Method and device for determining the thickness of decarburized layer of hot-rolled strip

By performing sub-image division and grayscale analysis on the metallographic image of the decarburization layer of the strip, the problem of low efficiency in determining the thickness of the decarburization layer of the hot-rolled strip is solved, fast and accurate measurement of the decarburization layer thickness is achieved, and the efficiency and accuracy of steel performance evaluation are improved.

CN115239741BActive Publication Date: 2025-10-24SHOUGANG GROUP CO LTD +2
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210695354.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-20
Publication Date
2025-10-24
Estimated Expiration
2042-06-20

AI Technical Summary

Technical Problem

In the prior art, the determination of the thickness of the decarburized layer of hot-rolled strip steel is inefficient, resulting in inaccurate evaluation of steel properties.

Method used

By acquiring the metallographic image of the decarburized layer of the strip, dividing it into multiple sub-images, calculating the grayscale average of each sub-image, and using image recognition technology to determine the thickness of the decarburized layer, including rotating the metallographic image and grayscale curve slope analysis.

Benefits of technology

It can quickly and efficiently determine the thickness of the decarburization layer of the steel strip, improve the detection efficiency, accurately grasp the decarburization degree of the steel, and ensure the accuracy of the steel performance evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115239741B_ABST
    Figure CN115239741B_ABST
Patent Text Reader

Abstract

The present application relates to hot-rolled strip steel technical field, especially to a kind of hot-rolled strip steel decarburization layer thickness determination method, the method comprises: after obtaining the metallographic image of the decarburization layer of strip steel, the metallographic image is divided into multiple sub-images, and the gray average value of each sub-image in the multiple sub-images is obtained;According to the gray average value of each sub-image in the multiple sub-images, obtain the distance difference of multiple groups of sub-images;According to the distance difference of the multiple groups of sub-images, the thickness of the decarburization layer is obtained.The method can quickly and efficiently determine the thickness of the decarburization layer of strip steel, improve the determination efficiency of the decarburization layer thickness of strip steel, quickly and accurately master the real decarburization degree of steel, accurately evaluate the performance of steel.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hot-rolled strip steel, and particularly relates to a method and device for determining the thickness of a decarburized layer of hot-rolled strip steel. BACKGROUND

[0002] Decarburization refers to the phenomenon that the carbon content of the surface of a strip steel decreases during heating. The decrease in the carbon content of the surface layer of the strip steel can cause a series of performance deterioration of the steel, such as insufficient hardness of the strip steel after quenching, reduced wear resistance of the strip steel, or reduced fatigue strength of the strip steel, and the like. Therefore, the degree of decarburization of the steel is an important index for evaluating the performance of the material.

[0003] In the prior art, the thickness of the decarburized layer of the strip steel is usually measured by using a metallographic method, a hardness method, or a chemical analysis method, so as to detect and evaluate the degree of decarburization of the strip steel. However, the metallographic method is based on the difference between the decarburized region and the base structure of the strip steel, and the thickness of the decarburized layer is determined manually. The hardness method is based on the correlation between the carbon content of the strip steel and the hardness of the strip steel after heat treatment, and the decarburization of the strip steel is determined by the change in the microhardness. However, the hardness method has limitations such as high requirement for the precision of the detection equipment and complicated detection process. The chemical method determines the thickness of the decarburized layer by measuring the change in the carbon content in the thickness direction of the steel, and the detection process is complex and time-consuming, which is not suitable for industrial detection. Therefore, the existing technical solutions cause the problem of low efficiency in determining the thickness of the decarburized layer of the strip steel. SUMMARY

[0004] The embodiments of the present application provide a method and device for determining the thickness of a decarburized layer of hot-rolled strip steel, which solve the technical problem of low efficiency in determining the thickness of the decarburized layer of the strip steel in the prior art, achieve the technical effects of quickly and efficiently determining the thickness of the decarburized layer of the strip steel, improving the efficiency of determining the thickness of the decarburized layer of the strip steel, quickly and accurately grasping the real degree of decarburization of the steel, accurately evaluating the performance of the steel, and the like.

[0005] In a first aspect, the embodiments of the present application provide a method for determining the thickness of a decarburized layer of hot-rolled strip steel, comprising:

[0006] After obtaining a metallographic image of the decarburized layer of the strip steel, the metallographic image is divided into a plurality of sub-images, and the average gray value of each sub-image in the plurality of sub-images is obtained;

[0007] According to the average gray value of each sub-image in the plurality of sub-images, a plurality of groups of distance differences of the sub-images are obtained;

[0008] According to the distance differences of the plurality of groups of sub-images, the thickness of the decarburized layer is obtained.

[0009] Preferably, the metallographic image is an image obtained by rotating a front view of the decarburized layer by a preset angle, and the plurality of sub-images are M*N sub-images, where M is a number of rows of the plurality of sub-images, N is a number of columns of the plurality of sub-images, and M and N are both integers greater than 1.

[0010] The distance difference of each group of sub-images is obtained according to the average gray value of each sub-image in the plurality of sub-images.

