CN115855952A

CN115855952A - Method and equipment for detecting defects of flap disc

Info

Publication number: CN115855952A
Application number: CN202211503216.0A
Authority: CN
Inventors: 谢果
Original assignee: Mianyang Zhongyan Grinding Tool Co ltd
Current assignee: Mianyang Zhongyan Grinding Tool Co ltd
Priority date: 2022-11-28
Filing date: 2022-11-28
Publication date: 2023-03-28

Abstract

The application discloses a sand page disc defect detection method and detection equipment, wherein the detection method comprises the following steps: collecting an image of a sand page disc to be detected; carrying out graying processing on the image to obtain a grayscale image; extracting characteristic information in the gray level image, and inputting the characteristic information into a database for comparison; the database stores defect type data corresponding to the sand page disc characteristics; according to the comparison result, whether the current sand page disc to be detected belongs to a defective product or not is judged, and the method has the advantages of improving the accuracy of detecting the defects of the sand page disc and meeting the requirements of detecting the defects of the sand page disc.

Description

Method and equipment for detecting defects of flap disc

Technical Field

The application relates to the technical field of flap disc manufacturing, in particular to a flap disc defect detection method and detection equipment.

Background

The abrasive disc is a disc-shaped coated abrasive tool formed by bonding steel paper serving as a base body, silicon carbide or corundum serving as an abrasive and synthetic resin or other synthetic binders.

The sand page disc product with the standard of GBT 20962-2007 coated abrasive tool sand page disc is easily unqualified due to the influence of air pressure, temperature, vibration, glue viscosity and the like in the production process, quality detection is needed to select the unqualified products, and the existing detection method aims at the problems that the quality detection of the sand page disc is inaccurate, and the production cycle of the sand page disc is influenced due to the conditions of missing detection and wrong detection.

Disclosure of Invention

The application mainly aims to provide a flap disc defect detection method and detection equipment, and aims to solve the technical problem that the existing detection method is inaccurate in flap disc defect detection.

In order to achieve the above object, the present application provides a sand page disc defect detecting method, which includes the following steps:

collecting an image of a sand page disc to be detected;

carrying out graying processing on the image to obtain a grayscale image;

extracting characteristic information in the gray level image, and inputting the characteristic information into a database for comparison; the database stores defect type data corresponding to the sand page disc characteristics;

and judging whether the current sand page disc to be detected belongs to a defective product or not according to the comparison result.

Optionally, the extracting the feature information in the grayscale image, and entering the feature information into a database for comparison includes:

extracting gray difference information in the gray image, and comparing the gray difference information with the database to judge whether the gray difference information belongs to first-class defect information; the first type of defect information comprises an iron ring, a sticky cover and a sticky glue;

extracting contour information in the gray image, and comparing the contour information with the database according to the contour information to judge whether the contour information belongs to second type defect information; and the second type of defect information comprises uneven distribution and out-of-round of the sand slices.

Optionally, the extracting gray scale difference information in the gray scale image, and comparing the gray scale difference information with the database to determine whether the gray scale difference information belongs to the first type of defect information includes:

setting the exposure of a gray scale image until a glue area and a gear piece area in the gray scale image form a first image with clear black and white;

performing image segmentation on the first image to obtain a plurality of sub image blocks;

detecting gray values of a plurality of sub image blocks to obtain gray difference information;

and comparing the gray difference information with a preset gray value in the database to judge that the gray difference information belongs to first-class defect information.

Optionally, the extracting the contour information in the grayscale image, and comparing the contour information with the database according to the contour information to determine whether the contour information belongs to second type defect information includes:

extracting the most prominent outer edge sharp point of each gear piece area in the gray level image to obtain contour information;

fitting all the outer edge sharp points into a minimum circumscribed circle, and acquiring the diameter of the minimum circumscribed circle;

and comparing the diameter of the minimum circumscribed circle with a standard value preset in the database to judge whether the contour information belongs to second-class defect information.

