Continuous casting breakout prediction method and system based on deep learning

Abstract

The present application relates to the field of continuous casting detection technology in the metallurgical industry, and specifically to a method and system for predicting continuous casting steel leakage based on deep learning. The method includes: obtaining multiple samples; obtaining the temperature change deviation of each thermocouple in each sample; analyzing the distribution range of the temperature data of each thermocouple in each sample and the temperature change deviation to obtain the temperature change value of each thermocouple in each sample; obtaining the spatial distribution difference of each thermocouple in each sample by comparing the temperature distribution of each thermocouple in each sample with all other thermocouples, as well as the temperature difference between each thermocouple and its adjacent thermocouple at the same position; obtaining the fitness of each sample; assigning labels to all samples according to the fitness, and training a neural network with the labeled samples to obtain a steel leakage prediction model. The present application improves the accuracy of distinguishing between bonded steel leakage samples and normal samples, thereby improving the prediction accuracy of the steel leakage prediction model.

Description

Technical Field

[0001] The present application relates to the field of continuous casting detection technology in the metallurgical industry, and specifically to a method and system for predicting continuous casting breakout based on deep learning. Background Art

[0002] In the continuous casting production process, bonding breakout is the most common form of breakout. Once a breakout accident occurs, it may seriously damage the equipment and even endanger personal safety. Therefore, it is very necessary to develop a real-time and effective breakout prediction model.

[0003] In the process of constructing the steel leakage prediction model, when distinguishing the temperature data under different working conditions, the temperature change characteristics of a single thermocouple and the relationship between the temperature changes of different rows of thermocouples were not fully considered, resulting in insufficient accuracy in distinguishing the temperature data. As a result, the subsequent steel leakage prediction model obtained using the differentiated temperature data is prone to omissions or false alarms. Summary of the Invention

[0004] In view of the above, it is necessary to provide a continuous casting breakout prediction method and system based on deep learning. Compared with the traditional continuous casting breakout prediction method, it improves the accuracy of distinguishing between bonded breakout samples and normal samples, thereby improving the prediction accuracy of the breakout prediction model:

[0005] In a first aspect, an embodiment of the present application provides a method for predicting continuous casting breakout based on deep learning, the method comprising the following steps:

[0006] Acquire multiple samples, each sample containing temperature data of all thermocouples within a preset time period;

[0007] By comparing the temperature data of each thermocouple in each sample with the temperature data of all thermocouples in all samples, the temperature change deviation of each thermocouple in each sample is obtained;

[0008] Analyzing the distribution range of the temperature data of each thermocouple in each sample and the temperature change deviation to obtain the temperature change value of each thermocouple in each sample;

[0009] By comparing the temperature distribution of each thermocouple in each sample with that of all other thermocouples, and the temperature difference between each thermocouple and its adjacent thermocouples, the spatial distribution difference of each thermocouple in each sample is obtained;

[0010] Combining the temperature change values ​​and spatial distribution differences of all thermocouples in each sample to obtain the fitness of each sample;

[0011] All samples are assigned labels according to the fitness, and a neural network is trained using the labeled samples to obtain a steel breakout prediction model.

[0012] In one embodiment, the process of obtaining the temperature change deviation is:

[0013] Arrange all temperature data of each thermocouple in each sample in time sequence to form each temperature sequence, and obtain a fitting curve of all temperature data in each temperature sequence;

[0014] Obtaining a curvature calculation formula for each fitting curve, and calculating a definite integral result of each curvature calculation formula in the interval [1, N], where N is the total number of data in the temperature series; the change is reflected by the definite integral result;

[0015] Calculating the mean of the definite integral results of all thermocouples in all samples;

[0016] The temperature variation deviation is obtained by comparing the definite integral result of each thermocouple in each sample with the mean value.

[0017] In one embodiment, the expression of the temperature variation deviation is: S j,i =I j,i -I j,avg Where S j,i Indicates the temperature change deviation of the i-th thermocouple in the j-th sample; I j,i I represents the integration result of the i-th thermocouple in the j-th sample; j,avg represents the mean of the integration results for all thermocouples in all samples.

[0018] In one embodiment, the process of obtaining the temperature change value is as follows:

[0019] Calculate the range of all temperature data for each thermocouple in each sample;

[0020] The temperature change value is positively correlated with the range and the temperature change deviation respectively.

[0021] In one embodiment, the expression of the spatial distribution difference is:

[0022] Where Z j,i represents the spatial distribution difference of the i-th thermocouple in the j-th sample; norm() represents the normalization function; calculate the mean temperature data of each row of thermocouples in the j-th sample at each acquisition time, and record the difference in the mean temperature data between the row where the i-th thermocouple in the j-th sample is located and the row above it as the temperature value difference, t j,irepresents the sum of the temperature differences of the i-th thermocouple in the j-th sample at all acquisition moments; obtains the stationary point of the fitting curve of each thermocouple, arranges the occurrence moments of the stationary points of all thermocouples in the j-th sample in chronological order to form a time series, and arranges the time intervals between any two adjacent moments in the time series to form a time difference series, ΔT avg represents the sum of all values ​​in the first-order difference sequence of the time difference sequence; α represents a preset value greater than 0.