[0011] For each row of sub-images in the plurality of sub-images, a starting sub-image and a terminal sub-image are obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and a distance difference of a group of sub-images is obtained according to the starting sub-image and the terminal sub-image.

[0012] After the operation on each row of sub-images is completed, M groups of distance differences of sub-images are obtained.

[0013] Preferably, the starting sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and the method comprises the following steps.

[0014] In order, the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images is determined, and if the average gray value of a certain sub-image is not less than a gray threshold value, the sub-image is determined as the starting sub-image.

[0015] Preferably, the terminal sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and the method comprises the following steps.

[0016] After the starting sub-image is obtained, the average gray value of each sub-image after the starting sub-image in the N sub-images corresponding to the row of sub-images is determined in order, and if the average gray value of a certain sub-image is less than the gray threshold value, the sub-image is determined as the terminal sub-image.

[0017] Preferably, the terminal sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and the method comprises the following steps.

[0018] After the starting sub-image is obtained, a gray curve is obtained according to the average gray value of each sub-image after the starting sub-image in the N sub-images corresponding to the row of sub-images.

[0019] The terminal sub-image is obtained according to the gray curve.

[0020] Preferably, the terminal sub-image is obtained according to the gray curve, and the method comprises the following steps.

[0021] In the gray scale curve, the slope of the gray scale curve corresponding to each of the N sub-images after the starting sub-image is determined in sequence, if the slope of the gray scale curve corresponding to a certain sub-image is not greater than a first slope threshold, and the slope of the corresponding gray scale curve is not less than a second slope threshold, the sub-image is determined as the termination sub-image, wherein the second slope threshold is less than the first slope threshold.

[0022] Preferably, the thickness of the decarburized layer is obtained according to the distance difference of the multiple groups of sub-images.

[0023] The thickness of the decarburized layer is obtained by mean processing the distance difference of the multiple groups of sub-images.

[0024] Based on the same inventive concept, in a second aspect, the present application also provides a device for determining the thickness of a decarburized layer of a hot-rolled strip steel, comprising:

[0025] The dividing module is configured to divide the metallographic image of the decarburized layer of the strip steel into multiple sub-images after the metallographic image is obtained, and obtain the average gray scale of each of the multiple sub-images.

[0026] The first obtaining module is configured to obtain the distance difference of multiple groups of sub-images according to the average gray scale of each of the multiple sub-images.

[0027] The second obtaining module is configured to obtain the thickness of the decarburized layer according to the distance difference of the multiple groups of sub-images.

[0028] Based on the same inventive concept, in a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to realize the steps of the method for determining the thickness of a decarburized layer of a hot-rolled strip steel.

[0029] Based on the same inventive concept, in a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the program is executed by a processor to realize the steps of the method for determining the thickness of a decarburized layer of a hot-rolled strip steel.

[0030] The one or more technical solutions in the embodiments of the present application have at least the following technical effects or advantages:

[0031] In the embodiment of the present application, after the metallographic image of the decarburized layer of the strip steel is acquired, the metallographic image is processed, and the specific processing method is that the metallographic image is first divided into a plurality of sub-images, and then the gray average value of each sub-image in the plurality of sub-images is acquired. Here, by fully utilizing the image recognition technology, the effect of quickly and efficiently processing the metallographic image is achieved by recognizing the gray values of different regions in the metallographic image of the decarburized layer, and the determination efficiency of the thickness of the decarburized layer of the strip steel is improved.

[0032] Then, according to the gray average value of each sub-image in the plurality of sub-images, a plurality of sets of distance differences of the sub-images are obtained, and according to the distance differences of the plurality of sets of sub-images, the thickness of the decarburized layer is obtained. Here, according to the gray average value of each sub-image, the distance differences of the plurality of sets of sub-images are obtained, and then the thickness of the decarburized layer is obtained, so that the thickness of the decarburized layer of the strip steel can be quantitatively calculated, and the measurement error in the process of identifying the thickness of the decarburized layer by artificial recognition is eliminated. Therefore, the method of the embodiment of the present application quickly and efficiently determines the thickness of the decarburized layer of the strip steel, improves the determination efficiency of the thickness of the decarburized layer of the strip steel, quickly and accurately masters the real decarburization degree of the steel, and accurately evaluates the performance of the steel. BRIEF DESCRIPTION OF DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not to be construed as limiting the application. Moreover, in the drawings, like reference numerals designate similar parts throughout the several views, and in which:

[0034] Figure 1 A step flow schematic diagram of the method for determining the thickness of the decarburized layer of the hot-rolled strip steel in the embodiment of the present application is shown;

[0035] Figure 2 A structural schematic diagram of the upper surface of the strip steel in the embodiment of the present application is shown;

[0036] Figure 3 A front view of the decarburized layer of the strip steel in the embodiment of the present application is shown;

[0037] Figure 4 A metallographic image after the front view of the decarburized layer is rotated in the embodiment of the present application is shown;

[0038] Figure 5 A structural schematic diagram of a plurality of sub-images of the metallographic image in the embodiment of the present application is shown;

[0039] Figure 6 A schematic diagram of the coordinate system of the plurality of sub-images of the metallographic image in the embodiment of the present application is shown;

[0040] Figure 7A schematic diagram of the gray scale table in the embodiment of the present application is shown.

