Method and device for determining defect position of steel coil

By comparing the surface defect information of the initial detection area with the preset defect information to be repaired in the steel coil detection system, and comparing the image when matching, it is solved that it is impossible to distinguish between the need for repair and the need for repair in the prior art. The problem of wear defects has achieved accurate identification and grinding of steel coil surface defects, and improved production efficiency.

CN119068051APending Publication Date: 2024-12-03BEIJING SHOUGANG AUTOMATION INFORMATION TECH
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411074741.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When identifying defects on the surface of steel coils, existing inspection systems cannot effectively distinguish between defects that require grinding and do not require grinding, resulting in the production rhythm and efficiency of the production line.

Method used

By comparing the information of detecting the surface defect of the steel coil in the initial detection area with the preset information of the defect to be repaired, if the matching is made, the coil will be controlled to stop running, and the surface defect image will be compared with the image of the defect to be repaired, if Matching determines the defect coordinate information for precise grinding.

Benefits of technology

It improves the accuracy of surface defect identification of steel coils, improves the production rhythm and production efficiency of the production line, and lays the foundation for realizing the fully automatic grinding process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068051A_ABST
    Figure CN119068051A_ABST
Patent Text Reader

Abstract

The invention discloses a method and a device for determining a defect position of a steel coil, and the method and the device for determining the defect position of the steel coil provided by the invention are characterized in that information and an image of a preset defect to be ground are taken as a reference, and in a grinding process, information of a surface defect of the steel coil is firstly compared with the information of the preset defect to be ground; if the two images are matched, controlling the steel coil to stop running based on the moving speed of the steel coil so as to stop the surface defect in the target area, then comparing the image of the surface defect with a preset image of the defect to be ground, and if the two images are matched, determining coordinate information of the surface defect in the target area; therefore, whether the surface of the steel coil needs to be ground or not is accurately recognized, and accurate grinding is carried out. The production rhythm and the production efficiency of a production line are improved, and a foundation is laid for achieving the full-automatic coping process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of steel coil defect position determination, and in particular to a steel coil defect position determination method and device. Background Art

[0002] In order to avoid product quality problems on the surface of the steel coil, the surface defects of the steel coil need to be polished. This requires that when the steel coil is stopped, the detection system collects images of the surface defects of the steel coil and then identifies the defects from the images.

[0003] However, the types and degrees of surface defects of steel coils vary. Some defects need to be polished, while some do not. The existing detection system will identify both defects that need to be polished and those that do not, which restricts the production rhythm and efficiency of the production line. Summary of the invention

[0004] In view of the above problems, the present application is proposed to provide a method and device for determining the position of steel coil defects that overcome the above problems or at least partially solve the above problems.

[0005] In a first aspect, a method for determining a defect position of a steel coil is provided, comprising:

[0006] In the grinding process, for the steel coil to be ground, if a surface defect is detected on the steel coil in the initial detection area, the information of the surface defect is compared with the information of the defect to be ground, wherein the information of the surface defect includes the longitudinal position and transverse position of the surface defect on the steel coil and the type of the surface defect, and the information of the defect to be ground includes the longitudinal position and transverse coordinates of the defect to be ground and the type of the defect to be ground;

[0007] If the information of the surface defect matches the information of the defect to be repaired, the target time at which the surface defect is detected in the target area is determined based on the moving speed of the steel coil, and the steel coil is controlled to stop running at the target time;

[0008] Acquire an image of the surface defect, and compare the image of the surface defect with an image of the defect to be repaired;

[0009] If the image of the surface defect matches the image of the defect to be repaired, the coordinate information of the surface defect in the target area is determined based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area.

[0010] Optionally, the information of the surface defect is compared with the information of the defect to be repaired, including:

[0011] Obtain the difference between the longitudinal position of the surface defect on the steel coil and the longitudinal position of the defect to be repaired. If the difference is within the set threshold range, compare the lateral position of the surface defect on the steel coil with the lateral position of the defect to be repaired, and compare the type of the surface defect with the type of the defect to be repaired.

