CN220490706U - Equipment for on-line detecting impurity inside toughened glass - Google Patents
Equipment for on-line detecting impurity inside toughened glass Download PDFInfo
- Publication number
- CN220490706U CN220490706U CN202222566478.3U CN202222566478U CN220490706U CN 220490706 U CN220490706 U CN 220490706U CN 202222566478 U CN202222566478 U CN 202222566478U CN 220490706 U CN220490706 U CN 220490706U
- Authority
- CN
- China
- Prior art keywords
- linear array
- glass
- camera
- toughened glass
- digital image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000005341 toughened glass Substances 0.000 title claims abstract description 55
- 239000012535 impurity Substances 0.000 title claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 57
- 239000011521 glass Substances 0.000 claims abstract description 52
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 230000010287 polarization Effects 0.000 claims description 4
- 238000005096 rolling process Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 13
- 239000000428 dust Substances 0.000 abstract description 8
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 description 22
- 238000000034 method Methods 0.000 description 7
- 239000000523 sample Substances 0.000 description 6
- 239000002245 particle Substances 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- WWNBZGLDODTKEM-UHFFFAOYSA-N sulfanylidenenickel Chemical compound [Ni]=S WWNBZGLDODTKEM-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses equipment for detecting impurities in toughened glass on line, which comprises a polarized light source, a roller conveyor belt, a glass test piece to be detected, a linear array camera, a detection sensor and a digital image processor, wherein the roller conveyor belt is arranged on the roller conveyor belt; the equipment for online detecting the impurities in the toughened glass is simple, low in manufacturing cost, low in detection environment dependence and high in popularization rate, and the digital image processor performs subtraction operation on a group of images shot by the linear camera, so that the influence of dust fall and ambient light on a detection result is avoided to a great extent; the equipment provided by the utility model can identify specific conditions such as scratch damage on the surface of the glass, effectively reduce false detection and omission rate of inclusion detection in the toughened glass, improve quality inspection reliability, and is more energy-saving and environment-friendly.
Description
Technical Field
The utility model relates to the technical field of detecting impurities in toughened glass, in particular to equipment for detecting the impurities in the toughened glass on line.
Background
In recent years, the breakage accident of the glass curtain wall frequently occurs, the breakage of the glass curtain wall has a great hidden trouble to the life and property safety of people, the self-explosion and the breakage of the toughened glass can be generally attributed to impurities and defects contained in the glass, and the contained impurities mainly comprise nickel sulfide stones, simple substance silicon or other heterogeneous phase particles; the defects mainly comprise bubbles and holes, surface damage caused by external particle impact or corrosion and the like, and the germination and expansion of cracks in the tempered glass are mainly caused by the comprehensive effect of residual tensile stress caused by heterogeneous particles and the residual stress of the glass in a service state; besides, the glass curtain wall and doors and windows are adopted, the delivery of the smart phone in China is 3 hundred million meters early, the cover plate of the smart phone is toughened glass which is subjected to toughening treatment, and the service life of the smart phone can be greatly influenced if the defective glass cover plate of the smart phone is used; therefore, detection is performed before toughened glass leaves a factory, and it is important to avoid that the toughened glass with defects flows into the market for use, so that development of a method and equipment capable of detecting the toughened glass on line, so that the glass with problems is detected on a production line, and it is important to avoid that the toughened glass with defects flows into the market for use.
In the existing detection mode, a few parts adopt foreign equipment to carry out laser scanning imaging, and defect detection is carried out in an image recognition mode, so that the laser detection has very high environmental dependence degree, the whole set of equipment has very high price, and the cost reaches 2-3 ten million yuan, so that the detection method can be born by far from a general small factory; at present, only a few large factories use foreign equipment for online detection in China, and no corresponding standard matching equipment exists in China.
At present, the detection technology mainly adopted in China is that a single-line-array camera rapidly scans glass pieces, and then an image recognition or machine learning method is adopted to recognize defects in the glass pieces; however, the method is easy to be influenced by transparent impurities such as dust falling on the surface of the glass and bubbles in the glass, so that misjudgment is caused; and the scratch damage on the surface of the glass cannot be identified.
Accordingly, a person skilled in the art has been dedicated to developing an apparatus for on-line detecting impurities inside tempered glass, aiming at solving the problem of defects existing in the apparatus for on-line detecting impurities inside tempered glass in the prior art.
