Method, device, equipment and medium for controlling transient level fluctuation of slab continuous casting mold

Abstract

The application relates to the technical field of crystallizers, and discloses a slab continuous casting crystallizer instantaneous liquid level fluctuation control method, device, equipment and medium, the method comprises the following steps: extracting parameter data from a slab continuous casting crystallizer of a target steel plant; analyzing a first relationship and a second relationship between argon blowing amount at a stopper and argon blowing amount at a slide and liquid level fluctuation data based on a Pearson correlation coefficient and a Spearman correlation coefficient; determining a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data; obtaining real-time argon blowing amount data, predicting real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship, and obtaining predicted liquid level fluctuation data; and in response to the real-time liquid level fluctuation data exceeding a preset normal range, adjusting the argon blowing amount at the stopper and / or the argon blowing amount at the slide to control the real-time liquid level fluctuation data to be maintained within the preset normal range. Through the scheme, the liquid level fluctuation can be quickly and accurately judged, and the crystallizer liquid level fluctuation can be stably controlled.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of crystallizers, in particular to a method and device for controlling transient liquid level fluctuation of a slab continuous casting crystallizer, equipment and a medium. BACKGROUND

[0002] Continuous casting is a core link in the steel production process, and its position and role are very important. However, due to the large number of complex processes involved in the continuous casting process, the produced continuous casting billets have surface defects, which reduces the quality of the continuous casting billets. Many research results have proved that the liquid level fluctuation of the crystallizer has a significant impact on the surface quality of the continuous casting billets, and the generation of abnormal fluctuations will greatly increase the probability of the generation of surface defects of the continuous casting billets. Among them, the transient crystallizer liquid level abnormal fluctuation is difficult to effectively control and eliminate in the actual production process because it does not have the characteristics of periodic change. The frequent generation of transient crystallizer liquid level abnormal fluctuation will seriously reduce the continuous casting production efficiency and the quality of the continuous casting billets, and thus cause significant economic losses. At present, with the continuous development of computer technology and data feature mining technology, using big data feature analysis to analyze the potential relationship between abnormal phenomena and processes and to optimize and eliminate abnormal phenomena in the production process has become an inevitable trend for eliminating the crystallizer liquid level abnormal fluctuation. SUMMARY

[0003] The embodiments of the present application provide a method and device for controlling transient liquid level fluctuation of a slab continuous casting crystallizer, equipment and a medium, aiming at solving many technical problems in the related art.

[0004] In a first aspect, the embodiments of the present application provide a method for controlling transient liquid level fluctuation of a slab continuous casting crystallizer, comprising:

[0005] extracting parameter data from a slab continuous casting crystallizer of a target steel plant, wherein the parameter data includes liquid level fluctuation data, stopper position data and argon blowing amount data at different positions;

[0006] analyzing a first relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on a Pearson correlation coefficient, and analyzing a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on a Spearman correlation coefficient;

[0007] determining a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data according to the first relationship and the second relationship;

[0008] obtaining real-time argon blowing amount data in the slab continuous casting crystallizer of the target steel plant, and predicting real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship to obtain predicted liquid level fluctuation data;

[0009] In response to the real-time liquid level fluctuation data exceeding the preset normal range, the argon blowing amount at the stopper and / or the argon blowing amount at the slide plate are adjusted to control the real-time liquid level fluctuation data to be maintained within the preset normal range.

[0010] In one embodiment, after extracting the parameter data, the method further comprises:

[0011] The parameter data is preprocessed to obtain preprocessed parameter data, wherein the preprocessing process comprises:

[0012] Abnormal fluctuation data caused by changes in process conditions is removed from the parameter data to obtain preliminary screening data;

[0013] All liquid level abnormal fluctuation data in the same time period is obtained from the preliminary screening data based on the process stabilization time, and is arranged in descending order;

[0014] From the all liquid level abnormal fluctuation data, a preset number of target liquid level abnormal fluctuation data ranked in the front are selected, and the average value corresponding to all target liquid level abnormal fluctuation data is calculated;

[0015] The average value is taken as the liquid level fluctuation degree in the time period.

[0016] In one embodiment, optionally, the first relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data is analyzed based on the Pearson correlation coefficient, comprising:

[0017] The argon blowing amount at the stopper and the first liquid level fluctuation degree corresponding thereto, and the argon blowing amount at the slide plate and the second liquid level fluctuation degree corresponding thereto are extracted from the preprocessed parameter data to obtain two groups of variable pairs;

[0018] Based on the Pearson correlation coefficient calculation formula, the first correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the second correlation coefficient between the argon blowing amount at the slide plate and the second liquid level fluctuation degree are calculated respectively;

[0019] The first correlation coefficient, the second correlation coefficient and a first preset coefficient threshold value are compared, and a first target variable pair with a correlation coefficient greater than the preset coefficient threshold value is selected according to the comparison result to form a first effective correlation data set.

[0020] In one embodiment, optionally, the second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data is analyzed based on the Spearman correlation coefficient, comprising:

[0021] The variable values of the two groups of variable pairs are sorted respectively, and a unique rank order is assigned to each variable value, wherein if there are variable values with the same numerical value, the average value of the rank orders corresponding to the same numerical value variable values in this group is taken as the common rank of the same numerical value variable values;

[0022] For each group of variable pairs, the rank difference of the corresponding variable values is calculated according to the assigned rank order;

[0023] According to the rank difference and the Spearman correlation coefficient calculation formula, the third correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the fourth correlation coefficient between the argon blowing amount at the slide plate and the second liquid level fluctuation degree are calculated respectively.

[0024] The third correlation coefficient, the fourth correlation coefficient and a second preset coefficient threshold are compared, and a second target variable pair with a correlation coefficient greater than the second preset coefficient threshold is selected according to the comparison result to form a second effective correlation data set.

[0025] In one embodiment, optionally, the method further comprises:

[0026] According to the first effective correlation data set and the second effective correlation data set, a final effective correlation data set is determined;

[0027] The final effective correlation data set is subjected to big data feature analysis, and a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation degree is obtained by least square fitting.

[0028] In one embodiment, optionally, the method further comprises:

[0029] Actual real-time liquid level fluctuation data corresponding to the real-time argon blowing amount data is extracted from the slab continuous casting crystallizer;

[0030] The real-time liquid level fluctuation data and the predicted liquid level fluctuation data are compared, and it is determined whether to update the fitting linear relationship according to the comparison result.

[0031] In one embodiment, optionally, comparing the real-time liquid level fluctuation data and the predicted liquid level fluctuation data according to the comparison result to determine whether to update the fitting linear relationship comprises:

[0032] The mean absolute error value and the determination coefficient between the real-time liquid level fluctuation data and the predicted liquid level fluctuation data are calculated;

[0033] In response to the average absolute error value being greater than or equal to a preset error threshold value and the determination coefficient being greater than or equal to a preset coefficient threshold value, it is determined that the fitted linear relationship is not updated, otherwise, it is determined that the fitted linear relationship is updated.