Optionally, the collecting an image of the sand-leaf disc to be detected includes:

and (3) constructing a CCD camera and a light source, wherein the CCD camera is used for collecting images, and the light source is used for illuminating the flap disc to be detected.

Optionally, before the step of setting the exposure level of the gray scale image until the glue area and the gear piece area in the gray scale image form the first image with clear black and white, the method further comprises the following steps:

and a polaroid is built below the CCD camera and used for filtering reflected light.

Optionally, before the step of extracting the most prominent outer edge sharp point of each gear piece region in the grayscale image to obtain the contour information, the method further comprises the following steps:

the light source is set to be blue light and is arranged in an annular mode, so that the edge of the flap disc to be detected is clear.

Optionally, a self-learning database is arranged in the database, and the self-learning database is used for storing defect type data corresponding to the unrecognized sand page disc characteristics.

The detection device is used for realizing the sand page disc defect detection method and comprises a conveying device, an identification device and an industrial personal computer, wherein the conveying device and the identification device are both electrically connected with the industrial personal computer; wherein,

the conveying device comprises a case, a driving motor is arranged on the case, the top of the driving motor is connected with a rotating disc, a plurality of bases are arranged at the top of the rotating disc, the bases surround the center of the rotating disc and are distributed in an annular array mode, positioning columns are arranged on the top portions of the bases in a surrounding mode, the sand page disc can be sleeved on the positioning columns, and the rotating disc is used for rotating the sand page disc to the position below the recognition device.

Optionally, the identification device comprises a rack, a CCD camera and a light supplement mechanism are arranged at the top in the rack, the CCD camera and the light supplement mechanism are both located above any one of the bases, and the CCD camera is used for collecting an image of the flap disc to be detected; the light supplementing mechanism comprises a connecting rod connected to the top in the rack, a lampshade is connected to the bottom of the connecting rod, the lampshade is open vertically, the CCD camera is located right above the lampshade, and a plurality of groups of light sources are arranged on the inner wall of the lampshade.

The beneficial effect that this application can realize is as follows:

the method and the device have the advantages that the gray level image is obtained by carrying out gray level processing on the image of the sand page disc to be detected, the characteristic information in the gray level image is convenient to extract, the characteristic information is compared with the database, the defect type data corresponding to the sand page disc characteristics are stored in the database, whether the characteristic information of the current sand page disc to be detected is matched with the defect type data or not can be automatically judged and recognized, if the characteristic information is matched with the defect type data, the unqualified sand page disc is indicated, the automatic identification and judgment effects are realized, the process is mainly executed by depending on a computer, manual intervention is not needed, the error risk of manual identification is reduced, the accuracy of sand page disc defect detection is improved, the conditions of missing detection and error detection are not prone to exist, and the high-standard detection requirements are met.

Drawings

In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings that are needed in the detailed description of the present application or the technical solutions in the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.

Fig. 1 is a schematic flow chart of a method for detecting defects of a sand page disc in an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a detection apparatus according to an embodiment of the present application;

FIG. 3 is a schematic structural view of the left side view of FIG. 2;

FIG. 4 is a schematic structural diagram of a top view of FIG. 2 (omitting an industrial personal computer);

FIG. 5 is a schematic view of a conveyor apparatus according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a light supplement mechanism in an embodiment of the present application;

FIG. 7 is a schematic structural view of a transfer device in an embodiment of the present application;

fig. 8 is a schematic structural diagram of a sorting robot in an embodiment of the present application;

FIG. 9 is a schematic diagram of a certified product of a sand page disc detected by the present application;

FIG. 10 is a schematic diagram of the defective sand-leaf disc detected by the present application (iron ring removed);

FIG. 11 is a schematic diagram of a defective sand tray (stuck cover) detected by the present application;

FIG. 12 is a schematic illustration of a sandpage disc reject (stickies) detected by the present application;

FIG. 13 is a schematic diagram of defective sand trays (uneven distribution of sand flakes) detected by the present application;

fig. 14 is a schematic diagram of defective sand page plates (out of round) detected by the present application.

