Rolling process curve steady state identification method, device, equipment, storage medium and product

Abstract

The application provides a rolling process curve steady state identification method, device, equipment, storage medium and product. The method comprises the following steps: obtaining rolling data of a middle section of a target hot continuous rolling plate; fitting the rolling data using a preset polynomial to obtain fitting data; calculating a difference value between the rolling data and the fitting data; determining an area of a figure surrounded by a straight line corresponding to the fitting curve and the average value of the ordinate of the fitting curve according to the fitting data; determining a definite integral of the fitting curve according to the fitting data; and judging the steady state of the middle section of the target hot continuous rolling plate curve according to the difference value, the area and the definite integral.

Description

Technical Field

[0001] This application relates to the field of metal processing technology, and in particular to a method, apparatus, equipment, storage medium and product for steady-state identification of rolling process curves. Background Technology

[0002] Hot strip rolling is a key process in metal material production. Its process curves reflect the state and performance of the strip in the rolling mill, recording parameters such as deformation degree, temperature, and strain. These curves are crucial for real-time monitoring and adjustment of the production process. By recording parameters such as deformation degree, temperature, strain, mechanical properties, and thickness, the curves provide a comprehensive understanding of the hot strip rolling process. Using curve analysis helps in real-time monitoring and adjustment of the production process, ensuring final product quality, improving production efficiency, and extending equipment life.

[0003] Current research mostly focuses on determining out-of-tolerance and overshoot at the beginning and end of the rolling curve, while there is limited research on online identification of steady-state conditions in the middle of the rolling curve. Steady-state assessment lacks a unified definition and quantitative standard; existing identification methods rely on manual visual inspection and experience, making real-time monitoring and identification of steady-state conditions in the middle of the rolling curve impossible. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, storage medium, and product for steady-state identification of a rolling process curve, which can identify the steady state of the middle section of the rolling curve.

[0005] In a first aspect, this application provides a method for steady-state identification of a rolling process curve, the method comprising:

[0006] Obtain rolling data for the middle section of the target hot strip;

[0007] The rolling data is fitted using a preset polynomial to obtain fitted data;

[0008] Calculate the difference between the rolling data and the fitted data;

[0009] Based on the fitted data, determine the area of ​​the figure enclosed by the fitted curve and the line corresponding to the average ordinate of the fitted curve;

[0010] Based on the fitted data, determine the definite integral of the fitted curve;

[0011] The steady state of the middle section of the target hot-rolled plate curve is determined based on the difference, the area, and the definite integral.

[0012] In some possible implementations, obtaining the rolling data of the middle section of the target hot strip includes:

[0013] Obtain all rolling data for the target hot strip;

[0014] According to a preset ratio, determine the head and tail data of the target hot-rolled plate;

[0015] Based on the head data and the tail data, the rolling data of the middle section of the target hot strip is extracted.

[0016] In some possible implementations, after extracting the rolling data of the middle section of the target hot strip based on the head data and the tail data, the method further includes:

[0017] The rolling data of the middle section of the target hot strip is normalized.

[0018] In some possible implementations, calculating the difference between the rolling data and the fitted data includes:

[0019] The residual between the rolling data and the fitted data is obtained based on the deviation of the rolling data and the fitted data in the vertical direction.

[0020] The root mean square error of the residual is calculated to obtain the difference between the rolling data and the fitted data.

[0021] In some possible implementations, determining the area of ​​the figure enclosed by the fitted curve and the line corresponding to the average ordinate of the fitted curve based on the fitted data includes:

[0022] Based on the fitted data, calculate the average ordinate of the data points in the fitted data;

[0023] Determine the straight line containing the average value of the ordinate based on the average value of the ordinate;

[0024] Calculate the area of ​​the figure enclosed by the fitted curve and the straight line.

[0025] In some possible implementations, determining the steady state of the middle segment of the target hot-rolled strip curve based on the difference, the area, and the definite integral includes:

[0026] If the difference is less than or equal to a first threshold, the area is less than or equal to a second threshold, and the definite integral is less than or equal to a third threshold, the steady state of the middle section of the target hot strip curve is determined to be stable.

[0027] If the difference is greater than the first threshold, or the area is greater than the second threshold, or the definite integral is greater than the third threshold, the steady state of the middle section of the target hot-rolled plate curve is determined to be unstable.

[0028] Secondly, this application provides a rolling process curve steady-state identification device, the device comprising:

[0029] The acquisition module is used to acquire rolling data of the middle section of the target hot strip.

[0030] The fitting module is used to fit the rolling data using a preset polynomial to obtain fitted data;

[0031] The calculation module is used to calculate the difference between the rolling data and the fitted data;

[0032] The determination module is used to determine the area of ​​the figure enclosed by the fitted curve and the straight line corresponding to the average value of the ordinate of the fitted curve, based on the fitted data.

[0033] The determining module is also used to determine the definite integral of the fitted curve based on the fitted data;

[0034] The judgment module is used to determine the steady state of the middle section of the target hot-rolled plate curve based on the difference, the area, and the definite integral.

[0035] Thirdly, this application provides a rolling process curve steady-state identification device, the device comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the rolling process curve steady-state identification method as described above.

[0036] Fourthly, this application provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the steady-state identification method for rolling process curves as described above.

[0037] Fifthly, this application provides a computer program product in which the instructions are executed by the processor of an electronic device, causing the electronic device to perform the rolling process curve steady-state identification method as described above.

[0038] The rolling process curve steady-state identification method, apparatus, equipment, storage medium, and product provided in this application, by fitting data from the middle of the curve, can more accurately capture subtle changes in the curve, and the fitted curve is closer to the actual data. By calculating the difference between the rolling data and the fitted data, the degree of fit between the fitted curve and the original data is quantitatively evaluated, ensuring the reliability of the fitting results. Multiple quantitative indicators, such as the enclosed area and definite integral, are introduced to evaluate the smoothness of the middle section of the curve from different angles, enabling the identification of the steady state of the middle section of the rolling curve. Attached Figure Description

[0039] This application can be better understood from the following description of specific embodiments in conjunction with the accompanying drawings, wherein:

[0040] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings, wherein the same or similar reference numerals denote the same or similar features.

[0041] Figure 1 This is a flowchart of a method for steady-state identification of rolling process curves provided in one embodiment of this application;

[0042] Figure 2 It is a broken line graph of the hot strip rolling process;

[0043] Figure 3 It is the image of the middle section of the hot strip rolling process curve after normalization and the fitted curve;

[0044] Figure 4 This is a schematic diagram of the structure of a rolling process curve steady-state identification device provided in one embodiment of this application;

[0045] Figure 5 This is a schematic diagram of the hardware structure of the rolling process curve steady-state identification device provided in the embodiments of this application. Detailed Implementation

[0046] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0047] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0048] To address the problems of the prior art, embodiments of this application provide a method, apparatus, equipment, storage medium, and product for steady-state identification of rolling process curves. The method for steady-state identification of rolling process curves provided in this application embodiment will be described first below.

[0049] Figure 1 A schematic flowchart of a steady-state identification method for rolling process curves according to an embodiment of this application is shown. Figure 1 As shown, the method includes the following steps: S101 to S106.

[0050] S101: Obtain rolling data for the middle section of the target hot strip.

[0051] In practical implementation, the first step is to acquire rolling data of the hot-rolled sheet from a database or sensors. Rolling data typically includes physical quantities such as temperature, speed, torque, and thickness. At this stage, the main focus is on acquiring data from the middle section of the target hot-rolled sheet during the rolling process. Assuming the data is collected chronologically, each data point includes a timestamp and related physical parameters. For the middle section of the hot-rolled sheet, the data is filtered to ensure that only rolling data from that specific region is acquired.

[0052] S102: Fit the above rolling data using a preset polynomial to obtain fitted data.

[0053] In practical implementation, polynomial fitting methods, such as the least squares method, are used. Specifically, an appropriate polynomial order (such as a first-order polynomial, a second-order polynomial, etc.) is selected to fit the data of the middle section of the target hot-rolled sheet. The rolling data is used as input, and optimization algorithms such as the least squares method are used to solve for the coefficients of the fitting polynomial. The fitting process involves adjusting the polynomial coefficients to make the fitted curve as close as possible to the original data points. The fitting result will be a polynomial function, and the output of the fitted curve calculation result includes the fitting coefficients and the data points of the fitted curve.

[0054] S103: Calculate the difference between the above rolling data and the above fitted data.

[0055] In practice, for each rolling data point, the corresponding value is calculated using the fitted polynomial and compared with the original data point. The difference is the deviation between the original data and the fitted data. These differences are recorded to form a new dataset.

[0056] S104: Based on the above fitting data, determine the area of ​​the figure enclosed by the fitted curve and the straight line corresponding to the average value of the ordinate of the fitted curve.

[0057] In the specific implementation, the average y-coordinate of the fitted curve is calculated. A horizontal line is drawn using the average y-coordinate of the fitted curve. The area enclosed by this line and the fitted curve is a closed region, which may be a combination of multiple smaller regions. Then, the area enclosed by the fitted curve and the line is calculated using integration or numerical methods. This area measures the difference between the fitted data and the constant line.

[0058] S105: Based on the above fitted data, determine the definite integral of the fitted curve.

[0059] In practical implementation, based on the above fitted data, the definite integral can be calculated using numerical integration methods, such as the rectangular method, trapezoidal method, or Simpson's method. The result of the definite integral can be viewed as the area or sum of the regions enclosed by the fitted curve.

[0060] S106: Determine the steady state of the middle section of the target hot-rolled plate curve based on the above difference, the above area, and the above definite integral.

[0061] In practical implementation, steady state usually means that the system's behavior is stable and no longer subject to significant changes. The stability of the rolling process is analyzed by combining the difference, area, and definite integral. If the changes in these values ​​are within a certain tolerable range, the rolling process in that section is considered steady state; otherwise, it may be in a non-steady state, requiring further analysis or adjustment.

[0062] The steady-state identification method for rolling process curves provided in this application can more accurately capture subtle changes in the curve by fitting data from the middle section of the curve, resulting in a fitted curve that more closely resembles the actual data. By calculating the difference between the rolling data and the fitted data, the degree of fit between the fitted curve and the original data is quantitatively evaluated, ensuring the reliability of the fitting results. Multiple quantitative indicators, such as the enclosed area and definite integral, are introduced to evaluate the smoothness of the middle section of the curve from different perspectives, enabling the identification of the steady state in the middle segment of the rolling curve.

[0063] In order to provide stable and reliable rolling data, in some embodiments, the above S101 may include the following steps: S1011 to S1013.

[0064] S1011: Obtain all rolling data for the target hot strip.

[0065] In practice, during hot continuous rolling production, rolling data is typically collected by sensors and monitoring systems, including various parameters such as temperature, pressure, speed, and torque. Raw rolling data is then retrieved from data storage devices.

[0066] S1012: Determine the head and tail data of the target hot strip according to the preset ratio.

[0067] In practical implementation, the head and tail ratio of the data segments is determined, and this ratio is set according to the needs of the rolling process. For example, the head and tail data may each account for 10% of the total data, or the ratio may be adjusted based on factors such as the actual length of the rolling process and downtime. The total rolling data is segmented according to the preset ratio. Assuming that the rolling data of the target hot strip has multiple data points, the head and tail data are extracted from the overall data. For example, if the preset ratio is 10%, the head data is determined from the first 10% of the dataset, and the tail data is determined from the last 10% of the dataset.

[0068] S1013: Based on the above head data and the above tail data, extract the rolling data of the middle section of the target hot strip.

[0069] In practice, by determining the positions of the head and tail data, the range of the middle section can be calculated. The middle section of the rolling data is then extracted using the calculated index range. For example, array slicing techniques can be used to extract data within a range from the original data array. This data represents the core part of the rolling process and is generally unaffected by temperature changes or equipment adjustments at the beginning and end.

[0070] The above-described implementation method of this application first obtains all rolling data from multiple sources and ensures the integrity of the data; then divides the data into head, tail and middle sections according to a preset ratio; finally, based on the positioning of the head and tail sections, extracts the middle section data of the rolling process, thereby providing stable and reliable rolling data for subsequent analysis and judgment.

[0071] To eliminate differences in data scale, in some embodiments, after S1013 above, the method further includes:

[0072] The rolling data of the middle section of the target hot strip are normalized.

[0073] In practical implementation, the first step is to determine the normalization range. For the rolling data of the middle section of the target hot-rolled sheet, the minimum and maximum values ​​within this data segment must first be calculated. Based on the minimum and maximum values, the value of each data point is scaled proportionally to the set range. Once the data of the middle section has been normalized, the normalized data can be passed to the next stage of analysis or modeling. Normalized data typically has a uniform scale, which allows subsequent algorithms to process and learn from this data more efficiently.

[0074] The above-described implementation method of this application determines the target range; then calculates the minimum and maximum values ​​of the data segment; next, applies a normalization formula; performs appropriate processing when handling abnormal data; and finally saves the normalized data for further analysis and use. The main purpose of normalization is to scale the data to a fixed range to eliminate differences in the scale of the data itself.

[0075] In order to accurately obtain the difference between the rolling data and the above-mentioned fitted data, in some embodiments, the above-mentioned S103 may include the following steps: S1031 to S1032.

[0076] S1031: Based on the deviation in the vertical direction between the above rolling data and the above fitted data, the residual between the above rolling data and the above fitted data is obtained.

[0077] In practical implementation, rolling data refers to data actually collected during the production process, typically indicating certain characteristics of the sheet metal during rolling. Fitting data, on the other hand, is data calculated based on mathematical models or theories, usually obtained by modeling the expected rolling process. For each data point, the difference between the rolling data and the fitted data on a specific coordinate axis is calculated, resulting in a deviation sequence. For each data point, the residual is calculated; the residual represents the error between the rolling data and the fitted data, reflecting the degree of deviation between the actual and expected data, resulting in the final residual set. This is a sequence containing the residuals of all data points, and subsequent steps will be based on this residual sequence for error evaluation.

[0078] S1032: Calculate the root mean square error of the above residuals to obtain the difference between the above rolling data and the above fitted data.

[0079] In practical implementation, when calculating the root mean square error (RMSE), each residual is first squared, and the sum of the squares of all residuals is calculated. This sum represents the overall level of error between the rolling data and the fitted data. After calculating the RMSE, its square root is applied to obtain the final RMSE. The smaller the RMSE value, the smaller the error between the rolling data and the fitted data. Ultimately, the RMSE, as a measure of the difference between the rolling data and the fitted data, is returned as the output. This error value helps engineers determine the deviation between the rolling process and theoretical expectations.

[0080] The embodiments described above in this application calculate the vertical deviation between the rolling data and the fitted data to obtain a residual sequence, representing the difference between the actual data and the expected data. The root mean square error of the residuals is calculated, and by calculating the square root of the squared mean of the residuals, a scalar value is obtained to measure the difference between the rolling data and the fitted data, thereby accurately obtaining the difference between the rolling data and the aforementioned fitted data.

[0081] In order to obtain an accurate area value, in some embodiments, the above S104 may include the following steps: S1041 to S1043.

[0082] S1041: Based on the above fitted data, calculate the average ordinate of the data points in the above fitted data.

[0083] In the specific implementation, the ordinate values ​​of the fitted data are extracted, then each ordinate value in the fitted data is traversed and summed, and the sum of all ordinate values ​​is divided by the total number of data points to obtain the average value of the ordinates. The average value can be used as the representative value of the ordinates of the fitted data.

[0084] S1042: Determine the line containing the average value of the ordinate based on the above average ordinate values.

[0085] In the actual implementation, the average value of the ordinate will be used as a constant to define a horizontal line, and thus determine the line containing the average value of the ordinate.

[0086] S1043: Based on the above straight line, calculate the area of ​​the figure enclosed by the fitted curve and the above straight line.

[0087] In a practical implementation, the area enclosed by the fitted curve and the straight line determined by the average value of the ordinate is calculated. The area can be obtained by calculating the integral between the curve and the straight line. For example, the region between the fitted curve and the straight line is divided into several small intervals. For each small interval, the difference between the curve and the straight line is calculated. Then, the area of ​​the interval is calculated using the trapezoidal rule. The areas between all the small intervals are summed to obtain the total area between the fitted curve and the straight line.

[0088] The above-described embodiments of this application calculate the average value of the vertical coordinate in the fitted data to provide a benchmark for subsequent straight line calculations. The horizontal straight line is determined based on the average value, and the corresponding straight line data points are generated. The area enclosed by the fitted curve and the straight line is calculated, and the area value is usually obtained by numerical integration to obtain an accurate area value.

[0089] In order to accurately determine the steady state of the middle section of the target hot-rolled plate curve, in some embodiments, S106 may include the following steps: S1061 to S1062.

[0090] S1061: If the above difference is less than or equal to the first threshold, the above area is less than or equal to the second threshold, and the above definite integral is less than or equal to the third threshold, the steady state of the middle section of the above target hot strip curve is determined to be stable.

[0091] In practical implementation, firstly, the differences between certain data points on the target hot-rolled steel plate curve are determined. This difference can be understood as the degree of fluctuation or rate of change between consecutive data points. If these changes are small, it indicates that the curve's change tends to be stable. Next, the area enclosed by the target hot-rolled steel plate curve and the reference straight line is determined. This area represents the degree of difference between the curve and the straight line; a smaller area indicates that the curve and the straight line are close, and the change is small. The definite integral calculates the precise regional difference between the curve and the straight line. If the definite integral value is small, it indicates that the curve's change is small and tends to be stable. When the difference is less than or equal to the first threshold, the area is less than or equal to the second threshold, and the definite integral is less than or equal to the third threshold, it indicates that the fluctuation in the middle section of the target hot-rolled steel plate curve is small, the change tends to be stable, and the system enters a steady state. Therefore, the steady state of the middle section of the curve is determined to be stable.

[0092] S1062: If the above difference is greater than the first threshold, or the above area is greater than the second threshold, or the above definite integral is greater than the third threshold, the steady state of the middle section of the above target hot strip curve is determined to be unstable.

[0093] In practical implementation, if the difference between data points on the target hot-rolled strip curve is too large, it indicates that the curve is changing drastically and may be in an unstable state. In this case, the condition is that the difference is greater than the first threshold. If the area between the fitted curve and the baseline is large, it indicates that the curve is changing drastically and may experience significant fluctuations. If the definite integral value is large, it indicates a large regional difference between the curve and the line, further suggesting that the curve is changing significantly and may be unstable. When the difference is greater than the first threshold, or the area is greater than the second threshold, or the definite integral is greater than the third threshold, it indicates that the fluctuation of the target hot-rolled strip curve is too large, and the system enters an unstable state. Therefore, the steady state of the middle segment of the curve is determined to be unstable.

[0094] The embodiments described above in this application calculate the difference, area, and definite integral, and compare them with set thresholds. If all three conditions are met (i.e., all are less than or equal to their respective thresholds), the steady state of the middle section of the target hot-rolled plate curve is determined to be stable. If any one of the difference, area, or definite integral is greater than its corresponding threshold, the steady state of the middle section of the curve is determined to be unstable, thereby accurately determining the steady state of the middle section of the target hot-rolled plate curve.

[0095] In one embodiment of this application, reference may be made to Figure 2 , Figure 2To create a line graph of the hot strip rolling process, first obtain the scatter plot data of the curve to be analyzed. Then, depending on the needs of different analysis scenarios, select the middle proportion points a and b (0 < a < 1; 0 < b < 1; a < b), discard the data from the beginning and end, and only retain the middle data. For example, select the first 15% as the head data, the last 10% as the tail data, and the remaining 75% as the middle data, retaining only the middle data.

[0096] Next, the data in the middle section is normalized, and the x-coordinates are recalculated. Normalization involves linearly mapping the data to the interval [0,1]. The maximum value in x is found. The minimum value in x is found, and each element in x is subtracted from the minimum value. The result is then divided by the range (maximum value minus minimum value) to normalize it to the interval [0,1]. The normalization formula is as follows:

[0097]

[0098] Where, x do This represents the normalized value of x; min(x) represents the minimum value in the x data; max(x) represents the maximum value in the x data.

[0099] Then, a high-order polynomial is used to fit the data in the middle of the curve. (See reference...) Figure 3 , Figure 3 This section describes the normalized image of the middle section of the hot strip rolling process curve and the fitted curve. The root mean square error (RMSE) is calculated from the normalized data and the fitted data to ensure it meets accuracy requirements. In this implementation, a 12th-order polynomial is used as an example; however, when the curve exhibits significant dispersion, a higher-order polynomial can be used to meet the requirements. The relevant formulas are as follows:

[0100]

[0101] Among them, y 12 (x do (x) represents the normalized curve, which is a 12th-degree polynomial curve; do Here are the normalized length direction coordinates of the curve; a i The coefficients are those of a 12th-degree polynomial.

[0102] The root mean square error (RMSE) is obtained from normalized data and curve-fitted data. This is achieved by calculating the residuals between the original data and the fitted curve—that is, the vertical deviation of each data point—and then calculating the root mean square error of these residuals. This yields an index used to measure how well the fitted curve fits the original data. The relevant formulas are as follows:

[0103] ε(i)=y middle (i)-yFix (i)

[0104]

[0105] Among them, y middle (i) represents the y-value of the i-th point in the middle data; y Fix (i) represents the y-value of the i-th point in the fitted data; ε(i) represents the residual of the i-th point; n represents the total number of data points; RMSE represents the root mean square error.

[0106] The sum of the areas enclosed by the fitted curve and the line containing the average ordinate of the fitted curve is obtained from the curve-fitted data. First, the average ordinate of the data points is calculated, as follows:

[0107]

[0108] Where n is the total number of data points, y F (i) is the value of the fitted curve at the i-th data point.

[0109] Then calculate the areas of the upper and lower portions bounded by the curve and the line containing the average value of the ordinate, as follows:

[0110]

[0111] Among them, Area under Area is the area under the fitted curve; above x represents the area above the fitted curve. do The x-coordinate value after normalization; max(x) do ) and min(x do ) are the maximum and minimum values ​​of the fitted curve on the dataset, respectively.

[0112] Therefore, the total area of ​​the upper and lower portions of the surface enclosed by the curve and the line containing the average value of the ordinate can be calculated as follows:

[0113] Area total＝ |Area under -Area above |

[0114] Among them, Area total This represents the total area enclosed.

[0115] The definite integral of the fitted curve with respect to the x-axis is obtained from the curve-fitted data. Specifically, the definite integral from 0 to 1 is performed on the fitted continuous curve, calculated using the following formula:

[0116]

[0117] Where, x doIt is the normalized x-axis of the data; y F (x) is x do The corresponding y-value; while Integral represents the result of the definite integral.

[0118] The smoothness of the curve's center is judged based on the root mean square error, the total enclosed area, and the definite integral. For example, it is set that the root mean square error is no greater than 0.005 mm. 2 If the sum of the enclosed areas is no greater than 0.0001 and the definite integral value is no greater than 0.0075, the curve is considered to be of acceptable flatness; otherwise, it is unacceptable. Standard values ​​can be set independently in practical applications.

[0119] As another embodiment, rolling data for the entire length of a hot-rolled strip is acquired from online data acquisition sensors. This data comprises arbitrary physical information evenly spaced along the strip's length direction, such as a strip length X = 1098 mm, a total number of discrete points N = 1099 along the length direction, and a unit discrete point length Δx = 0.999 mm. The data is divided into three parts: head, middle, and tail, with the head accounting for the first 0.1% and the tail accounting for the last 0.1%. The head and tail data are then discarded. The acquired middle section data is normalized, and the middle section data is shown in Table 1.

[0120] Table 1

[0121]

[0122]

[0123] Then, normalization was performed, and the results are shown in Table 2.

[0124] Table 2

[0125]

[0126] The data were fitted using a higher-order polynomial based on a 12th-degree polynomial, and the fitted y-values ​​were obtained. The results are shown in Table 3.

[0127] Table 3

[0128] 0 -0.00747 0.0011 -0.00663 0.0023 -0.00590 0.0034 -0.00528 0.0046 -0.004767 0.0057 -0.00436 0.0068 -0.00404 0.0080 -0.00380 …… …… 0.9932 0.00316 0.9943 0.00305 0.9954 0.00292 993.01 0.00276 0.9966 0.00254 0.9977 0.00231 0.9988 0.00201 1 0.00167

[0129] The root mean square error (RMSE) was calculated from the normalized data and the data after curve fitting, with an RMSE of 0.0049. Then, the sum of the areas enclosed by the fitted curve and the line containing the average ordinate of the fitted curve was calculated from the data after curve fitting. Finally, the definite integral of the fitted curve with respect to the x-axis was calculated from the data after curve fitting. This process was then used to determine whether the steady-state condition of the middle section of the plate-strip curve was acceptable.

[0130] This embodiment first divides the original data into three parts—head, middle, and tail—using a specified segmentation ratio to ensure that the length ratio of each part meets expectations. Then, the extracted middle data is normalized to ensure that different data ranges do not adversely affect the fitting results during polynomial fitting. A 12th-order polynomial is used to fit the middle data to obtain the fitted curve. Quantitative indicators, such as RMSE, total area of ​​integration, and definite integral, are introduced to make the judgment of curve characteristics more accurate and reliable. The root mean square error (RMSE) is used as the dispersion index of the fitted curve to evaluate the accuracy of the fitting; the total area enclosed by the fitted curve and the line containing the y-mean value is used to judge the curve's smoothness; and the definite integral of the fitted curve within a certain range is used to judge the curve's fit to the x-axis. A detailed analysis of the curve's quality provides comprehensive data support for product quality assessment.

[0131] Based on the rolling process curve steady-state identification method provided in the above embodiments, this application also provides a specific implementation of the rolling process curve steady-state identification device. Please refer to the following embodiments.

[0132] First see Figure 4 The rolling process curve steady-state identification device 400 provided in this application embodiment includes the following modules:

[0133] The acquisition module 401 is used to acquire the rolling data of the middle section of the target hot strip.

[0134] The fitting module 402 is used to fit the above rolling data using a preset polynomial to obtain fitted data.

[0135] The calculation module 403 is used to calculate the difference between the above rolling data and the above fitted data.

[0136] The determination module 404 is used to determine the area of ​​the figure enclosed by the fitted curve and the straight line corresponding to the average value of the ordinate of the fitted curve, based on the above fitted data.

[0137] The determination module 404 is also used to determine the definite integral of the fitted curve based on the above-mentioned fitted data.

[0138] The judgment module 405 is used to determine the steady state of the middle section of the target hot strip curve based on the above difference, the above area and the above definite integral.

[0139] The rolling process curve steady-state identification device provided in this application can more accurately capture subtle changes in the curve by fitting the data in the middle of the curve, and the fitted curve is closer to the actual data. By calculating the difference between the rolling data and the fitted data, the degree of fitting between the fitted curve and the original data is quantitatively evaluated to ensure the reliability of the fitting results. Multiple quantitative indicators, such as the enclosed area and definite integral, are introduced to evaluate the flatness of the middle section of the curve from different angles, which can complete the steady-state identification of the middle section of the rolling curve.

[0140] As one implementation of this application, the above-mentioned acquisition module 401 includes:

[0141] The acquisition unit is used to acquire all rolling data of the target hot strip.

[0142] The determining unit is used to determine the head and tail data of the target hot-rolled plate according to a preset ratio.

[0143] The extraction unit is used to extract the rolling data of the middle section of the target hot strip based on the above-mentioned head data and tail data.

[0144] As one implementation of this application, the rolling process curve steady-state identification device 400 includes:

[0145] The processing module is used to normalize the rolling data of the middle section of the target hot strip.

[0146] As one implementation of this application, the computing module 403 includes:

[0147] The determining unit is used to obtain the residual between the rolling data and the fitted data based on the deviation in the vertical direction between the rolling data and the fitted data.

[0148] The calculation unit is used to calculate the root mean square error of the residuals and obtain the difference between the rolling data and the fitted data.

[0149] As one implementation of this application, module 404 is defined, including:

[0150] The calculation unit is used to calculate the average value of the ordinate of the data points in the above-mentioned fitted data based on the above-mentioned fitted data.

[0151] The determining unit is used to determine the line containing the average value of the ordinate based on the above average ordinate value.

[0152] The calculation unit is also used to calculate the area of ​​the figure enclosed by the fitted curve and the straight line, based on the straight line.

[0153] As one implementation of this application, the judgment module 405 includes:

[0154] The judgment unit is used to determine that the steady state of the middle section of the target hot-rolled plate curve is stable when the difference is less than or equal to the first threshold, the area is less than or equal to the second threshold, and the definite integral is less than or equal to the third threshold.

[0155] The judgment unit is also used to determine that the steady state of the middle section of the target hot-rolled plate curve is unstable when the difference is greater than the first threshold, the area is greater than the second threshold, or the definite integral is greater than the third threshold.

[0156] Each module in the rolling process curve steady-state identification device provided in this application embodiment can realize each step in the above-mentioned rolling process curve steady-state identification method and achieve the corresponding effect. For the sake of brevity, it will not be described in detail here.

[0157] Figure 5 A schematic diagram of the structure of the rolling process curve steady-state identification hardware provided in an embodiment of this application is shown.

[0158] The steady-state identification device for the rolling process curve may include a processor 501 and a memory 502 storing computer program instructions.

[0159] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0160] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 502 is non-volatile solid-state memory.

[0161] The memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, a memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the rolling process curve steady-state identification method according to any embodiment of this disclosure.

[0162] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any of the rolling process curve steady-state identification methods in the above embodiments.

[0163] In one example, the rolling process curve steady-state identification device may further include a communication interface 503 and a bus 510. Wherein, as Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 510 and complete communication with each other.

[0164] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0165] Bus 510 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 510 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0166] Furthermore, in conjunction with the method for steady-state identification of rolling process curves in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods for steady-state identification of rolling process curves in the above embodiments.

[0167] This application also provides a computer program product, including a computer program, which, when executed, implements any of the methods for steady-state identification of rolling process curves in the above embodiments.

[0168] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0169] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0170] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0171] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0172] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for steady-state identification of a rolling process curve, characterized in that, The method includes: Obtain rolling data for the middle section of the target hot-rolled strip, wherein the rolling data includes at least one of temperature, speed, torque, and thickness; the specific steps include: Obtain all rolling data for the target hot strip; According to a preset ratio, determine the head and tail data of the target hot-rolled plate; Based on the head data and the tail data, the rolling data of the middle section of the target hot strip is extracted; The rolling data of the middle section of the target hot strip is normalized. The rolling data is fitted using a preset polynomial to obtain fitted data; Calculate the difference between the rolling data and the fitted data; the specific steps include: The residual between the rolling data and the fitted data is obtained based on the deviation of the rolling data and the fitted data in the vertical direction. Calculate the root mean square error of the residual to obtain the difference between the rolling data and the fitted data; Based on the fitted data, determine the area of ​​the figure enclosed by the fitted curve and the line corresponding to the average ordinate of the fitted curve; the specific steps include: Based on the fitted data, calculate the average ordinate of the data points in the fitted data; Determine the straight line containing the average value of the ordinate based on the average value of the ordinate; Based on the straight line, calculate the area of ​​the figure enclosed by the fitted curve and the straight line; Based on the fitted data, determine the definite integral of the fitted curve; The steady state of the middle section of the target hot-rolled plate curve is determined based on the difference, the area, and the definite integral; the specific steps include: If the difference is less than or equal to a first threshold, the area is less than or equal to a second threshold, and the definite integral is less than or equal to a third threshold, the steady state of the middle section of the target hot strip curve is determined to be stable. If the difference is greater than the first threshold, or the area is greater than the second threshold, or the definite integral is greater than the third threshold, the steady state of the middle section of the target hot-rolled plate curve is determined to be unstable.

2. A steady-state identification device for a rolling process curve, characterized in that, The device is capable of implementing the steady-state identification method for the rolling process curve as described in claim 1, and the device comprises: The acquisition module is used to acquire rolling data of the middle section of the target hot strip. The fitting module is used to fit the rolling data using a preset polynomial to obtain fitted data; The calculation module is used to calculate the difference between the rolling data and the fitted data; The determination module is used to determine the area of ​​the figure enclosed by the fitted curve and the straight line corresponding to the average value of the ordinate of the fitted curve, based on the fitted data. The determining module is also used to determine the definite integral of the fitted curve based on the fitted data; The judgment module is used to determine the steady state of the middle section of the target hot-rolled plate curve based on the difference, the area, and the definite integral.

3. A steady-state identification device for a rolling process curve, characterized in that, The device includes a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the rolling process curve steady-state identification method as described in claim 1.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the steady-state identification method for rolling process curves as described in claim 1.

5. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the rolling process curve steady-state identification method as described in claim 1.

Images