[0041] Figure 8 A slope curve of the gray scale curve between the sub-image with the abscissa of 649 and the sub-image with the abscissa of 1155 in the embodiment of the present application is shown.

[0042] Figure 9 A slope curve of the gray scale curve between the sub-image with the abscissa of 649 and the sub-image with the abscissa of 1155 in the embodiment of the present application is shown.

[0043] Figure 10 A module schematic diagram of the determination device of the decarburized layer thickness of the hot-rolled strip steel in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art.

[0045] Embodiment One

[0046] The first embodiment of the present application provides a method for determining the decarburized layer thickness of a hot-rolled strip steel, as shown in the figure, comprising: Figure 1

[0047] S101, after obtaining the metallographic image of the decarburized layer of the strip steel, dividing the metallographic image into a plurality of sub-images, and obtaining the gray scale average value of each sub-image in the plurality of sub-images;

[0048] S102, obtaining the distance difference of multiple groups of sub-images according to the gray scale average value of each sub-image in the multiple sub-images;

[0049] S103, obtaining the thickness of the decarburized layer according to the distance difference of multiple groups of sub-images.

[0050] In this embodiment, after obtaining the metallographic image of the decarburized layer of the strip steel, the metallographic image is processed, and the specific processing method is to first divide the metallographic image into a plurality of sub-images, and then obtain the gray scale average value of each sub-image in the plurality of sub-images. Here, by fully utilizing the image recognition technology, through the recognition of the gray scale values of different regions in the metallographic image of the decarburized layer, the effect of quickly and efficiently processing the metallographic image is achieved, and the efficiency of determining the decarburized layer thickness of the strip steel is improved.

[0051] ​Then, based on the grayscale average of each of the multiple sub-images, the distance difference between the multiple groups of sub-images is obtained; and based on the distance difference between the multiple groups of sub-images, the thickness of the decarburized layer is obtained. Here, by using the grayscale average of each sub-image to obtain the distance difference between the multiple groups of sub-images, and then the thickness of the decarburized layer, the thickness of the decarburized layer in the steel strip can be quantitatively calculated, eliminating the measurement errors that occur during manual identification of the decarburized layer thickness. Therefore, the method of this embodiment achieves rapid and efficient determination of the thickness of the decarburized layer in the steel strip, improving the efficiency of determining the thickness of the decarburized layer in the steel strip, quickly and accurately determining the true degree of decarburization in the steel material, and accurately evaluating the steel material's performance.

[0052] Next, combine Figure 1 The specific implementation steps of the method for determining the thickness of the decarburized layer of the hot-rolled strip provided in this embodiment are described in detail:

[0053] First, before executing step S101, a metallographic image of the decarburized layer of the strip is obtained. The specific process of obtaining the metallographic image is as follows: Figure 2 As shown in FIG, the upper or lower surface of the strip is photographed by a device for taking metallographic photographs to obtain a metallographic image of the decarburized layer of the strip. Figure 2 In the figure, the black frame on the strip represents the viewing angle of the upper surface of the strip. The metallographic image of the decarburized layer of the strip is as follows: Figure 3 As shown, Figure 3 This is a metallographic image of the decarburized layer of the strip, and also a main view of the decarburized layer.

[0054] by Figure 3 For example, in the metallographic image, Figure 3 The top black area is the non-strip steel area, the white area below the black area is the decarburized layer area, the light gray area below the white area is the boundary area between the decarburized layer and the strip steel, the dark gray area below the light gray area is the strip steel area, and the strip steel area is a uniform gray area.

[0055] Next, step S101 is performed. After obtaining a metallographic image of the decarburized layer of the steel strip, the metallographic image is divided into a plurality of sub-images, and the grayscale average value of each of the plurality of sub-images is obtained.

[0056] Specifically, after obtaining the metallographic image of the decarburized layer of the steel strip, in order to quickly determine the thickness of the decarburized layer, that is, to quickly process from the non-steel strip area to the steel strip area of ​​the metallographic image, the main view of the decarburized layer is usually rotated by a preset angle as the metallographic image for subsequent processing (i.e., the target metallographic image), wherein the preset angle is set according to actual needs, such as Figure 4 The main view of the decarburized layer is rotated 90° to the left as the target metallographic image, as shown in Figure 4 As shown. Of course, Figure 4The main view of the decarburized layer can also be directly used as the target metallographic image.

