A method and apparatus for detecting defects in a sanding disc

Abstract

The application discloses a sand page disc defect detection method and a detection device. The detection method comprises the following steps: collecting an image of a sand page disc to be detected; performing gray scale processing on the image to obtain a gray scale image; extracting feature information in the gray scale image, and recording the feature information in a database for comparison; wherein defect type data corresponding to sand page disc features are stored in the database; and according to a comparison result, whether the sand page disc to be detected is unqualified is judged. The application has the advantages of improving sand page disc defect detection accuracy and meeting sand page disc defect detection requirements.

Description

Technical Field

[0001] This application relates to the field of sand sheet manufacturing technology, and in particular to a method and equipment for detecting defects in sand sheet manufacturing. Background Technology

[0002] Abrasive discs, also known as steel paper grinding discs, high-speed grinding discs, and abrasive pads, are the most commonly used abrasive discs and steel grinding discs. They are circular coated abrasives formed by bonding steel paper as the base material with silicon carbide or corundum as the abrasive through synthetic resin or other synthetic binders.

[0003] Sanding discs conforming to the standard GB / T 20962-2007 are prone to defects during production due to factors such as air pressure, temperature, vibration, and adhesive viscosity. Quality inspection is required to identify these defective products. However, existing inspection methods are inaccurate for sanding disc quality inspection, often resulting in missed or incorrect inspections, which affects the production cycle of sanding discs. Summary of the Invention

[0004] The main purpose of this application is to provide a method and equipment for detecting defects in sand sheet disks, aiming to solve the technical problem that existing detection methods are inaccurate in detecting defects in sand sheet disks.

[0005] To achieve the above objectives, this application provides a method for detecting defects in sand discs, comprising the following steps:

[0006] Acquire images of the sand disc to be inspected;

[0007] The image is converted to grayscale to obtain a grayscale image;

[0008] Feature information is extracted from the grayscale image and entered into a database for comparison; wherein, the database stores defect type data corresponding to the features of the sand sheet disk;

[0009] Based on the comparison results, determine whether the sand sheet to be tested is a defective product.

[0010] Optionally, the step of extracting feature information from the grayscale image and inputting the feature information into a database for comparison includes:

[0011] Extract grayscale difference information from the grayscale image, and compare the grayscale difference information with the database to determine whether the grayscale difference information belongs to the first type of defect information; wherein, the first type of defect information includes missing iron rings, glued caps, and glued adhesive.

[0012] The contour information in the grayscale image is extracted, and the contour information is compared with the database to determine whether the contour information belongs to the second type of defect information; wherein, the second type of defect information includes uneven distribution of sand flakes and out-of-roundness.

[0013] Optionally, the step of extracting grayscale difference information from the grayscale image and comparing the grayscale difference information with the database to determine whether the grayscale difference information belongs to the first type of defect information includes:

[0014] Set the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white distinction;

[0015] The first image is segmented to obtain multiple sub-image blocks;

[0016] The grayscale values ​​of multiple sub-image blocks are detected to obtain grayscale difference information;

[0017] The grayscale difference information is compared with the preset grayscale values ​​in the database to determine whether the grayscale difference information belongs to the first type of defect information.

[0018] Optionally, the step of extracting contour information from the grayscale image and comparing the contour information with the database to determine whether the contour information belongs to the second type of defect information includes:

[0019] Extract the most prominent outer edge cusp of each gear plate region in the grayscale image to obtain contour information;

[0020] Fit all the outer edge cusps to a minimum circumcircle and obtain the diameter of the minimum circumcircle;

[0021] The diameter of the minimum circumscribed circle is compared with a preset standard value in the database to determine whether the contour information belongs to the second type of defect information.

[0022] Optionally, acquiring the image of the sand disc to be inspected includes:

[0023] Set up a CCD camera and a light source. The CCD camera is used to acquire images, and the light source is used to illuminate the sand disc to be inspected.

[0024] Optionally, before the step of setting the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white contrast, the method further includes the following steps:

[0025] A polarizer is installed below the CCD camera to filter out reflected light.

