Grinding method and device

By tracking surface defects in real time and performing image splicing recognition during the strip steel production process, the problems of manual grinding detection and inaccurate positioning are solved, and precise grinding and efficient production of strip steel surface defects are achieved.

CN118977145AActive Publication Date: 2024-11-19BEIJING SHOUGANG AUTOMATION INFORMATION TECH

Patent Information

Application Number
CN202411074639.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-19
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

During the production process of strip steel, manual polishing has problems such as difficulty in detection, inaccurate defect positioning, limited production line speed and low production efficiency, which makes it difficult to avoid surface quality problems.

Method used

By detecting surface defects in the initial detection area, tracking defect positions in real time based on the moving speed of the target object, obtaining images of multiple cameras for perspective transformation and splicing, identifying the grinding coordinates of surface defects in the coordinate system of the preset grinding platform. And grinding and polishing are carried out according to the coordinates.

Benefits of technology

Accurate positioning and efficient grinding of strip surface defects is achieved, and production efficiency and product quality are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118977145A_ABST
    Figure CN118977145A_ABST
Patent Text Reader

Abstract

The invention discloses a grinding method and device, and the method comprises the steps: determining a target moment when a surface defect is detected in a target region based on the moving speed of the target object if the surface defect exists on the target object in an initial detection region, and controlling the target object to stop running at the target moment. Acquiring a first real-world image of the target area, identifying the surface defect from the first real-world image, and determining a grinding coordinate of the surface defect in a preset grinding platform coordinate system; and grinding the surface defects according to the grinding coordinates. According to the invention, rough positioning, tracking positioning and fine positioning of the surface defects in the strip steel production process can be realized, and finally accurate coordinates and efficient grinding of the surface defects of the strip steel are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of surface defect determination, and in particular to a grinding method and device. Background Art

[0002] During strip production, there are usually some defects on the strip surface: 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. In order to avoid problems with the surface quality of the strip, the surface defects of the strip need to be polished. Manual polishing has difficulties such as difficulty in detecting defects, inaccurate defect positioning, limited production line speed, low production efficiency, and time-consuming and labor-intensive. Summary of the invention

[0003] In view of the above problems, the present application is proposed to provide a grinding method and device that overcomes the above problems or at least partially solves the above problems.

[0004] In a first aspect, a grinding method is provided, comprising:

[0005] If a surface defect is detected on the target object in the initial detection area, a target time at which the surface defect is detected in the target area is determined based on the moving speed of the target object, and at the target time, the target object is controlled to stop running;

[0006] Acquire a first real-world image of the target area, identify surface defects from the first real-world image, and determine grinding coordinates of the surface defects in a preset grinding platform coordinate system;

[0007] Grind the surface defects according to the grinding coordinates.

[0008] Optionally, after grinding the surface defects according to the grinding coordinates, the method further includes:

[0009] An image of the target area after grinding is obtained, and whether the target object after grinding is qualified is identified from the image of the target area after grinding. If so, the target object after grinding is polished according to the grinding coordinates; if not, the surface defects of the target object after grinding are ground according to the grinding coordinates.

[0010] Optionally, obtaining a first real-world image of the target area includes:

[0011] By using each of the multiple cameras, an image of a portion of the target object located in the target area is captured to obtain a total of multiple first images, wherein the multiple cameras have different viewing angles;

[0012] Based on the set perspective transformation parameters and moving stitching parameters, perspective transformation and moving stitching are performed on the multiple first images to obtain a first real-world image.

[0013] Optionally, perspective transformation parameters and motion stitching parameters are obtained by the following steps:

[0014] Using each of the multiple cameras, an image of the calibration plate located in the target area is captured to obtain a total of multiple second images;

[0015] For each second image among the plurality of second images, perform perspective transformation on the second image to obtain a corresponding third image, and determine a perspective transformation sub-parameter corresponding to the second image according to pixel displacement information between the second image and the corresponding third image;

[0016] Obtaining a perspective transformation parameter based on the perspective transformation sub-parameter corresponding to each second image;

[0017] The plurality of third images are moved and spliced ​​to obtain a second real-world image, and a moving and splicing sub-parameter corresponding to the third image is determined according to pixel displacement information between each third image in the plurality of third images and the second real-world image.

[0018] Based on the motion stitching sub-parameters corresponding to each third image, a motion stitching parameter is obtained.