[0034] In a second aspect, an embodiment of the present application provides a slab continuous casting mold transient liquid level fluctuation control device, comprising:

[0035] An extraction module is configured to extract parameter data from a slab continuous casting mold of a target steel plant, wherein the parameter data comprises liquid level fluctuation data, stopper position data, and argon blowing amount data at different positions.

[0036] An analysis module is configured to analyze a first relationship between argon blowing amount at a stopper, argon blowing amount at a slide plate, and the liquid level fluctuation data based on a Pearson correlation coefficient, and analyze a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate, and the liquid level fluctuation data based on a Spearman correlation coefficient.

[0037] A relationship determination module is configured to determine a fitted linear relationship between the argon blowing amount data and the liquid level fluctuation data according to the first relationship and the second relationship.

[0038] A prediction module is configured to obtain real-time argon blowing amount data in the slab continuous casting mold of the target steel plant, and predict real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitted linear relationship, to obtain predicted liquid level fluctuation data.

[0039] A control module is configured to adjust the argon blowing amount at the stopper and / or the argon blowing amount at the slide plate in response to the real-time liquid level fluctuation data being out of a preset normal range, so as to control the real-time liquid level fluctuation data to be maintained within the preset normal range.

[0040] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the slab continuous casting mold transient liquid level fluctuation control method when executing the computer program.

[0041] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program implements the steps of the slab continuous casting mold transient liquid level fluctuation control method when executed by a processor.

[0042] The scheme realized by the above slab continuous casting mold transient liquid level fluctuation control method, device, equipment and medium extracts parameter data from the slab continuous casting mold of the target steel plant, wherein the parameter data includes liquid level fluctuation data, stopper position data and argon blowing amount data at different positions; the first relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data is analyzed based on the Pearson correlation coefficient, and the second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data is analyzed based on the Spearman correlation coefficient; the fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data is determined according to the first relationship and the second relationship; the real-time argon blowing amount data in the slab continuous casting mold of the target steel plant is obtained, the real-time liquid level fluctuation data is predicted according to the real-time argon blowing amount data and the fitting linear relationship, and the predicted liquid level fluctuation data is obtained; in response to the real-time liquid level fluctuation data exceeding the preset normal range, the argon blowing amount at the stopper and / or the argon blowing amount at the slide plate is adjusted to control the real-time liquid level fluctuation data to be maintained within the preset normal range. Through the above technical scheme of the present application, a new evaluation standard for the degree of transient mold liquid level abnormal fluctuation is first proposed by data feature mining technology, and the connection between the fluctuation degree and the production process is established to determine the continuous casting production process causing the transient mold liquid level abnormal fluctuation, so that the liquid level fluctuation can be quickly and accurately judged, and the mold liquid level fluctuation can be controlled to be stable. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 A schematic flowchart of a slab continuous casting mold transient liquid level fluctuation control method according to an embodiment of the present application is shown.

[0045] Figure 2 A flowchart of a parameter data preprocessing process in a slab continuous casting mold transient liquid level fluctuation control method according to an embodiment of the present application is shown.

[0046] Figure 3 A schematic flowchart of step S102 in a slab continuous casting mold transient liquid level fluctuation control method according to an embodiment of the present application is shown.

[0047] Figure 4 A schematic flowchart of step S102 in a slab continuous casting mold transient liquid level fluctuation control method according to another embodiment of the present application is shown.

[0048] Figure 5 A schematic flowchart of a method for controlling instantaneous liquid level fluctuations in a slab continuous casting crystallizer according to another embodiment of this application is shown.

[0049] Figure 6 A liquid level fluctuation diagram according to an embodiment of this application is shown.

[0050] Figure 7 A correlation analysis result graph is shown according to an embodiment of this application.

[0051] Figure 8 A comparison graph of field data and a straight line obtained by fitting a formula is shown according to an embodiment of this application.

[0052] Figure 9 A graph showing the comparison results of different evaluation parameters according to one embodiment of this application is illustrated.

[0053] Figure 10 A block diagram of a device for controlling instantaneous liquid level fluctuations in a slab continuous casting crystallizer according to an embodiment of this application is shown.

[0054] Figure 11 A block diagram of a computer device according to one embodiment of this application is shown. Detailed Implementation

[0055] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0056] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0057] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0058] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0059] Please see Figure 1 , Figure 1 A schematic flowchart of a method for controlling instantaneous liquid level fluctuations in a slab continuous casting crystallizer according to an embodiment of this application is shown.

[0060] likeFigure 1 As shown, the flow of the transient liquid level fluctuation control method of the slab continuous casting mold according to one embodiment of the present application includes:

[0061] Step S101, extracting parameter data from the slab continuous casting mold of the target steel plant, wherein the parameter data includes liquid level fluctuation data, stopper position data, and argon blowing amount data at different positions;

[0062] The slab continuous casting mold is the core equipment of continuous casting production, which is a metal container for continuously cooling and solidifying molten steel into a slab embryo, and the stability of the molten steel liquid level inside the mold directly determines the surface quality of the slab. The liquid level fluctuation data is a numerical sequence of the change of the molten steel liquid level height in the mold with time collected by a liquid level sensor (such as an electromagnetic induction type or a thermocouple type), usually in millimeters (mm), reflecting the dynamic change of the molten steel liquid level. The stopper position data is the real-time displacement data of the stopper (a columnar part for adjusting the molten steel outflow) installed above the submerged nozzle of the mold, in millimeters (mm), and its position change directly controls the opening degree of the nozzle passage. The argon blowing amount data at different positions is the flow data of the protective argon introduced into the mold through the argon pipeline, mainly including the argon flow at the stopper (stopper center hole) and the sliding plate (gap between the sliding part of the nozzle and the stopper), usually in liters per minute (L / min), which is used to prevent nozzle clogging and improve molten steel fluidity.

[0063] In this step, first, the target steel plant and the corresponding slab continuous casting machine are determined, and the parameter data in the continuous production process is extracted from the data storage by the automatic data acquisition system (such as the PLC control system and the SCADA system) matched with the mold. The acquisition frequency needs to match the process dynamic change to ensure the capture of transient liquid level fluctuation. The extracted data needs to be aligned by timestamp to ensure that the liquid level fluctuation, stopper position, and argon blowing amount data at the same time are one-to-one corresponding.

[0064] Through the above technical solution, the systematic collection of key process parameters is realized, the randomness and errors of manual collection are avoided, the data integrity and timeliness are ensured, and original data support is provided for subsequent analysis of the correlation between argon blowing amount and liquid level fluctuation.

