Glass defect detection method and system

By using a workbench and detection mechanism in the glass detection system to obtain optical information, combining the image and light round trip time, and analyzing glass defects, the problem that traditional detection technology cannot capture micro defects in all aspects and takes time to detect manual detection is realized, and the glass is Fast and accurate defect detection.

CN119086601APending Publication Date: 2024-12-06SICHUAN XUHONG OPTOELECTRONICS TECH +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411269681.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Traditional glass inspection technology cannot achieve full-range scanning, it is difficult to capture small defects, and manual inspection takes a long time, affecting the rapid evaluation of glass product quality.

Method used

A glass defect detection system is designed, including a workbench, detection mechanism and defect analysis mechanism. By obtaining optical information of each glass acquisition point along the X and Y directions on the XY plane, combining the image and light round trip time, it analyzes whether there are defects. , the system can rotate and lift to adjust the detection angle and distance.

Benefits of technology

It realizes all-round and accurate defect detection of glass, improves measurement accuracy and efficiency, and quickly evaluates the quality of glass products.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086601A_ABST
    Figure CN119086601A_ABST
Patent Text Reader

Abstract

The invention provides a glass defect detection method and system, and relates to the technical field of optical measurement. The glass defect detection system comprises a workbench used for placing glass to be detected along an X-direction reference edge and a Y-direction reference edge, and the X-direction reference edge and the Y-direction reference edge form an XY plane; the detection mechanism is arranged above the workbench and used for sequentially obtaining optical information of all the collection points of the glass from a coordinate origin based on horizontal coordinates of all the collection points of the glass, the optical information comprises images and light round-trip time, and the coordinate origin is an intersection point of the X-direction reference edge and the Y-direction reference edge; and the defect analysis mechanism is connected with the detection mechanism and is used for analyzing whether the glass has defects or not based on receiving the optical information, sent by the detection mechanism, of each collection point of the glass. According to the system, through omnibearing data acquisition, accurate measurement of contour data of the glass and accurate detection of defects of the glass can be realized, and the measurement precision is improved, so that the quality of a glass product is rapidly evaluated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of optical measurement technology, and in particular to a glass defect detection method and system. Background Art

[0002] In industrial production, glass quality inspection is a key link to ensure product quality, safety and aesthetics. Through accurate inspection, the reliability of glass products in the application process can be guaranteed, and functional or aesthetic problems caused by potential defects can be avoided.

[0003] However, traditional glass inspection technology has some limitations. On the one hand, ordinary inspection equipment cannot achieve all-round glass scanning inspection, and it is difficult to capture small but critical defects on the glass surface. On the other hand, manual defect inspection of the glass surface or adding a visual sorting process will take too long or the process route will be too long, affecting the rapid evaluation of glass product quality. Summary of the invention

[0004] A technical problem to be solved by the present disclosure is: how to achieve all-round glass defect detection.

[0005] To solve the above technical problems, in a first aspect, an embodiment of the present disclosure provides a glass defect detection system, the system comprising: a workbench, for placing a glass to be tested along an X-direction reference edge and a Y-direction reference edge, wherein the X-direction reference edge and the Y-direction reference edge form an XY plane; a detection mechanism, arranged above the workbench, for sequentially acquiring optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass starting from the coordinate origin, wherein the optical information includes an image and a round-trip time of light, and the coordinate origin is the intersection of the X-direction reference edge and the Y-direction reference edge; a defect analysis mechanism, connected to the detection mechanism, for analyzing whether the glass has defects based on the optical information of each collection point of the glass sent by the detection mechanism.

[0006] In some embodiments, the workbench is connected to a rotating mechanism and a lifting mechanism, wherein the rotating mechanism is used to control the rotation angle of the workbench, and the lifting mechanism is used to control the lifting height of the workbench.

[0007] In some embodiments, the distance between the detection mechanism and the XY plane is adjusted by controlling the rotation height of the workbench, and the angle between the detection mechanism and the XY plane is adjusted by controlling the rotation angle of the workbench.