[0026] Optionally, before the step of extracting the most prominent outer edge cusp of each gear plate region in the grayscale image to obtain contour information, the following steps are further included:

[0027] The light source is set to blue light and arranged in a ring to make the edge of the sand disc to be tested clear.

[0028] Optionally, the database includes a self-learning database, which stores defect type data corresponding to the unidentified sand sheet features.

[0029] A testing device is provided for implementing a method for detecting defects in sand sheet discs, comprising a conveying device, an identification device, and an industrial control computer. The conveying device and the identification device are both electrically connected to the industrial control computer. The conveying device conveys the sand sheet disc to a position below the identification device. The identification device acquires an image of the sand sheet disc to be inspected. The industrial control computer processes and identifies the acquired image to determine whether the sand sheet disc to be inspected is a defective product.

[0030] The conveying device includes a housing, on which a drive motor is mounted. A rotating disk is connected to the top of the drive motor. Multiple bases are mounted on the top of the rotating disk, and the multiple bases are arranged in a circular array around the center of the rotating disk. Each base is provided with a positioning post on its top. The sand sheet can be fitted onto the positioning post. The rotating disk is used to rotate the sand sheet to a position below the identification device.

[0031] Optionally, the identification device includes a frame, with a CCD camera and a supplementary lighting mechanism disposed at the top of the frame. Both the CCD camera and the supplementary lighting mechanism are located above any of the bases. The CCD camera is used to acquire images of the sand disc to be inspected. The supplementary lighting mechanism includes a connecting rod connected to the top of the frame, with a lampshade connected to the bottom of the connecting rod. The lampshade is open at both the top and bottom, and the CCD camera is located directly above the lampshade. Multiple light sources are disposed on the inner wall of the lampshade.

[0032] The beneficial effects that this application can achieve are as follows:

[0033] This application obtains a grayscale image by converting the image of the sand sheet to be inspected into grayscale, which facilitates the extraction of feature information from the grayscale image. The feature information is then compared with a database. Since the database stores defect type data corresponding to the features of the sand sheet, it can automatically determine whether the feature information of the sand sheet to be inspected matches the defect type data. If they match, it indicates that the product is defective, thus achieving automatic identification and judgment. This process is mainly executed by computer without human intervention, thereby reducing the risk of errors in manual identification, improving the accuracy of sand sheet defect detection, and reducing the likelihood of missed or incorrect detections, meeting high-standard inspection requirements. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0035] Figure 1 This is a flowchart illustrating a method for detecting defects in a sand sheet disk according to an embodiment of this application;

[0036] Figure 2 This is a schematic diagram of the structure of a detection device according to an embodiment of this application;

[0037] Figure 3 for Figure 2 A structural schematic diagram of the left view;

[0038] Figure 4 for Figure 2 A top view structural diagram (industrial control computer omitted);

[0039] Figure 5 This is a schematic diagram of the conveying device in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the supplementary lighting mechanism in an embodiment of this application;

[0041] Figure 7 This is a schematic diagram of the transfer device in an embodiment of this application;

[0042] Figure 8 This is a schematic diagram of the sorting robot in an embodiment of this application;

[0043] Figure 9 A schematic diagram of qualified sand discs that passed the test in this application;

[0044] Figure 10A schematic diagram of the non-conforming sand discs (with missing iron rings) detected in this application;

[0045] Figure 11 A schematic diagram of the non-conforming sand discs (with caps) detected in this application;

[0046] Figure 12 A schematic diagram of the non-conforming sand discs (adhesive) detected in this application;

[0047] Figure 13 This is a schematic diagram of the non-conforming sand discs detected in this application (uneven distribution of sand discs);

[0048] Figure 14 This is a schematic diagram of a non-conforming sand disc (out of roundness) that passed the inspection in this application.

[0049] Figure label:

[0050] 100-Conveying device, 110-Chassis, 120-Drive motor, 130-Rotating disk, 140-Base, 150-Positioning column, 200-Identification device, 210-Frame, 220-Supplemental lighting mechanism, 221-Connecting rod, 222-Lamp cover, 223-Light source, 230-CCD camera, 300-Industrial computer, 400-Transfer device, 410-First support column, 420-First motor, 430-First rotating column, 440-Crossbar, 450-First gripping mechanism, 500-Sorting robot, 510-Second support column, 520-Second motor, 530-Second rotating column, 540-First support, 550-Second support, 560-Second gripping mechanism.

