Method and system for detecting width and height of sealing ring rubber and medium

Abstract

The embodiment of the invention discloses a sealing ring rubber width and height detection method and system and a medium, and belongs to the technical field of industrial measurement. The method comprises the following steps: after the automatic gluing machine finishes gluing, a tray flows into a visual inspection station, a PLC triggers a camera to scan, the camera scans three-dimensional point clouds of glue paths in the movement process, the three-dimensional point clouds are obtained in real time through an algorithm and processed, after all the glue paths are scanned, the algorithm finishes processing at the same time, and a result is fed back to the PLC. According to the invention, the width and height of the sealing ring rubber can be detected based on the line scanning camera, strict movement along the rubber path is not required to be controlled, splicing of different rubber path pictures is not required, and the CT time of the whole system is greatly shortened.

Description

Technical Field

[0001] The present invention relates to the field of industrial measurement technology, and in particular to a method, system and medium for detecting the width and height of a sealing ring rubber. Background Art

[0002] In the field of industrial automation, the hot melt glue on the box sealing ring is usually applied by automatic glue coating equipment on the automatic line. The industry needs to control the glue coating quality. After the automatic glue coating machine is finished, an effective detection method is needed to detect defects such as glue breakage, glue width, glue height, and process design. There are traditionally two methods for testing glue coating quality:

[0003] One is manual observation and detection, but this method has a certain degree of subjectivity, a high misjudgment rate, and requires relevant inspection personnel to enter the equipment for confirmation, which greatly consumes human resources. When production is busy and personnel are tired, inspection personnel often cannot achieve 100% full inspection, which poses a safety hazard.

[0004] The second is to use 2D cameras for detection. In fact, the glue path of the box seal ring is irregular and long, often beyond the field of view of the 2D camera. The camera needs to shoot multiple times to collect the complete glue path, which seriously causes the overall CT time of the system to time out. At the same time, the seal ring glue shape is a three-dimensional structure, and the 2D camera can only detect the glue width, but not the glue height.

[0005] Therefore, how to provide a box sealing ring glue type detection system and method to improve the accuracy, efficiency and safety of box sealing ring glue type detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method, system and medium for detecting the width and height of a seal ring glue, which can improve the detection efficiency.

[0007] On the one hand, an embodiment of the present invention provides a method for detecting the width and height of a sealing ring glue, comprising the following steps: S100, in response to the sealing ring glue path completing the gluing operation and entering the visual inspection station, the camera moves along a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the camera movement; S200, processing the three-dimensional point cloud data of different glue path sections according to a preset detection method to obtain glue height and width detection results; the step S200 includes: S210, obtaining a glue path skeleton based on a 2D image processing method, and taking all center point sets on the skeleton as the center path of the glue path; S220, downsampling the center point set according to a specified step size, and calculating the direction between the current point and the next point as the direction of the current micro glue path α=atan2(p iy -p (i-1)y ,p ix -p(i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x S230, grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current small glue path, and calculate the midpoint P of the left and right edge points c , get glue height h p =h pc -0.5*(h p1 +h p2 ), where h pc ,h p1 ,h p2 The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

[0008] According to some embodiments of the present invention, step S200 includes: S240, if the current glue path section is a straight glue path, then calculating the distance between the left and right edge points P1 and P2 to obtain the glue width of the current straight glue path section.

[0009] According to some embodiments of the present invention, step S200 includes: S250, if the current glue road section is an R-corner glue road, let the camera scan the R-corner glue road according to the first path and the second path respectively, to obtain a first R-corner three-dimensional point cloud S and a second R-corner three-dimensional point cloud S1; wherein the second path is perpendicular to the direction of the first path; there is a shadow in the B-side area of ​​the first R-corner three-dimensional point cloud S, and there is a shadow in the C-side area of ​​the second R-corner three-dimensional point cloud S1; S260, respectively detect the arcs B1 and C1 of the B-side area and the C-side area of ​​S and S1, and the distance between the center of the arc and the intersection of the two arcs is used as the glue width of the current R-corner glue road section.