[0019] Optionally, for each second image among the multiple second images, performing perspective transformation on the second image to obtain a corresponding third image, and determining a perspective transformation sub-parameter corresponding to the second image according to pixel displacement information between the second image and the corresponding third image, including:

[0020] For each second image, a three-dimensional world coordinate system is created based on all corner points of the second image. According to the boundary of the calibration plate area corresponding to the second image, the pixels of the second image are moved in the three-dimensional world coordinates to obtain a third image corresponding to the second image.

[0021] A perspective transformation matrix is ​​obtained according to movement information of corresponding pixels between the second image and the third image, and the perspective transformation matrix is ​​used as a perspective transformation sub-parameter.

[0022] Optionally, performing mobile stitching on the plurality of third images to obtain a second real-world image, and determining a mobile stitching sub-parameter corresponding to the third image according to pixel displacement information between each third image in the plurality of third images and the second real-world image, comprises:

[0023] Arrange the plurality of third images according to set positions, and determine, for each third image, an initial coordinate of the third image in a real-world image coordinate system of the calibration plate;

[0024] Each third image is moved to stitch out a second real-world image, and a final coordinate of each third image in the real-world image coordinate system of the calibration plate is determined;

[0025] According to the initial coordinates and the final coordinates, the moving stitching sub-parameters are determined.

[0026] Optionally, based on the set perspective transformation parameters and moving stitching parameters, performing perspective transformation and moving stitching on the plurality of first images to obtain a first real-world image includes:

[0027] Performing perspective transformation on each of the plurality of first images according to the perspective transformation parameter to obtain a fourth image corresponding to the first image;

[0028] arranging the plurality of fourth images in a first real-world image coordinate system according to the initial coordinates;

[0029] According to the final coordinates, each fourth image is moved and spliced ​​to obtain the first real-world image.

[0030] Optionally, identifying a surface defect from the first real-world image and determining a grinding coordinate of the surface defect in a preset grinding platform coordinate system includes:

[0031] identifying a surface defect from the first real-world image and determining a first coordinate of the surface defect in a coordinate system of the first real-world image;

[0032] A coordinate conversion relationship between the first real-world image coordinate system and the preset grinding platform coordinate system is determined, and based on the coordinate conversion relationship, the first coordinate is converted to the preset grinding platform coordinate system to obtain the grinding coordinate.

[0033] Optionally, determining a coordinate transformation relationship between the first real-world image coordinate system and a preset grinding platform coordinate system, and based on the coordinate transformation relationship, transforming the first coordinates into the preset grinding platform coordinate system to obtain the grinding coordinates includes:

[0034] Determine a first coordinate transformation relationship between the first real-world image coordinate system and the target area coordinate system, and transform the first coordinate into the target area coordinate system based on the first coordinate transformation relationship to obtain a second coordinate;

[0035] A second coordinate transformation relationship between the target area coordinate system and the preset grinding platform coordinate system is determined, and based on the second coordinate transformation relationship, the second coordinate is transformed into the preset grinding platform coordinate system to obtain the grinding coordinate.

[0036] In a second aspect, a grinding device is provided, comprising:

[0037] An operation control unit, for determining a target time at which the surface defect is detected in the target area based on the moving speed of the target object if a surface defect is detected on the target object in the initial detection area, and controlling the target object to stop running at the target time;

[0038] A coordinate determination unit, used to obtain a first real-world image of the target area, identify the surface defect from the first real-world image, and determine the grinding coordinates of the surface defect in a preset grinding platform coordinate system;

[0039] The grinding unit is used to grind the surface defects according to the grinding coordinates.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] The technical solution provided by this application has at least the following technical effects or advantages:

[0044] The grinding method and device provided in the present application detect whether the target object has surface defects in the initial detection area. When it is determined that there are surface defects, since the distance between the initial detection area and the target area is fixed, the real-time position of the surface defects of the target object can be tracked in real time according to the speed of the target object during the operation of the target object, so as to stop the movement of the target object at the target time so that the surface defects are located in the target area. The surface defects are identified in the first real-world image of the target area and their grinding coordinates are determined. The surface grinding system can be controlled to grind and polish the surface defects according to the grinding coordinates. In this way, the rough positioning of surface defects, the tracking positioning of surface defects, and the precise positioning of surface defects are achieved during the production of strip steel, and finally the precise coordinates and efficient grinding of the surface defects of the strip steel are achieved.