[0051] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0053] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationship and movement of each component in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0054] In this application, unless otherwise expressly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0055] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution where both A and B are satisfied simultaneously. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0056] Example 1

[0057] Reference Figure 1 This embodiment provides a method for detecting defects in sand sheet disks, including the following steps:

[0058] Acquire images of the sand disc to be inspected;

[0059] The image is converted to grayscale to obtain a grayscale image;

[0060] Feature information is extracted from the grayscale image and entered into a database for comparison; wherein, the database stores defect type data corresponding to the features of the sand sheet disk;

[0061] Based on the comparison results, determine whether the sand sheet to be tested is a defective product.

[0062] In existing technologies, all defective products can be reworked into qualified products before curing. However, once cured, they cannot be reworked and become scrap. This necessitates online inspection before product curing to identify defective products. Currently, the industry uses two methods in production: one is visual inspection by operators, which is inefficient, labor-intensive, and has a high rate of missed inspections, making it impossible for one person to operate multiple machines; the other is no inspection at all, but selection is done after curing and before packaging, with defective products being downgraded or scrapped. Although not selecting can improve production efficiency, such as allowing one person to operate multiple machines, a scrap rate of over 1% results in significant resource waste.

[0063] Therefore, in this embodiment, the image of the sand sheet to be inspected is processed into grayscale to obtain a grayscale image, which facilitates the extraction of feature information from the grayscale image. The feature information is then compared with the database. Since the database stores defect type data corresponding to the features of the sand sheet, it can automatically determine whether the feature information of the sand sheet to be inspected matches the defect type data. If they match, it indicates that the product is defective, thus achieving automatic identification and judgment. This process is mainly executed by computer without human intervention, thereby reducing the error risk of manual identification and improving the accuracy of sand sheet defect detection. It is less likely to miss or misdetect products. This embodiment can provide online inspection before product curing, identifying products as defective online without affecting production efficiency or generating waste, thus meeting the current new inspection requirements.

[0064] It should be noted that when a sand sheet is detected as a defective product, an alarm message can be sent, and the defective product can then be picked out manually or automatically.

[0065] As an optional implementation, the step of extracting feature information from the grayscale image and recording the feature information into a database for comparison includes:

[0066] Extract grayscale difference information from the grayscale image, and compare the grayscale difference information with the database to determine whether the grayscale difference information belongs to the first type of defect information; wherein, the first type of defect information includes missing iron rings, glued caps, and glued adhesive.

[0067] The contour information in the grayscale image is extracted, and the contour information is compared with the database to determine whether the contour information belongs to the second type of defect information; wherein, the second type of defect information includes uneven distribution of sand flakes and out-of-roundness.

[0068] In this embodiment, the defects of the sanding disc mainly include missing iron rings, glued covers, glue residue, uneven distribution of sanding sheets, and out-of-roundness. Missing iron rings refer to the absence of the base portion in the center of the sanding disc; glued covers refer to the back cover portion of the sanding sheet being mistakenly glued to the front of the sanding sheet; glue residue refers to glue overflowing onto the surface of the sanding sheet; uneven distribution of sanding sheets refers to the uneven distribution among the gear pieces (the sanding sheet is composed of multiple gear pieces); and out-of-roundness refers to the uneven outer contour of the sanding sheet, with protrusions, preventing it from forming a complete circle. Defects such as missing iron rings, glued covers, and glue residue all cause obvious abnormalities on the surface of the sanding disc. Therefore, by extracting grayscale difference information from the grayscale image—that is, comparing whether there are grayscale differences in the grayscale image—if there are obvious differences, it is determined that one of the above-mentioned defect types exists. However, the defects of uneven distribution of sanding sheets and out-of-roundness do not have obvious abnormalities on the entire surface of the sanding disc. Therefore, by extracting contour information from the grayscale image—that is, by identifying whether there are obvious protrusions at the outer edge of the grayscale image—if there are obvious protrusions, it indicates the presence of defects such as uneven distribution of sanding sheets and out-of-roundness.