Disclosure of Invention
In view of the defects in the prior art, the technical problem to be solved by the utility model is that the existing equipment for detecting the impurities in the toughened glass on line has high price and high requirements on detection environment; domestic equipment is easily influenced by transparent impurities such as dust falling on the surface of glass, bubbles in the glass and the like, and the scratch damage on the surface of the glass is difficult to identify.
In order to achieve the above purpose, the utility model provides equipment for online detecting impurities in toughened glass, which comprises a polarized light source, a roller conveyor belt, a glass test piece to be detected, a linear array camera, a detection sensor and a digital image processor, wherein the polarized light source is arranged on the roller conveyor belt;
the polarized light source is positioned below the roller conveyor belt, polarized light rays emitted by the polarized light source irradiate the glass test piece to be tested through a gap of the roller conveyor belt, and the polarized light rays penetrate the glass test piece to be tested and are received by the linear array camera;
the number of the linear array cameras is 2 or 4, and the linear array cameras are all positioned right above the gap of the rolling shaft;
the linear array cameras are arranged in pairs side by side or front and back, polaroids are arranged in front of camera lenses or camera targets of the linear array cameras, every two linear array cameras are in a group, and the polaroids arranged by each linear array camera have different polarization directions;
the digital image processor is connected with the linear array camera through a wire, and the digital image processor and the linear array camera are electrically connected;
the linear array camera is connected with the object detection sensor through a wire, and the linear array camera and the object detection sensor are electrically connected;
1-4 detection sensors are arranged above or on the side surface of the glass test piece to be tested;
further, the number of the linear array cameras is an even number;
further, the object detection sensor is a reflection type object detection sensor, whether the glass test piece to be detected passes through the linear array camera or not is detected through whether reflected light exists, when the glass test piece to be detected passes through the linear array camera, the linear array camera is triggered to take a picture, and when the glass test piece to be detected passes through the object detection sensor completely, the linear array camera is stopped to take a picture in time;
further, the digital image processor is electrically connected with the linear camera; taking a group of two cameras as an example, the images shot by the two cameras are respectively recorded as I 1 ，I 2 The method comprises the steps of carrying out a first treatment on the surface of the The digital image processor is acquiring I 1 And I 2 Then, coordinate matching is firstly carried out on the two images, and the pixel positions of the same physical point on the two images are found; then subtracting the images of the same physical point shot by a group of cameras on the glass test piece to be tested;
furthermore, after the subtraction operation processing is carried out on the digital image processor, stripe patterns with peculiar shapes appear around the inclusions on the processed image, the distribution range of the patterns is much larger than the size of the defects, the gray level change gradient is large, and the pattern features with extremely large gradient change do not appear at the places without the inclusions, so that the recognition degree of the defects is increased, and the omission ratio is reduced;
further, the digital image processor performs defect identification by using a photoelastic principle: the internal defect of the toughened glass, whether transparent or not, can generate more obvious stress concentration on the glass around the toughened glass, and the intensity of the toughened glass is reflected on the processed image to be more violently changed (namely, larger gradient);
further, the digital image processor performs subtraction operation on a group of images shot by the linear camera, so that influence of dust fall and ambient light on image gray scale is avoided; the false detection rate of the inclusion detection in the toughened glass is effectively reduced;
in a specific embodiment of the utility model, the number of the linear array cameras is 2, and the linear array cameras are arranged side by side;
in a specific embodiment of the utility model, the number of the object detection sensors is 1, and the object detection sensors are positioned on the side surface of the glass test piece to be detected;
in a specific embodiment of the utility model, the model of the digital image processor is MCIMX27VOP4ABGA-404;
by adopting the scheme, the equipment for on-line detecting the impurities in the toughened glass has the following technical effects
1. The equipment for detecting the impurities in the toughened glass on line is simple, low in detection environment dependence degree, low in manufacturing cost of the whole equipment and capable of being popularized and detected in most factories;
2. according to the equipment for on-line detection of the impurities in the toughened glass, the object detection sensor is electrically connected with the linear array camera, the linear array camera is activated when detection is needed, and the camera is triggered to take a picture, so that the equipment is more power-saving, energy-saving and environment-friendly; the combination of the linear array cameras increases the identification degree of defects;
3. according to the equipment for detecting the impurities in the toughened glass on line, subtraction operation is carried out between a group of images shot by the linear camera by the digital image processor, so that the influence of dust fall and ambient light on the gray level of the images is avoided; and specific conditions such as scratch damage and the like on the surface of the glass can be identified; the false detection rate and the omission rate of the inclusion detection in the toughened glass are effectively reduced;
in summary, the device for detecting the impurities in the toughened glass on line has low dependence on detection environment, low manufacturing cost and high popularization rate, and the influence of dust fall on the image gray scale is avoided by the unique design of the device; and specific conditions such as scratch damage and the like on the surface of the glass can be identified; the defect recognition degree is increased, and the false detection rate and the omission rate of the inclusion detection in the toughened glass are effectively reduced; and is more energy-saving and environment-friendly.