[0045] 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

[0046] 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:

[0047] Figure 1 This is the grinding method process in the embodiment of this application Figure 1 ;

[0048] Figure 2 This is a schematic diagram of a steel strip photographed by a camera in an embodiment of the present application;

[0049] Figure 3 This is the grinding method process in the embodiment of this application Figure 2 ;

[0050] Figure 4 This is a schematic diagram of the second image in the embodiment of the present application;

[0051] Figure 5 This is a schematic diagram of the third image in the embodiment of the present application;

[0052] Figure 6 A schematic diagram of a real-world checkerboard image in an embodiment of the present application;

[0053] Figure 7 This is the grinding method process in the embodiment of this application Figure 3 ;

[0054] Figure 8 This is the grinding method process in the embodiment of this application Figure 4 ;

[0055] Fig. 9 Implementation scenario diagram of the grinding method in the embodiment of the present application;

[0056] Fig.10 This is a flow chart of the grinding operation of the strip steel in the embodiment of the present application;

[0057] Fig.11 This is a structural block diagram of the grinding device in the embodiment of the present application. DETAILED DESCRIPTION

[0058] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings.

[0059] 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.

[0060] 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.

[0061] During strip steel production, surface defects need to be repaired. The existing technology is to reduce the production line to the lowest crawling speed, and the workers have to find defects with the naked eye, which seriously limits the production efficiency. At the same time, it poses a great threat to the personal safety of the workers. There are even cases of missing defects, and the product quality cannot be positively controlled.

[0062] In the grinding system, defect location technology is the core technology fortress. If the defects cannot be accurately located, the grinding task cannot be completed and the purpose of improving the surface quality of the strip cannot be achieved. Therefore, it is imperative to be able to scientifically deduce the defect location information.

[0063] In view of this, this application provides a grinding method, please refer to Figure 1 , Figure 1 This is a flow chart of the grinding method in the embodiment of the present application, including:

[0064] S101, if a surface defect is detected on the target object in the initial detection area, a target time at which the surface defect is detected in the target area is determined based on the moving speed of the target object, and at the target time, the target object is controlled to stop running.

[0065] S102, acquiring a first real-world image of a target area, identifying surface defects from the first real-world image, and determining grinding coordinates of the surface defects in a preset grinding platform coordinate system.

[0066] S103, grinding the surface defects according to the grinding coordinates.

[0067] The initial detection area is provided with a surface detection device. During the strip rolling process, the surface detection device is used to capture images of the strip surface to preliminarily detect whether the strip has surface defects. When the presence of surface defects is determined from the images captured by the surface detection device, the position of the surface defects on the strip is recorded. The distance between the initial detection area and the target area is fixed. Therefore, during the operation of the strip, the position of the strip surface defects in the strip production line can be tracked in real time according to the speed of the strip, so that the strip production line can be stopped at the target time so that the surface defects are located in the target area.

[0068] In the first real-world image of the target area, the surface defects of the strip are identified and their grinding coordinates are determined. According to the grinding coordinates, the surface grinding system can be controlled to grind and polish the surface defects. In this way, the rough positioning, tracking positioning and fine positioning of surface defects in the production process of the strip can be realized, and finally the accurate coordinates and efficient grinding of the surface defects of the strip can be achieved.

[0069] In some optional implementations, after executing the operation of S103, the following operations are further included:

[0070] An image of the target area after grinding is obtained, and whether the target object after grinding is qualified is identified from the image of the target area after grinding. If so, the target object after grinding is polished according to the grinding coordinates; if not, the surface defects of the target object after grinding are ground according to the grinding coordinates.

[0071] After grinding, take photos again for verification. If the surface defects of the strip are removed, the target object after grinding is determined to be qualified, and the surface grinding system can be controlled to perform polishing. If the surface defects of the strip still exist after grinding, it will be ground again to ensure the grinding quality.

[0072] The following example describes how to accurately locate surface defects of strip steel through the operation of S102.

[0073] In some optional implementations, the specific operation of acquiring the first real-world image of the target area in S102 includes:

[0074] In the first step, each of the multiple cameras collects an image of the portion of the target object located in the target area, thereby obtaining a total of multiple first images, where the viewing angles of the multiple cameras are different.