[0069] It should be noted that, based on production requirements, defects such as uneven sand distribution and out-of-roundness are minor and can be used as substandard products. However, defects such as missing iron rings, stuck caps, and glue adhesion are more significant. Therefore, identifying the first type of defect information is a necessary step, while identifying the second type of defect information can be omitted according to process requirements. That is, a step that only identifies the first type of defect information can be preset, or a step that requires identifying both the first and second types of defect information can be preset. If any defect information is identified, the product is judged as unqualified. This embodiment uses targeted different detection methods for different defect types of sand discs, resulting in more accurate detection results and meeting high-standard detection requirements. At the same time, the detection type can be flexibly selected according to the actual situation, providing high flexibility.

[0070] As an optional implementation, the step of extracting grayscale difference information from the grayscale image and comparing the grayscale difference information with the database to determine whether the grayscale difference information belongs to the first type of defect information includes:

[0071] Set the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white distinction;

[0072] The first image is segmented to obtain multiple sub-image blocks;

[0073] The grayscale values ​​of multiple sub-image blocks are detected to obtain grayscale difference information;

[0074] The grayscale difference information is compared with the preset grayscale values ​​in the database to determine whether the grayscale difference information belongs to the first type of defect information.

[0075] In this embodiment, when detecting and identifying first-type defect information, especially adhesive defects, the exposure needs to be set very high so that the glue can be clearly displayed, forming a clear black and white first image. Then, the first image is segmented to obtain multiple sub-image blocks. The grayscale value of each sub-image block is identified individually and compared with the preset grayscale values ​​in the database. If the grayscale value of any sub-image block is different, it is determined that there is first-type defect information, thereby achieving accurate detection of adhesive defects. Similarly, defects such as missing iron rings and glued caps will also have obvious uneven grayscale images on the sand sheet surface, which can also be identified by the grayscale difference method, which is accurate and effective.

[0076] It should be noted that when detecting and identifying the first type of defect information, the grayscale values ​​of each obtained sub-image block can be analyzed using Boolean operations.

[0077] As an optional implementation, the step of extracting contour information from the grayscale image and comparing the contour information with the database to determine whether the contour information belongs to the second type of defect information includes:

[0078] Extract the most prominent outer edge cusp of each gear plate region in the grayscale image to obtain contour information;

[0079] Fit all the outer edge cusps to a minimum circumcircle and obtain the diameter of the minimum circumcircle;

[0080] The diameter of the minimum circumscribed circle is compared with a preset standard value in the database to determine whether the contour information belongs to the second type of defect information.

[0081] In this embodiment, since both uneven distribution of abrasive pieces and out-of-roundness defects cause the outer edge of the abrasive pieces to protrude, when detecting and identifying the second type of defect information, the outer edge apex of each gear piece is extracted and fitted into a minimum circumcircle. If the minimum circumcircle is significantly larger or smaller than a preset standard value (the preset standard value can be a range value), it indicates that the gear pieces in the abrasive pieces are protruding outward or shrinking inward, which means that there is uneven distribution or out-of-roundness of the abrasive pieces, thereby achieving accurate identification of uneven distribution or out-of-roundness defects of the abrasive pieces.

[0082] It should be noted that when detecting and identifying Type II defect information, it is only necessary to make the outline clearly visible, so it is only necessary to make the product form a strong color contrast, and a long exposure time is not required.

[0083] As an optional implementation, acquiring the image of the sand disc to be inspected includes:

[0084] The setup includes a CCD camera and a light source. The CCD camera is used to acquire images, and the light source is used to illuminate the sand disc to be inspected. A CCD is a semiconductor device that converts optical images into digital signals. The tiny photosensitive materials embedded in a CCD are called pixels. The more pixels a CCD contains, the higher the image resolution it provides. The function of a CCD is similar to that of film, but it converts image pixels into digital signals to meet usage requirements.