[0012] If the difference between the lateral position of the surface defect on the steel coil and the lateral position of the defect to be repaired is within the set threshold range, and the type of the surface defect is the same as the type of the defect to be repaired, it is determined that the information of the surface defect matches the information of the defect to be repaired.

[0013] Optionally, the image of the surface defect is compared with the image of the defect to be repaired, including:

[0014] The similarity between the image of the surface defect and the image of the defect to be repaired is determined. If the similarity is greater than or equal to a set threshold, it is determined that the image of the surface defect and the image of the defect to be repaired match.

[0015] Optionally, comparing the image of the surface defect with the image of the defect to be repaired, further comprising:

[0016] If the similarity is less than a set threshold, the image of the surface defect and the image of the defect to be repaired are sent to a display device, so that a user can compare the image of the surface defect and the image of the defect to be repaired for similarity through the display device.

[0017] Optionally, before the grinding process, it also includes:

[0018] In the gadolinium manufacturing process, an image of a steel coil in the gadolinium manufacturing process is acquired;

[0019] If a defect to be repaired is identified from the image of the steel coil in the manufacturing process, a longitudinal position and a transverse position of the defect to be repaired in the steel coil in the manufacturing process and a type of the defect to be repaired are determined as information of the defect to be repaired;

[0020] And the image of the steel coil in the milling process corresponding to the defect to be repaired is used as the image of the defect to be repaired, and the image of the defect to be repaired and the information of the defect to be repaired are associated with the set steel coil number.

[0021] Optionally, before the grinding process, it also includes:

[0022] An information database and an image database are established, wherein the information database stores information of defects to be repaired associated with each of the M steel coil numbers; and the image database stores images of defects to be repaired associated with each of the M steel coil numbers;

[0023] In the grinding process, according to the steel coil number, information of the defect to be ground associated with each of the M steel coil numbers is obtained from the information database;

[0024] According to the steel coil number and the information of the defect to be repaired, an image of the defect to be repaired corresponding to the information of each defect to be repaired is acquired from the image library.

[0025] Optionally, based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area, determining the coordinate information of the surface defect in the target area includes:

[0026] Obtaining a first coordinate of the surface defect in a coordinate system of the image of the surface defect;

[0027] According to the coordinate conversion relationship between the coordinate system of the image of the surface defect and the coordinate system of the target area, the first coordinate is converted into the coordinate system of the target area to obtain the second coordinate, and the second coordinate is used to control the grinding device to grind the surface defect.

[0028] In a second aspect, a device for determining a defect position of a steel coil is provided, comprising:

[0029] An information comparison unit is used for comparing, in the grinding process, for the steel coil to be ground, if a surface defect is detected on the steel coil in the initial detection area, the information of the surface defect with the information of the defect to be ground, wherein the information of the surface defect includes the longitudinal position, the transverse position and the type of the surface defect on the steel coil, and the information of the defect to be ground includes the longitudinal position, the transverse coordinate and the type of the defect to be ground;

[0030] The steel coil operation control unit is used to determine the target time when the surface defect is detected in the target area based on the moving speed of the steel coil if the information of the surface defect matches the information of the defect to be repaired, and control the steel coil to stop running at the target time;

[0031] An image comparison unit, used for acquiring an image of a surface defect, and comparing the image of the surface defect with an image of the defect to be repaired;

[0032] The coordinate information determining unit is used to determine the coordinate information of the surface defect in the target area based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area if the image of the surface defect matches the image of the defect to be repaired.

[0033] In a third aspect, the present application also provides a server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the server executes the method provided in the first aspect.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the computer executes the method provided in the first aspect.

[0035] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed, enables a computer to execute the method provided in the first aspect.