[0065] Step S102, analyzing a first relationship between the argon blowing amount at the stopper, the argon blowing amount at the sliding plate, and the liquid level fluctuation data based on the Pearson correlation coefficient, and analyzing a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the sliding plate, and the liquid level fluctuation data based on the Spearman correlation coefficient;

[0066] Pearson correlation coefficient is a statistical index used to measure the strength of linear association between two continuous variables, with a value range of [-1, 1], the closer to 1, the stronger the linear association; positive correlation means that when one variable increases, the other variable also increases, and vice versa.

[0067] Spearman correlation coefficient is an index used to measure the strength of monotonic association between two variables, without the need to satisfy the normal distribution of variables, with a value range of [-1, 1], by assigning ranks to the sorted values of variables, the correlation is calculated, and the abnormal values are more resistant, which can capture linear and nonlinear monotonic association.

[0068] The first relationship is the linear association between the argon blowing amount at the stopper and the liquid level fluctuation data obtained by Pearson correlation coefficient analysis.

[0069] The second relationship is the monotonic association between the argon blowing amount at the stopper and the liquid level fluctuation data obtained by Spearman correlation coefficient analysis.

[0070] As shown in Figure 2 In one embodiment, after extracting the parameter data, the method further comprises:

[0071] preprocessing the parameter data to obtain preprocessed parameter data, wherein the preprocessing process includes:

[0072] Step S201: removing abnormal fluctuation data caused by changes in process conditions from the parameter data to obtain preliminary screening data;

[0073] Process condition change: a deterministic process operation that leads to non-instantaneous abnormal fluctuation of liquid level in continuous casting production, mainly including changing ladle (changing liquid ladle), reducing speed / increasing speed (adjusting casting speed), changing water gap, etc. The fluctuation caused by such operation is irrelevant to argon blowing amount and needs to be excluded to avoid interference with correlation analysis.

[0074] Preliminary screening data is the remaining parameter data that only reflects the influence of controllable factors such as argon blowing amount after removing abnormal fluctuation data caused by changes in process conditions, providing clean data samples for subsequent calculation of liquid level fluctuation degree.

[0075] In this step, the interference of uncontrollable factors (process operation) on liquid level fluctuation data is eliminated to ensure that the correlation between argon blowing amount and liquid level fluctuation in subsequent analysis only reflects the true influence of the two, avoiding false correlation and improving data quality.

[0076] Step S202: obtaining all liquid level abnormal fluctuation data within the same time period from the preliminary screening data based on the process stable time, and arranging them in descending order;

[0077] Process stable time is the time period that the process parameters (casting speed, stopper position, argon blowing amount) are kept stable in continuous casting production, to ensure that the liquid level fluctuation in this time period is mainly affected by the argon blowing amount, rather than process adjustment.

[0078] Liquid level abnormal fluctuation data is the fluctuation value deviating from the set value in the initial screening data, reflecting the abnormal deviation degree of the liquid level at that moment.

[0079] In this step, the initial screening data is divided into multiple continuous time segments with process stable time (such as 30 seconds) as the time unit. All the liquid level abnormal fluctuation data (taking absolute value, only focusing on the fluctuation size) in each time segment are ranked in descending order according to the value from large to small.

[0080] Step S203, from the all liquid level abnormal fluctuation data, select the target liquid level abnormal fluctuation data in the pre-set number of front ranks, and calculate the average value corresponding to all target liquid level abnormal fluctuation data;

[0081] Among them, the pre-set number can be set according to the process requirements, for example, set the pre-set number to 10, so as to ensure covering the main abnormal fluctuation in this time period, while avoiding too many small fluctuation data to lower the average value representative.

[0082] For example, set the pre-set number (such as 10), select the top 10 maximum values from the descending fluctuation data of each process stable time period as the target data. If there are less than 10 fluctuation data in this time period (such as only 8), all of them are selected. Calculate the arithmetic mean of these target data, for example, the target data is 5mm, 4.8mm, 4.5mm, 4.2mm, 3.9mm, 3.7mm, 3.5mm, 3.3mm, 3.1mm, 2.9mm, and the average value is 3.8mm.

[0083] Step S204, taking the average value as the liquid level fluctuation degree in the time period.

[0084] The liquid level fluctuation degree is the average value of the target liquid level abnormal fluctuation data in each process stable time period, with the unit of millimeter (mm), which is used to measure the severity of the instantaneous liquid level abnormal fluctuation in this time period.

[0085] In this technical solution, the discrete instantaneous fluctuation data is converted into a quantitative index (average value) reflecting the overall fluctuation degree of the time period, which is convenient for subsequent correlation analysis with the argon blowing amount data, thereby avoiding the randomness interference of single moment data. At the same time, the calculation standard of fluctuation degree is unified, which ensures the comparability of fluctuation data in different time periods, and improves the accuracy of correlation analysis.

[0086] For example, Figure 3As shown, in one embodiment, step S102 includes:

[0087] Step S301, extracting the argon blowing amount at the stopper and the first liquid level fluctuation degree corresponding thereto, and the argon blowing amount at the slide and the second liquid level fluctuation degree corresponding thereto from the pre-processed parameter data, respectively, to obtain two groups of variable pairs;

[0088] From the aligned parameter data, the argon blowing amount at the stopper and the first liquid level fluctuation degree corresponding thereto, and the argon blowing amount at the slide and the second liquid level fluctuation degree corresponding thereto are split out.

[0089] Step S302, based on the Pearson correlation coefficient calculation formula, respectively calculating the first correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the second correlation coefficient between the argon blowing amount at the slide and the second liquid level fluctuation degree;

[0090] The correlation strength and correlation direction between different process parameters and the mold level fluctuation in continuous casting production are accurately judged. In this study, Pearson correlation coefficient is introduced as the core analysis tool. Through the quantitative calculation of the coefficient, the linear correlation degree between the change of process parameters and the liquid level fluctuation can be objectively measured, which provides data support for subsequent screening of key process factors affecting liquid level fluctuation. Specifically, Pearson correlation coefficient is a classic quantitative index in the field of statistics for analyzing the correlation of two continuous random variables. Its core function is to describe the closeness of linear correlation between two random variables in numerical form, and the coefficient has a clear statistical meaning in representing the linear relationship between variables, which can effectively avoid the deviation caused by subjective judgment. From the definition level, for any two random variables M and N, the calculation logic of their Pearson correlation coefficient is: first, solve the covariance of the two variables (used to measure the trend of common change between variables), and then divide the covariance result by the product of the standard deviations of the two variables (used to eliminate the influence of the difference in the magnitude of the variable itself on the correlation judgment). Through this standardization processing, the correlation coefficient with a value range strictly limited between-1 and 1 is finally obtained, ensuring the comparability of the correlation of variables in different dimensions.