[0010] According to some embodiments of the present invention, step S200 includes: S270, if the current glue road section is an arc glue road, obtaining the glue road skeleton for fitting to obtain the arc center; S280, extracting the inner edge point P of the arc i , according to the center of the arc and P i The extension line of the connecting line is used to obtain the ray L, and the highest point p on the ray L is extracted. c As the center point of the glue path; S290, calculate P i Relative to p c The symmetric point P along the ray L i '; with P i 'Set ROI as the center and find the minimum point P in ROI i ”, that is, the shadow boundary of the glue road, then this point is taken as the outer edge point of the glue road; P i With Pi The distance between the two is the rubber width of the current arc rubber section.

[0011] According to some embodiments of the present invention, step S290 further includes: if P i If there is an invalid point in the area where P i As the outer edge point P of the glue path i ”.

[0012] According to some embodiments of the present invention, the step S210 includes: S211, processing the image to be detected acquired by the camera through a binary segmentation method to obtain a glue road area; S212, performing a connected domain analysis on the glue road area, and taking each connected domain as a glue road area to be measured; S213, for each glue road area to be measured, determining the central pixel point corresponding to the glue road area to be measured based on the pixel points corresponding to the glue road area to be measured; S214, constructing a glue road skeleton corresponding to the glue road area to be measured based on the central pixel points.

[0013] According to some embodiments of the present invention, step S100 includes: acquiring a sensor signal disposed at a visual inspection station in real time, and determining whether the tray with the sealing ring enters the visual inspection station according to the sensor information.

[0014] According to some embodiments of the present invention, step S100 includes: when the tray of the sealing ring enters the visual inspection station, the PLC triggers the camera to scan; when the camera moves along a preset path and obtains a three-dimensional point cloud, the three-dimensional point cloud is processed in real time based on a preset detection method, and while all glue paths are scanned, the glue width and height detection of the glue paths are completed, and the glue width and height detection results are fed back to the PLC.

[0015] The method of the embodiment of the present invention includes at least the following beneficial effects: The method of detecting glue width and height based on line scan camera proposed by the present invention is simple in detection method, and does not require control to strictly move along the glue path, especially at R corners and arcs, does not require control to make arc movements, and does not require splicing of different glue path pictures, which greatly shortens the CT time of the entire system. The detection system has high repeatability accuracy. The system measures the same product multiple times, and the repeatability accuracy of glue width and height is less than or equal to 0.01mm.

[0016] On the other hand, an embodiment of the present invention provides a sealing ring glue width and height detection system, including: a first module, in response to the sealing ring glue path completing the gluing operation and entering the visual inspection station, the camera moves according to a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the camera movement; a second module, for processing the three-dimensional point cloud data of different glue path sections according to a preset detection method to obtain glue height and glue width detection results; wherein the second module includes: a first submodule, for obtaining a glue path skeleton based on a 2D image processing method, and taking all center point sets on the skeleton as the glue path center path; a second submodule, for downsampling the center point set according to a specified step size, and calculating the direction between the current point and the next point as the direction of the current micro glue path α=atan2(p iy -p (i-1)y ,p ix -p (i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x are the horizontal coordinates of the next point and the current point respectively; the third submodule is used to grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current micro glue path, and calculate the midpoint P of the left and right edge points c , get glue height h p =h pc -0.5*(h p1 +h p2 ), where h pc ,h p1 ,h p2 The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

[0017] The system of the embodiment of the present invention includes at least the following beneficial effects: The system of the embodiment of the present invention uses a method based on line scanning camera to detect glue width and height. The detection method is simple and does not require control to strictly move along the glue path, especially at R corners and arcs. There is no need to control arc movement and no need to splice different glue path pictures, which greatly shortens the CT time of the entire system. The detection system has high repeatability. The system measures the same product multiple times, and the repeatability of glue width and height is less than or equal to 0.01mm.

[0018] Another aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described above is implemented.