[0008] In some embodiments, the detection mechanism includes a camera and a generator; the camera is used to sequentially acquire images of each collection point of the glass starting from the coordinate origin, wherein the focal length of the camera is adjusted during the acquisition process to make the image clear; the generator is used to sequentially emit laser or infrared rays to each collection point of the glass starting from the coordinate origin and acquire the round-trip time of light at each collection point of the glass, wherein the generator remains perpendicular to the XY plane during the acquisition process.

[0009] In some embodiments, the detection mechanism also includes a robotic arm and a slide rail; the robotic arm is connected to the slide rail; the camera and the generator are arranged at the top of the robotic arm, and the robotic arm is controlled to move along the slide rail to control the camera and the generator to move along the positive direction of the X-direction reference edge.

[0010] In some embodiments, the images of each collection point of the glass include images of each collection point of the glass at different visual distances and different visual angles, where the visual distance is the distance between the detection mechanism and the XY plane, and the visual angle is the angle between the detection mechanism and the XY plane.

[0011] In a second aspect, an embodiment of the present disclosure provides a glass defect detection method, the method comprising: starting from the coordinate origin, sequentially acquiring optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass to be tested, wherein the optical information includes an image and a round-trip time of light, and the coordinate origin is the intersection of an X-direction reference edge and a Y-direction reference edge; based on the optical information of each collection point of the glass, analyzing whether the glass has defects.

[0012] In some embodiments, before sequentially acquiring optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass, the method further includes: determining the horizontal coordinates of each collection point of the glass based on a theoretical design drawing of the glass, wherein the horizontal coordinates include an X coordinate and a Y coordinate.

[0013] In some embodiments, based on the optical information of each collection point of the glass, analyzing whether the glass has defects includes: determining the Z coordinate of each collection point of the glass based on the round-trip time of light at each collection point of the glass; determining contour data of the glass based on the X coordinate, Y coordinate and Z coordinate of each collection point of the glass, wherein the contour data includes width, length and depth; analyzing whether the glass has defects based on images of each collection point of the glass in combination with the contour data of the glass.

[0014] In some embodiments, based on the images of each acquisition point of the glass and in combination with the contour data of the glass, the glass is analyzed to determine whether it has defects, including: based on the images of each acquisition point of the glass, identifying abnormal areas of the glass; based on the contour data of the abnormal areas, analyzing whether the glass has defects according to preset defect standards.

[0015] Through the above technical solution, the glass defect detection system provided by the present disclosure can achieve accurate measurement of glass contour data and accurate detection of glass defects, improve measurement accuracy, and thus quickly evaluate the quality of glass products. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a structural schematic diagram of a glass defect detection system disclosed in an embodiment of the present disclosure;

[0018] Figure 2 is a partial structural schematic diagram of a glass defect detection system disclosed in an embodiment of the present disclosure;

[0019] Figure 3 is a schematic diagram of a theoretical design diagram of a glass disclosed in an embodiment of the present disclosure;

[0020] Figure 4 is a schematic diagram of contour data of a glass disclosed in an embodiment of the present disclosure;

[0021] Figure 5 is a schematic diagram of contour data of another type of glass disclosed in an embodiment of the present disclosure;

[0022] Figure 6 is another partial structural schematic diagram of the glass defect detection system disclosed in the embodiment of the present disclosure;

[0023] Figure 7 It is a flow chart of a glass defect detection method disclosed in an embodiment of the present disclosure.

[0024] Description of reference numerals:

[0025] 1. Workbench; 2. Detection mechanism; 3. Defect analysis mechanism; 11. Rotation mechanism; 12. Lifting mechanism; 21. Camera; 22. Generator; 23. Robotic arm; 24. Slide rail. DETAILED DESCRIPTION

[0026] The following is a further detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to exemplarily illustrate the principles of the present disclosure, but cannot be used to limit the scope of the present disclosure. The present disclosure can be implemented in many different forms and is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

[0027] The present disclosure provides these embodiments to make the present disclosure thorough and complete, and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the parts and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary, and not as limiting.