[0075] In the second step, the multiple first images are perspective transformed and moved and stitched based on the set perspective transformation parameters and moving stitching parameters to obtain a first real-world image. It can be understood that the effective shooting ranges of the multiple cameras constitute a target area, and the target area is located on a set grinding platform. The grinding platform can be a platform set on the production line for the surface grinding system for performing grinding operations, and the surface grinding system is used to grind the strip on the grinding platform.

[0076] The specific operations of performing S102 to identify the surface defect from the first real-world image and determine the grinding coordinates of the surface defect in the preset grinding platform coordinate system include:

[0077] In the first step, a surface defect is identified from a first real-world image, and a first coordinate of the surface defect in a coordinate system of the first real-world image is determined.

[0078] The second step is to determine the coordinate transformation relationship between the first real-world image coordinate system and the preset grinding platform coordinate system, and based on the coordinate transformation relationship, transform the first coordinates into the preset grinding platform coordinate system to obtain the grinding coordinates.

[0079] In some optional embodiments, such as Figure 8 As shown, the second step is as follows:

[0080] S801, determining a first coordinate transformation relationship between a first real-world image coordinate system and a target area coordinate system, and based on the first coordinate transformation relationship, transforming a first coordinate into the target area coordinate system to obtain a second coordinate.

[0081] S802, determining a second coordinate transformation relationship between the target area coordinate system and the preset grinding platform coordinate system, and based on the second coordinate transformation relationship, transforming the second coordinate into the preset grinding platform coordinate system to obtain a grinding coordinate.

[0082] The grinding method provided in the embodiment of the present application performs perspective transformation and mobile splicing on the first image of the target object obtained by multiple cameras to obtain a first real-world image, ensuring that the position of the surface defect in the first real-world image is consistent with the actual situation. The first real-world image comes from the target area, and the target area and the grinding platform have a fixed positional relationship. Therefore, based on the one-to-one coordinate conversion relationship between the corresponding coordinate systems, the coordinates of the surface defect of the strip in the first real-world image can be converted into the actual coordinates of the surface defect of the strip in the target area, and the relative position of the target area on the grinding platform is set, so the actual coordinates of the surface defect of the strip in the target area can be converted into the actual coordinates of the surface defect of the strip on the grinding platform, that is, the grinding coordinates, so as to accurately locate the defects, improve the grinding efficiency of the production line, and improve the grinding quality and yield rate of the production line.

[0083] It is understandable that the above grinding method can be applied to terminal devices and / or servers. The terminal devices and / or servers can be understood as test devices. The server can be, but is not limited to, a network server, a database server, a cloud server, etc. The terminal device can be, but is not limited to, an office computer.

[0084] The following is a specific example of applying the method of the above embodiment to an actual strip steel production line to obtain the specific coordinates of the surface defects of the strip steel on the grinding platform.

[0085] (1) Define the surface inspection device, strip production line, and grinding robot in the same coordinate system.

[0086] For example, Figure 2 As shown, four cameras 201 arranged at intervals can be slidably installed on the slide 202, and each camera 201 takes an image of the surface of the steel strip 203 at a set height and angle from the surface of the steel strip 203. Compared with the real image, the captured image has certain deformity and deviation, and each image has regional overlap. Therefore, it is necessary to convert the image of the surface of the steel strip 203 taken by the camera 201 into a real image, and then splice each image in the overlapping area.

[0087] When a camera is replaced, maintained, or serviced, the new camera is installed in place, and the camera parameters may change, and the installation angle and height may deviate. At this time, when eliminating deformities and deviations and stitching pictures taken by the new camera, the parameters used to process the images taken by the previous camera cannot be used. New image processing parameters need to be configured according to the parameters and position of the new camera.

[0088] Therefore, in some optional embodiments, such as Figure 3 As shown, the perspective transformation parameters and the moving stitching parameters are obtained by the following steps:

[0089] S301, using each camera of a plurality of cameras to capture an image of a calibration plate located in a target area, to obtain a plurality of second images in total.

[0090] The calibration plate uses a black and white chessboard. 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 4 The trapezoid shown is not the same as the real image of the chessboard.

[0091] S302, for each second image among the multiple second images, perform perspective transformation on the second image to obtain a corresponding third image, and determine the perspective transformation sub-parameters corresponding to the second image according to the displacement information of the pixels between the second image and the corresponding third image.