[0091] In the value meaning of Pearson correlation coefficient, when the coefficient value is 0, it represents that there is no linear correlation between the two variables, that is, the change of process parameters will not cause regular change of liquid level fluctuation; on the contrary, when the Pearson correlation coefficient takes the value of-1 or 1, it means that there is a complete monotone linear relationship between the two variables. Among them, the coefficient is 1, which is a complete positive linear correlation (when the process parameter increases, the liquid level fluctuation amplitude increases synchronously), and the coefficient is-1, which is a complete negative linear correlation (when the process parameter increases, the liquid level fluctuation amplitude decreases synchronously), both of which mean that there is a strong linear linkage rule between variables.

[0092] Based on the above definition, the mathematical expression of Pearson correlation coefficient is shown as formula (1), which directly outputs the linear correlation degree of two variables by quantifying the statistical characteristics of variables M and N, and is the core calculation basis for subsequent analysis of the correlation between process parameters and liquid level fluctuation.

[0093] (1)

[0094] Where Me is the average value of variable Mi, and Ne is the average value of variable Ni. The value range of correlation coefficient rMN is -1 to 1.

[0095] Based on the Pearson correlation coefficient formula, the correlation coefficient of two variable pairs is calculated: first, the mean value of each variable is calculated, then the covariance (reflecting the common trend of variables) is solved, and finally the product of the standard deviations of the two variables (eliminating the difference in magnitude) is divided to obtain the linear correlation quantitative value.

[0096] Step S303, compare the first correlation coefficient, the second correlation coefficient and the first preset coefficient threshold, and select the first target variable pair with a correlation coefficient greater than the preset coefficient threshold according to the comparison result to form a first effective correlation data set.

[0097] The first preset coefficient threshold is a critical value for judging whether the Pearson correlation coefficient is significant. According to the characteristics of continuous casting process data, if the coefficient is greater than the threshold, it means that the linear correlation is significant and can be included in the subsequent analysis. The first target variable pair is a variable pair with a Pearson correlation coefficient greater than the first preset coefficient threshold (such as argon blowing amount at stopper - fluctuation degree), which reflects that the linear correlation of this group of variables has statistical significance and can be used to construct an effective correlation data set. The first effective correlation data set is a data set composed of sample data of all first target variable pairs, which provides a basis for cross-validation with the Spearman coefficient screening result in the subsequent step.

[0098] For example, set the first preset coefficient threshold to 0.6, and compare the calculated first correlation coefficient (0.72) and second correlation coefficient (0.65) with the threshold respectively: both are greater than 0.6, so the argon blowing amount at stopper - fluctuation degree and the argon blowing amount at slide - fluctuation degree are determined as the first target variable pair. All sample data of the two variable pairs (such as argon blowing amount and fluctuation degree value in each time period) are integrated to form the first effective correlation data set.

[0099] In the above technical solution, the variable pairs with insignificant linear correlation are removed, the interference of invalid data on model fitting is reduced, the analysis efficiency is improved, and a data set focusing on strong linear correlation variables is formed.

[0100] As shown in FIG. 1, Figure 4 In one embodiment, step S102 includes:

[0101] Step S401, sort the variable values of the two sets of variable pairs respectively, and assign a unique rank order to each variable value, wherein if there are variable values with the same value, the average of the rank orders corresponding to the same variable value in this set is taken as the common rank of the variable value;

[0102] The rank order is the serial number assigned to each value after sorting the variable values by size (for example, the variable values [2.3, 2.5, 2.1] are sorted as [2.1, 2.3, 2.5], and the rank orders are 1, 2, and 3, respectively), which is used to calculate the Spearman correlation coefficient.

[0103] Step S402, for each set of variable pairs, calculate the rank difference of the corresponding variable values according to the assigned rank order;

[0104] The rank difference is the difference between the argon blowing level and the fluctuation level in the same data sample (for example, the argon blowing level of a sample is 1.5, the fluctuation level is 2, and the rank difference is 1.5-2=-0.5), which is the core intermediate variable for calculating the Spearman correlation coefficient.

[0105] The difference reflects the deviation of the two sets of ranks, and the smaller the difference, the stronger the monotonic correlation between the argon blowing amount and the fluctuation degree, providing an intuitive intermediate result for coefficient calculation.

[0106] Step S403, according to the rank difference and the formula for calculating the Spearman correlation coefficient, calculate the third correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the fourth correlation coefficient between the argon blowing amount at the slide and the second liquid level fluctuation degree;

[0107] In analyzing the correlation between continuous casting process parameters and instantaneous crystallizer liquid level abnormal fluctuation, in addition to the Pearson correlation coefficient mentioned earlier, the Spearman correlation coefficient is also an important quantitative analysis tool. The core function of this coefficient is to evaluate the strength and direction of the correlation between two variables, and unlike the focus on linear relationships of the Pearson correlation coefficient, the Spearman correlation coefficient describes the correlation between variables through a monotonic function, i.e. without strict linear relationship, as long as the variables show a monotonic trend of "one variable increases, the other variable consistently increases or consistently decreases", this coefficient can effectively capture this correlation.

[0108] In terms of application scope, the Spearman correlation coefficient has stronger flexibility, not only for continuous variables, but also for discrete variables, especially for ordinal variable correlation analysis, which has a significant advantage. This feature enables it to cover more types of process parameters and liquid level fluctuation data combinations in continuous casting production, making up for the lack of Pearson correlation coefficient analysis for some parameters due to data type restrictions.

[0109] The calculation process of the Spearman correlation coefficient is as follows: the values of two random variables A and B are sorted from small to large (or from large to small), that is, each variable value is assigned a rank order according to its position relative to other variable values in its group. When there are no two A values with the same rank order or two B values with the same rank order, the Spearman correlation coefficient is defined by formula (2).

[0110] (2)

[0111] where d represents the difference between the rank order of A and B, and n is the number of ordered pairs. In terms of coefficient value meaning, the Spearman correlation coefficient has similar interpretation logic as the Pearson correlation coefficient: when the coefficient value is 0, it indicates that there is no monotonic association between the two variables, i.e. the change of one variable cannot be predicted by a monotonic function; on the contrary, when the coefficient value is -1, it represents a complete negative monotonic relationship between the two variables (when one variable increases, the other variable continuously decreases); when the coefficient value is 1, it represents a complete positive monotonic relationship between the two variables (when one variable increases, the other variable continuously increases), both of which mean that there is a strong monotonic linkage between the variables.