[0028] It should be noted that, in the description of the present disclosure, unless otherwise specified, the meaning of "multiple" is greater than or equal to two; the terms "upper", "lower", "left", "right", "inner", "outer", etc., indicating the orientation or positional relationship, are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present disclosure. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0029] In addition, the words "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. "Vertical" does not mean vertical in the strict sense, but is within the tolerance range. "Parallel" does not mean parallel in the strict sense, but is within the tolerance range. "Include" or "comprising" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements.

[0030] It should also be noted that in the description of the present disclosure, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present disclosure can be understood according to the specific circumstances. When a specific device is described as being located between a first device and a second device, there may or may not be an intermediate device between the specific device and the first device or the second device.

[0031] All terms used in the present disclosure have the same meanings as those understood by those of ordinary skill in the art to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, for example, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0032] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0033] Figure 1 is a structural schematic diagram of a glass defect detection system disclosed in an embodiment of the present disclosure, such as Figure 1 As shown, the glass defect detection system includes: a workbench 1, a detection mechanism 2 and a defect analysis mechanism 3, the workbench 1 is provided with an X-direction reference edge and a Y-direction reference edge, the detection mechanism 2 is arranged above the workbench 1, and the defect analysis mechanism 3 is connected to the detection mechanism 2.

[0034] The workbench 1 is used to place the glass to be tested along the X-direction reference edge and the Y-direction reference edge, wherein the X-direction reference edge and the Y-direction reference edge form an XY plane.

[0035] In some embodiments, Figure 2 As shown, the workbench 1 may be connected with a rotating mechanism 11 and a lifting mechanism 12, wherein the rotating mechanism 11 is used to control the rotation angle of the workbench 1, and the lifting mechanism 12 is used to control the lifting height of the workbench 1. Specifically, the rotating mechanism 11 may include a rotating platform, which is arranged below the workbench 1, and the rotation angle of the rotating platform is controlled to control the rotation angle of the workbench 1. The lifting mechanism 12 may include a link block and a lead screw slide, and the workbench 1 is connected to the lead screw slide through the link block, and the link block is controlled to move up and down along the lead screw slide, thereby controlling the lifting height of the workbench 1.

[0036] The distance between the detection mechanism 2 and the XY plane can be adjusted by controlling the rotation height of the workbench 1, and the angle between the detection mechanism 2 and the XY plane can be adjusted by controlling the rotation angle of the workbench 1. Specifically, the rotation angle range of the workbench 1 can be set to 0-360°, and the lifting range can be set to 0-50cm, so as to measure the glass from various angles and positions.

[0037] In the embodiment of the present disclosure, the workbench 1 is designed to be a rotatable and liftable workbench, which can conveniently measure the glass from various angles and positions. Not only can the flat surface of the glass be measured, but also the curved surface of the glass can be measured, thereby realizing all-round and full-coverage scanning measurement of the glass, avoiding the problem of inaccurate measurement results due to the inability to conduct comprehensive measurement.

[0038] The detection mechanism 2 is used to sequentially obtain optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass starting from the coordinate origin, wherein the optical information includes the image and the round-trip time of the light, and the coordinate origin is the intersection of the X-direction reference edge and the Y-direction reference edge.

[0039] It should be noted that the horizontal coordinates of each collection point of the glass are predetermined. Figure 3As shown, based on the theoretical design drawing of the glass to be tested on the workbench 1 (the plane to be tested is coplanar with any three points in the XY plane), the Cartesian coordinate system can be used to describe the positions of the various collection points of the glass to be tested in three-dimensional space (including the X direction, the Y direction and the Z direction). According to the unit coordinate length, the various collection points of the glass can be determined, wherein the difference between every two collection points is a unit coordinate length. The smaller the value of the unit coordinate length, the denser the collection points of the glass and the higher the measurement accuracy. The coordinates (x, y, z) can be used to describe the theoretical spatial coordinates of the glass, and the coordinates (X, Y, Z) can be used to describe the theoretical spatial coordinates of a unit coordinate length.

[0040] In the embodiments of the present disclosure, the surface defects of the glass are mainly analyzed, with emphasis on the measurement of the surface contour data of the glass. Therefore, the determined acquisition points (x, y) can be measured in the z direction to obtain the three-dimensional spatial coordinates of the actual measurement, and the images of the determined acquisition points (x, y) can be obtained to perform image recognition of surface defects based on the images.