[0036] The technical solution provided by this application has at least the following technical effects or advantages:

[0037] The method and device for determining the position of steel coil defects provided in the present application use the preset information and image of the defects to be repaired as a reference. In the grinding process, the information of the surface defects of the steel coil is first compared with the preset information of the defects to be repaired. If the two match, the steel coil is controlled to stop running based on the moving speed of the steel coil to stop the surface defects in the target area. Then, the image of the surface defect is compared with the preset image of the defect to be repaired. If the two match, the coordinate information of the surface defect in the target area is determined, thereby accurately identifying whether the surface of the steel coil needs to be repaired for precise grinding. Improving the production rhythm and production efficiency of the production line lays the foundation for realizing a fully automatic grinding process. The preset information and image of the defects to be repaired can be obtained from the rolling process before the grinding process.

[0038] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0040] Figure 1 This is a flow chart of a method for determining a defect position of a steel coil in an embodiment of the present application;

[0041] Figure 2 This is a process flow chart for determining the defect position of a steel coil in an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the second image in the embodiment of the present application;

[0043] Figure 4 This is a schematic diagram of the third image in the embodiment of the present application;

[0044] Figure 5 A schematic diagram of a real-world chessboard image in an embodiment of the present application;

[0045] Figure 6 This is a structural diagram of a device for determining a defect position of a steel coil in an embodiment of the present application;

[0046] Figure 7 This is a schematic diagram of a server in an embodiment of the present application; DETAILED DESCRIPTION

[0047] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.

[0048] Various structural schematic diagrams according to embodiments of the present application are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may further design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0049] In order to better understand the above-mentioned technical scheme, the above-mentioned technical scheme will be described in detail below in combination with specific implementation methods. It should be understood that the embodiments of the present disclosure and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0050] There are usually some defects on the surface of steel coils: oxide scale, foreign matter intrusion, edge cracks or other defects. These defects may be stretched or deepened during the rolling process, resulting in problems with the surface quality of the final product.

[0051] In order to avoid product quality problems on the surface of steel coils, surface defects of steel coils need to be polished. During the grinding process, grinding defect detection and grinding defect identification accuracy are key factors restricting the production rhythm and production efficiency of the production line, so improving the accuracy of grinding defect detection is crucial.

[0052] In view of this, this application provides a method for determining the defect location of a steel coil, please refer to Figure 1 , Figure 1 This is a flow chart of a method for determining a defect position of a steel coil in an embodiment of the present application, comprising:

[0053] S101, in the grinding process, for the steel coil to be ground, if a surface defect is detected on the steel coil in the initial detection area, the information of the surface defect is compared with the information of the defect to be ground. The information of the surface defect includes the longitudinal position and transverse position of the surface defect on the steel coil and the type of the surface defect, and the information of the defect to be ground includes the longitudinal position and transverse coordinates of the defect to be ground and the type of the defect to be ground.

[0054] S102, if the information of the surface defect matches the information of the defect to be repaired, a target time at which the surface defect is detected in the target area is determined based on the moving speed of the steel coil, and the steel coil is controlled to stop running at the target time.

[0055] S103, acquiring an image of the surface defect, and comparing the image of the surface defect with an image of the defect to be repaired;

[0056] S104, if the image of the surface defect matches the image of the defect to be repaired, the coordinate information of the surface defect in the target area is determined based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area.

[0057] The method and device for determining the position of steel coil defects provided in the embodiment of the present application use the preset information and image of the defect to be repaired as a reference. In the grinding process, the information of the surface defect of the steel coil is first compared with the preset information of the defect to be repaired. If the two match, the steel coil is controlled to stop running based on the moving speed of the steel coil to stop the surface defect in the target area. Then, the image of the surface defect is compared with the preset image of the defect to be repaired. If the two match, the coordinate information of the surface defect in the target area is determined, thereby accurately identifying whether the surface of the steel coil needs to be repaired for precise grinding. Improving the production rhythm and production efficiency of the production line lays the foundation for realizing a fully automatic grinding process.