[0023] In one embodiment, the process of obtaining the fitness is as follows:

[0024] Calculate the fusion results of the temperature change value and spatial distribution difference of each thermocouple in each sample;

[0025] The fitness is the sum of the fusion results of all thermocouples in each sample.

[0026] In one embodiment, the process of assigning labels to all samples using the fitness is as follows:

[0027] A genetic algorithm is used to select initial cluster centers according to the suitability of each sample, and a clustering algorithm is used to cluster all samples based on the initial cluster centers. The bonding leak samples and normal samples are distinguished by the clustering results, and different labels are assigned to the bonding leak samples and the normal samples. The label of the normal sample is a first preset value, and the label of the bonding leak sample is a second preset value.

[0028] In one embodiment, the step of training a neural network using labeled samples includes:

[0029] All bonded steel leakage samples are divided into training sets and test sets according to the preset ratio, and normal samples are divided into training sets and test sets according to the preset ratio;

[0030] The neural network is trained and tested using the training set and the test set.

[0031] In one embodiment, when testing the trained neural network, the test result evaluation indicators include prediction accuracy and reporting rate;

[0032] Forecast accuracy σ p The expression is: Report rate σ r The expression is: Where N r Indicates the number of correct alarms, N f Indicates the number of false alarms, and N1 indicates the number of missed alarms;

[0033] When the output of the neural network reaches the second preset value, an alarm is issued.

[0034] In the second aspect, an embodiment of the present application also provides a continuous casting steel leakage prediction system based on deep learning, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned continuous casting steel leakage prediction methods based on deep learning.

[0035] This application has at least the following beneficial effects:

[0036] This application fully considers the temperature changes of thermocouples installed at different positions on the crystallizer, including the fact that the temperature of a single thermocouple shows a trend of first rising and then falling when bonding breakout occurs, and the temperature change range of a single thermocouple is large, as well as the temperature changes of adjacent rows of thermocouples showing "time lag" and "temperature inversion" in space, to obtain fitness, which more accurately reflects the working conditions to which the temperature data belongs; compared with the traditional use of the quality index of clustering results as fitness, the calculated fitness does not depend on the intra-cluster distance and the inter-cluster distance, so that under data noise or dimensionality disaster, it can reduce the distance measurement deviation, select the optimal initial clustering center, and then classify the samples based on the initial clustering center, thereby improving the accuracy of sample distinction;

[0037] Furthermore, the steel breakout prediction model is trained based on the accurately distinguished samples, so that the steel breakout prediction model can more accurately capture the intrinsic characteristics of the temperature data, and thus have higher prediction accuracy when using the steel breakout prediction model to predict steel breakout in the continuous casting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0039] Figure 1 A flowchart of the steps of a continuous casting breakout prediction method based on deep learning provided in one embodiment of the present application;

[0040] Figure 2 Schematic diagram of the layout of thermocouples;

[0041] Figure 3 Schematic diagram of temperature change during bonding breakout;

[0042] Figure 4 This is a schematic diagram of the temperature changes of adjacent rows of thermocouples when bonding steel breaks out;

[0043] Figure 5 This is a structural diagram of the Transformer model;

[0044] Figure 6 This is a structural diagram of the Transformer-BiLSTM model;

[0045] Figure 7 This is a diagram of the accuracy-loss value of the Transformer-BiLSTM model;

[0046] Figure 8 This is a diagram of the accuracy-loss value of the Kmeans-Transformer-BiLSTM model;

[0047] Figure 9 The following is a diagram of the accuracy-loss value of the GA-Kmeans-Transformer-BiLSTM model. DETAILED DESCRIPTION

[0048] In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application relates. The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. It should be understood that, unless otherwise indicated, " / " represents or.

[0050] It should also be noted that the terms "first" and "second" in this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0051] The specific scheme of the continuous casting breakout prediction method and system based on deep learning provided by this application is described in detail below with reference to the accompanying drawings.

[0052] See also Figure 1 , which shows a flowchart of a method for predicting continuous casting breakout based on deep learning provided by one embodiment of the present application, the method comprising the following steps:

[0053] Step 1: Acquire multiple samples, each sample containing temperature data of all thermocouples within each preset time period.

[0054] Temperature data is collected using thermocouples embedded in the copper plate of the crystallizer, wherein the thermocouples are evenly embedded in the copper plate of the crystallizer.