[0041] Specifically, the coordinates (x, y) are used to describe the theoretical horizontal coordinates of each collection point. According to the theoretical horizontal coordinates of each collection point, the detection mechanism 2 can be controlled to move from the coordinate origin to the corresponding collection point to collect optical information. For example, if the coordinates of a collection point are (3X, 2Y), the detection mechanism 2 is controlled to move from the coordinate origin to (3X, 2Y) to collect the optical information of the collection point. It can be understood that if the coordinate origins referenced during measurement are different, they need to be converted to the same coordinate origin, so as to ensure that the coordinate system of the detection mechanism 2 and each collection point of the glass is the same, so as to accurately locate each collection point.

[0042] In some embodiments, Figure 2 As shown, the detection mechanism 2 may include a camera 21 and a generator 22. The camera 21 is used to sequentially acquire images of various acquisition points of the glass starting from the coordinate origin, and the focal length of the camera 21 may be adjusted during the acquisition process to make the image clear. The generator 22 is used to sequentially emit laser or infrared rays to various acquisition points of the glass starting from the coordinate origin and acquire the round-trip time of the light at each acquisition point of the glass, and the generator 22 remains perpendicular to the XY plane during the acquisition process.

[0043] Specifically, the resolution of the camera 21 can be 1920*1080, the frame rate can be 60fps, and the focal length can be set to be adjustable between 0.2mm and 800mm to adapt to glass of different sizes and shapes. The generator 22 can be an optical device such as an infrared generator and a laser generator, and its emission angle and emission frequency can be adjusted. In a specific embodiment, an infrared generator is used, and the wavelength range of the infrared ray can be set to be adjustable between 750nm and 1mm, and the emission frequency is 1khz; in another specific embodiment, a laser generator is used, and the wavelength of the laser ray can be set to 633nm and the emission frequency is 1khz.

[0044] In the embodiment of the present disclosure, the depth information of each acquisition point is obtained by the round trip time of the light of the optical device, and the image information of each acquisition point is obtained by the camera. It can be understood that the distance between the detection mechanism 2 and each acquisition point can be calculated according to the round trip time of the light, and the height coordinates of each acquisition point can be obtained by subtracting the distance between the detection mechanism 2 and each acquisition point from the distance between the detection mechanism 2 and the XY plane.

[0045] Specifically, in the optical device coordinate system, the actual three-dimensional space coordinate reference Figure 4 As shown, the optical device emits light to a certain collection point on the glass on the workbench. Based on the time difference between the emission and the reception of feedback, the coordinate z' of the collection point in the Z direction can be calculated. The actual three-dimensional space coordinates when performing contour measurement can be described by (x', y', z'), and the unit coordinate length is represented by (X', Y', Z'). In the camera coordinate system, the actual three-dimensional space coordinates obtained are referenced to Figure 5 As shown, the actual three-dimensional space coordinates during defect identification can be represented by (x", y", z"), and the unit coordinate length is represented by (X", Y", Z"). The two coordinate systems have the following relationship: (x'+A, y'+B, z'+C) = (x", y", z"), A can be the lateral distance difference between the optical device and the camera, and B can be the longitudinal distance difference between the optical device and the camera, where A, B, and C are all natural numbers. When integrating data, both coordinate systems need to be converted to the intersection of the X-direction reference edge and the Y-direction reference edge as the coordinate origin, so that each acquisition point of the glass corresponds one-to-one with the acquired image information and depth information.

[0046] It should be noted that since the motion camera and the infrared generator or laser generator are not in the same position, but both can be used to acquire data at the same time, the positions of the motion camera and the infrared generator or laser generator relative to the coordinate origin are different at the beginning, that is, the reference coordinate system may be different.

[0047] By using a high-precision motion camera, you can accurately capture defects such as dents, scratches, and dirt on the glass surface, and select them. By using an infrared generator or a laser generator, you can accurately obtain the curved surface profile data of the glass and improve the measurement accuracy.