Reference numerals:

100-conveying device, 110-cabinet, 120-driving motor, 130-rotating disc, 140-base, 150-positioning column, 200-recognition device, 210-frame, 220-light supplement mechanism, 221-connecting rod, 222-lamp shade, 223-light source, 230-CCD camera, 300-industrial computer, 400-transfer device, 410-first support column, 420-first motor, 430-first rotating column, 440-cross bar, 450-first grabbing mechanism, 500-sorting robot, 510-second support column, 520-second motor, 530-second rotating column, 540-first support column, 550-second support column, 560-second grabbing mechanism.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that all the directional indicators (such as upper, lower, left, right, front, and rear … …) in the present embodiment are only used to explain the relative position relationship between the components, the movement situation, and the like in a specific posture, and if the specific posture is changed, the directional indicator is changed accordingly.

In this application, unless expressly stated or limited otherwise, the terms "connected," "secured," and the like are to be construed broadly, and thus, for example, "secured" may be a fixed connection, a removable connection, or an integral part; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

In addition, if there is a description relating to "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In addition, the meaning of "and/or" appearing throughout includes three juxtapositions, exemplified by "A and/or B" including either A or B or both A and B. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present application.

Example 1

Referring to fig. 1, the present embodiment provides a method for detecting defects of a sand page disc, including the following steps:

collecting an image of a sand page disc to be detected;

carrying out graying processing on the image to obtain a grayscale image;

In the prior art, all unqualified products can become qualified products through repairing before solidification, and if the unqualified products are solidified, the unqualified products can not be repaired and can only become waste products, so that the online detection is required to be provided before the products are solidified, the unqualified products are selected, and the industry adopts two modes to produce at present: firstly, the detection is carried out by naked eyes of an operator, but the efficiency is low, the strength is high, the missing rate is high, and a plurality of devices cannot be operated by one person; and secondly, the unqualified products selected are degraded or scrapped without detection and are selected before being packaged after solidification, and although the unqualified products are not selected, the production efficiency can be improved, for example, one person operates a plurality of devices, the scrappage of more than 1% causes great resource waste.

Therefore, in the embodiment, the image of the sand page disc to be detected is grayed to obtain the grayscale image, so that the feature information in the grayscale image is convenient to extract, and the feature information is compared with the database, and because the database stores the defect type data corresponding to the sand page disc features, whether the feature information of the current sand page disc to be detected is matched with the defect type data or not can be automatically judged and identified, if so, the sand page disc to be detected belongs to a defective product, so that the automatic identification and judgment are realized.

It should be noted that when detecting whether the sand page disc belongs to the unqualified product, an alarm message can be sent, and then the unqualified product can be sorted manually or automatically.

As an optional implementation manner, the extracting feature information in the grayscale image, and entering the feature information into a database for comparison includes:

extracting contour information in the gray image, and comparing the contour information with the database to judge whether the contour information belongs to second type defect information; and the second type of defect information comprises uneven distribution and out-of-round of the sand slices.

In the embodiment, the defects of the flap disc mainly comprise an iron ring, a sticky cover, viscose glue, uneven distribution of sand pieces and out-of-round glue, wherein the iron ring is lost, the sticky cover is that a base body part in the middle of the flap disc is lost, the sticky cover is that a cover body part on the back of the sand piece is stuck and misplaced on the front of the sand piece, the viscose glue is that the glue overflows to the surface of the sand piece, the uneven distribution of the sand piece is that the gear pieces (the sand piece is composed of a plurality of gear pieces) are unevenly distributed, and the out-of-round glue is that the outer contour of the sand piece is uneven and has a protrusion, so that a full circle cannot be formed; the defects of the iron ring, the cover and the viscose can cause the surface of the whole sand page disc to form obvious abnormal shapes, so that the gray difference information in the gray image is extracted, namely whether the gray image has gray difference or not is compared, and if the gray image has obvious difference, one of the defect types is judged to exist; the defects of uneven distribution and out-of-round of the sand flakes do not have obvious abnormal shapes on the surface of the whole sand page disc, so that the defects of uneven distribution and out-of-round of the sand flakes can be proved by extracting the contour information in the gray level image, namely identifying whether the outer edge in the gray level image is obviously protruded or not and if the outer edge in the gray level image is obviously protruded.