[0112] Based on the Spearman correlation coefficient formula, the correlation coefficient of the two groups of variable pairs is calculated: first, sort each group of variable values in ascending / descending order and assign ranks (if there are identical values, take the average rank), then calculate the sum of squared rank differences, and substitute it into the formula to get the monotonic association quantitative value.

[0113] Step S404, compare the third correlation coefficient, the fourth correlation coefficient and the second preset coefficient threshold, and select a second target variable pair with a correlation coefficient greater than the second preset coefficient threshold according to the comparison result to form a second effective correlation data set.

[0114] The second preset coefficient threshold is a critical value for judging whether the Spearman correlation coefficient is significant, and is usually consistent with the first preset threshold, ensuring the uniformity of the double coefficient screening standard.

[0115] The second target variable pair is a variable pair with a Spearman correlation coefficient greater than the second preset coefficient threshold, reflecting that the monotonic association of this group of variables is significant.

[0116] The second effective correlation data set is a data set composed of sample data of all second target variable pairs, which is used for cross-validation with the first effective correlation data set.

[0117] For example, set the second preset coefficient threshold to 0.6, compare the third correlation coefficient (0.7) and the fourth correlation coefficient (0.63) with the threshold respectively: both are greater than 0.6, so the argon blowing amount and the fluctuation degree at the stopper, and the argon blowing amount and the fluctuation degree at the slide are determined as the second target variable pair, and the sample data is integrated to form a second effective correlation data set.

[0118] In the technical solution, the Pearson coefficient focuses on linear correlation, and the Spearman coefficient covers monotonic correlation. By complementary analysis of the two coefficients, potential correlations that are missed by a single coefficient (for example, when the argon blowing amount and the liquid level fluctuation have a nonlinear monotonic relationship, the Pearson coefficient may underestimate the correlation strength) are avoided. The influence degree of the argon blowing amount on the liquid level fluctuation is quantified, providing data basis for subsequent screening of key control variables and avoiding blind adjustment of process parameters.

[0119] Although both the Pearson correlation coefficient and the Spearman correlation coefficient can be used to represent the correlation between variables, and the results have certain consistency in some linear correlation scenarios, the core application scenarios and calculation logic of the two coefficients have essential differences. The Pearson correlation coefficient focuses on linear relationship, and has higher requirements for data normality and absence of abnormal values; the Spearman correlation coefficient focuses on monotonic relationship, and has no strict requirement for data distribution, and is more resistant to abnormal values.

[0120] Therefore, in order to ensure the comprehensiveness and reliability of the analysis of the correlation between the continuous casting process and the instantaneous crystallizer liquid level abnormal fluctuation, and avoid the limitations that may exist in single coefficient analysis, the Pearson correlation coefficient and the Spearman correlation coefficient are selected as double reference indexes for joint analysis. Through mutual verification and supplement of the calculation results of the two coefficients, it is comprehensively judged whether there is a correlation between the continuous casting process parameters and the instantaneous crystallizer liquid level abnormal fluctuation, what type of correlation (linear or monotonic) exists, and the strength of the correlation, so as to provide more comprehensive data analysis support for subsequent screening of key influence process parameters and optimization of liquid level control strategy.

[0121] In step S103, a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data is determined according to the first relationship and the second relationship.

[0122] The fitting linear relationship is a linear function model between the argon blowing amount and the liquid level fluctuation data constructed by a mathematical method (such as least squares method) based on a large amount of sample data, and the form is usually y=kx+b (single variable) or y=k1x1+k2x2+b (double variable), wherein y is the liquid level fluctuation data, x1 / x2 is the argon blowing amount at the stopper / slide, k1 / k2 is the influence coefficient, and b is the constant term.

[0123] In the above technical solution, the analysis results of the first relationship (linear correlation) and the second relationship (monotonic correlation) are combined: for example, if the argon blowing amount at a certain position simultaneously satisfies “the absolute value of Pearson correlation coefficient ≥ a first preset threshold (such as 0.5)” and “the absolute value of Spearman correlation coefficient ≥ a second preset threshold (such as 0.5)”, the argon blowing amount at the position is determined as a key variable. Based on the effective samples of the key variable and the liquid level fluctuation data, the least square method is used to solve the coefficients (k, b) of the linear function, and a fitting linear relationship is obtained. For example, if only the argon blowing amount at the stopper is the key variable, the fitting formula can be .

[0124] In one embodiment, optionally, step S103 comprises:

[0125] determining a final effective correlation data set according to the first effective correlation data set and the second effective correlation data set;

[0126] The final effective correlation data set can take the intersection of the first effective correlation data set and the second effective correlation data set, that is, the sample data of the variable pair existing in both data sets at the same time, ensuring that the data samples satisfy the requirements of significant linear correlation and monotonic correlation at the same time.

[0127] performing big data feature analysis on the final effective correlation data set, and fitting a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation degree by the least square method.

[0128] The least square method is a mathematical method for solving the optimal straight line of data fitting, which minimizes the sum of squared errors between actual data points and the fitting straight line, and ensures that the fitting model is closest to the true data law.

[0129] Step S104, acquiring real-time argon blowing amount data in the slab continuous casting mold of the target steel plant, and predicting real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship to obtain predicted liquid level fluctuation data;

[0130] The real-time argon blowing amount data is the argon flow data at the stopper / slide collected in real time by the flow meter (such as vortex flow meter, mass flow meter) installed on the argon pipeline, and the collection frequency matches the control demand, reflecting the current argon supply state of the process.

[0131] The predicted liquid level fluctuation data is the predicted value of the liquid level fluctuation of the molten steel in the mold at the current time calculated by substituting the real-time argon blowing amount data into the fitting linear relationship, with the unit of millimeter (mm), which is used to predict the liquid level fluctuation trend.

[0132] Step S105, in response to the real-time liquid level fluctuation data exceeding the preset normal range, adjusting the argon blowing amount at the stopper and / or the argon blowing amount at the slide to control the real-time liquid level fluctuation data to maintain within the preset normal range.

[0133] The preset normal range is a crystallizer liquid level fluctuation allowed interval set according to slab quality requirements (such as surface crack, subcutaneous bubble control standards).

[0134] The argon blowing amount adjustment is achieved by controlling the regulating valve (such as electric regulating valve, pneumatic regulating valve) on the argon pipeline to change the argon flow at the stopper / slide, and the adjustment range needs to be determined according to the deviation of the predicted liquid level fluctuation from the normal range.

[0135] In this step, the predicted liquid level fluctuation data is compared with the preset normal range: if the predicted value is higher than the upper limit of the normal range (such as predicted 827mm, upper limit 825mm), it is judged that the argon blowing amount needs to be reduced (such as the argon blowing amount at the stopper from 2.5L / min to 2.0L / min); if the predicted value is lower than the lower limit of the normal range (such as predicted 813mm, lower limit 815mm), the argon blowing amount needs to be increased. The adjustment instruction is sent to the argon regulating valve through the control system, and the valve response time is ≤1 second, ensuring rapid adjustment of the argon blowing amount to maintain the subsequent actual liquid level fluctuation within the normal range.