[0048] In some embodiments, Figure 6 As shown, the detection mechanism 2 also includes a robotic arm 23 and a slide rail 24. The robotic arm 23 is connected to the slide rail 24. The camera 21 and the generator 22 are arranged at the top of the robotic arm 23. The robotic arm 23 is controlled to move along the slide rail 24 to control the camera 21 and the generator 22 to move along the X-direction reference edge.

[0049] In some embodiments, the robotic arm can rotate 90°, so that accurate positioning of each collection point of the glass can be achieved by controlling the rotation angle of the workbench, the rotation angle of the robotic arm, and the translation distance of the robotic arm.

[0050] In the disclosed embodiment, by controlling the movement of the robot arm to control the movement of the camera and the generator, the shape and surface contour data of the glass can be quickly and accurately acquired, thereby improving the measurement accuracy and efficiency, saving manual labor, and saving measurement time.

[0051] In the disclosed embodiment, the workbench 1 and the detection mechanism 2 are both mounted on a frame, and the actions of the corresponding mechanisms are controlled by a servo motor.

[0052] After acquiring the optical information of each collection point, the detection mechanism 2 sends it to the defect analysis mechanism 3. The defect analysis mechanism 3 is used to analyze whether the glass has defects based on the optical information of each collection point of the glass sent by the detection mechanism 2.

[0053] In some embodiments, the defect analysis mechanism 3 analyzes whether the glass has defects based on the optical information of each collection point of the glass in the following manner: determining the Z coordinate of each collection point of the glass based on the round-trip time of light at each collection point of the glass; determining the contour data of the glass based on the X coordinate, Y coordinate and Z coordinate of each collection point of the glass, wherein the contour data includes width, length and depth; analyzing whether the glass has defects based on the images of each collection point of the glass in combination with the contour data of the glass.

[0054] In some embodiments, the defect analysis mechanism 3 analyzes whether the glass has defects based on the images of each acquisition point of the glass in combination with the contour data of the glass in the following manner: based on the images of each acquisition point of the glass, the abnormal area of ​​the glass is identified; based on the contour data of the abnormal area, the glass is analyzed according to the preset defect standard to determine whether the glass has defects. The images of each acquisition point of the glass include images of each acquisition point of the glass at different visual distances and different visual angles, wherein the visual distance is the distance between the detection mechanism 2 and the XY plane, and the visual angle is the angle between the detection mechanism 2 and the XY plane.

[0055] It should be noted that some glasses have relatively high requirements for defect recognition. For example, for vehicle-mounted cover glass, small cracks may affect the safety of the glass, and large areas of dirt may affect the user's field of vision, thereby increasing the risk of accidents during driving. For cover glass, after the glass is installed on the car, the user has a certain visual distance and a certain visual angle when visually viewing the cover glass in the car. In order to simulate the user's perspective to identify defects, images of various acquisition points of the glass can be obtained at different visual distances and different visual angles, so as to identify defects on the glass surface in all directions. The defect detection system of the disclosed embodiment can simulate the user's visual angle and visual distance to identify defects. Specifically, the visual distance can be 20cm to 80cm, and the visual angle can be 90±45° (up and down).

[0056] In some embodiments, after the defect analysis mechanism 3 receives the optical information of each collection point of the glass sent by the detection mechanism 2, a detailed measurement report will be generated, including the external dimensions, curved surface contour, and contour data of the glass. In addition, it is determined whether it is a defective product based on preset defect standards (such as scratch depth, length, etc.). At the same time, the system will automatically determine whether the contour of the glass is within the allowable range based on the set threshold. If it exceeds the range, the system will issue a notification to prompt the staff to conduct further inspection and processing. The defect detection system provided in the embodiment of the present disclosure can realize automated measurement and monitoring, effectively improving work efficiency.

[0057] For example, the difference between the corresponding coordinate point and the theoretical coordinate point in each of the above coordinate systems is automatically calculated by a computer. For example, if the coordinates of a point are (P, Q, R) and the theoretical coordinates are (P1, Q1, R1), then (P-P1, Q-Q1, R-R1) is the error value between the actual contour and the theoretical contour.

[0058] That is, the embodiment of the present disclosure first calculates the contour data of the glass according to the round-trip time of the light, and then performs defect analysis in combination with the image data of the glass.