[0058] The following is a detailed description of the method for determining the defect position of a steel coil provided in an embodiment of the present application. This example does not constitute a limitation on the embodiment of the present application. The following embodiments can be combined with each other, and the same or similar concepts or processes will not be described in detail. The operation of executing S101 specifically includes:

[0059] Obtain the difference between the longitudinal position of the surface defect on the steel coil and the longitudinal position of the defect to be repaired. If the difference is within the set threshold range, compare the transverse position of the surface defect on the steel coil with the transverse position of the defect to be repaired, and compare the type of the surface defect with the type of the defect to be repaired. If the difference between the transverse position of the surface defect on the steel coil and the transverse position of the defect to be repaired is within the set threshold range, and the type of the surface defect is the same as the type of the defect to be repaired, then determine that the information of the surface defect matches the information of the defect to be repaired.

[0060] The longitudinal position of the surface defect on the steel coil is determined by the distance between the surface defect and the head of the steel coil to be ground, and the transverse position of the surface defect on the steel coil is determined by the distance between the surface defect and the side of the steel coil to be ground. The side distance specifically refers to the distance between the surface defect and the working side and / or transmission side of the steel coil to be ground.

[0061] The information of the defects to be repaired is obtained by the following method:

[0062] In the gadolinium manufacturing process, an image of a steel coil in the gadolinium manufacturing process is acquired;

[0063] If a defect to be repaired is identified from the image of the steel coil in the manufacturing process, a longitudinal position and a transverse position of the defect to be repaired in the steel coil in the manufacturing process and a type of the defect to be repaired are determined as information of the defect to be repaired;

[0064] And the image of the steel coil in the milling process corresponding to the defect to be repaired is used as the image of the defect to be repaired, and the image of the defect to be repaired and the information of the defect to be repaired are associated with the set steel coil number.

[0065] An information database and an image database are established, wherein the information of defects to be repaired associated with each of the M steel coil numbers is stored in the information database; and images of defects to be repaired associated with each of the M steel coil numbers are stored in the image database.

[0066] In the grinding process, according to the steel coil number, the information of the defect to be ground associated with each of the M steel coil numbers is obtained from the information library. According to the steel coil number and the information of the defect to be ground, the image of the defect to be ground corresponding to the information of each defect to be ground is obtained from the image library.

[0067] When S101 is executed, according to the steel coil number of the steel coil to be ground, information of the defect to be ground associated with the steel coil to be ground is obtained from the information library, and an image corresponding to the information of the defect to be ground is obtained from the image library.

[0068] It can be understood that the longitudinal position of the defect to be repaired is determined by the distance between the defect to be repaired and the head of the steel coil in the rolling process, and the lateral position of the defect to be repaired is determined by the distance between the defect to be repaired and the side of the steel coil in the rolling process. The distance on the side here specifically refers to the distance between the defect to be repaired and the working side and / or transmission side of the steel coil in the rolling process.

[0069] In some optional implementations, the operation of acquiring an image of a surface defect in S103 specifically includes:

[0070] Through each of the multiple cameras, the surface defects located in the target area are imaged, and multiple first images are obtained. Based on the set perspective transformation parameters and mobile stitching parameters, the multiple first images are perspective transformed and mobile stitching is performed to obtain a real-world image of the surface defects. Among them, the effective shooting ranges of the multiple cameras constitute the target area, and the target area is located on the set grinding platform.

[0071] The grinding platform may be a platform set up for the grinding system on the grinding production line for performing grinding operations, and the grinding system is used to grind surface defects of the steel coil on the grinding platform.

[0072] In some optional implementations, the perspective transformation parameters are obtained using the following method:

[0073] In the first step, each of the multiple cameras is used to capture an image of the calibration plate located in the target area, thereby obtaining a total of multiple second images.