The conception, specific structure, and technical effects of the present utility model will be further described with reference to the drawings and the detailed description to fully understand the objects, features, and effects of the present utility model.
Drawings
Fig. 1 is a schematic structural view of an apparatus for on-line detecting impurities inside tempered glass according to the present utility model;
FIG. 2 is a flowchart showing the operation of the apparatus for on-line detecting the foreign substances inside the tempered glass according to the present utility model;
in the figure, 1, a polarized light source; 2. a roller conveyor belt; 3. a glass test piece to be tested; 4. a line camera; 5. a probe sensor; 6. a digital image processor.
Detailed Description
The following description of the preferred embodiments of the present utility model refers to the accompanying drawings, which make the technical contents thereof more clear and easier to understand. This utility model may be embodied in many different forms of embodiments and should not be construed as limited to the embodiments set forth herein.
In the drawings, like structural elements are referred to by like reference numerals and components having similar structure or function are referred to by like reference numerals. The dimensions and thickness of each component shown in the drawings are arbitrarily shown, and the present utility model is not limited to the dimensions and thickness of each component. The thickness of the components is exaggerated in some places in the drawings for clarity of illustration.
As shown in fig. 1, the equipment for on-line detecting the impurities in the toughened glass comprises a polarized light source 1, a roller conveyor belt 2, a glass test piece 3 to be detected, a linear camera 4, a probe sensor 5 and a digital image processor 6;
the polarized light source 1 is positioned below the roller conveyor belt 2, polarized light rays emitted by the polarized light source 1 irradiate onto the glass test piece 3 to be tested through a gap of the roller conveyor belt 2, and the polarized light rays penetrate through the glass test piece 3 to be tested and are received by the linear camera 4;
the number of the linear array cameras 4 is 2, and the linear array cameras 4 are all positioned right above the gap of the rolling shaft; the linear array cameras 4 are arranged side by side, the polaroids are arranged in front of the camera lenses or the camera targets of the linear array cameras 4, the polarization axes of the polaroids arranged by the linear array cameras 4 have different phase difference angles, and the images shot by a group of two cameras are respectively marked as I 1 ，I 2 ；
The number of the object detection sensors 5 is 1, and the object detection sensors are positioned on the side face of the glass test piece 3 to be tested; the object detection sensor 5 is a reflective object detection sensor 5, whether the glass test piece 3 to be detected passes through the linear array camera 4 or not is detected by emitting reflected light, when the glass test piece 3 to be detected passes through the linear array camera 4, the linear array camera 4 is triggered to take a picture, and when the glass test piece 3 to be detected completely passes through the object detection sensor 5, the linear array camera 4 is timely dormant;
the digital image processor 6 is connected with the linear array camera 4 through a wire, and the digital image processor and the linear array camera are electrically connected; the linear array camera 4 is connected with the object detection sensor 5 through a wire, and the two are electrically connected;
the digital image processor 6 is electrically connected with the linear array camera 4, and the images shot by a group of two cameras are respectively marked as I 1 ，I 2 The method comprises the steps of carrying out a first treatment on the surface of the The digital image processor 6 is acquiring I 1 And I 2 After that, the two graphs will be first coordinate matched:
i.e. finding the pixel position of the same physical point on both images; then aiming at the image (I) of the same physical point shot by a group of cameras on the glass test piece 3 to be tested 1 、I 2 ) Performing subtraction operation; after subtraction processing, the digital image processor 6 generates a stripe pattern with a peculiar shape around the inclusions on the processed image, the distribution range of the pattern is much larger than the size of the defect, the gradient of gray level change is large, and the pattern feature with a great gradient change does not appear at the place without the inclusions;
the digital image processor 6 performs defect recognition using the photoelastic principle: the internal defect of the toughened glass, whether transparent or not, can generate more obvious stress concentration on the glass around the toughened glass, and the intensity of the toughened glass is more severely changed when reflected on the processed image, namely, a larger gradient exists;
in the present embodiment, in the case of the present embodiment,
the model of the digital image processor is MCIMX27VOP4ABGA-404;
example 1 quality inspection of 100 tempered glass pieces in a batch from a tempered glass curtain wall manufacturer using the apparatus of the present utility model