[0019] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0021] Figure 1 A schematic diagram of a method according to an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a sealing ring glue path for glue width and height detection using an embodiment of the present invention;

[0023] Figure 3 A schematic flow chart of a method according to another embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of the R corner glue section of the sealing ring;

[0025] Figure 5 The schematic diagram of the arc section glue path of the sealing ring;

[0026] Figure 6 The module schematic block diagram of the system according to the embodiment of the present invention.

[0027] Reference numerals:

[0028] The first module 100 , the second module 200 , the first submodule 210 , the second submodule 220 , and the third submodule 230 . DETAILED DESCRIPTION

[0029] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0030] In the description of the present invention, "several" means one or more, "more" means two or more, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0031] Reference Figure 1 An embodiment of the present invention provides a method for detecting the width and height of a sealing ring glue based on a line scan camera, comprising the following steps: after the automatic glue coating machine completes the gluing, the tray flows into the visual inspection station; the PLC triggers the camera to scan, and the three-dimensional point cloud of the glue path is scanned during the movement of the camera; the algorithm obtains and processes the three-dimensional point cloud in real time; after scanning all the glue paths, the algorithm completes the processing at the same time and feeds back the results to the PLC.

[0032] In this embodiment, the line scan camera is fixed on the 5-axis motion control system; the camera angle is adjusted to ensure that the camera is perpendicular to the glue path plane; the scanning path is planned in advance to ensure that the laser lines overlap and cover all glue paths as much as possible; and the detection ROI is set for each glue path section.

[0033] like Figure 2 As shown, the seal ring glue path is complex, including arc segments, turning segments, and R angles. The method proposed by the present invention does not need to scan different glue path sections multiple times. As long as the laser line can cover the current glue path section, the current glue path section can be detected by scanning the glue path once.

[0034] The following is a detailed description of the detection methods for different glue paths. Before detection, adjust the scanning path to ensure that the glue path is roughly located in the center of the laser line.

[0035] Reference Figure 3 The method for detecting the width and height of the seal ring of the present invention comprises the following steps:

[0036] S100, in response to the sealing ring glue path completing the gluing operation and entering the visual inspection station, the camera moves along a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the camera movement.

[0037] S200, processing the three-dimensional point cloud data of different rubber road sections according to a preset detection method to obtain rubber height and width detection results.

[0038] Wherein, step S200 includes:

[0039] S210, obtaining a glue path skeleton based on a 2D image processing method, and taking all center point sets on the skeleton as the glue path center path.

[0040] S220, downsample the central point set according to the specified step length, and calculate the direction between the current point and the next point as the direction of the current micro glue path α=atan2(p iy -p (i-1)y ,p ix -p (i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x They are the horizontal coordinates of the next point and the current point respectively.

[0041] S230, grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current small glue path, and calculate the midpoint P of the left and right edge points c , get glue height h p =h pc -0.5*(h p1 +hp2 ), where h pc ,h p1 ,h p2 The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

[0042] In some embodiments, for the straight line + turning section glue width and height detection, the camera scans the glue path along the straight path to obtain glue path depth point cloud data. Step S200 includes: S240, if the current glue path section is a straight glue path, calculate the distance between the left and right edge points P1 and P2 to obtain the glue width of the current straight glue path section.

[0043] Reference Figure 4 , the arrow points to the R angle. Due to the limitation of operation and control, the line scan camera can only scan along a straight line path. There is always a shadow at the R angle of the glue line, such as Figure 4 As shown. The existence of this shadow causes the glue width at the R corner to be too large, which is easy to cause false detection. In response to this problem, the embodiment of the present invention proposes the following detection method: Step S200 includes: S250, if the current glue road section is the R corner glue road, the camera is allowed to scan the R corner glue road according to the first path and the second path respectively, to obtain the first R corner three-dimensional point cloud S and the second R corner three-dimensional point cloud S1; wherein the second path is perpendicular to the direction of the first path; there is a shadow in the B side area of ​​the first R corner three-dimensional point cloud S, and there is a shadow in the C side area of ​​the second R corner three-dimensional point cloud S1; S260, respectively detect the arcs B1 and C1 of the B side area and the C side area of ​​S and S1, and the distance between the center of the arc and the intersection of the two arcs is taken as the glue width of the current R corner glue road section.

[0044] Reference Figure 5 , the arc segment also has a shadow problem because the laser line is not perpendicular to the glue path. To address this problem, the embodiment of the present invention proposes the following detection scheme: Step S200 includes: S270, if the current glue path section is an arc segment glue path, obtain the glue path skeleton for fitting to obtain the arc center; S280, extract the inner edge point P of the arc i , according to the arc center and P i Extension line of the connection (such as Figure 5 As shown), we get the ray L and extract the highest point p on the ray L. c As the center point of the glue path; S290, calculate P i Relative to p c The symmetric point P along the ray L i '; with P i 'Set ROI as the center and find the minimum point P in ROI i ”, that is, the shadow boundary of the glue road, then this point is taken as the outer edge point of the glue road; P i With P iThe distance between the two is the rubber width of the current arc rubber section.

[0045] In some embodiments, step S290 further includes: if P i If there is an invalid point in the area where P i As the outer edge point P of the glue path i ”.

[0046] In some embodiments, step S210 includes: S211, processing the image to be detected acquired by the camera through a binary segmentation method to obtain a glue road area; S212, performing a connected domain analysis on the glue road area, and taking each connected domain as a glue road area to be measured; S213, for each glue road area to be measured, determining the central pixel point corresponding to the glue road area to be measured based on the pixel points corresponding to the glue road area to be measured; S214, constructing a glue road skeleton corresponding to the glue road area to be measured based on the central pixel points.

[0047] In some embodiments, step S100 includes: acquiring a sensor signal disposed at a visual inspection station in real time, and determining whether the tray with the sealing ring enters the visual inspection station according to the sensor information.

[0048] Corresponding to the above-mentioned embodiments, the present invention also provides system embodiments. As for the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments.

[0049] Reference Figure 6 The embodiment of the present invention provides a sealing ring rubber width and height detection system, comprising:

[0050] The first module 100 is used for responding to the sealing ring glue path completing the gluing operation and entering the visual inspection station, the camera moves along a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the movement of the camera.

[0051] The second module 200 is used to process the three-dimensional point cloud data of different rubber road sections according to a preset detection method to obtain rubber height and width detection results.

[0052] Wherein, the second module 200 includes:

[0053] The first submodule 210 is used to obtain the glue path skeleton based on a 2D image processing method, and use all the center point sets on the skeleton as the glue path center path.

[0054] The second submodule 220 is used to downsample the central point set according to the specified step length, and calculate the direction between the current point and the next point as the direction of the current micro glue path α=a tan 2(p iy -p (i-1)y ,p ix -p(i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x They are the horizontal coordinates of the next point and the current point respectively.

[0055] The third submodule 230 is used to grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current small glue path, and calculate the midpoint P of the left and right edge points. c , get glue high in, The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

[0056] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.

[0057] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0058] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present application. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for detecting the width and height of a sealing ring rubber, characterized in that: The following steps are involved: S100, in response to the sealing ring glue path completing the gluing operation and entering the visual inspection station, the camera moves along a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the movement of the camera; S200, processing the three-dimensional point cloud data of different rubber road sections according to a preset detection method to obtain rubber height and width detection results; The step S200 includes: S210, obtaining a glue path skeleton based on a 2D image processing method, and taking all center point sets on the skeleton as the glue path center path; S220, downsample the central point set according to the specified step length, and calculate the direction between the current point and the next point as the direction of the current micro glue path α=atan2(p iy -p (i-1)y ,p ix -p (i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x They are the horizontal coordinates of the next point and the current point respectively; S230, grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current small glue path, and calculate the midpoint P of the left and right edge points c , get glue height h p =h pc -0.5*(h p1 +h p2 ), where h pc ,h p1 ,h p2 The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

2. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S200 includes: S240: If the current glue road section is a straight glue road, the distance between the left and right edge points P1 and P2 is calculated to obtain the glue width of the current straight glue road section.

3. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S200 includes: S250, if the current glue path section is an R-angle glue path, the camera is made to scan the R-angle glue path according to the first path and the second path respectively, to obtain a first R-angle three-dimensional point cloud S and a second R-angle three-dimensional point cloud S1; wherein the second path is perpendicular to the direction of the first path; a shadow exists in the B-side area of ​​the first R-angle three-dimensional point cloud S, and a shadow exists in the C-side area of ​​the second R-angle three-dimensional point cloud S1; S260, respectively detect the arcs B1 and C1 in the B side area and the C side area of ​​S and S1, and use the distance between the center of the arc and the intersection of the two arcs as the rubber width of the current R corner rubber section.

4. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S200 includes: S270, if the current rubber road section is an arc section rubber road, obtain the rubber road skeleton for fitting to obtain the arc center; S280, extract the inner edge point P of the arc i , according to the center of the arc and P i The extension line of the connecting line is used to obtain the ray L, and the highest point p on the ray L is extracted. c As the center point of the glue path; S290, calculate P i Relative to p c The symmetric point P along the ray L i '; with P i 'Set ROI as the center and find the minimum point P in ROI i ”, that is, the shadow boundary of the glue road, then this point is taken as the outer edge point of the glue road; P i With P i The distance between the two is the rubber width of the current arc rubber section.

5. The method for detecting the width and height of the seal ring according to claim 4, characterized in that: The step S290 further includes: if P i If there is an invalid point in the area where P i As the outer edge point P of the glue path i ”.

6. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S210 includes: S211, processing the image to be detected acquired by the camera by a binary segmentation method to obtain a glue path area; S212, performing connected domain analysis on the glue path area, and treating each connected domain as a glue path area to be measured; S213, for each glue path area to be measured, determining a central pixel point corresponding to the glue path area to be measured according to each pixel point corresponding to the glue path area to be measured; S214. Constructing a glue path skeleton corresponding to the glue path area to be measured according to each central pixel point.

7. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S100 includes: acquiring a sensor signal disposed at a visual inspection station in real time, and determining whether the tray with the sealing ring enters the visual inspection station according to the sensor information.

8. The method for detecting the width and height of the seal ring according to claim 1, characterized in that: The step S100 includes: when the tray of the sealing ring enters the visual inspection station, the PLC triggers the camera to scan; when the camera moves along the preset path and obtains the three-dimensional point cloud, the three-dimensional point cloud is processed in real time based on the preset detection method, and when all the glue paths are scanned, the glue width and height of the glue paths are detected and processed, and the glue width and height detection results are fed back to the PLC.

9. A sealing ring rubber width and height detection system, characterized in that: include: The first module is used to respond to the sealing ring glue path completing the gluing operation and entering the visual inspection station, and the camera moves along a preset path, and obtains a three-dimensional point cloud by scanning the glue path during the camera movement; The second module is used to process the three-dimensional point cloud data of different rubber road sections according to the preset detection method to obtain the rubber height and width detection results; The second module includes: The first submodule is used to obtain the glue path skeleton based on the 2D image processing method, and take all the center point sets on the skeleton as the glue path center path; The second submodule is used to downsample the central point set according to the specified step size, and calculate the direction between the current point and the next point as the direction of the current micro glue path α = atan2 (p iy -p (i-1)y ,p ix -p (i-1)x ), where p iy , p (i-1)y are the ordinates of the next point and the current point respectively, p ix , p (i-1)x They are the horizontal coordinates of the next point and the current point respectively; The third submodule is used to grab the left and right edge points P1 and P2 of the glue path in a direction perpendicular to the current small glue path, and calculate the midpoint P of the left and right edge points. c , get glue high in, The midpoint P c , the height values ​​of the left and right edge points P1 and P2.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 8 when executed by a processor.

Images