[0085] It should be noted that the CCD camera should have a resolution of 2448*2048 or higher, a camera target area of ​​2 / 3", a camera object distance of 170mm, a camera field of view of 123mm*102mm, a pixel accuracy of 0.05mm / pixel, a distance of 130mm between the light source and the object being measured, and a vertical adjustment range of ±20mm for both the CCD camera and lens, as well as a vertical adjustment range of ±20mm for the light source, to meet the visual inspection requirements for sand discs.

[0086] As an optional implementation, before the step of setting the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white contrast, the following steps are also included:

[0087] A polarizer is installed below the CCD camera to filter out reflected light.

[0088] In this embodiment, when detecting and identifying the first type of defect information, especially when inspecting adhesive, a high exposure setting is required. However, increasing the exposure will cause bright spots on the product surface to affect the detection. Therefore, a polarizer needs to be added to the camera to filter out light reflected from other directions, minimizing the impact and ensuring the detection effect. When detecting and identifying the second type of defect information, a polarizer cannot be added because it will blur the detection edges, making it impossible to obtain the detection points and causing unstable assembly inspection.

[0089] As an optional implementation, before the step of extracting the most prominent outer edge cusp of each gear plate region in the grayscale image to obtain contour information, the following steps are also included:

[0090] The light source is set to blue light and arranged in a ring to make the edge of the sand disc to be tested clear.

[0091] In this embodiment, when detecting and identifying the second type of defect information, a blue ring light source is used, which can improve the edge clarity of the sand disc, facilitate camera recognition, and improve the image recognition accuracy.

[0092] As an optional implementation, the database includes a self-learning database, which stores defect type data corresponding to the unidentified sand sheet features.

[0093] In this embodiment, if a defect not present in the database is detected during the detection process, the defect type data corresponding to the unidentified sand sheet features can be stored through machine learning algorithms, thereby automatically improving the defect type data in the database to identify more defect types.

[0094] Images of qualified and unqualified sand discs (including various defect types) detected using the method of this application are shown below. Figure 9 as well as Figure 10-14 As shown, the imaging effect is good, the recognition is high, and it can accurately identify various defect types.

[0095] Example 2

[0096] Reference Figure 2 This embodiment provides a detection device for implementing the sand sheet disc defect detection method described in Embodiment 1. It includes a conveying device 100, an identification device 200, and an industrial control computer 300. The conveying device 100 and the identification device 200 are electrically connected to the industrial control computer 300. The conveying device 100 conveys the sand sheet disc to the area below the identification device 200. The identification device 200 acquires an image of the sand sheet disc to be inspected. The industrial control computer 300 processes and identifies the acquired image to determine whether the sand sheet disc to be inspected is a defective product. The conveying device 100 includes a housing 110, on which a drive motor 120 is mounted. A rotating disk is connected to the top of the drive motor 120. Multiple bases 140 are mounted on the top of the rotating disk, arranged in a circular array around the center of the rotating disk. Positioning posts 150 are provided around the top of each base 140. The sand sheet disc can be fitted onto the positioning posts 150. The rotating disk rotates the sand sheet disc to the area below the identification device 200.

[0097] Since the method in Example 1 requires individual testing of each sand sheet, if a traditional chain or belt conveyor is used to transport the sand sheet, there may be sand sheet overlap or the sand sheet position may be offset and not within the recognition range of the identification device 200, which will affect the detection results. Therefore, a new set of conveying device 100 needs to be designed to meet the current detection method. Therefore, in this embodiment, during operation, the circular hole of the sand disc base is aligned with the positioning post 150 and inserted, thereby positioning and installing the sand disc on the base 140 (this loading operation can be completed manually or automatically by a robotic arm). Then, the drive motor 120 drives the rotating disk to rotate at a certain angle, so that the sand disc on the corresponding base 140 rotates to be directly below the identification device 200. The identification device 200 then collects the image of the sand disc and transmits the image to the industrial control computer 300. The industrial control computer 300 processes and identifies the image to determine whether there are any defects. Compared with traditional chain or belt conveyors, the conveying device 100 in this embodiment occupies less space, can make reasonable use of space, and can realize the positioning of the sand disc and perform individual inspections to ensure the validity of the inspection results.