[0055] The dimensions of the crystallizer in this embodiment are 1870 cm long, 400 cm wide, and 1200 cm high. Six rows of thermocouples are installed on the two fixed wide faces, the left narrow face, and the right narrow face of the crystallizer. Among them, eight rows of thermocouples are installed on the two fixed wide faces, and two rows of thermocouples are installed on the left narrow face and the right narrow face, for a total of 120 thermocouples. The layout diagram of the thermocouples is shown in FIG. Figure 2 As shown, Figure 2 In the middle, 101 represents a fixed wide surface, and the surface parallel to 101 is also a fixed wide surface. 102 represents a right narrow surface, and the surface parallel to the right narrow surface is a left narrow surface. 103 represents a thermocouple. The implementer can set the number of rows and columns of thermocouples and the distance between adjacent thermocouples by himself. This application does not impose any special restrictions.

[0056] In this embodiment, during the process of collecting temperature data, the collection time interval is 2s. The value of the collection time interval is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0057] Due to the complex environment of continuous casting sites, the temperature data collected by thermocouples is subject to various noise interferences, so the collected temperature data needs to be filtered. The useful information in the temperature signal is concentrated in the low-frequency part, while the noise is in the high-frequency part. Therefore, a low-pass filter is used to filter the temperature data to remove the high-frequency noise. The low-pass filter is a well-known technology and will not be described in detail in this application.

[0058] By analyzing the historical temperature data of any steel plant, it is found that after a single thermocouple experiences bonding and steel leakage, the temperature data collected by the thermocouple first rises and then falls. The temperature change diagram during bonding and steel leakage is shown in the figure below. Figure 3 As shown, Figure 3 In the figure, 104 represents the ascending mode, 105 represents the intermediate transition mode, 106 represents the full process mode, and 107 represents the descending mode.

[0059] In the present embodiment, bonding steel leakage samples and normal samples with large fluctuations that are prone to false alarms are selected from historical temperature data. Specifically: 40 groups of bonding steel leakage samples are selected in each mode during the bonding steel leakage process, a total of 160 groups of bonding steel leakage samples, and 140 groups of normal samples are selected. Each group of samples is a matrix, and the matrix has a total of 120 rows. Each row of the matrix is ​​a temperature sequence composed of temperature data collected by a single thermocouple within 30s arranged in a time sequence. Among them, 40 and 140 are only an embodiment of the present application. The implementer can select other numbers of bonding steel leakage samples and normal samples at his own discretion, and the present application does not make special restrictions. 30s is because it is learned through analysis of historical temperature data that when bonding steel leakage occurs, the temperature mutation time of a single thermocouple is 30s.

[0060] Step 2: Comprehensively analyze the temperature change characteristics of a single thermocouple and the relationship between the temperature changes of different rows of thermocouples to obtain the fitness.

[0061] This application uses a K-means clustering algorithm based on a genetic algorithm to cluster all samples. By comparing and measuring the similarity between data, all samples are divided into K categories. For the samples in this embodiment, they can be divided into bonding leakage samples and normal samples, so K is set to 2.

[0062] Selecting cluster centers through a genetic algorithm can avoid imbalanced cluster center distribution and the tendency to fall into local optimal solutions. However, the traditional GA-Kmeans algorithm typically uses clustering result quality metrics as fitness indicators, such as the silhouette coefficient and the Davidson-Bourdin index. This fitness function relies on intra-cluster distance and inter-cluster distance, and does not consider the complete temporal sequence of single thermocouples and the spatial linkage characteristics of group thermocouples. In the presence of data noise or the curse of dimensionality, the distance metric has large deviations, which affects the selection of the optimal cluster center, resulting in inaccurate clustering results and affecting subsequent identification. Therefore, the fitness function can be determined based on the temperature variation characteristics of the thermocouples.

[0063] The temperature change diagram of adjacent rows of thermocouples during bonding leakage is shown in the figure below: Figure 4 As shown, Figure 4In the figure, a represents the bonding point, b represents the crystallizer copper plate, 1, 2, and 3 represent the first, second, and third rows of thermocouples, respectively. In the longitudinal direction, due to the increase in the thickness of the billet shell, the temperature of the lower row of thermocouples is lower than that of the upper row of thermocouples. Under normal conditions, the thermocouple temperature curve is stable, as shown in stage ①. When bonding and steel leakage occur, the bonding point first passes through the first row of thermocouples, the molten steel contacts the crystallizer copper plate, and the temperature of the thermocouples rises rapidly, as shown in stage ②. When the bonding point continues to move downward, the temperature of the first row of thermocouples drops, and the temperature of the second row of thermocouples rises rapidly, as shown in stage ③. Similarly, as the bonding point moves downward and passes through the third row of thermocouples, the temperature of the third row of thermocouples rises, and the temperatures of the first and second rows of thermocouples drop, as shown in stage ④. Finally, as the bonding point moves away, the temperature of the thermocouples continues to drop, as shown in stage ⑤.

[0064] When bonding and steel leakage occurs, the temperature of the thermocouples shows a trend of first rising and then falling, and the temperature curve of the lower row of thermocouples shows a "time lag" phenomenon compared with the upper row. The phenomenon that the temperature of the lower row of thermocouples is higher than that of the upper row is called "temperature inversion".