[0092] S303: Obtain a perspective transformation parameter based on the perspective transformation sub-parameter corresponding to each second image.

[0093] The operation of S302 is performed, specifically including:

[0094] In the first step, for each second image, a three-dimensional world coordinate system is created according to all corner points of the second image.

[0095] like Figure 4 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.

[0096] In the second step, the pixels of the second image are moved in the three-dimensional world coordinates according to the boundary of the calibration plate area corresponding to the second image, and a third image corresponding to the second image is obtained. The goal of this operation is to perform a 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 second real-world image, and the third image can be understood as a real-world image of a sub-area of ​​the calibration plate.

[0097] 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 5 The third image shown.

[0098] The third step is to obtain a perspective transformation matrix according to the movement information of corresponding pixels between the second image and the third image, and use the perspective transformation matrix as a perspective transformation sub-parameter.

[0099] When the camera 201 is used to capture the surface image of the steel strip 203 in the target area, there will naturally be deviations, which are not conducive to analyzing the position of the surface defects of the steel strip 203 through the image. Therefore, the image needs to be perspective transformed, and the image of the steel strip 203 has no regularity, and it is difficult to determine the perspective transformation parameters. Therefore, the four cameras 201 are used to respectively capture the chessboard images and perform perspective transformation, and the perspective transformation parameters of each image are recorded. They can be directly applied to the perspective transformation operation of the image of the steel strip 203 in S102 to obtain the real-world images of multiple sub-areas on the surface of the steel strip 203. It can be understood that there are overlaps between these sub-areas, and these sub-areas are pieced together to form a complete target area.

[0100] S304, performing motion stitching on the plurality of third images to obtain a second real-world image, and determining a motion stitching sub-parameter corresponding to the third image according to pixel displacement information between each third image in the plurality of third images and the second real-world image.

[0101] S305: Obtain a motion stitching parameter based on the motion stitching sub-parameter corresponding to each third image.

[0102] The operation of S304 is performed, specifically including:

[0103] In the first step, a plurality of third images are arranged according to set positions, and for each third image, an initial coordinate of the third image in the real-world image coordinate system of the calibration plate is determined.

[0104] In the second step, each third image is moved to stitch out a second real-world image, and the final coordinates of each third image in the real-world image coordinate system of the calibration plate are determined.

[0105] The third step is to determine the moving splicing sub-parameters based on the initial coordinates and the final coordinates.

[0106] Using the specific operation of S303 above, multiple Figure 5 The third image shown is stitched into Figure 6 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.

[0107] Specifically, the third image can be moved by operating a defined operation keyboard. In the process of completely stitching the second real-world image, the operation keyboard is recorded to calculate the final coordinates of each corner point of the third image after the stitching is completed.

[0108] In summary, in the process of perspective transformation and mobile stitching of multiple second images collected by multiple cameras on the calibration plate of the target area, standard perspective transformation parameters and mobile stitching parameters are generated based on the displacement parameters of the corresponding pixels, and the perspective transformation parameters and mobile stitching parameters are applied to multiple first images collected by multiple cameras on the target object in the target area for processing, that is, the first real-world image is obtained. The integrity and authenticity of the images of the target object collected by multiple cameras are guaranteed, so as to facilitate the accuracy of defect detection of the target object, and also provide convenience for future equipment maintenance work.

[0109] In some optional embodiments, such as Figure 7 As shown, in the specific operation of acquiring the first real-world image of the target area in S102, the operation of the second step specifically includes:

[0110] S701, performing perspective transformation on each first image of a plurality of first images according to a perspective transformation parameter to obtain a fourth image corresponding to the first image.

[0111] S702 , arranging a plurality of fourth images in a first real-world image coordinate system according to the initial coordinates.

[0112] S703: Move and splice each fourth image according to the final coordinates to obtain a first real-world image.

[0113] In some optional implementations, after obtaining the second real-world image, the edges of the second real-world image are cropped so that the second real-world image reaches a set size, and the coordinate range of the pixels for cropping the edges of the second real-world image is determined.

[0114] Thus, after executing the operation of S703 to obtain the first real-world image, the method further includes:

[0115] The edge portion of the first real-world image is cropped according to the coordinate range of the pixels cropped at the edge of the second real-world image, so that the size of the first real-world image reaches a set size.