[0057] After the metallographic image is determined, the metallographic image is divided into a plurality of sub-images of equal size, wherein the plurality of sub-images are MxN sub-images, M is the number of rows of the plurality of sub-images, N is the number of columns of the plurality of sub-images, and M and N are both integers greater than 1. For example, the metallographic image of FIG. 1 is divided into a plurality of sub-images, i.e., 10x20 sub-images, as shown in FIG. 2. Figure 4 Figure 5 After being divided into a plurality of sub-images, each sub-image is subjected to grayscale processing to obtain the grayscale average value of each sub-image. The process of obtaining the grayscale average value of each sub-image is that, for each sub-image in the plurality of sub-images, the grayscale average value of the sub-image is obtained according to the grayscale value of each pixel of the sub-image. For example, for each sub-image, the sum of the grayscale values of each pixel of the sub-image is divided by the number of pixels of the sub-image to obtain the grayscale average value of the sub-image.

[0058] After the grayscale average value of each sub-image is obtained, the grayscale average value of each sub-image can be explicitly represented by the coordinate system of each sub-image. It should be noted that while the metallographic image is divided into a plurality of sub-images, the coordinates of each sub-image are obtained, which can be represented by the coordinates of the center point of each sub-image, or the coordinates of the lower right corner point of each sub-image, or the coordinates of a point set according to actual needs.

[0059] For example, the metallographic image of FIG. 1 is divided into 50x100 sub-images, i.e., 50 rows and 100 columns of sub-images, each sub-image is 22 microns (μm) long and 150 μm wide, and the coordinates of each sub-image are as shown in FIG. 3. The corresponding grayscale average value is displayed on each sub-image. In order to clearly and clearly show the coordinates of FIG. 1 and the grayscale average value of each sub-image, the coordinates of FIG. 1 and the grayscale average value of each sub-image are converted into a grayscale table in the format of the grayscale table. For example, the coordinates of the center point of each sub-image represent the coordinates of each sub-image, and the converted grayscale table is as shown in FIG. 4, which shows the coordinates and grayscale average value of part of the sub-images of FIG. 1. In FIG. 4, the first column indicates the horizontal position of the center point of each sub-image, and the horizontal position represents the horizontal coordinate of the center point of each sub-image. The first row indicates the vertical position of the center point of each sub-image, and the vertical position represents the vertical coordinate of the center point of each sub-image. The grayscale average value of each sub-image corresponding to each coordinate is indicated in the other cells except the first column and the first row. Figure 4 Figure 6 Figure 6 Figure 6 Figure 6 Figure 7 Figure 7 Figure 6 Figure 7

[0060] ​​​​​​​​​​In this embodiment, after obtaining the metallographic image of the decarburized layer of the steel strip, the metallographic image is divided into multiple sub-images, and the grayscale average value of each sub-image in the multiple sub-images is obtained. By making full use of image recognition technology and identifying the grayscale values ​​of different areas in the metallographic image of the decarburized layer, the metallographic image can be processed quickly and efficiently, laying a solid foundation for the subsequent determination of the thickness of the decarburized layer.

[0061] Then, step S102 is executed to obtain the distance differences of the multiple groups of sub-images according to the grayscale average value of each sub-image in the multiple sub-images.

[0062] Specifically, after dividing the metallographic image into multiple sub-images (i.e., M×N sub-images) and obtaining the grayscale average value of each sub-image, the distance difference between the multiple groups of sub-images is obtained based on the grayscale average value of each sub-image in the multiple sub-images. There are two methods for obtaining the distance difference between the multiple groups of sub-images, which are as follows:

[0063] The first method is to obtain a starting sub-image and an ending sub-image based on the grayscale average value of each sub-image in the N sub-images corresponding to the row of sub-images for each row of sub-images, and obtain the distance difference of a group of sub-images based on the starting sub-image and the ending sub-image; after completing the above operation for each row of sub-images, the distance difference of M groups of sub-images is obtained.

[0064] The specific process for obtaining the starting and ending sub-images based on the grayscale average of each of the N sub-images corresponding to the row of sub-images is to determine the grayscale average of each of the N sub-images, in order from the first to the Nth sub-image. If the grayscale average of a sub-image is not less than the grayscale threshold, the sub-image is determined as the starting sub-image. After obtaining the starting sub-image, the grayscale average of each of the N sub-images following the starting sub-image is determined in order from the starting to the Nth sub-image. If the grayscale average of a sub-image is less than the grayscale threshold, the sub-image is determined as the ending sub-image. The grayscale threshold is set according to actual needs, such as 80.

[0065] by Figure 6 The coordinate system of each sub-image of the metallographic image and Figure 7 Take the grayscale table as an example, for Figure 6 Each row of sub-images in Figure 6 As an example, the first row of sub-images Figure 7For example, the second column of the second row, the average gray value of each sub-image in the first row of sub-images is observed in order from the first sub-image to the N (i.e. 100)th sub-image. As can be seen from the second column of the seventh figure, in the second column, the average gray value of the sub-image with the horizontal coordinate of 429 is not less than the gray threshold value 80, and thus the sub-image with the horizontal coordinate of 429 is determined as the starting sub-image. The starting sub-image represents the junction of the non-steel strip region and the decarburized layer, and the junction is also the surface of the steel strip.