[0065] Step 2.1: Compare the temperature data of each thermocouple in each sample with the temperature data of all thermocouples in all samples to obtain the temperature variation deviation of each thermocouple in each sample.

[0066] When bonding breakout occurs, the temperature of a single thermocouple will fluctuate significantly. Initially, the molten steel contacts the copper plate, causing a sudden increase in heat flux and a sharp rise in temperature. As the bonding point shifts, the heat transfer in the mold changes, and the heat exchange in the molten steel becomes more complex, causing the temperature to fluctuate or drop. Under normal operating conditions, the temperature of a single thermocouple is relatively stable, and any temperature fluctuations are relatively small. This is because under normal operating conditions, the heat distribution and transfer within the mold reach a state of equilibrium, where heat is distributed and transferred through conduction, convection in the molten steel, and heat dissipation to the surrounding environment, forming a dynamic thermal equilibrium.

[0067] Based on the above analysis, taking the jth sample as an example, to better distinguish between bonding breakout and normal operating conditions, we obtain fitting curves for all data in each temperature series, obtain the curvature calculation formula for each fitting curve, and calculate the definite integral of each curvature calculation formula in the interval [1, N], where N is the total number of data in the temperature series. The curvature calculation formula and the calculation of the definite integral are both well-known techniques and will not be further described in this application.

[0068] In this embodiment, the least squares method is used to obtain the fitting curve of all the data in each temperature sequence. As other implementation methods, on the basis of obtaining the fitting curve of all the data in each temperature sequence, the implementer can adopt other existing technologies, such as polynomial fitting methods, etc., and this application does not impose any special restrictions.

[0069] Furthermore, by comparing the definite integral results of each thermocouple in each sample with all thermocouples in all samples, the temperature change deviation of each thermocouple in each sample is obtained, and the temperature change deviation of each thermocouple in each sample is characterized. The expression is:

[0070] S j,i =I j,i -I j,avg Where S j,i Indicates the temperature change deviation of the i-th thermocouple in the j-th sample; I j,i I represents the integration result of the i-th thermocouple in the j-th sample; j,avg represents the mean of the integration results for all thermocouples in all samples.

[0071] It should be noted that the integration result represents the cumulative effect of the curvature of the fitting curve in the interval [1, N]. The greater the temperature change deviation, the greater the temperature change of the i-th thermocouple in the j-th sample compared with all thermocouples in all samples, and the temperature data of the i-th thermocouple in the j-th sample is more likely to be the temperature data when bonding leakage occurs.

[0072] Step 2.2: Analyze the distribution range of the temperature data of each thermocouple in each sample and the temperature change deviation to obtain the temperature change value of each thermocouple in each sample.

[0073] When temperature fluctuations occur or a thermocouple fails, the temperature will jump. At this time, there is no bonding or steel leakage, and the system is still in normal working condition, but the temperature change deviation will be large. To avoid misjudgment, it is necessary to further judge the distribution range of the thermocouple temperature data.

[0074] Based on the above analysis, the distribution range of the temperature data of each thermocouple in each sample and the temperature change deviation are analyzed to obtain the temperature change value of each thermocouple in each sample, and the degree of temperature change of each thermocouple in each sample is characterized. The expression is:

[0075] X j,i =norm(R j,i ×S j,i ); where X j,i represents the temperature change value of the i-th thermocouple in the j-th sample; norm() represents the normalization function; R j,i represents the range of the data in the temperature series of the i-th thermocouple in the j-th sample; S j,i Indicates the temperature change deviation of the i-th thermocouple in the j-th sample.

[0076] In this embodiment, the Min-Max normalization method is used to normalize R j,i ×S j,iNormalization is performed, as another implementation method, in which R j,i ×S j,i On the basis of normalization processing, the implementer may adopt other existing technologies, such as decimal calibration normalization method, Sigmoid function, etc., and this application does not impose any special restrictions.

[0077] It should be noted that for all individual thermocouples in all samples, even if temperature fluctuations or thermocouple failures occur under normal operating conditions, causing temperature jumps, the temperature variation range is much smaller than when bonding and breakout occur. This is because filtering removes data with excessive deviations from the temperature data. The greater the cumulative effect of the curvature of the fitting curve for the i-th thermocouple and the larger the temperature variation range, the more likely the temperature data for the i-th thermocouple in the j-th sample is that it is the temperature data for bonding and breakout, and the greater the temperature variation value. The temperature variation value is used as part of the fitness of the genetic algorithm. The larger the fitness value, the more suitable the sample is for serving as a cluster center; otherwise, it is less suitable.

[0078] Step 2.3, by comparing the temperature distribution of each thermocouple in each sample with that of all other thermocouples, and the temperature difference between each thermocouple and its adjacent thermocouples, the spatial distribution difference of each thermocouple in each sample is obtained.