[0116] Combine the following Fig. 9 , 10 , introduces a specific operation example of grinding the surface defects of strip steel using the method provided in the embodiment of the present application.

[0117] In the first step, according to the approximate position information of the surface defect area 906 of the steel strip 901 provided by the surface detection device 905 (i.e., the approximate position information of the sub-area where the surface defect is located), the early deceleration threshold is set. When the tracking position of the steel strip 901 (the real-time position of the defect area 906) reaches the threshold, the steel strip 901 automatically decelerates so that after the defect is detected, the defect position is stopped at the target area 907 of the grinding area 902. If the surface detection device 905 is far enough from the grinding area 902 (greater than the braking distance of the maximum speed of the production line), it is not necessary to decelerate in advance.

[0118] When a defect is detected on the surface, the surface detection device 905 can send the defect coordinates to the first-level automation of the production line, and start the defect stop positioning to stop the defective part in the grinding area 902.

[0119] In the second step, after the defective area 906 stops at the target area 907 of the grinding area 902, the grinding robot 903 located on one side of the target area 907 uses the visual camera 904 installed on the head of the machine to take a photo of the defective area 906. After the photo is taken, the photo is synthesized and analyzed according to the operation of S102, the precise coordinate position of the defective area 906 in the grinding area 902 is calculated, and the grinding coordinate position is sent to the grinding robot.

[0120] In the third step, the grinding robot 903 grinds the defective area 906 on the surface of the strip steel 901 according to the precise grinding coordinate position. After the grinding is completed, the camera 904 is used to take a photo of the defective area 906 again for review. If the review is unqualified, the grinding will continue. If the review is qualified, the robot switches the grinding head to polish the defective part. It can be understood that a bidirectional force control device and a floating device are installed on the grinding head of the robot to achieve a good grinding effect.

[0121] Based on the same inventive concept, the present application also provides a grinding device, such as Fig.11 As shown, the grinding device 1100 comprises:

[0122] The operation control unit 1101 is used to determine the target time when the surface defects are detected in the target area based on the moving speed of the target object if surface defects are detected on the target object in the initial detection area, and control the target object to stop running at the target time.

[0123] The coordinate determination unit 1102 is used to obtain a first real-world image of the target area, identify the surface defect from the first real-world image, and determine the grinding coordinates of the surface defect in a preset grinding platform coordinate system.

[0124] The grinding unit 1103 is used to grind the surface defects according to the grinding coordinates.

[0125] 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.

[0126] An embodiment of the present application also provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the server executes the method provided in the above embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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 grinding method, characterized in that: include: If a surface defect is detected on the target object in the initial detection area, a target time at which the surface defect is detected in the target area is determined based on the moving speed of the target object, and at the target time, the target object is controlled to stop running; Acquire a first real-world image of the target area, identify the surface defect from the first real-world image, and determine the grinding coordinates of the surface defect in a preset grinding platform coordinate system; The surface defects are ground according to the grinding coordinates.

2. The grinding method according to claim 1, characterized in that: After the surface defects are ground according to the grinding coordinates, the method further comprises: An image of the target area after grinding is acquired, and whether the target object after grinding is qualified is identified from the image of the target area after grinding. If so, the target object after grinding is polished according to the grinding coordinates; if not, the surface defects of the target object after grinding are ground according to the grinding coordinates.

3. The grinding method according to claim 1 or 2, characterized in that: The acquiring a first real-world image of the target area comprises: By using each camera among a plurality of cameras, an image of a portion of the target object located in the target area is captured to obtain a plurality of first images in total, wherein the plurality of cameras have different viewing angles; Based on the set perspective transformation parameters and moving stitching parameters, perspective transformation and moving stitching are performed on the multiple first images to obtain the first real-world image.

4. The grinding method according to claim 3, characterized in that: The perspective transformation parameters and the motion stitching parameters are obtained by the following steps: Capturing an image of a calibration plate located in the target area by each of the plurality of cameras to obtain a plurality of second images; For each second image among the plurality of second images, perform perspective transformation on the second image to obtain a corresponding third image, and determine a perspective transformation sub-parameter corresponding to the second image according to pixel displacement information between the second image and the corresponding third image; Obtaining the perspective transformation parameter based on each perspective transformation sub-parameter corresponding to the second image; Performing motion stitching on the plurality of third images to obtain the second real-world image, and determining a motion stitching sub-parameter corresponding to the third image according to pixel displacement information between each third image in the plurality of third images and the second real-world image; The motion stitching parameter is obtained based on the motion stitching sub-parameter corresponding to each of the third images.