[0098] It should be noted that the drive motor 120 can be a stepper motor or a servo motor, which can precisely adjust the speed or direction to meet the usage requirements.

[0099] As an optional implementation, the identification device 200 includes a frame 210, with a CCD camera 230 and a supplementary lighting mechanism 220 disposed at the top of the frame 210. Both the CCD camera 230 and the supplementary lighting mechanism 220 are located above any base 140. The CCD camera 230 is used to acquire images of the sand disc to be inspected. The supplementary lighting mechanism 220 includes a connecting rod 221 connected to the top of the frame 210. A lampshade 222 is connected to the bottom of the connecting rod 221. The lampshade 222 is open at both the top and bottom. The CCD camera 230 is located directly above the lampshade 222. Multiple light sources 223 are disposed on the inner wall of the lampshade 222.

[0100] In this embodiment, the light source 223 can provide exposure for the CCD camera 230 and illuminate the sand plate at the same time, avoiding the presence of shadows on the sand plate which would be detrimental to the CCD camera 230 acquiring clear images, thereby ensuring the accuracy and recognizability of image acquisition.

[0101] As an optional implementation, it also includes a transfer device 400, which includes a first support column 410, a first motor 420 is disposed inside the first support column 410, a first rotating column 430 is connected to the top of the first motor 420, the first rotating column 430 extends movably out of the top of the first support column 410 and is connected to a crossbar 440, and a first gripping mechanism 450 is connected to the bottom of both sides of the crossbar 440, the first gripping mechanism 450 is used to grip and place the sand sheet disk to be tested.

[0102] In this embodiment, the sand sheet disks to be tested can be centrally placed in the product storage area. The sand sheet disks to be tested can be transferred and installed onto the base 140 of the conveying device 100 via the transfer device 400. In specific operation, after the first gripping mechanism 450 grips the sand sheet disk to be tested, the first motor 420 drives the first rotating column 430 to rotate 180°, so that the sand sheet disk gripped by the first gripping mechanism 450 rotates to the other side near the conveying device 100. Then, the first gripping mechanism 450 places the sand sheet disk on the base 140 of the conveying device 100. At the same time, the first gripping mechanism 450 on the other side of the crossbar 440 rotates to the side near the product storage area to be tested for gripping work. That is, the gripping and placement of the sand sheet disks are carried out simultaneously, which improves work efficiency and has a high degree of automation.

[0103] It should be noted that the first motor 420 is a stepper motor or a servo motor; the first gripping mechanism 450 can be gripped by electromagnetic adsorption, vacuum adsorption or a tensioning mechanism, or it can be an automated robotic arm. The mechanism for gripping and placing items is a relatively mature existing technology, and there are many ways to implement it. It should not be restricted here, and any method that meets the usage requirements can be applied.

[0104] As an optional implementation, a sorting robot 500 is also included. The sorting robot 500 includes a second pillar 510, a second motor 520 is disposed inside the second pillar 510, a second rotating column 530 is connected to the top of the second motor 520, the second rotating column 530 extends movably out of the top of the second pillar 510 and is connected to a first bracket 540 and a second bracket 550, and a second gripping mechanism 560 is disposed at the bottom of the side of the first bracket 540 and the second bracket 550 away from the second pillar 510. The second gripping mechanism 560 is used to grip and place the sand sheet disk after inspection.

[0105] In this embodiment, when a qualified product is detected, the sorting robot 500 operates. The second motor 520 drives the second rotating column 530 to rotate, causing the second gripping mechanism 560 on the first support 540 to rotate to a position close to the qualified product. Then, the second gripping mechanism 560 grips the qualified product, and the second motor 520 drives the second rotating column 530 to rotate back, so that the qualified product on the second gripping mechanism 560 rotates to the qualified product temporary storage area. Similarly, when a defective product is detected, the second gripping mechanism 560 on the second support 550 rotates to a position close to the defective product, grips it, and places the defective product in the defective product temporary storage area. The degree of automation is high.

[0106] It should be noted that the second motor 520 also uses a stepper motor or a servo motor; the second gripping mechanism 560 here adopts the same structure as the first gripping mechanism 450.

