dimensionality reduction are divided into variables; According to the time sequence of different processes, the multi-source heterogeneous data of equal length after the variables are divided and the source heterogeneous data after dimensionality reduction are spliced; Normalize the spliced multi-source heterogeneous data; The normalized multi-source heterogeneous data are input into different convolutional neural networks corresponding to different processes for feature extraction to obtain the features corresponding to different processes.
4. The method for predicting the shape quality of thick steel plates guided by forward process according to claim 3, characterized in that: The different convolutional neural networks include: a convolutional layer, an attenuation layer, a flattening layer and a fully connected layer.
5. The method for predicting the shape quality of thick steel plates guided by forward process according to claim 1, characterized in that: The different processes include: a heating process, a rolling process and a cooling process.
6. The method for predicting the shape quality of thick steel plates guided by forward process according to claim 5, characterized in that: The pre-trained collaborative attention mechanism model includes: A first collaborative attention layer and a second collaborative attention layer; the first collaborative attention layer includes: a first query vector, a first key vector and a first value vector; the second collaborative attention layer includes: a second query vector, a second key vector and a second value vector; the characteristics of the heating process are superimposed in the first query vector as the input of the first collaborative attention layer, the characteristics of the rolling process are superimposed in the first key vector and the first value vector respectively as the attention weight of the first collaborative attention layer, the output of the first collaborative attention layer is superimposed in the second query vector as the input of the second collaborative attention layer, the cooling process is superimposed in the second key vector and the second value vector respectively as the attention weight of the second collaborative attention layer, and the output of the second collaborative attention layer is used as the fusion feature.
7. A device for predicting the shape quality of thick steel plates guided by a forward process, characterized in that: include: The data acquisition module is used to obtain multi-source heterogeneous data of the entire thick plate production process; The data preprocessing module is used to preprocess the multi-source heterogeneous data of the entire thick plate production process; The process feature extraction module is used to extract features from the pre-processed multi-source heterogeneous data of the entire thick plate production process according to different processes, and obtain the features corresponding to different processes; The fusion feature extraction module is used to input the features corresponding to different processes into the pre-trained collaborative attention mechanism model to obtain fusion features; The quality prediction module is used to input the fusion features into the pre-trained prediction model to obtain the steel plate shape quality prediction result.
8. An electronic device, characterized in that: include: One or more processors, and a memory, wherein the memory is used to store instructions, and when the instructions are executed by the one or more processors, the one or more processors execute the forward process-guided steel thick plate shape quality prediction method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: The device stores executable instructions, which, when executed, enable the processor to execute the forward process-guided steel thick plate shape quality prediction method as claimed in any one of claims 1 to 6.
10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the forward process-guided steel plate shape quality prediction method described in any one of claims 1 to 6 is implemented.
Citation Information
Patent Citations
Visual question and answer method based on multi-modal depth feature fusion and model thereof
CN114398961A
Air quality integrated prediction method based on time sequence missing perception and multi-source factor fusion
CN114841461A
Method and device for predicting plate shape of medium-thickness plate
CN116189829A
Cold rolled steel mechanical property prediction method fusing multiple attention mechanisms
CN117034755A
Aluminum foil production quality prediction method and device, computer equipment and storage medium
CN117291288A
Cited By
River comprehensive management and control data collaborative optimization method and system based on Internet of Things
CN120146322A
ERP data collaborative analysis method for photovoltaic product defect detection
CN120654070A