It should be noted that, according to the production requirement, the defects of uneven distribution and out-of-round of the sand pieces are small, which can meet the requirement of using as inferior-quality products, and the defects of iron ring dropping, cover sticking and glue sticking are large, so that the identification of the first type of defect information is a necessary step, and the identification of the second type of defect information can be omitted according to the process requirement, namely: the step of identifying only the first type of defect information can be preset, the step of identifying the first type of defect information and the step of identifying the second type of defect information simultaneously can also be preset, and the defective products are judged to be unqualified products as long as any defect information is identified. According to the embodiment, different targeted detection methods are adopted for different defect types of the sand page disc, the detection result is more accurate, so that the high-standard detection requirement is met, the detection type can be flexibly selected according to the actual condition, and the flexibility is strong.

As an optional implementation manner, the extracting gray scale difference information in the gray scale image, and comparing the gray scale difference information with the database to determine whether the gray scale difference information belongs to the first type of defect information includes:

In this embodiment, when detecting and identifying the first type of defect information, particularly the adhesive defect, it is necessary to set the exposure to be very large, so that the glue can be obviously presented to form a first image with clear black and white, then perform image segmentation on the first image to obtain a plurality of sub-image blocks, perform individual gray value identification on each sub-image block, and when comparing the gray value of any sub-image block with the preset gray value in the database, if there is a difference in gray value of any sub-image block, it is determined that the first type of defect information exists, thereby implementing accurate detection on the adhesive defect.

When the first type defect information is detected and identified, the obtained gray value of each sub image block may be analyzed by boolean operation.

As an optional implementation manner, the extracting the contour information in the grayscale image, and comparing the contour information with the database according to the contour information to determine whether the contour information belongs to the second type of defect information includes:

and comparing the diameter of the minimum circumscribed circle with a standard value preset in the database to judge whether the profile information belongs to second-class defect information.

In this embodiment, because the defects of uneven distribution and out-of-round of the abrasive pieces cause the outer edges of the abrasive pieces to have protrusions, when the second type of defect information is detected and identified, the outer edge cusps of each gear piece are extracted and fitted into a minimum circumscribed circle, and if the minimum circumscribed circle is obviously greater than or less than a preset standard value (the preset standard value can be a range value), the gear pieces in the abrasive pieces are indicated to protrude outwards or contract inwards, that is, the condition that the distribution of the abrasive pieces is uneven or the sand is out-of-round is indicated, so that the defect of uneven distribution or out-of-round of the abrasive pieces is accurately identified.

When the second type of defect information is detected and identified, only the outline needs to be clearly displayed, so that the product only needs to be formed into a sharp color contrast, and a large exposure time is not needed.

As an optional implementation manner, the acquiring an image of the sand-paper disc to be detected includes:

and (3) constructing a CCD camera and a light source, wherein the CCD camera is used for collecting images, and the light source is used for illuminating the flap disc to be detected. The CCD is a semiconductor device which can convert optical images into digital signals, the micro photosensitive material implanted on the CCD is called pixels (pixels), the more the number of pixels contained on one CCD, the higher the image resolution provided by the CCD, the CCD acts like a film, but the CCD converts image pixels into digital signals, and the use requirement is met.