[0136] Through the above technical solution, the instantaneous liquid level fluctuation is actively controlled, the probability of fluctuation exceeding the normal range is greatly reduced, and the generation of slab surface defects is reduced. The frequency of manual intervention is reduced, the labor intensity of the operator is reduced, the hysteresis and errors of manual adjustment are avoided, and the stability of continuous casting production is improved.

[0137] As shown in Figure 5 In one embodiment, the method further comprises:

[0138] Step S501, extracting actual real-time liquid level fluctuation data corresponding to the real-time argon blowing amount data from the slab continuous casting crystallizer;

[0139] The actual real-time liquid level fluctuation data is the fluctuation value of the current time molten steel liquid level deviating from the set value collected by the crystallizer liquid level sensor in real time, which is different from the predicted value based on the fitting model, and is the true basis for verifying the accuracy of the model.

[0140] Step S502, comparing the real-time liquid level fluctuation data and the predicted liquid level fluctuation data, and determining whether to update the fitting linear relationship according to the comparison result.

[0141] By comparing the predicted value with the actual value, the accuracy of the fitting model can be intuitively judged, the model can be prevented from deviating from the actual production situation, a trigger basis for subsequent model updating can be provided, the linear model can be dynamically optimized according to the change of production conditions, and high prediction accuracy can be maintained for a long time.

[0142] In one embodiment, optionally, step S502 comprises:

[0143] calculating a mean absolute error value and a coefficient of determination between the real-time liquid level fluctuation data and the predicted liquid level fluctuation data;

[0144] In response to the mean absolute error value being greater than or equal to a preset error threshold value and the coefficient of determination being greater than or equal to a preset coefficient threshold value, it is determined that the fitting linear relationship is not updated, otherwise, it is determined that the fitting linear relationship is updated.

[0145] In order to more intuitively show the fitting effect, the mean absolute error (MAE) and the coefficient of determination (R2) are selected to quantitatively evaluate the effect of linear fitting. The MAE represents the average value of the absolute error between the predicted value and the actual value, and directly reflects the average level of prediction error, and is less sensitive to abnormal values. The coefficient of determination is used to measure the proportion of the model in explaining the variance of the dependent variable, and the value is between 0 and 1, and the closer to 1, the better the fitting effect of the model.

[0146] The above technical solutions of the present application are described in detail below with one specific embodiment.

[0147] Step 1: Collecting on-site continuous casting production data, including liquid level fluctuation data, stopper position data, and different position argon blowing amount, etc. The steel composition is shown in Table 1, and the continuous casting machine related parameters are shown in Table 2. The liquid level fluctuation data and related process data collection frequency is 10Hz.

[0148] Table 1 Steel composition (%)

[0149]

[0150] Table 2 Continuous casting machine parameters

[0151]

[0152] Step 2: The mold liquid level fluctuation data collected on site is shown in Figure 6 The on-site liquid level fluctuation set value is 820mm. From Figure 6It is known that the fluctuation range of the crystallizer level at certain times far exceeds the normal range. Combined with actual production processes, it is understood that process operations such as ladle changes and speed adjustments can cause significant abnormal fluctuations in the crystallizer level. Therefore, it is necessary to combine the level fluctuation data with the on-site process data for preliminary data cleaning. Furthermore, considering that the one-to-one correspondence between abnormal crystallizer level fluctuations and continuous casting process data is not clear, data processing is performed on the crystallizer level fluctuation data and different process data to explore the relationship between the two. Using the process stabilization time as a benchmark, the average of the ten largest values ​​in the instantaneous abnormal crystallizer level fluctuation data within the same time period is taken as the degree of crystallizer level fluctuation within that time period.

[0153] Step 3: Analyze the relationship between the argon blowing volume at the stopper rod and the slide plate and the crystallizer liquid level fluctuation data based on Pearson correlation coefficient.

[0154] Step 4: To ensure the comprehensiveness and rigor of the research process, Spearman's correlation coefficient was used to analyze the relationship between the argon blowing rate at the stopper rod and the slide plate and the crystallizer liquid level fluctuation data. The results of the Pearson correlation coefficient and Spearman's correlation coefficient were used together as the analytical standard. The analysis results are as follows: Figure 7 As shown.

[0155] Step 5: Based on data collected from the steel plant, a linear formula was fitted to express the relationship between the argon blowing rate and the crystallizer level fluctuation. This data clearly shows how changes in the argon blowing rate affect the crystallizer level fluctuation. Specifically, according to this formula, the maximum fluctuation of the crystallizer level can be calculated from the argon blowing rate at the submersible nozzle. This method provides a powerful tool for predicting and controlling crystallizer level fluctuations. The calculation formula for when the submersible nozzle is blocked is shown in formula (3), where Ml is the maximum fluctuation of the crystallizer level and a is the argon blowing rate.

[0156] (3)

[0157] Step 6: The field data and the straight line obtained by fitting the formula are as follows: Figure 8 As shown. From Figure 8 It can be seen that the maximum fluctuation of the crystallizer liquid level corresponding to different argon blowing rates differs little from the fitted results, and the field data are evenly distributed around the fitted line, indicating a good fitting effect. This shows that the relationship between argon blowing rate and crystallizer liquid level fluctuation is relatively stable under the condition of immersion nozzle blockage, and can be well described by a linear model. Furthermore, this stability also indicates that in actual production, monitoring the argon blowing rate can accurately predict the fluctuation of the crystallizer liquid level, thus providing a basis for process adjustment.

[0158] Step 7: To more intuitively demonstrate the fitting effect, the mean absolute error (MAE) and coefficient of determination (COP) were selected. ) to quantitatively evaluate the effect of linear fitting, and the comparison results of parameters are shown in Table 2. Figure 9 MAE represents the average of the absolute error between the predicted value and the actual value, which directly reflects the average level of prediction error and is less sensitive to outliers. R-squared is used to measure the proportion of the variance of the dependent variable explained by the model, and the value is between 0 and 1. The closer to 1, the better the fitting effect of the model.

[0159] Figure 10 A block diagram of a transient liquid level fluctuation control device of a slab continuous casting mold according to an embodiment of the application is shown.

[0160] As shown in Figure 10 , in a second aspect, the embodiments of the application provide a transient liquid level fluctuation control device 1000 of a slab continuous casting mold, comprising:

[0161] An extraction module 1001 is configured to extract parameter data from a slab continuous casting mold of a target steel plant, wherein the parameter data comprises liquid level fluctuation data, stopper position data, and argon blowing amount data at different positions.