5. The grinding method according to claim 4, characterized in that: The step of performing perspective transformation on each second image of the plurality of second images to obtain a corresponding third image, and determining a perspective transformation sub-parameter corresponding to the second image according to pixel displacement information between the second image and the corresponding third image, comprises: For each of the second images, a three-dimensional world coordinate system is created according to all corner points of the second image, and pixels of the second image are moved in the three-dimensional world coordinate system according to a boundary of a calibration plate area corresponding to the second image, so as to obtain the third image corresponding to the second image; A perspective transformation matrix is ​​obtained according to movement information of corresponding pixels between the second image and the third image, and the perspective transformation matrix is ​​used as the perspective transformation sub-parameter.

6. The grinding method according to claim 4, characterized in that: The step of performing mobile stitching on the plurality of third images to obtain the second real-world image, and determining a mobile stitching sub-parameter corresponding to the third image according to pixel displacement information between each third image in the plurality of third images and the second real-world image, comprises: Arrange the plurality of third images according to set positions, and determine, for each of the third images, an initial coordinate of the third image in the real-world image coordinate system of the calibration plate; Move each of the third images to stitch the second real-world image, and determine the final coordinates of each of the third images in the real-world image coordinate system of the calibration plate; The mobile splicing sub-parameters are determined according to the initial coordinates and the final coordinates.

7. The grinding method according to claim 3, characterized in that: The step of performing perspective transformation and motion stitching on the plurality of first images based on the set perspective transformation parameters and motion stitching parameters to obtain the first real-world image includes: performing perspective transformation on each first image of the plurality of first images according to the perspective transformation parameter to obtain a fourth image corresponding to the first image; arranging the plurality of fourth images in the first real-world image coordinate system according to the initial coordinates; According to the final coordinates, each of the fourth images is moved and spliced ​​to obtain the first real-world image.

8. The grinding method according to claim 1, characterized in that: The step of identifying the surface defect from the first real-world image and determining the grinding coordinates of the surface defect in a preset grinding platform coordinate system includes: identifying the surface defect from the first real-world image and determining a first coordinate of the surface defect in a first real-world image coordinate system; A coordinate conversion relationship between the first real-world image coordinate system and the preset grinding platform coordinate system is determined, and based on the coordinate conversion relationship, the first coordinate is converted to the preset grinding platform coordinate system to obtain the grinding coordinate.

9. The grinding method according to claim 8, characterized in that: The determining of the coordinate conversion relationship between the first real-world image coordinate system and the preset grinding platform coordinate system, and based on the coordinate conversion relationship, converting the first coordinate to the preset grinding platform coordinate system to obtain the grinding coordinate includes: Determine a first coordinate transformation relationship between the first real-world image coordinate system and the target area coordinate system, and based on the first coordinate transformation relationship, transform the first coordinate into the target area coordinate system to obtain a second coordinate; A second coordinate transformation relationship between the target area coordinate system and the preset grinding platform coordinate system is determined, and based on the second coordinate transformation relationship, the second coordinate is transformed into the preset grinding platform coordinate system to obtain the grinding coordinate.

10. A grinding device, characterized in that: include: An operation control unit, for determining a target time at which the surface defect is detected in the target area based on the moving speed of the target object if a surface defect is detected on the target object in the initial detection area, and controlling the target object to stop running at the target time; A coordinate determination unit, configured to acquire a first real-world image of the target area, identify the surface defect from the first real-world image, and determine a grinding coordinate of the surface defect in a preset grinding platform coordinate system; A grinding unit is used to grind the surface defects according to the grinding coordinates.

Citation Information

Patent Citations

  • Robot flexible grinding method for surface defects of steel plate

    CN112139857A

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

    CN115205220A

  • Visual guidance method, device and system for polishing of high-brightness surface defects

    CN117697630A

  • Method and apparatus for detecting shape fault of strip- like material and continuously treating line of the strip-like material

    JP2000275038A

  • Automatic detection of surface defects for continuously cast products with continuous mechanical removal of the material

    ZA199804341B

Cited By

  • Online processing method and device for strip steel edge defects

    CN120715750A