It should be noted that the pixels of the CCD camera should be 2448 × 2048 or more, the camera target surface should be 2/3", the camera object distance should be 170mm, the camera view should be 123mm × 102mm, the pixel accuracy should be 0.05mm/pixel, the distance between the light source and the object to be measured should be 130mm, the up-down adjustable space of the CCD camera and the lens should be ± 20mm, and the up-down adjustable space of the light source should be ± 20mm, so as to meet the visual inspection requirement for the sand-leaf disk.

As an optional implementation manner, before the step of setting the exposure level of the gray scale image until the glue area and the gear piece area in the gray scale image form the first image with clear black and white, the method further includes the following steps:

In the embodiment, when the first type of defect information is detected and identified, particularly when glue is detected, exposure needs to be set to be large, but after exposure is increased, bright spots on the surface of a product can affect detection, so that a polarizer needs to be added at a camera to filter light reflected from other directions, so as to ensure that the influence is reduced to the minimum, and thus, the detection effect is ensured. When the second type of defect information is detected and identified, the polaroid cannot be added, and the detected edge is blurred, so that point positions cannot be obtained, and the assembly detection is unstable.

As an optional implementation manner, before the step of extracting the most prominent outer edge cusp of each gear piece region in the grayscale image to obtain the contour information, the method further includes the following steps:

the light source is set to be blue light and is arranged in an annular shape, so that the edge of the flap disc to be detected is clear.

In this embodiment, when detecting discernment second type defect information, adopt blue annular light source, can improve sand page or leaf dish's marginal definition, the camera discernment of can being convenient for to be favorable to the degree of discernment of formation of image.

As an optional implementation manner, a self-learning database is arranged in the database, and the self-learning database is used for storing defect type data corresponding to the unidentified sand page disc characteristics.

In the embodiment, in the detection process, if a defect which does not exist in the database is detected, the defect type data corresponding to the unrecognized sand page disc features can be stored through a machine learning algorithm, so that the defect type data in the database can be automatically perfected to recognize more defect types.

The images of the qualified sand page disc and the images of the unqualified sand page disc (including various defect types) detected by the method are respectively shown in the figure 9 and the figures 10-14, the imaging effect is good, the identification degree is high, and various defect types can be accurately identified.

Example 2

Referring to fig. 2, the embodiment provides a detection device for implementing the method for detecting the defect of the sand page disc in embodiment 1, which includes a conveying device 100, a recognition device 200 and an industrial personal computer 300, wherein the conveying device 100 and the recognition device 200 are both electrically connected to the industrial personal computer 300, the conveying device 100 is used for conveying the sand page disc to the position below the recognition device 200, the recognition device 200 is used for acquiring an image of the sand page disc to be detected, and the industrial personal computer 300 is used for processing and recognizing the acquired image to determine whether the sand page disc to be detected belongs to a defective product; the conveying device 100 comprises a case 110, a driving motor 120 is arranged on the case 110, a rotating disc is connected to the top of the driving motor 120, a plurality of bases 140 are arranged on the top of the rotating disc, the bases 140 surround the center of the rotating disc and are distributed in an annular array, positioning columns 150 are arranged on the top portions of the bases 140 in an enclosing mode, the sand page disc can be sleeved on the positioning columns 150, and the rotating disc is used for rotating the sand page disc to the position below the recognition device 200.

Since each flap disc needs to be individually detected in the method of embodiment 1, if the flap discs are conveyed by a conventional chain or belt conveyor, the flap discs may overlap, and the position of the flap disc is shifted and not within the identification range of the identification device 200, which may affect the detection result, a set of conveying device 100 needs to be redesigned to meet the current detection method. Therefore, in this embodiment, during operation, the circular hole of the sand page disc base is aligned with the positioning column 150 to be sleeved in, so as to position and mount the sand page disc on the base 140 (the feeding operation can be completed manually or automatically by a mechanical arm), then the driving motor 120 drives the rotating disc to rotate by a certain angle, so that the sand page disc on the corresponding base 140 rotates to a position under the identification device 200, then the image of the sand page disc is collected by the identification device 200 and transmitted to the industrial personal computer 300, and the industrial personal computer 300 processes and identifies the image to judge whether the defect exists.