[0162] An analysis module 1002 is configured to analyze a first relationship between argon blowing amount at a stopper, argon blowing amount at a slide plate, and the liquid level fluctuation data based on a Pearson correlation coefficient, and analyze a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate, and the liquid level fluctuation data based on a Spearman correlation coefficient.

[0163] A relationship determination module 1003 is configured to determine a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data according to the first relationship and the second relationship.

[0164] A prediction module 1004 is configured to obtain real-time argon blowing amount data in the slab continuous casting mold of the target steel plant, and predict real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship, to obtain predicted liquid level fluctuation data.

[0165] A control module 1005 is configured to adjust the argon blowing amount at the stopper and / or the argon blowing amount at the slide plate in response to the real-time liquid level fluctuation data exceeding a preset normal range, to control the real-time liquid level fluctuation data to be maintained within the preset normal range.

[0166] In an embodiment, optionally, after the parameter data is extracted, the device further comprises:

[0167] A preprocessing module is configured to preprocess the parameter data to obtain preprocessed parameter data, wherein the preprocessing process comprises:

[0168] eliminate abnormal fluctuation data caused by changes in process conditions from the parameter data to obtain preliminary screening data;

[0169] obtain all liquid level abnormal fluctuation data in the same time period from the preliminary screening data based on process stabilization time, and arrange in descending order;

[0170] select a preset number of target liquid level abnormal fluctuation data ranked in the front from all the liquid level abnormal fluctuation data, and calculate the average value corresponding to all the target liquid level abnormal fluctuation data;

[0171] take the average value as the liquid level fluctuation degree in the time period.

[0172] In one embodiment, the analysis module comprises:

[0173] The extraction unit is configured to extract the argon blowing amount at the stopper and the first liquid level fluctuation degree corresponding thereto, the argon blowing amount at the slide plate and the second liquid level fluctuation degree corresponding thereto from the preprocessed parameter data respectively, and obtain two groups of variable pairs.

[0174] The first calculation unit is configured to calculate the first correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the second correlation coefficient between the argon blowing amount at the slide plate and the second liquid level fluctuation degree based on the Pearson correlation coefficient calculation formula.

[0175] The first comparison unit is configured to compare the first correlation coefficient, the second correlation coefficient and the first preset coefficient threshold, and select a first target variable pair with a correlation coefficient greater than the preset coefficient threshold according to the comparison result to form a first effective correlation data set.

[0176] In one embodiment, the analysis module further comprises:

[0177] The sorting unit is configured to sort the variable values of the two groups of variable pairs respectively, and assign a unique rank order to each variable value, wherein if there are variable values with the same value, the average value of the rank orders corresponding to the same value variable values in this group is taken as the common rank of the same value variable values.

[0178] The second calculation unit is configured to calculate the rank difference of the corresponding variable value according to the assigned rank order for each group of variable pairs.

[0179] The third calculation unit is configured to calculate the third correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and the fourth correlation coefficient between the argon blowing amount at the slide plate and the second liquid level fluctuation degree according to the rank difference and the Spearman correlation coefficient calculation formula.

[0180] The second comparison unit is configured to compare the third correlation coefficient, the fourth correlation coefficient and a second preset coefficient threshold, and filter out a second target variable pair with a correlation coefficient greater than the second preset coefficient threshold to form a second effective correlation data set.

[0181] In an embodiment, the relationship determining module comprises, optionally:

[0182] The first determining unit is configured to determine a final effective correlation data set according to the first effective correlation data set and the second effective correlation data set.

[0183] The feature analysis unit is configured to perform big data feature analysis on the final effective correlation data set, and obtain a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation degree by a least square method.

[0184] In an embodiment, the device further comprises, optionally:

[0185] The extraction module is configured to extract actual real-time liquid level fluctuation data corresponding to the real-time argon blowing amount data from the slab continuous casting crystallizer.

[0186] The updating module is configured to compare the real-time liquid level fluctuation data and the predicted liquid level fluctuation data, and determine whether to update the fitting linear relationship according to a comparison result.

[0187] In an embodiment, the updating module comprises, optionally:

[0188] The fourth calculating unit is configured to calculate a mean absolute error value and a determination coefficient between the real-time liquid level fluctuation data and the predicted liquid level fluctuation data.

[0189] The second determining unit is configured to determine not to update the fitting linear relationship in response to the mean absolute error value being greater than or equal to a preset error threshold and the determination coefficient being greater than or equal to a preset coefficient threshold, and otherwise, determine to update the fitting linear relationship.

[0190] In a third aspect, a computer device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the slab continuous casting crystallizer transient liquid level fluctuation control method when executing the computer program.

[0191] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the slab continuous casting crystallizer transient liquid level fluctuation control method when executed by a processor.

[0192] It should be noted that, for the convenience and brevity of description, the specific working processes of the slab continuous casting crystallizer transient liquid level fluctuation control device and each module described above can be clearly understood by those skilled in the art, and the corresponding processes in the foregoing slab continuous casting crystallizer transient liquid level fluctuation control method embodiments can be referred to, and will not be repeated here.

[0193] It should be noted that, for the convenience and brevity of description, the specific working processes of the model training device and each module described above can be clearly understood by those skilled in the art, and the corresponding processes in the foregoing slab continuous casting crystallizer transient liquid level fluctuation control method embodiments can be referred to, and will not be repeated here.

[0194] The slab continuous casting crystallizer transient liquid level fluctuation control device described above can be implemented in the form of a computer program, which can run on a computer device as shown in the accompanying drawings. Figure 11

[0195] Figure 11 A block diagram of a computer device according to an embodiment of the present application is shown.

[0196] Referring to Figure 11 , the computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory can include a storage medium and an internal memory.

[0197] The storage medium can store an operating system and a computer program. The computer program includes program instructions which, when executed, can cause the processor to perform any one of the slab continuous casting crystallizer transient liquid level fluctuation control methods for multi-source data provided by the embodiments of the present application.

[0198] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0199] The internal memory provides an environment for the running of the computer program in the storage medium, which, when executed by the processor, can cause the processor to perform any one of the infectious disease transmission path analysis methods or the training method of the prediction neural network. The storage medium can be non-volatile or volatile.

[0200] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that Figure 11 The structure shown in the accompanying drawings is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the drawings, or combine certain components, or have a different arrangement of components.

[0201] ​It should be appreciated that a processor can be a Central Processing Unit (CPU), the processor can also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general purpose processor can be a microprocessor or the processor can be any conventional processor.

[0202] In addition, the embodiment of the present application provides a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are used for executing the method steps in the first aspect.