[0079] The temperature change of a single thermocouple is insufficient to reflect the occurrence of bonding and steel breakout. Since multiple rows of thermocouples are installed in the crystallizer, the temperature changes and correlation between the thermocouples in different rows can reflect the movement characteristics of the bonding point, thereby determining whether bonding has occurred. Under normal operating conditions, the temperature field in the crystallizer is uniform and stable. The multiple thermocouples work together smoothly, the temperature changes on each surface and between each row are small, the heat conduction is uniform, and a stable spatial temperature pattern is formed.

[0080] When bonding and steel leakage occurs, it will cause temperature imbalance and the bonding point will form a strong heat source. For each row of thermocouples, below the bonding point, the thermocouple closest to the bonding point will heat up first. As the position of the bonding point changes, the thermocouples in the lower row will gradually heat up, while the upper row of thermocouples will gradually cool down as they move away from the bonding point, eventually forming a temperature inversion phenomenon in which the temperature of the lower row of thermocouples is higher than that of the upper row of thermocouples.

[0081] Based on the above analysis, by comparing the temperature distribution of each thermocouple in each sample with that of all other thermocouples, as well as the temperature difference between the row where each thermocouple is located and the row above it, the spatial distribution difference of each thermocouple in each sample is obtained, and the effect of the change in the position of the bonding point on the temperature change of each row of thermocouples is characterized. The expression is:

[0082] Where Z j,irepresents the spatial distribution difference of the i-th thermocouple in the j-th sample; norm() represents the normalization function; calculate the mean temperature data of each row of thermocouples in the j-th sample at each acquisition time, and record the difference in the mean temperature data between the row where the i-th thermocouple in the j-th sample is located and the row above it as the temperature value difference, t j,i represents the sum of the temperature differences of the i-th thermocouple in the j-th sample at all acquisition moments; obtains the stationary point of the fitting curve of each thermocouple, arranges the occurrence moments of the stationary points of all thermocouples in the j-th sample in chronological order to form a time series, and arranges the time intervals between any two adjacent moments in the time series to form a time difference series, ΔT avg represents the sum of all values ​​in the first-order difference sequence of the time difference sequence; α represents a preset value greater than 0, the purpose of which is to avoid the denominator being 0. The value of α is preset manually and can be set by the implementer. In this embodiment, the value of α is 0.1.

[0083] In this embodiment, the difference between the mean values ​​of the temperature data is the absolute value of the difference. As other implementation methods, the implementer may adopt other calculation methods, such as the square of the difference, the ratio, etc., and this application does not impose any special restrictions.

[0084] In this embodiment, the Min-Max normalization method is used to Normalization is performed, as another implementation method, in which On the basis of normalization processing, the implementer may adopt other existing technologies, such as decimal calibration normalization method, Sigmoid function, etc., and this application does not impose any special restrictions.

[0085] It should be noted that: j,i When the value is larger, the difference between the temperature of each row of thermocouples and the temperature of the previous row is greater, indicating that bonding leakage is more likely to occur and temperature inversion phenomenon will occur; the stagnation point indicates the point where the temperature is the highest and begins to drop, ΔT avg The smaller it is, the more time-lag there is in the temperature changes of different rows of thermocouples, that is, the temperatures of different rows of thermocouples reach the highest point at different times; the more likely it is that bonding and leakage will occur, and the greater the value of the spatial distribution difference. Among them, for the temperature sequence under normal working conditions and the temperature sequence of thermocouples far away from the bonding point, the fitting curve does not have a stagnation point. If the fitting curve of any thermocouple does not have a stagnation point, then when calculating the spatial distribution difference of any thermocouple, ΔT avg The value of is 0. The spatial distribution difference is used as part of the fitness of the genetic algorithm. The larger the fitness value, the more suitable it is as a cluster center, and vice versa.

[0086] Step 2.4: Combining the temperature change values ​​and spatial distribution differences of all thermocouples in each sample, obtain the fitness of each sample.

[0087] In summary, the fusion results of the temperature change value and spatial distribution difference of each thermocouple in each sample are calculated; the fitness of each sample is obtained by combining the fusion results of all thermocouples in each sample, and the expression is:

[0088] Where, F j represents the fitness of the jth sample; n represents the number of thermocouples in the jth sample; H j,i It represents the fusion result of the temperature change value and spatial distribution difference of the i-th thermocouple in the j-th sample.

[0089] It should be understood that fusion refers to combining multiple independent variables in a way that enhances the overall effect, such as additive relationship, multiplicative relationship, etc. The implementer can limit it according to the actual situation, and this application does not impose any special restrictions.

[0090] In this embodiment, the fusion result is the sum of the temperature change value and the spatial distribution difference.

[0091] In another embodiment, the fusion result is the product of the temperature change value and the spatial distribution difference.

[0092] The calculated fitness of each sample replaces the traditional silhouette coefficient and Davidson-Bourdin index. This calculated fitness is independent of intra-cluster and inter-cluster distances and takes into account the temperature variation characteristics of a single thermocouple, as well as the relationship between the temperature variations of thermocouples in different rows. The greater the fitness of any sample, the more consistent it is with the bonding breakout phenomenon and the more suitable it is to become a cluster center.

[0093] Step 3: Optimize the GA-Kmeans model and assign labels to all samples according to the fitness.

[0094] In order to cluster all samples and distinguish between bonded breakout samples and normal samples based on the clustering results, two initial cluster centers are required: the initial cluster center for bonded breakout samples and the initial cluster center for normal samples. When selecting the initial cluster centers for bonded breakout samples using a genetic algorithm based on the fitness of each sample, samples selected from the historical temperature data are first encoded and converted into gene form. An initial population is then randomly generated, and the sample quality is determined based on the fitness. Selection, crossover, and mutation operations are then performed until the maximum number of iterations or the convergence threshold is reached. The sample with the highest fitness output by the genetic algorithm is used as the initial cluster center for bonded breakout samples. When selecting the initial cluster centers for normal samples using a genetic algorithm based on the fitness of each sample, samples selected from the historical temperature data are first encoded and converted into gene form. An initial population is then randomly generated, and the sample quality is determined based on the inverse of the fitness. Selection, crossover, and mutation operations are then performed until the maximum number of iterations or the convergence threshold is reached. The sample with the highest fitness output by the genetic algorithm is used as the initial cluster center for normal samples.

[0095] In this embodiment, when using a genetic algorithm to select the initial cluster center, the population size is set to 200, the crossover probability is set to 0.8, the mutation probability is set to 0.05, the maximum number of iterations is set to 200, and the convergence threshold is set to 0.01. The values ​​of the population size, crossover probability, mutation probability, maximum number of iterations and convergence threshold are preset manually. The implementer can choose the values ​​according to actual conditions, and this application does not impose any special restrictions.

[0096] Based on the initial cluster centers determined by the genetic algorithm, a clustering algorithm is used to assign each sample selected from the historical temperature data to the nearest cluster center. Samples belonging to the same cluster center as the initial cluster center of the bonded breakout samples are designated as bonded breakout samples; samples belonging to the same cluster center as the initial cluster center of the normal samples are designated as normal samples. During this process, the cluster center positions are continuously updated until the cluster to which the sample belongs no longer changes or the preset number of iterations is reached. This achieves a stable partitioning of the temperature data based on similarity, effectively distinguishing the temperature data corresponding to bonded breakout samples from those corresponding to normal samples, and providing solid data preprocessing support for the subsequent breakout prediction model. After clustering, each sample is assigned a label: the normal sample's label is the first preset value, and the bonded breakout sample's label is the second preset value.

[0097] In this embodiment, the first preset value is 0, indicating a normal working condition, and the second preset value is 1, indicating that bonding leakage occurs.

[0098] In this embodiment, the value of the preset number of iterations is 200. The value of the preset number of iterations is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0099] Step 4: Build the Transformer-BiLSTM model.

[0100] Bi-directional Long Short-Term Memory (BiLSTM) is an improved version of Long Short-Term Memory (LSTM) and contains two LSTM layers. BiLSTM can process sequences in both the forward and backward directions simultaneously, capturing the past and future information of the sequence, which helps to improve the prediction performance of the model. However, due to its own recursive structure, BiLSTM cannot truly solve the problem of long-term dependency. The Transformer model based on the self-attention mechanism uses a parallel attention mechanism for feature extraction, which does not have the problem of long-term dependency and can extract distant time series features. The Transformer is combined with BiLSTM to enhance the ability to capture time series data. The core mechanisms of the Transformer model include self-attention mechanism, multi-head attention, position encoding, residual connection and layer normalization. The structural diagram of the Transformer model is shown in the figure below. Figure 5 As shown in the figure. In the steel breakout prediction model, the input is the known historical temperature data, and the output is the temperature data classification result. In this case, the attention layer structure of the decoder is not required. Therefore, the decoder part of the traditional Transformer model is modified into a fully connected layer, and the original attention part is replaced by the BiLSTM part to establish the Transformer-BiLSTM model. The structural diagram of the Transformer-BiLSTM model is shown in the figure. Figure 6 The traditional Transformer-BiLSTM model is a well-known technology.

[0101] In this embodiment, the input is a sample consisting of temperature data from 120 thermocouples, and the classification output is a label. The Transformer-BiLSTM model has 128 hidden neurons, 4 attention heads, 128 key channels, a batch size of 64, an initial learning rate of 0.01, a maximum number of iterations of 100, an Adam optimizer, and a Softmax classifier. The values ​​of the number of hidden neurons, number of attention heads, number of key channels, batch size, initial learning rate, and maximum number of iterations can be set by the implementer according to actual conditions and are not specifically limited in this application.

[0102] Step 5: Train the neural network by assigning labeled samples to obtain a steel breakout prediction model.

[0103] The optimized GA-Kmeans model and the Transformer-BiLSTM model are combined to form a GA-Kmeans-Transformer-BiLSTM model. In order to improve the adaptability and generalization ability of the steel leakage prediction model, the training samples and test samples are cross-selected to avoid duplication, the bonding steel leakage samples are divided into the training set and the test set according to the first preset ratio, and the normal samples are divided into the training set and the test set according to the second preset ratio. The training set is used to train the Transformer-BiLSTM model, the Kmeans-Transformer-BiLSTM model and the GA-Kmeans-Transformer-BiLSTM model respectively. Among them, the samples in the training set and the test set are all labeled. The loss function is the cross entropy loss function. The accuracy-loss value diagram of the Transformer-BiLSTM model is as follows. Figure 7 As shown, the accuracy-loss value diagram of the Kmeans-Transformer-BiLSTM model is as follows Figure 8 As shown, the accuracy-loss value diagram of the GA-Kmeans-Transformer-BiLSTM model is as follows Figure 9 As shown. Figure 7 As can be seen from the figure, after 100 iterations of the Transformer-BiLSTM model, neither the accuracy nor the loss value reached the best. Figure 8 As can be seen from the figure, the Kmeans-Transformer-BiLSTM model achieves 100% accuracy after 44 iterations and the loss value drops to 0. Figure 9 As can be seen in the figure, the GA-Kmeans-Transformer-BiLSTM model achieves 100% accuracy and drops its loss to 0 after 18 iterations, reaching its optimal state faster and achieving the best training performance. Model training and accuracy calculation are well-known techniques and will not be further described in this application.

[0104] In this embodiment, the first preset ratio is 5:3, and the second preset ratio is 5:2. The implementer can set the values ​​of the first preset ratio and the second preset ratio at will, and this application does not impose any special restrictions.

[0105] The trained Transformer-BiLSTM, Kmeans-Transformer-BiLSTM, and GA-Kmeans-Transformer-BiLSTM models are tested using the test set. An alarm is issued when the output of the Transformer-BiLSTM, Kmeans-Transformer-BiLSTM, and GA-Kmeans-Transformer-BiLSTM models reaches the second preset value. Test result evaluation metrics are introduced, including prediction accuracy and report rate.

[0106] Forecast accuracy σ p The expression is: Report rate σ r The expression is: Where N r Indicates the number of correct alarms, N f Indicates the number of false alarms, and N1 indicates the number of missed alarms.

[0107] The test results of the Transformer-BiLSTM model, the Kmeans-Transformer-BiLSTM model, and the GA-Kmeans-Transformer-BiLSTM model are shown in Table 1.

[0108] Table 1. Test results of the model

[0109]

[0110] Table 1 shows that both the Transformer-BiLSTM and Kmeans-Transformer-BiLSTM models suffer from false negatives, while the GA-Kmeans-Transformer-BiLSTM model has zero false negatives and a 100% accuracy rate. Furthermore, the Transformer-BiLSTM and Kmeans-Transformer-BiLSTM models have six and four false positives, respectively, with prediction rates of 93.0% and 96.0%, respectively. The GA-Kmeans-Transformer-BiLSTM model has only one false positive, achieving a prediction accuracy of 99.5%, a significant improvement over the other two models. This indicates that the GA-Kmeans-Transformer-BiLSTM model improves the recognition accuracy of both normal and bonded steel breakout samples, effectively addressing both false negatives and false positives, and exhibiting superior recognition performance and generalization capabilities.

[0111] The trained GA-Kmeans-Transformer-BiLSTM model is used as the steel breakout prediction model.

[0112] The sample to be classified is fed into the GA-Kmeans-Transformer-BiLSTM model, which outputs a prediction result, which serves as the sample label. During continuous casting, this prediction result can be used to guide the production of high-quality steel.

[0113] Based on the same inventive concept as the above-mentioned method, an embodiment of the present application also provides a continuous casting breakout prediction system based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned continuous casting breakout prediction methods based on deep learning are implemented.

[0114] In summary, the present application fully considers the temperature changes of thermocouples installed at different positions on the crystallizer, including the fact that the temperature of a single thermocouple shows a trend of first rising and then falling when bonding breakout occurs, and the temperature change range of a single thermocouple is large, as well as the temperature changes of adjacent rows of thermocouples showing "time lag" and "temperature inversion" in space, to obtain fitness, which more accurately reflects the working conditions to which the temperature data belongs; compared with the traditional use of the quality index of clustering results as fitness, the calculated fitness does not depend on the intra-cluster distance and the inter-cluster distance, thereby reducing the distance metric deviation under data noise or dimensionality disaster, selecting the optimal initial clustering center, and then classifying the samples based on the initial clustering center, thereby improving the accuracy of sample distinction;

[0115] Furthermore, the steel breakout prediction model is trained based on the accurately distinguished samples, so that the steel breakout prediction model can more accurately capture the intrinsic characteristics of the temperature data, and thus have higher prediction accuracy when using the steel breakout prediction model to predict steel breakout in the continuous casting process.