It should be noted that the driving motor 120 may be a stepping motor or a servo motor, and the rotation speed or the rotation direction may be precisely adjusted to meet the use requirement.

As an optional embodiment, the recognition device 200 includes a frame 210, a CCD camera 230 and a light supplementing mechanism 220 are disposed at the top inside the frame 210, the CCD camera 230 and the light supplementing mechanism 220 are both located above any one of the bases 140, and the CCD camera 230 is used for collecting an image of the sand-leaf disc to be detected; the light supplementing mechanism 220 comprises a connecting rod 221 connected to the top of the inside of the frame 210, the bottom of the connecting rod 221 is connected with a lampshade 222, the lampshade 222 is open vertically, the CCD camera 230 is located right above the lampshade 222, and a plurality of groups of light sources 223 are arranged on the inner wall of the lampshade 222.

In this embodiment, the light source 223 can provide exposure for the CCD camera 230, illuminate the sand page disc at the same time, and avoid the sand page disc to have shadow which is unfavorable for the CCD camera 230 to acquire clear images, thereby ensuring the accuracy and the recognition degree of image acquisition.

As an optional implementation manner, the transfer device 400 is further included, the transfer device 400 includes a first support column 410, a first motor 420 is disposed in 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 movably extends out of the top of the first support column 410 and is connected to a cross rod 440, the bottoms of two sides of the cross rod 440 are both connected to a first grabbing mechanism 450, and the first grabbing mechanism 450 is used for grabbing and placing the flap disc to be detected.

In this embodiment, can concentrate to place the flap disc that waits to detect and wait to detect the product memory area, can transport the flap disc that waits to detect through transfer device 400 and install on conveyor 100's base 140, during specific operation, after first grabbing mechanism 450 snatchs the flap disc that waits to detect, first motor 420 drives first column spinner 430 and rotates 180, make the flap disc that first grabbing mechanism 450 snatched rotate to the opposite side and be close to conveyor 100, then first grabbing mechanism 450 puts the flap disc onto conveyor 100's base 140, the first grabbing mechanism 450 of horizontal pole 440 opposite side rotates to being close to waiting to detect the product memory area simultaneously, in order to snatch the work, the snatching and putting of flap disc are gone on in step, and the work efficiency is improved, and degree of automation is high.

It should be noted that the first motor 420 is a stepping motor or a servo motor; the first grabbing mechanism 450 can adopt an electromagnetic adsorption, vacuum adsorption or expansion mechanism clamping mode, and also can adopt an automatic robot arm, the mechanism for clamping and placing the articles belongs to the mature prior art, the realization mode is more, the first grabbing mechanism is not limited, and the first grabbing mechanism can be suitable for meeting the use requirement.

As an optional implementation manner, the sorting robot 500 is further included, the sorting robot 500 includes a second support column 510, a second motor 520 is disposed in the second support column 510, a second rotating column 530 is connected to the top of the second motor 520, the second rotating column 530 movably extends out of the top of the second support column 510 and is connected to a first support 540 and a second support 550, a second grabbing mechanism 560 is disposed at the bottom of each of the first support 540 and the second support 550, which is far away from the second support column 510, and the second grabbing mechanism 560 is used for grabbing and placing the detected sand-leaf discs.

In this embodiment, when a qualified product is detected, the sorting robot 500 operates, the second motor 520 drives the second rotary column 530 to rotate, so that the second grabbing mechanism 560 on the first support 540 rotates to a position close to the qualified product, then the second grabbing mechanism 560 grabs the qualified product, and the second motor 520 drives the second rotary column 530 to rotate, so as to drive the qualified product on the second grabbing mechanism 560 to rotate to the temporary storage area of the qualified product; similarly, when an unqualified product is detected, the second grabbing mechanism 560 on the second support 550 is rotated to a position close to the unqualified product, and the unqualified product is placed in the temporary storage area of the unqualified product after grabbing, so that the automation degree is high.

It should be noted that the second motor 520 also adopts a stepping motor or a servo motor; here, the second grasping mechanism 560 adopts the same structure as the first grasping mechanism 450.

Example 3

A computer device comprising a memory having a computer program stored therein and a processor executing the computer program to implement the method as described in embodiment 1.

Example 4

A computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the method as described in embodiment 1.

The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.

Claims

1. A sand page disc defect detection method is characterized by comprising the following steps:

collecting an image of a sand page disc to be detected;

carrying out graying processing on the image to obtain a grayscale image;

2. The method for detecting the defect of the sand page disc as claimed in claim 1, wherein the step of extracting the characteristic information in the gray image and inputting the characteristic information into a database for comparison comprises the following steps:

3. The method as claimed in claim 2, wherein said extracting gray scale difference information from the gray scale image, and comparing the gray scale difference information with the database to determine whether the gray scale difference information belongs to a first type of defect information comprises:

4. The method as claimed in claim 3, wherein said extracting the contour information in the gray image, and comparing the contour information with the database to determine whether the contour information belongs to the second type of defect information comprises:

5. The sand page disc defect detecting method as claimed in claim 4, wherein the collecting the image of the sand page disc to be detected comprises:

and constructing a CCD camera and a light source, wherein the CCD camera is used for collecting images, and the light source is used for illuminating the flap disc to be detected.

6. The sand page disc defect detecting method as claimed in claim 5, wherein the step of setting the exposure level of the gray scale image until the glue area and the gear piece area in the gray scale image form a first image with clear black and white is further comprised by the following steps:

and a polarizer is built below the CCD camera and used for filtering reflected light.

7. The sand page disc defect detecting method as claimed in claim 5, wherein before the step of extracting the most prominent outer edge sharp point of each gear piece area in the gray scale image to obtain the contour information, the method further comprises the following steps:

8. The method for detecting the defect of the sand page disc is characterized in that a self-learning database is arranged in the database and used for storing defect type data corresponding to the unidentified sand page disc characteristics.

9. A detection device is used for realizing the sand-shale disc defect detection method of claim 1, and is characterized by comprising a conveying device, a recognition device and an industrial personal computer, wherein the conveying device and the recognition device are both electrically connected with the industrial personal computer, the conveying device is used for conveying the sand-shale disc to the position below the recognition device, the recognition device is used for collecting images of the sand-shale disc to be detected, and the industrial personal computer is used for processing and recognizing the collected images so as to judge whether the sand-shale disc to be detected belongs to unqualified products or not; wherein,

the conveying device comprises a case, a driving motor is arranged on the case, the top of the driving motor is connected with a rotating disc, a plurality of bases are arranged on the top of the rotating disc and surround the center of the rotating disc to be distributed in an annular array mode, positioning columns are arranged on the top portions of the bases in a surrounding mode, the sand page disc can be sleeved on the positioning columns, and the rotating disc is used for rotating the sand page disc to the position below the recognition device.

10. The detection device according to claim 9, wherein the recognition device comprises a frame, a CCD camera and a light supplementing mechanism are arranged at the top in the frame, the CCD camera and the light supplementing mechanism are both located above any one of the bases, and the CCD camera is used for collecting images of the sand-leaf disc to be detected; wherein,

the light supplementing mechanism comprises a connecting rod connected to the top in the rack, the bottom of the connecting rod is connected with a lampshade, the lampshade is open at the upper part and the lower part, the CCD camera is located right above the lampshade, and a plurality of groups of light sources are arranged on the inner wall of the lampshade.