[0059] For example, the following preset defect standards may be referred to for defect judgment.

[0060] Table 1 Defect judgment criteria

[0061]

[0062]

[0063] Wherein, L is the defect length, W is the defect width, D is the defect diameter, N is the number of defects, S (DS) is the distance between defects, X is the long side, Y is the wide side, and Z is the depth (or height). For example, three linear scratches are identified from the image, and after comparing the contour data, it is calculated that their defect widths W are 0.08mm, 0.09mm, and 0.1mm respectively, and the defect lengths L are 1mm, 2mm, and 3mm respectively, and the distances DS between the defects are all less than 10mm. According to the defect judgment criteria in Table 1 above, it is considered that the glass has linear scratch defects.

[0064] This technical solution uses a high-resolution motion camera and a lens with precisely adjustable focal length, as well as an infrared and laser generator with precisely adjustable emission angle and frequency. It can accurately obtain the shape and surface contour data of the glass and calculate the contour of the glass. The error is controlled within ±0.01mm, thereby improving the measurement accuracy.

[0065] Figure 7 is a flow chart of a glass defect detection method disclosed in an embodiment of the present disclosure; Figure 4 As shown, the glass defect detection method includes step S101 and step S102.

[0066] In step S101, starting from the coordinate origin, optical information of each collection point of the glass to be tested is sequentially acquired based on the horizontal coordinates of each collection point of the glass to be tested.

[0067] The optical information includes the image and the round trip time of the light, and the origin of the coordinate is the intersection of the X-direction reference edge and the Y-direction reference edge;

[0068] In some embodiments, before sequentially acquiring optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass, the method further includes: determining the horizontal coordinates of each collection point of the glass based on a theoretical design drawing of the glass, wherein the horizontal coordinates include an X coordinate and a Y coordinate.

[0069] In step S102, based on the optical information of each acquisition point of the glass, it is analyzed whether the glass has defects.

[0070] In some embodiments, based on the optical information of each collection point of the glass, analyzing whether the glass has defects includes: determining the Z coordinate of each collection point of the glass based on the round-trip time of light at each collection point of the glass; determining contour data of the glass based on the X coordinate, Y coordinate and Z coordinate of each collection point of the glass, wherein the contour data includes width, length and depth; analyzing whether the glass has defects based on images of each collection point of the glass in combination with the contour data of the glass.

[0071] In some embodiments, based on the images of each acquisition point of the glass and in combination with the contour data of the glass, the glass is analyzed to determine whether it has defects, including: based on the images of each acquisition point of the glass, identifying abnormal areas of the glass; based on the contour data of the abnormal areas, analyzing whether the glass has defects according to preset defect standards.

[0072] The detailed process of the above-mentioned step S101 and step 102 can refer to the specific description of the defect analysis mechanism of the defect detection system, which will not be repeated here.

[0073] Due to the advanced nature of the technical solution, it can be widely used in application fields such as vehicle engineering, optical measurement technology, and mechanical manufacturing. First, for the field of vehicle engineering, the present disclosure can quickly and accurately measure the contour of the vehicle cover glass, effectively reduce the scratches on the glass surface, improve the measurement efficiency and accuracy, meet the needs of large-scale production, and is of great significance for improving the safety and aesthetics of the vehicle. Secondly, for the field of optical measurement technology, the present disclosure introduces motion cameras, infrared, laser generators and other equipment, which can accurately obtain the shape and surface contour data of the object, and has a positive effect on promoting technological progress in this field. Finally, for the field of mechanical manufacturing, the present disclosure designs a precise workbench and defect analysis mechanism, which can ensure the measurement accuracy, and plays an important role in improving the efficiency and accuracy of mechanical manufacturing.

[0074] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0075] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. In particular, the various technical features mentioned in the various embodiments may be combined in any manner as long as there is no structural conflict.