[0203] It should be noted that the functions or steps that can be achieved by the computer readable storage medium or the electronic device described above can be referred to the related description in the foregoing method embodiments, and here will not be described one by one to avoid repetition.

[0204] It should be understood that the term "and / or" used herein only describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B, which can represent three cases of existence of A alone, existence of A and B together, and existence of B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0205] It should be understood that although the terms first, second, etc. can be used in this application to describe the setting units, these setting units should not be limited to these terms. These terms are only used to distinguish the setting units from each other. For example, the first setting unit can also be referred to as the second setting unit, and similarly, the second setting unit can also be referred to as the first setting unit without departing from the scope of the embodiments of the present application.

[0206] Depending on the context, the word "if" as used herein can be interpreted as meaning "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as meaning "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0207] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented by other manners. For example, the above-described device embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and in actual implementation, another division manner can be adopted, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0208] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0209] A person of ordinary skill in the art can understand that all or part of the processes in the above-described embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-described embodiments. In each embodiment provided in the present application, any reference to memory, storage, database or other medium can include non-volatile and / or volatile memory. The non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. The volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0210] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of controlling transient level fluctuations in a slab continuous casting mold, characterized by, The method comprises: extracting parameter data from a slab continuous casting crystallizer of a target steel plant, wherein the parameter data comprises liquid level fluctuation data, stopper position data and argon blowing amount data at different positions; analyzing a first relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on a Pearson correlation coefficient, and analyzing a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on a Spearman correlation coefficient; determining a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data according to the first relationship and the second relationship; obtaining real-time argon blowing amount data in the slab continuous casting crystallizer of the target steel plant, and predicting real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship to obtain predicted liquid level fluctuation data; in response to the real-time liquid level fluctuation data exceeding a preset normal range, adjusting the argon blowing amount at the stopper and / or the argon blowing amount at the slide plate to control the real-time liquid level fluctuation data to be maintained within the preset normal range.

2. The method of claim 1, wherein, After extracting the parameter data, the method further comprises: preprocessing the parameter data to obtain preprocessed parameter data, wherein the preprocessing process comprises: eliminating abnormal fluctuation data caused by changes in process conditions from the parameter data to obtain primary screening data; obtaining all liquid level abnormal fluctuation data within the same time period from the primary screening data based on a process stable time, and arranging the data in descending order; selecting a preset number of target liquid level abnormal fluctuation data in the front from all the liquid level abnormal fluctuation data, and calculating the average value corresponding to all the target liquid level abnormal fluctuation data; taking the average value as the liquid level fluctuation degree within the time period.

3. The method of claim 2, wherein, The first relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on the Pearson correlation coefficient comprises: extracting the argon blowing amount at the stopper and the first liquid level fluctuation degree corresponding thereto, and the argon blowing amount at the slide plate and the second liquid level fluctuation degree corresponding thereto from the preprocessed parameter data to obtain two groups of variable pairs; calculating a first correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree, and a second correlation coefficient between the argon blowing amount at the slide plate and the second liquid level fluctuation degree based on a Pearson correlation coefficient calculation formula; comparing the first correlation coefficient, the second correlation coefficient and a first preset coefficient threshold, and selecting a first target variable pair with a correlation coefficient greater than the preset coefficient threshold according to the comparison result to form a first effective correlation data set.

4. The method of claim 3, wherein, The second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide plate and the liquid level fluctuation data based on the Spearman correlation coefficient comprises: sorting the variable values of the two groups of variable pairs, and assigning a unique rank order to each variable value, wherein if there are variable values with the same value, the average value of the rank order corresponding to the same variable value in the group is taken as the common rank of the same variable value; for each group of variable pairs, calculating the rank difference of the corresponding variable value according to the assigned rank order; According to the grade difference value and the Spearman correlation coefficient calculation formula, a third correlation coefficient between the argon blowing amount at the stopper and the first liquid level fluctuation degree and a fourth correlation coefficient between the argon blowing amount at the slide and the second liquid level fluctuation degree are calculated respectively; The third correlation coefficient, the fourth correlation coefficient and a second preset coefficient threshold are compared, and a second target variable pair with a correlation coefficient greater than the second preset coefficient threshold is screened out according to a comparison result to form a second effective correlation data set.

5. The method of claim 4, wherein, The fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data is determined according to the first relationship and the second relationship, including: A final effective correlation data set is determined according to the first effective correlation data set and the second effective correlation data set; Big data feature analysis is performed on the final effective correlation data set, and a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation degree is obtained by least square fitting.

6. The method of claim 1, wherein, The method further includes: Actual real-time liquid level fluctuation data corresponding to the real-time argon blowing amount data is extracted from the slab continuous casting mold; The real-time liquid level fluctuation data and the predicted liquid level fluctuation data are compared, and it is determined whether to update the fitting linear relationship according to a comparison result.

7. The method of claim 6, wherein, The real-time liquid level fluctuation data and the predicted liquid level fluctuation data are compared, and it is determined whether to update the fitting linear relationship according to a comparison result, including: An average absolute error value and a determination coefficient between the real-time liquid level fluctuation data and the predicted liquid level fluctuation data are calculated; In response to the average absolute error value being greater than or equal to a preset error threshold and the determination coefficient being greater than or equal to a preset coefficient threshold, it is determined that the fitting linear relationship is not updated, otherwise, it is determined that the fitting linear relationship is updated.

8. A device for controlling instantaneous liquid level fluctuations in a slab continuous casting crystallizer, characterized in that, It includes: An extraction module is configured to extract parameter data from a slab continuous casting mold of a target steel plant, wherein the parameter data includes liquid level fluctuation data, stopper position data and argon blowing amount data at different positions; An analysis module is configured to analyze a first relationship between argon blowing amount at a stopper, argon blowing amount at a slide and the liquid level fluctuation data based on a Pearson correlation coefficient, and analyze a second relationship between the argon blowing amount at the stopper, the argon blowing amount at the slide and the liquid level fluctuation data based on a Spearman correlation coefficient; A relationship determination module is configured to determine a fitting linear relationship between the argon blowing amount data and the liquid level fluctuation data according to the first relationship and the second relationship; A prediction module is configured to obtain real-time argon blowing amount data in a slab continuous casting mold of the target steel plant, predict real-time liquid level fluctuation data according to the real-time argon blowing amount data and the fitting linear relationship, and obtain predicted liquid level fluctuation data; A control module is configured to adjust the argon blowing amount at the stopper and / or the argon blowing amount at the slide in response to the real-time liquid level fluctuation data exceeding a preset normal range, so as to control the real-time liquid level fluctuation data to be maintained within the preset normal range.

9. A computer device, comprising: It includes: At least one processor; And a memory connected in communication with the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being arranged to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, computer executable instructions for performing the method of any one of claims 1 to 7.

Images