[0074] In the second step, the calibration plate uses a black and white chessboard, and the four cameras 201 respectively capture images of the chessboard, i.e., the second image. The overall pattern of the chessboard in the second image is as follows: Figure 3 The trapezoid shown is not the same as the real image of the chessboard.

[0075] The third step is to perform perspective transformation on each second image to obtain a plurality of third images, and determine perspective transformation parameters according to displacement information of corresponding pixels between the second image and the third image.

[0076] Exemplarily, the operations of the third step specifically include:

[0077] First, a three-dimensional world coordinate system is created based on all corner points of each second image.

[0078] like Figure 3 As shown, the chessboard in a second image is trapezoidal, and the corner points are specifically the four corner points (A0, B0, C0, D0) of the trapezoidal image.

[0079] Then, in the three-dimensional world coordinates, the pixels of the second image are controlled to move to obtain multiple third images. The goal of this operation is to perform perspective transformation on the second image to achieve trapezoidal correction of the second image. It can be understood that the pixels of the multiple third images correspond one-to-one to the pixels of the real-world image of the calibration plate, and the third image can be understood as a real-world image of a sub-area of ​​the calibration plate.

[0080] This operation can obtain the corner point transformation matrix of the second image from the three-dimensional world coordinate system to the real world plane. After eliminating the trapezoidal distortion through perspective transformation stretching, we can get the following: Figure 3 The third image shown.

[0081] Finally, a perspective transformation matrix is ​​obtained according to the movement information of corresponding pixels between the second image and the third image, and the perspective transformation matrix is ​​used as a perspective transformation parameter.

[0082] In some optional implementations, the motion splicing parameters are obtained using the following method:

[0083] The plurality of third images are moved and stitched to obtain a real-world image of the calibration plate, and the moving stitching parameters are determined according to displacement information of corresponding pixels between each third image and the real-world image of the calibration plate.

[0084] Exemplarily, the above operations specifically include:

[0085] In the first step, the plurality of third images are arranged according to set positions, and the initial coordinates of each third image in the real-world image coordinate system of the calibration plate are determined.

[0086] In the second step, the multiple third images are moved to stitch together the real-world image of the calibration plate and determine the final coordinates of each third image.

[0087] The third step is to determine the mobile stitching parameters based on the initial coordinates and the final coordinates.

[0088] Using the above specific operations, multiple Figure 4 The third image shown is stitched into Figure 5 The real-world image of the chessboard in the target area shown is obtained by taking multiple images of sub-areas of the target area from multiple cameras, and obtaining the real-world image of the chessboard in the target area after perspective transformation and movement stitching.

[0089] Specifically, the third image can be moved by operating a defined operation keyboard. In the process of completely stitching together the real-world image of the calibration plate, the operation keyboard is recorded to calculate the final coordinates of each corner point of the third image after the stitching is completed.

[0090] In summary, in the process of perspective transformation and moving stitching of multiple second images collected by multiple cameras on the calibration plate of the target area, standard perspective transformation parameters and moving stitching parameters are generated based on the displacement parameters of the corresponding pixels, and the perspective transformation parameters and moving stitching parameters are applied to multiple first images collected by multiple cameras on the surface defects of the target area for processing, that is, the real-world images of the surface defects are obtained. The integrity and authenticity of the images of surface defects collected by multiple cameras are guaranteed, so as to facilitate the accuracy of surface defect detection, and also ensure the accuracy of comparing the images of surface defects with the images of defects to be repaired.

[0091] In some optional implementations, the operation of performing S103 is specifically:

[0092] Determine the similarity between the image of the surface defect and the image of the defect to be repaired, and if the similarity is greater than or equal to a set threshold, determine that the image of the surface defect and the image of the defect to be repaired match. If the similarity is less than the set threshold, send the image of the surface defect and the image of the defect to be repaired to a display device, so that a user can determine the similarity between the image of the surface defect and the image of the defect to be repaired through the display device.

[0093] In some optional implementations, the operation of performing S104 is specifically:

[0094] The first coordinate of the surface defect in the coordinate system of the image of the surface defect is obtained. According to the coordinate conversion relationship between the coordinate system of the image of the surface defect and the coordinate system of the target area, the first coordinate is converted into the coordinate system of the target area to obtain a second coordinate, which is used to control the grinding device to grind the surface defect.

[0095] The following examples and Figure 2 , it is introduced how to use the method provided in the above embodiment to determine the defect position of the steel coil.

[0096] In the grinding process, the steel coils in the grinding process are put on line, and the Bestech system is used to detect defects in real time. The specific operation is: the Bestech system obtains the image of the steel coils in the grinding process in real time. If a defect that needs to be repaired (i.e., the defect to be repaired) is identified from the image, the image of the defect is saved, and the information of the defect (the distance from the belt head (longitudinal position), the distance from the transmission side and / or the working side (lateral position) and the type of the defect) is entered into the three-level consistent system and associated with the steel coil number of the steel coil.

[0097] In the defect repair process, the steel coil to be repaired comes online, and the first-level automation sends the number of the steel coil online to the repair system. At this time, the repair system requests to read the information of the steel coil that needs to be repaired. The specific operation is: access the three-level consistent system, and read the longitudinal position, transverse position and type of the defect that needs to be repaired according to the steel coil number.

[0098] The coil grinding system can filter out defects that do not require grinding by reading the information, thereby shortening the grinding defect detection distance and detection range.

[0099] The coil grinding system accesses the database of the server of the Bestech system, and reads the image of the defect that needs to be ground according to the information of the defect that needs to be ground provided by the three-level consistent system. It can be understood that the defect that needs to be ground corresponding to each coil number has unique information and image, that is, the information and image corresponding to the same defect that needs to be ground are interrelated. The image of the defect that needs to be ground read here is the image corresponding to the information associated with each defect that needs to be ground, and the information and image of the defect that needs to be ground are sent to the defect grinding system.

[0100] It should be noted that if there are multiple defects that need to be repaired on the steel coil, the location and type information and images of the multiple defects that need to be repaired associated with the steel coil number will be arranged in ascending order of the longitudinal position of the defects that need to be repaired on the steel coil.

[0101] When the steel coil is running in the grinding process, when the grinding system detects the first surface defect on the steel coil in the initial detection area, it is necessary to identify whether the surface defect needs grinding. The specific operation is: compare the longitudinal position of the first surface defect on the steel coil with the longitudinal position of the first defect that needs grinding provided by the three-level consistent system. If the difference between the two is within the set threshold range, then the lateral position and type of the first surface defect on the steel coil to be ground are compared one by one with the lateral position and type of the first defect that needs grinding. If the difference between the lateral position of the first surface defect on the steel coil to be ground and the lateral position of the first defect that needs grinding is within the set threshold range, and the two types are the same, then it is determined that the two match. At this time, the longitudinal position of the first surface defect on the steel coil to be ground is sent to the first-level automatic control system of the production line. The first-level automatic control system of the production line decelerates and positions in advance according to the current speed of the steel coil to be ground, and controls the steel coil to be ground to stop running. The surface defect is located in the grinding area (i.e., the target area). The grinding area is the area where the grinding device is used to grind the surface of the steel coil, so that the defect is located in the grinding area.

[0102] After identifying the grinding defect, the grinding system collects an image of the grinding area, that is, obtains an image of the first surface defect on the steel coil to be ground, and compares the image with the image of the first defect that needs to be ground. If the similarity is greater than or equal to 90%, the system determines that the first surface defect is a defect that needs to be ground. If the similarity is less than 90%, the system pops up a manual defect detection window, and the operator manually confirms it. If it is manually determined to be a defect that needs to be ground, the grinding process is started, otherwise the steel coil to be ground is controlled to continue running, and the grinding system continues to detect the next surface defect, and then performs the above operation again when the second surface defect is detected.

[0103] The above operation adopts the steel coil defect position determination method provided in the embodiment of the present application to realize the data interface docking between the grinding system and the Bestech system (cold-rolled steel coil surface detection system based on artificial neural network classification) in the previous rolling process, and reads the steel coil grinding defect information in Bestech. Through the comparison and graphic analysis of the grinding position, the accuracy of defect positioning can be improved, the situation of misjudgment of defects can be reduced, and frequent shutdown of the production line and on-site confirmation by operators due to misjudgment of defects can be avoided.

[0104] Based on the same inventive concept, the present application also provides a device for determining the position of a steel coil defect. Figure 6 , Figure 6 This is a schematic diagram of a device for determining a defect position of a steel coil in an embodiment of the present application. The device 600 for determining a defect position of a steel coil includes:

[0105] The information comparison unit 601 is used to compare the information of the surface defect with the information of the defect to be ground if surface defects are detected on the steel coil in the initial detection area during the grinding process, wherein the information of the surface defect includes the longitudinal position, transverse position and type of the surface defect on the steel coil, and the information of the defect to be ground includes the longitudinal position, transverse coordinates and type of the defect to be ground.

[0106] The steel coil operation control unit 602 is used to determine the target time when the surface defect is detected in the target area based on the moving speed of the steel coil if the information of the surface defect matches the information of the defect to be repaired, and control the steel coil to stop running at the target time.

[0107] The image comparison unit 603 is used to determine the coordinate information of the surface defect in the target area based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area if the image of the surface defect matches the image of the defect to be repaired.

[0108] The coordinate information determining unit 604 is used to determine the coordinate information of the surface defect in the target area based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area if the image of the surface defect matches the image of the defect to be repaired.

[0109] The steel coil defect position determination device 600 provided in the above embodiment can be used to implement the steel coil defect position determination method S101 to S104 in the above embodiment.

[0110] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the computer executes the method provided in the above embodiment.

[0111] The embodiment of the present application also provides a server. As shown in the figure, the server 700 includes a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and executable on the processor 702. When the processor 702 executes the computer program 703, the server 700 executes the method provided in the above embodiment.

[0112] The embodiments of the present application also provide a computer program product, including a computer program. When the computer program is executed, the computer executes the method provided in the above embodiments.

[0113] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0115] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

Claims

1. A method for determining the position of a steel coil defect, characterized in that: include: In the grinding process, for the steel coil to be ground, if a surface defect is detected on the steel coil in the initial detection area, the information of the surface defect is compared with the information of the defect to be ground, wherein the information of the surface defect includes the longitudinal position and the transverse position of the surface defect on the steel coil and the type of the surface defect, and the information of the defect to be ground includes the longitudinal position and the transverse coordinate of the defect to be ground and the type of the defect to be ground; If the information of the surface defect matches the information of the defect to be repaired, a target time at which the surface defect is detected in a target area is determined based on the moving speed of the steel coil, and at the target time, the steel coil is controlled to stop running; Acquire an image of the surface defect, and compare the image of the surface defect with an image of the defect to be repaired; If the image of the surface defect matches the image of the defect to be repaired, the coordinate information of the surface defect in the target area is determined based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area.

2. The method for determining the defect position of a steel coil according to claim 1, characterized in that: The comparing the information of the surface defect with the information of the defect to be repaired includes: Obtaining a difference between the longitudinal position of the surface defect on the steel coil and the longitudinal position of the defect to be repaired, and if the difference is within a set threshold range, comparing the lateral position of the surface defect on the steel coil with the lateral position of the defect to be repaired, and comparing the type of the surface defect with the type of the defect to be repaired; If the difference between the lateral position of the surface defect on the steel coil and the lateral position of the defect to be repaired is within a set threshold range, and the type of the surface defect is the same as the type of the defect to be repaired, it is determined that the information of the surface defect matches the information of the defect to be repaired.

3. The method for determining the position of a steel coil defect according to claim 1, characterized in that: The comparing the image of the surface defect with the image of the defect to be repaired comprises: The similarity between the image of the surface defect and the image of the defect to be repaired is determined, and if the similarity is greater than or equal to a set threshold, it is determined that the image of the surface defect and the image of the defect to be repaired match.

4. The method for determining the defect position of a steel coil according to claim 3, characterized in that: The comparing the image of the surface defect with the image of the defect to be repaired further comprises: If the similarity is less than a set threshold, the image of the surface defect and the image of the defect to be repaired are sent to a display device, so that a user can compare the image of the surface defect and the image of the defect to be repaired for similarity through the display device.

5. The method for determining the defect position of a steel coil according to claim 1, characterized in that: Before the grinding process, it also includes: In a gadolinium manufacturing process, an image of the steel coil in the gadolinium manufacturing process is collected; If a defect to be repaired is identified from the image of the steel coil in the gadolinium manufacturing process, a longitudinal position and a transverse position of the defect to be repaired in the steel coil in the gadolinium manufacturing process and a type of the defect to be repaired are determined as information of the defect to be repaired; And the image of the steel coil in the grinding process corresponding to the defect to be repaired is used as the image of the defect to be repaired, and the image of the defect to be repaired and the information of the defect to be repaired are associated with the set steel coil number.

6. The method for determining the defect position of a steel coil according to claim 5, characterized in that: Before the grinding process, it also includes: Establishing an information library and an image library, wherein the information library stores information of defects to be repaired associated with each of the M steel coil numbers; and the image library stores images of defects to be repaired associated with each of the M steel coil numbers; In the grinding process, according to the steel coil number, information of the defect to be ground associated with each of the M steel coil numbers is obtained from the information database; According to the steel coil number and the information of the defect to be repaired, an image of the defect to be repaired corresponding to the information of each defect to be repaired is acquired from the image library.

7. The method for determining the position of a steel coil defect according to claim 1, characterized in that: The determining the coordinate information of the surface defect in the target area based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area includes: Acquire a first coordinate of the surface defect in a coordinate system of an image of the surface defect; According to the coordinate conversion relationship between the coordinate system of the image of the surface defect and the coordinate system of the target area, the first coordinate is converted into the coordinate system of the target area to obtain a second coordinate, and the second coordinate is used to control the grinding device to grind the surface defect.

8. A device for determining the position of a steel coil defect, characterized in that: include: an information comparison unit, for comparing, in a grinding process, for a steel coil to be ground, information about the surface defect with information about the defect to be ground, if surface defects are detected on the steel coil in an initial detection area, wherein the information about the surface defect includes a longitudinal position, a transverse position of the surface defect on the steel coil and a type of the surface defect, and the information about the defect to be ground includes a longitudinal position, a transverse coordinate and a type of the defect to be ground; A steel coil operation control unit, configured to determine a target time at which the surface defect is detected in a target area based on the moving speed of the steel coil if the information of the surface defect matches the information of the defect to be repaired, and control the steel coil to stop running at the target time; An image comparison unit, used for acquiring an image of the surface defect, and comparing the image of the surface defect with an image of the defect to be repaired; A coordinate information determining unit is used to determine the coordinate information of the surface defect in the target area based on the coordinates of the surface defect in the image of the surface defect and the conversion relationship between the image coordinates of the surface defect and the coordinates of the target area if the image of the surface defect matches the image of the defect to be repaired.

9. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the server is caused to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the computer is caused to perform the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Strip steel surface defect grinding method and device, terminal equipment and storage medium

    CN115205220A

  • Track generation method and device, equipment and medium

    CN116188526A

  • Defect detection method and device for steel surface defect grinding

    CN118096695A

  • Wafer defect detection method, device, equipment and system and storage medium

    CN118229609A

  • Cross-scale defect detection method based on deep learning

    US20230306577A1