Claims

1. A glass defect detection system, characterized in that: The system comprises: A workbench (1) is used to place the glass to be tested along an X-direction reference edge and a Y-direction reference edge, wherein the X-direction reference edge and the Y-direction reference edge form an XY plane; A detection mechanism (2) is arranged above the workbench (1) and is used to sequentially acquire optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass starting from the coordinate origin, wherein the optical information includes an image and a round-trip time of light, and the coordinate origin is the intersection of the X-direction reference edge and the Y-direction reference edge; The defect analysis mechanism (3) is connected to the detection mechanism (2) and is used to analyze whether the glass has defects based on the optical information of each collection point of the glass sent by the detection mechanism (2).

2. The glass defect detection system according to claim 1, characterized in that: The workbench (1) is connected to a rotating mechanism (11) and a lifting mechanism (12), wherein the rotating mechanism (11) is used to control the rotation angle of the workbench (1), and the lifting mechanism (12) is used to control the lifting height of the workbench (1).

3. The glass defect detection system according to claim 2, characterized in that: The distance between the detection mechanism (2) and the XY plane is adjusted by controlling the rotation height of the workbench (1), and the angle between the detection mechanism (2) and the XY plane is adjusted by controlling the rotation angle of the workbench (1).

4. The glass defect detection system according to claim 1, characterized in that: The detection mechanism (2) comprises a camera (21) and a generator (22); The camera (21) is used to sequentially acquire images of various acquisition points of the glass starting from the coordinate origin, wherein the focal length of the camera (21) is adjusted during the acquisition process to make the image clear; The generator (22) is used to emit laser or infrared rays from the coordinate origin to each collection point of the glass in sequence and obtain the round-trip time of the light at each collection point of the glass, wherein the generator (22) remains perpendicular to the XY plane during the acquisition process.

5. The glass defect detection system according to claim 4, characterized in that: The detection mechanism (2) also includes a mechanical arm (23) and a slide rail (24); The mechanical arm (23) is connected to the slide rail (24); The camera (21) and the generator (22) are arranged at the top of the mechanical arm (23), and the camera (21) and the generator (22) are controlled to move along the X-direction reference edge by controlling the mechanical arm (23) to move along the slide rail (24).

6. The glass defect detection system according to any one of claims 1 to 5, characterized in that: The images of each collection point of the glass include images of each collection point of the glass at different visual distances and different visual angles, wherein the visual distance is the distance between the detection mechanism (2) and the XY plane, and the visual angle is the angle between the detection mechanism (2) and the XY plane.

7. A glass defect detection method, characterized in that: The method comprises: Starting from the coordinate origin, optical information of each collection point of the glass to be tested is sequentially acquired based on the horizontal coordinates of each collection point of the glass to be tested, wherein the optical information includes an image and a round-trip time of light, and the coordinate origin is the intersection of the X-direction reference edge and the Y-direction reference edge; Based on the optical information of each collection point of the glass, it is analyzed whether the glass has defects.

8. The glass defect detection method according to claim 7, characterized in that: Before sequentially acquiring optical information of each collection point of the glass based on the horizontal coordinates of each collection point of the glass, the method further includes: Based on the theoretical design diagram of the glass, the horizontal coordinates of each collection point of the glass are determined, wherein the horizontal coordinates include an X coordinate and a Y coordinate.

9. The glass defect detection method according to claim 8, characterized in that: The analyzing whether the glass has defects based on the optical information of each collection point of the glass includes: Determine the Z coordinate of each collection point of the glass based on the round trip time of light at each collection point of the glass; Determine contour data of the glass based on the X-coordinate, Y-coordinate and Z-coordinate of each acquisition point of the glass, wherein the contour data includes width, length and depth; Based on the images of each acquisition point of the glass and in combination with the contour data of the glass, it is analyzed whether the glass has defects.

10. The glass defect detection method according to claim 9, characterized in that: The analyzing whether the glass has defects based on the images of each acquisition point of the glass in combination with the contour data of the glass includes: Based on the images of each acquisition point of the glass, identifying the abnormal area of ​​the glass; Based on the contour data of the abnormal area, the glass is analyzed whether there are defects according to a preset defect standard.

Citation Information

Cited By

  • Vertical glass defect positioning mechanism and method

    CN120445993A

  • A vertical glass defect positioning mechanism and method

    CN120445993B