[0116] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to the embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0117] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic characteristics of the present application. Therefore, from all perspectives, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A continuous casting breakout prediction method based on deep learning, characterized in that: The method comprises the following steps: Acquire multiple samples, each sample containing temperature data of all thermocouples within a preset time period; By comparing the temperature data of each thermocouple in each sample with the temperature data of all thermocouples in all samples, the temperature change deviation of each thermocouple in each sample is obtained; Arrange all temperature data of each thermocouple in each sample in time sequence to form each temperature sequence, and obtain a fitting curve of all temperature data in each temperature sequence; analyze the distribution range of the temperature data of each thermocouple in each sample and the temperature change deviation to obtain the temperature change value of each thermocouple in each sample; Calculate the spatial distribution difference of each thermocouple in each sample, the expression is: Where Z j,i represents the spatial distribution difference of the i-th thermocouple in the j-th sample; norm() represents the normalization function; calculate the mean temperature data of each row of thermocouples in the j-th sample at each acquisition time, and record the difference in the mean temperature data between the row where the i-th thermocouple in the j-th sample is located and the row above it as the temperature value difference, t j,i represents the sum of the temperature differences of the i-th thermocouple in the j-th sample at all acquisition moments; obtains the stationary point of the fitting curve of each thermocouple, arranges the occurrence moments of the stationary points of all thermocouples in the j-th sample in chronological order to form a time series, and arranges the time intervals between any two adjacent moments in the time series to form a time difference series, ΔT avg represents the sum of all values ​​in the first-order difference sequence of the time difference sequence; α represents a value preset to be greater than 0; Calculate the fusion results of the temperature change value and spatial distribution difference of each thermocouple in each sample; The sum of the fusion results of all thermocouples in each sample is used as the fitness of each sample; A genetic algorithm is used to select the optimal initial cluster center based on the calculated fitness. All samples are clustered in combination with the clustering algorithm, and sample labels are assigned based on the clustering results. A GA-Kmeans-Transformer-BiLSTM model is constructed and trained with labeled samples to obtain a steel breakout prediction model.

2. The method for predicting continuous casting breakout based on deep learning according to claim 1, characterized in that: The process of obtaining the temperature change deviation is as follows: Obtaining a curvature calculation formula for each fitting curve, and calculating a definite integral result of each curvature calculation formula in the interval [1, N], where N is the total number of data in the temperature series; the change is reflected by the definite integral result; Calculating the mean of the definite integral results of all thermocouples in all samples; The temperature variation deviation is obtained by comparing the definite integral result of each thermocouple in each sample with the mean value.

3. The method for predicting continuous casting breakout based on deep learning according to claim 2, characterized in that: The expression of the temperature change deviation is: S j,i =I j,i -I j,avg Where S j,i Indicates the temperature change deviation of the i-th thermocouple in the j-th sample; I j,i I represents the integration result of the i-th thermocouple in the j-th sample; j,avg represents the mean of the integration results for all thermocouples in all samples.

4. The method for predicting continuous casting breakout based on deep learning according to claim 1, characterized in that: The process of obtaining the temperature change value is as follows: Calculate the range of all temperature data for each thermocouple in each sample; The temperature change value is positively correlated with the range and the temperature change deviation respectively.

5. The method for predicting continuous casting breakout based on deep learning according to claim 1, characterized in that: The process of assigning labels to all samples by using the fitness is as follows: A genetic algorithm is used to select initial cluster centers according to the suitability of each sample, and a clustering algorithm is used to cluster all samples based on the initial cluster centers. The bonding leak samples and normal samples are distinguished by the clustering results, and different labels are assigned to the bonding leak samples and the normal samples. The label of the normal sample is a first preset value, and the label of the bonding leak sample is a second preset value.

6. The method for predicting continuous casting breakout based on deep learning according to claim 5, characterized in that: The step of training the model by assigning labeled samples includes: All bonded steel leakage samples are divided into training sets and test sets according to the preset ratio, and normal samples are divided into training sets and test sets according to the preset ratio; The model is trained and tested using the training set and the test set.

7. The method for predicting continuous casting breakout based on deep learning according to claim 6, characterized in that: When testing the trained model, the test result evaluation indicators include prediction accuracy and reporting rate; Forecast accuracy σ p The expression is: Report rate σ r The expression is: Where N r Indicates the number of correct alarms, N f Indicates the number of false alarms, and N1 indicates the number of missed alarms; When the output of the model reaches the second preset value, an alarm is issued.

8. A continuous casting breakout prediction system based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the continuous casting breakout prediction method based on deep learning as described in any one of claims 1 to 7 are implemented.

Images