The operational workflow diagram of the device is shown in fig. 2; the use is the factory quality inspection of a certain toughened glass curtain wall manufacturer, and the equipment is arranged behind the factory quality inspection flow;
when the device is used, the device is electrified, a polarized light source below the roller conveyor belt emits polarized light, the roller conveyor belt starts to move at a constant speed, a reflective object detection sensor arranged on the side surface of a to-be-detected sample starts to work, the reflective object detection sensor emits light forward, when the to-be-detected sample passes through, the reflected light returns to judge that the to-be-detected glass is coming, a linear array camera is activated to start to work, at the moment, along with the continuous movement of the roller conveyor belt, the to-be-detected glass sample gradually passes through two linear array cameras in a side-by-side mode, the linear array cameras photograph the to-be-detected glass sample, and images photographed by the two cameras are respectively recorded as I 1 ，I 2 The method comprises the steps of carrying out a first treatment on the surface of the Camera acquisition I 1 And I 2 Then, coordinate matching is firstly carried out on the two images, and the pixel positions of the same physical point on the two images are found; then the images are transmitted back to the digital image processor, and the digital image processor performs subtraction operation on the images of the same physical point shot by a group of cameras on the glass test piece to be tested;
the subtraction operation adopted by the specific implementation on the image is I 3 ＝(I 1 -I 2 )×255/(I 1 +I 2 ) The method comprises the steps of carrying out a first treatment on the surface of the According to a certain algorithm, obtaining a result I 3 Judging and identifying; in case of finding I 3 If the local gray level is changed rapidly, the defect of inclusion in the glass to be detected is indicated;
finally, the number of blocks of the toughened glass passing the quality inspection is 95, 5 blocks of which the number is totally 5 and the prompt information is problematic are output, wherein 2 blocks of the toughened glass have heterogeneous phase particles, 2 blocks of the toughened glass have transparent inclusions such as bubbles and the like, and 1 block of the toughened glass have surface scratches; finally, rechecking 100 pieces of toughened glass manually, wherein 5 pieces of toughened glass have the defect problem corresponding to the rechecked glass, and the detection accuracy of the equipment is 100%.
Comparative example 1, using a conventional single-line camera to rapidly scan a glass test piece to be tested, and then performing quality inspection on 100 pieces of toughened glass in a batch of a certain toughened glass curtain wall manufacturer by adopting image recognition
The quality inspection of the comparative example 1 and the quality inspection of the example 1 are carried out in the same batch, after a traditional single-line array camera rapidly scans a glass test piece to be detected, the shot scanning image is uploaded to a computer host after machine learning to carry out image recognition, and after comparison, the computer host outputs an image recognition result;
the quality inspection passes through 97 blocks, 3 blocks have defect problems, then the quality inspection is manually repeated one by one, two blocks of 3 blocks outputting an image recognition result are found to have defects of heterogeneous phase particles, the other block is misjudgment caused by the fact that floating dust falls on the surface to influence the machine to perform image recognition, and in addition, 1 block of toughened glass is found to have bubbles and other transparent inclusions which are not recognized during the repeated inspection;
in the comparative example, the error detection rate of the traditional detection mode is 3 pieces of tempered glass which have error detection; the omission factor is that 1 piece of tempered glass which is not detected exists in 100 pieces of tempered glass.
Analysis of results:
by comparing the embodiment 1 with the comparative example 1, the equipment for detecting the impurities in the toughened glass on line has high detection accuracy, overcomes the defects of the traditional detection method, can detect the bubble transparent inclusion and the surface scratch, greatly reduces the false detection rate and the omission rate, and provides detection with more reference significance for factory quality inspection.
Through practical use, the equipment for detecting the impurities in the toughened glass on line is simple, low in manufacturing cost, low in detection environment dependence degree and high in popularity, and the digital image processor performs subtraction operation on a group of images shot by the linear camera, so that the influence of dust fall and ambient light on a detection result is avoided to a great extent; and specific conditions such as scratch damage and the like on the surface of the glass can be identified; the false detection rate and the omission rate of the inclusion detection in the toughened glass are effectively reduced; the quality inspection reliability is improved, and the method is more energy-saving and environment-friendly.