[0066] After the starting sub-image is obtained, the average gray value of each sub-image in the first row of sub-images after the starting sub-image is observed in order from the starting sub-image to the N (i.e. 100)th sub-image. As can be seen from the second column of the seventh figure, in the second column, the average gray value of the sub-image with the horizontal coordinate of 803 is less than the gray threshold value 80, and thus the sub-image with the horizontal coordinate of 803 is determined as the ending sub-image. The ending sub-image represents the junction of the decarburized layer and the steel strip region.

[0067] According to the horizontal coordinate of the starting sub-image and the horizontal coordinate of the ending sub-image, the distance difference of a group of sub-images is obtained, which is 803-429=374μm. The distance difference of the group of sub-images represents the thickness of the decarburized layer of the first row of sub-images, and thus the distance difference of each group of sub-images represents the thickness of the decarburized layer of each row of sub-images. Figure 6 After the above operation is completed for each row of sub-images, the distance differences of M (i.e. 50) groups of sub-images are obtained. Figure 6 After the above operation is completed for each row of sub-images, the distance differences of M (i.e. 50) groups of sub-images are obtained.

[0068] The method for obtaining the distance differences of multiple groups of sub-images is to directly determine a group of starting sub-images and ending sub-images according to the average gray value of each sub-image, and to obtain the distance difference of a group of sub-images according to the group of starting sub-images and ending sub-images. The method can quickly and efficiently determine the thickness of the decarburized layer, can quantitatively calculate the thickness of the decarburized layer of the steel strip, can eliminate the measurement error in the process of manually identifying the thickness of the decarburized layer, can improve the determination efficiency of the thickness of the decarburized layer of the steel strip, and can quickly and accurately master the real decarburization degree of the steel material and accurately evaluate the performance of the steel material.

[0069] Secondly, for each row of sub-images in the multiple sub-images, a gray curve and a starting sub-image are obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and an ending sub-image is obtained according to the gray curve and the starting sub-image, and a distance difference of a group of sub-images is obtained according to the starting sub-image and the ending sub-image. After the above operation is completed for each row of sub-images, the distance differences of M groups of sub-images are obtained.

[0070] The specific process of obtaining the starting sub-image is the same as that of obtaining the starting sub-image in the first distance difference method of obtaining multiple groups of sub-images. The specific process of obtaining the starting sub-image is that, in the order of the first sub-image to the Nth sub-image in the corresponding N sub-images, the gray average value of each sub-image in the corresponding N sub-images is sequentially judged, and if the gray average value of a certain sub-image is not less than the gray threshold, the sub-image is determined as the starting sub-image.

[0071] After obtaining the starting sub-image, a gray curve is obtained according to the gray average value of each sub-image in the N sub-images corresponding to the row of sub-images after the starting sub-image. And the terminal sub-image is obtained according to the gray curve.

[0072] The specific process of obtaining the terminal sub-image is that, in the gray curve, the slope of the gray curve corresponding to each sub-image in the N sub-images after the starting sub-image is sequentially judged, and if the slope of the gray curve corresponding to a certain sub-image is not greater than the first slope threshold and the slope of the gray curve corresponding to the certain sub-image is not less than the second slope threshold, the sub-image is determined as the terminal sub-image, wherein the second slope threshold is less than the first slope threshold. The first slope threshold and the second slope threshold can be set according to actual needs, such as the first slope threshold being 0.2 and the second slope threshold being -0.2.

[0073] Taking the coordinate system of each sub-image of the metallographic image of Figure 6 and the gray table of the gray curve of Figure 7 as an example, for each row of sub-images in Figure 6 , taking the first row of sub-images of Figure 6 as an example, that is, taking the second column of Figure 7 as an example. First, the starting sub-image is determined according to the gray average value of each sub-image of the first row of sub-images of Figure 6 , and the abscissa of the starting sub-image is 429 (for details of the specific process of determining the starting sub-image, please refer to the example in the first distance difference method of obtaining multiple groups of sub-images).

[0074] Then, a gray curve is fitted according to the gray average value of each sub-image in the first row of sub-images of Figure 6 after the starting sub-image, and the expression of the gray curve is f(x) = a1x 3 +a2x 2+a3x+a4, where x is the horizontal coordinate of each sub-image after the starting sub-image in the first row of sub-images, and f(x) is the average gray value of each sub-image after the starting sub-image in the first row of sub-images. Derivation of the gray value curve gives the slope of the gray value curve corresponding to each sub-image after the starting sub-image in the first row of sub-images. In order of the first sub-image after the starting sub-image to the Nth sub-image, the slopes corresponding to each sub-image after the starting sub-image in the first row of sub-images are observed.

[0075] In Figure 8 , Figure 8 The gray value curve fitted between the sub-image with the horizontal coordinate of 649 and the sub-image with the horizontal coordinate of 1155 in the first row of sub-images is shown. Derivation of the gray value curve shown in Figure 8 gives the slope curve composed of the slope corresponding to the sub-image with the horizontal coordinate of 649 to the slope corresponding to the sub-image with the horizontal coordinate of 1155, as shown in Figure 9 It can be seen from Figure 9 that the slope corresponding to the sub-image with the horizontal coordinate of 803 is not greater than the first slope threshold of 0.2 and not less than the second slope threshold of -0.2, so the sub-image with the horizontal coordinate of 803 is determined as the terminal sub-image.

[0076] According to the horizontal coordinates of the starting sub-image and the terminal sub-image, the distance difference of a group of sub-images is obtained, which is 374 μm. The distance difference of the group of sub-images represents Figure 6 the decarburized layer thickness of the first row of sub-images, so the distance difference of each group of sub-images represents the thickness of the decarburized layer of each row of sub-images. Figure 6 After each row of sub-images of the first row of sub-images is operated in the above manner, the distance differences of M (i.e. 50) groups of sub-images are obtained.

[0077] The method of obtaining the distance differences of multiple groups of sub-images is to fit a gray value curve according to the average gray value of each sub-image, to determine a group of starting sub-images and terminal sub-images according to the gray value curve, and to obtain the distance difference of a group of sub-images according to the group of starting sub-images and terminal sub-images. This method can quickly and efficiently determine the thickness of the decarburized layer, can quantitatively calculate the thickness of the decarburized layer of the strip steel, can eliminate the measurement error in the process of manually identifying the thickness of the decarburized layer, can improve the determination efficiency of the thickness of the decarburized layer of the strip steel, and can quickly and accurately master the true decarburization degree of the steel and accurately evaluate the performance of the steel. Moreover, the second method of obtaining the distance differences of multiple groups of sub-images is more accurate than the first method.

[0078] After obtaining the distance differences of multiple groups of sub-images, step S103 is performed to obtain the thickness of the decarburized layer according to the distance differences of the multiple groups of sub-images.

[0079] Specifically, the thickness of the decarburized layer is obtained by performing mean value processing on the distance differences of the multiple groups of sub-images. For example, the first method and the second method for obtaining the distance differences of the multiple groups of sub-images both obtain the distance differences of M (i.e., 50) groups of sub-images. The mean value of the distance differences of the M groups of sub-images is obtained, and the obtained mean value is taken as the thickness of the decarburized layer.

[0080] The method for determining the thickness of the decarburized layer of the hot-rolled strip steel according to the embodiment selects a target metallographic image as an image obtained by rotating the front view of the decarburized layer by 90° to the left, as shown in FIG. 6. Of course, the front view of the decarburized layer, as shown in FIG. 5, can also be taken as the target metallographic image. Figure 4 Figure 3

[0081] Figure 3 For example, the metallographic image is divided into 100*50 sub-images, and the gray average values of the sub-images are obtained. For each column of sub-images, the starting sub-image and the ending sub-image are obtained according to the gray average values of the 100 sub-images corresponding to the column of sub-images, and the distance difference of a group of sub-images is obtained according to the starting sub-image and the ending sub-image. After the above operation is completed for each column of sub-images, the distance differences of 50 groups of sub-images are obtained. The thickness of the decarburized layer is obtained according to the distance differences of the 50 groups of sub-images.

[0082] The specific process of obtaining the starting sub-image and the ending sub-image is that the gray average values of the sub-images in the corresponding 100 sub-images are sequentially judged in the order of the first sub-image to the 100th sub-image in the corresponding 100 sub-images, and if the gray average value of a sub-image is not less than the gray threshold value, the sub-image is determined as the starting sub-image. After the starting sub-image is obtained, the gray average values of the sub-images in the corresponding 100 sub-images after the starting sub-image are sequentially judged in the order of the starting sub-image to the 100th sub-image, and if the gray average value of a sub-image is less than the gray threshold value, the sub-image is determined as the ending sub-image.

[0083] Here, the specific process of obtaining the starting sub-image and the ending sub-image is described according to the first method for obtaining the distance differences of the multiple groups of sub-images. The second method for obtaining the distance differences of the multiple groups of sub-images can also obtain the starting sub-image and the ending sub-image, which will not be described here.

[0084] The one or more technical solutions in the embodiments of the present application have at least the following technical effects or advantages:

[0085] ​​​In the embodiment, after the metallographic image of the decarburized layer of the strip steel is acquired, the metallographic image is processed, and the specific processing method is that the metallographic image is first divided into a plurality of sub-images, and then the gray average value of each sub-image in the plurality of sub-images is acquired. Here, by fully utilizing the image recognition technology, the effect of quickly and efficiently processing the metallographic image is achieved by recognizing the gray values of different regions in the metallographic image of the decarburized layer, and the determination efficiency of the thickness of the decarburized layer of the strip steel is improved.

[0086] Then, according to the gray average value of each sub-image in the plurality of sub-images, a plurality of groups of distance differences of the sub-images are obtained, and according to the distance differences of the plurality of groups of sub-images, the thickness of the decarburized layer is obtained. Here, according to the gray average value of each sub-image, the distance differences of the plurality of groups of sub-images are obtained, and then the thickness of the decarburized layer is obtained, so that the thickness of the decarburized layer of the strip steel can be quantitatively calculated, and the measurement error in the process of identifying the thickness of the decarburized layer by artificial recognition is eliminated. Therefore, the method of the embodiment realizes the quick and efficient determination of the thickness of the decarburized layer of the strip steel, improves the determination efficiency of the thickness of the decarburized layer of the strip steel, quickly and accurately masters the real decarburization degree of the steel, and accurately evaluates the performance of the steel.

[0087] Embodiment two

[0088] Based on the same inventive concept, the second embodiment of the present application also provides a device for determining the thickness of a decarburized layer of a hot-rolled strip steel, as shown in the accompanying drawings, which comprises: Figure 10

[0089] The dividing module 201 is configured to divide the metallographic image of the decarburized layer of the strip steel into a plurality of sub-images after the metallographic image is acquired, and acquire the gray average value of each sub-image in the plurality of sub-images.

[0090] The first obtaining module 202 is configured to obtain the distance differences of a plurality of groups of sub-images according to the gray average value of each sub-image in the plurality of sub-images.

[0091] The second obtaining module 203 is configured to obtain the thickness of the decarburized layer according to the distance differences of the plurality of groups of sub-images.

[0092] As an optional embodiment, the metallographic image is an image obtained by rotating the front view of the decarburized layer by a preset angle, and the plurality of sub-images are MxN sub-images, where M is the number of rows of the plurality of sub-images, N is the number of columns of the plurality of sub-images, and M and N are both integers greater than 1.

[0093] The first obtaining module 202 is configured to obtain the distance differences of a plurality of groups of sub-images according to the gray average value of each sub-image in the plurality of sub-images, and comprises:

[0094] ​For each row of sub-images in the plurality of sub-images, a starting sub-image and a terminal sub-image are obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, and a distance difference of a group of sub-images is obtained according to the starting sub-image and the terminal sub-image.

[0095] After the above operation is completed for each row of sub-images, distance differences of M groups of sub-images are obtained.

[0096] As an optional embodiment, the starting sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, including:

[0097] In order, the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images is determined according to the first sub-image to the Nth sub-image in the N sub-images, if the average gray value of a certain sub-image is not less than a gray threshold, the sub-image is determined as the starting sub-image.

[0098] As an optional embodiment, the terminal sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, including:

[0099] After the starting sub-image is obtained, the average gray value of each sub-image after the starting sub-image in the N sub-images corresponding to the row of sub-images is determined in order of the starting sub-image to the Nth sub-image, if the average gray value of a certain sub-image is less than the gray threshold, the sub-image is determined as the terminal sub-image.

[0100] As an optional embodiment, the terminal sub-image is obtained according to the average gray value of each sub-image in the N sub-images corresponding to the row of sub-images, including:

[0101] After the starting sub-image is obtained, a gray curve is obtained according to the average gray value of each sub-image after the starting sub-image in the N sub-images corresponding to the row of sub-images.

[0102] The terminal sub-image is obtained according to the gray curve.

[0103] As an optional embodiment, the terminal sub-image is obtained according to the gray curve, including:

[0104] In the gray curve, the slope of the gray curve corresponding to each sub-image after the starting sub-image in the N sub-images corresponding to the row of sub-images is determined in order, if the slope of the gray curve corresponding to a certain sub-image is not greater than a first slope threshold, and the slope of the corresponding gray curve is not less than a second slope threshold, the sub-image is determined as the terminal sub-image, wherein the second slope threshold is less than the first slope threshold.

[0105] As an optional embodiment, the second obtaining module 203 is configured to obtain the thickness of the decarburized layer according to the distance differences of the multiple groups of sub-images, and includes:

[0106] The thickness of the decarburized layer is obtained by performing mean value processing on the distance differences of the multiple groups of sub-images.

[0107] Since the device for determining the thickness of the decarburized layer of the hot-rolled strip steel in the embodiment is a device used to implement the method for determining the thickness of the decarburized layer of the hot-rolled strip steel in Embodiment One, the specific implementation of the device for determining the thickness of the decarburized layer of the hot-rolled strip steel in the embodiment and various changes thereof can be understood by those skilled in the art based on the method for determining the thickness of the decarburized layer of the hot-rolled strip steel in Embodiment One, and therefore, how the device for determining the thickness of the decarburized layer of the hot-rolled strip steel implements the method in Embodiment One will not be described in detail here. As long as the device used to implement the method for determining the thickness of the decarburized layer of the hot-rolled strip steel in Embodiment One is implemented by those skilled in the art, it falls within the scope of the present application.

[0108] Embodiment Three

[0109] Based on the same inventive concept, the third embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any one of the methods for determining the thickness of the decarburized layer of the hot-rolled strip steel.

[0110] Embodiment Four

[0111] Based on the same inventive concept, the fourth embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the program implements the steps of any one of the methods for determining the thickness of the decarburized layer of the hot-rolled strip steel in Embodiment One when executed by a processor.

[0112] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) containing computer-usable program code.

[0113] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of 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, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1

[0114] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams block or blocks. Figure 1 Figure 1

[0116] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those of skill in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, the attached claims are intended to cover all such variations and modifications as falling within the scope of the application.

[0117] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.​​​​​​

Claims

1. A method of determining the thickness of the decarburized layer of a hot-rolled strip, characterized in that, include: After obtaining a metallographic image of the decarburized layer of the steel strip, dividing the metallographic image into a plurality of sub-images, and obtaining a grayscale average value of each of the plurality of sub-images; Obtaining distance differences between the multiple groups of sub-images according to the grayscale average value of each sub-image in the multiple sub-images; Obtaining the thickness of the decarburized layer according to the distance difference between the multiple groups of sub-images; The metallographic image is an image obtained by rotating the main view of the decarburized layer by a preset angle, and the plurality of sub-images are M×N sub-images, wherein M is the number of rows of the plurality of sub-images, N is the number of columns of the plurality of sub-images, and both M and N are integers greater than 1; The step of obtaining the distance difference between the plurality of groups of sub-images according to the grayscale average value of each sub-image in the plurality of sub-images comprises: For each row of sub-images in the plurality of sub-images, obtaining a starting sub-image and an ending sub-image based on the grayscale average of each sub-image in the N sub-images corresponding to the row of sub-images, and obtaining a distance difference of a group of sub-images based on the starting sub-image and the ending sub-image; After the above operation is completed for each row of sub-images, the distance differences of M groups of sub-images are obtained.

2. The method of claim 1, wherein, The step of obtaining a starting sub-image according to the grayscale average value of each sub-image in the N sub-images corresponding to the row of sub-images includes: According to the order of the first sub-image to the Nth sub-image in the corresponding N sub-images, the grayscale average value of each sub-image in the corresponding N sub-images is determined; if the grayscale average value of a sub-image is not less than the grayscale threshold, the sub-image is determined as the starting sub-image.

3. The method of claim 2, wherein, The step of obtaining the termination sub-image according to the grayscale average value of each sub-image in the N sub-images corresponding to the row of sub-images includes: After obtaining the starting sub-image, the grayscale average value of each sub-image after the starting sub-image in the corresponding N sub-images is determined in the order from the starting sub-image to the Nth sub-image. If the grayscale average value of a sub-image is less than the grayscale threshold, the sub-image is determined as the ending sub-image.

4. The method of claim 2, wherein, The step of obtaining the termination sub-image according to the grayscale average value of each sub-image in the N sub-images corresponding to the row of sub-images includes: After obtaining the starting sub-image, obtaining a grayscale curve according to the grayscale average value of each sub-image after the starting sub-image in the corresponding N sub-images; The terminator image is obtained according to the grayscale curve.

5. The method of claim 4, wherein, The step of obtaining the terminator image according to the grayscale curve includes: In the grayscale curve, the slope of the grayscale curve corresponding to each sub-image after the starting sub-image in the corresponding N sub-images is judged in turn. If the slope of the grayscale curve corresponding to a sub-image is not greater than the first slope threshold, and the slope of the corresponding grayscale curve is not less than the second slope threshold, then the sub-image is determined as the ending sub-image, wherein the second slope threshold is less than the first slope threshold.

6. The method of claim 1, wherein, Obtaining the thickness of the decarburized layer according to the distance difference between the multiple groups of sub-images includes: The thickness of the decarburized layer is obtained by performing mean processing on the distance differences of the multiple groups of sub-images.

7. An apparatus for determining the thickness of a decarburized layer of a hot-rolled steel strip, characterized in that include: The division module is configured to divide the metallographic image of the decarburized layer of the strip steel into a plurality of sub-images after the metallographic image of the decarburized layer of the strip steel is acquired, and acquire a gray average value of each of the plurality of sub-images. The first obtaining module is configured to obtain distance differences of a plurality of groups of sub-images according to the gray average value of each of the plurality of sub-images. The second obtaining module is configured to obtain the thickness of the decarburized layer according to the distance differences of the plurality of groups of sub-images. The metallographic image is an image obtained by rotating a front view of the decarburized layer by a preset angle, and the plurality of sub-images are M×N sub-images, where M is a number of rows of the plurality of sub-images, N is a number of columns of the plurality of sub-images, and M and N are both integers greater than 1. The obtaining of the distance differences of the plurality of groups of sub-images according to the gray average value of each of the plurality of sub-images includes: For each row of sub-images in the plurality of sub-images, a starting sub-image and a terminal sub-image are obtained according to the gray average value of each of N sub-images corresponding to the row of sub-images, and a distance difference of a group of sub-images is obtained according to the starting sub-image and the terminal sub-image. After the operation is completed for each row of sub-images, distance differences of M groups of sub-images are obtained.

8. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method steps of any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to implement the method steps of any one of claims 1-6.

Citation Information

Patent Citations

  • Melt-blown cloth thickness consistency detection method based on image processing

    CN113592811A

  • Device and method of Rolled-surface Recognition for Billets

    KR1020180064074A