[0107] Example 3

[0108] A computer device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method described in Embodiment 1.

[0109] Example 4

[0110] A computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the method described in Embodiment 1.

[0111] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting defects in sand discs, characterized in that, Includes the following steps: Acquire images of the sand disc to be inspected; The image is converted to grayscale to obtain a grayscale image; The process involves extracting feature information from a grayscale image and comparing it with a database. The database stores defect type data corresponding to the features of the sand disc. This includes: extracting grayscale difference information from the grayscale image and comparing it with the database to determine if the grayscale difference information belongs to a first type of defect; where the first type of defect includes missing metal rings, glued caps, and glue residue; extracting contour information from the grayscale image and comparing it with the database to determine if the contour information belongs to a second type of defect; where the second type of defect includes uneven sand disc distribution and out-of-roundness; and further includes: extracting the most prominent outer edge apex of each gear disc region in the grayscale image to obtain contour information; fitting all the outer edge apex apex into a minimum circumcircle and obtaining the diameter of the minimum circumcircle; comparing the diameter of the minimum circumcircle with a preset standard value in the database to determine if the contour information belongs to a second type of defect. Based on the comparison results, determine whether the sand sheet to be tested is a defective product.

2. The method for detecting defects in sand sheet discs as described in claim 1, characterized in that, The step of extracting grayscale difference information from the grayscale image and comparing the grayscale difference information with the database to determine whether the grayscale difference information belongs to the first type of defect information includes: Set the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white distinction; The first image is segmented to obtain multiple sub-image blocks; The grayscale values ​​of multiple sub-image blocks are detected to obtain grayscale difference information; The grayscale difference information is compared with the preset grayscale values ​​in the database to determine whether the grayscale difference information belongs to the first type of defect information.

3. The method for detecting defects in sand sheet discs as described in claim 2, characterized in that, The acquisition of images of the sand disc to be inspected includes: Set up a CCD camera and a light source. The CCD camera is used to acquire images, and the light source is used to illuminate the sand disc to be inspected.

4. The method for detecting defects in sand sheet discs as described in claim 3, characterized in that, Before the step of setting the exposure of the grayscale image until the glue area and gear plate area in the grayscale image form a first image with clear black and white distinction, the method further includes the following steps: A polarizer is installed below the CCD camera to filter out reflected light.

5. The method for detecting defects in sand-coated discs as described in claim 3, characterized in that, Before the step of extracting the most prominent outer edge cusp of each gear plate region in the grayscale image to obtain contour information, the following steps are also included: The light source is set to blue light and arranged in a ring to make the edge of the sand disc to be tested clear.

6. The method for detecting defects in sand sheet discs as described in claim 1, characterized in that, The database includes a self-learning database, which stores defect type data corresponding to unidentified sand sheet features.

7. A testing device for implementing the sand disc defect detection method according to claim 1, characterized in that, The system includes a conveying device, an identification device, and an industrial control computer. Both the conveying device and the identification device are electrically connected to the industrial control computer. The conveying device transports the sand sheet disk below the identification device. The identification device acquires an image of the sand sheet disk to be inspected. The industrial control computer processes and identifies the acquired image to determine whether the sand sheet disk to be inspected is a defective product. The conveying device includes a housing, on which a drive motor is mounted. A rotating disk is connected to the top of the drive motor. Multiple bases are mounted on the top of the rotating disk, and the multiple bases are arranged in a circular array around the center of the rotating disk. Each base has a positioning post on its top. The sand sheet is fitted onto the positioning post. The rotating disk is used to rotate the sand sheet to a position below the identification device.

8. The detection device as described in claim 7, characterized in that, The identification device includes a frame, within which a CCD camera and a supplementary lighting mechanism are mounted at the top. Both the CCD camera and the supplementary lighting mechanism are located above any of the bases. The CCD camera is used to acquire images of the sand disc to be inspected. The supplementary lighting mechanism includes a connecting rod connected to the top of the frame, a lampshade connected to the bottom of the connecting rod, the lampshade being open at both the top and bottom, the CCD camera being located directly above the lampshade, and multiple light sources being provided on the inner wall of the lampshade.

Images