The foregoing describes in detail preferred embodiments of the present utility model. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the utility model without requiring creative effort by one of ordinary skill in the art. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (2)
1. The equipment for detecting the impurities in the toughened glass on line is characterized by comprising a polarized light source (1), a roller conveyor belt (2), a glass test piece (3) to be detected, a linear array camera (4), a detection sensor (5) and a digital image processor (6);
the polarized light source (1) is positioned below the roller conveyor belt (2), polarized light rays emitted by the polarized light source (1) irradiate onto the glass test piece (3) to be detected through a gap of the roller conveyor belt (2), and the polarized light rays penetrate through the glass test piece (3) to be detected and are received by the linear camera (4);
2-4 linear array cameras (4) are provided, and the linear array cameras (4) are all positioned right above the gap of the rolling shaft;
the linear array cameras (4) are arranged in parallel or in front of each other, polaroids are arranged in front of camera lenses or camera targets of the linear array cameras (4), every two linear array cameras (4) are in a group, and the polaroids arranged in front of each linear array camera (4) have different polarization directions;
the digital image processor (6) is connected with the linear array camera (4) through a wire, and the digital image processor and the linear array camera are electrically connected;
the linear array camera (4) is connected with the object detection sensor (5) through a wire, and the two are electrically connected;
the number of the object detection sensors (5) is 1-4, and the object detection sensors are positioned above or on the side surface of the glass test piece (3) to be detected.
2. The apparatus for on-line detecting foreign substances inside tempered glass according to claim 1,
the polaroids placed in front of the linear array camera (4) have different polarization directions;
the number of the line cameras (4) is an even number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202222566478.3U CN220490706U (en) | 2022-09-27 | 2022-09-27 | Equipment for on-line detecting impurity inside toughened glass |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202222566478.3U CN220490706U (en) | 2022-09-27 | 2022-09-27 | Equipment for on-line detecting impurity inside toughened glass |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN220490706U true CN220490706U (en) | 2024-02-13 |
Family
ID=89825035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202222566478.3U Active CN220490706U (en) | 2022-09-27 | 2022-09-27 | Equipment for on-line detecting impurity inside toughened glass |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN220490706U (en) |
-
2022
- 2022-09-27 CN CN202222566478.3U patent/CN220490706U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108332689B (en) | Optical measurement system and method for detecting surface roughness and surface damage | |
| US7471383B2 (en) | Method of automated quantitative analysis of distortion in shaped vehicle glass by reflected optical imaging | |
| CN206114546U (en) | Printing defect vision detection system | |
| JP4930748B2 (en) | Film inspection apparatus and method | |
| CN103257465A (en) | Detecting device and method | |
| CN103364400A (en) | Multistation intelligent syncretic bottled beer online detection device | |
| CN106018431A (en) | Solid wood plate surface crack detecting system and detecting method | |
| CN103743761A (en) | Lens watermark defect image detection device | |
| CN107561091A (en) | A kind of detecting system and detection method of oblique fire formula solid wood board face crack | |
| JP7382519B2 (en) | Glass bottle inspection method, glass bottle manufacturing method, and glass bottle inspection device | |
| CN110208269A (en) | The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| Li et al. | The method for glass bottle defects detecting based on machine vision | |
| CN203908956U (en) | System for detecting surface defects of workpiece | |
| Wang et al. | Design of machine vision applications in detection of defects in high-speed bar copper | |
| Duan et al. | Study on surface defect vision detection system for steel plate based on virtual instrument technology | |
| CN109557098A (en) | Metal surface detection system based on machine vision | |
| CN220490706U (en) | Equipment for on-line detecting impurity inside toughened glass | |
| CN114235847A (en) | Liquid crystal display panel glass substrate surface defect detection device and detection method | |
| CN114002234A (en) | Simple ceramic tile surface defect detection device and method | |
| CN113916127A (en) | Visual inspection system and method for appearance of valve guide pipe finished product | |
| Agrawal | Glass defect detection techniques using digital image processing–a review | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN112881403A (en) | Hot rolling strip steel surface defect detection device | |
| CN109387525A (en) | On a kind of film in film defect determination method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |