CN112129762A - Spinneret plate defect detection method - Google Patents
Spinneret plate defect detection method Download PDFInfo
- Publication number
- CN112129762A CN112129762A CN202010935593.6A CN202010935593A CN112129762A CN 112129762 A CN112129762 A CN 112129762A CN 202010935593 A CN202010935593 A CN 202010935593A CN 112129762 A CN112129762 A CN 112129762A
- Authority
- CN
- China
- Prior art keywords
- image
- spinneret plate
- light
- spinneret
- defect
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
A spinneret plate defect detection method includes that in the process that a spinneret plate sprays tows into a spinneret plate barrel located right below the spinneret plate, a camera is firstly inserted into the spinneret plate barrel, an online image of the spinneret plate is shot from an upward viewing angle, a light source irradiates the spinneret plate while shooting, the online image is sent to an industrial personal computer, the industrial personal computer preprocesses the online image, the preprocessed image is subjected to image fusion, the image after image fusion is read, algorithm processing is carried out on the image, and then noise elimination and edge detection are sequentially carried out, wherein in the edge detection process, if an area different from a normal gray value exists in the image, the area is a defect area, so that defects are judged to exist, and the defect type can be further processed to judge. The design has the advantages of higher reliability, stronger safety, nondestructive testing and no interference to the smooth production.
Description
Technical Field
The invention relates to a method for detecting defects on a spinneret plate, belongs to the field of fiber production, and particularly relates to a method for detecting defects on a spinneret plate.
Background
In the production of the polyester fiber at present, production raw materials generate a melt through chemical reaction, the melt is formed into filaments through a spinning device, and then a final product is obtained through a series of subsequent processes of spinning, winding, drafting, packaging and the like. When the melt passes through the spinning device, polyester fiber accumulation easily occurs at the spinneret plate, different types of defects such as black lumps, yellow spots and crystalline lumps are formed, and the impurities can be sprayed out along with the yarn and mixed into the yarn, so that the quality of finished yarn is influenced.
The existing detection method is that an old worker with certain working experience bends down to lower the head, extends the head under a spinneret plate barrel and looks at the spinneret plate by naked eyes to judge whether defects are generated. The spinneret plate is high in temperature and dark in light, and meanwhile, the head extends to the position below the spinneret barrel and is too close to the filament bundle, and the spinning speed is extremely high, so that the visual detection method has serious potential safety hazards, and the conditions of erroneous judgment, missing judgment and the like are easy to occur.
The information disclosed in this background section is only for enhancement of understanding of the general background of the patent application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention aims to overcome the defects and problems of low reliability and low safety in the prior art, and provides a spinneret plate defect detection method with high reliability and high safety.
In order to achieve the above purpose, the technical solution of the invention is as follows: a spinneret plate defect detection method is characterized in that a spinneret plate sprays tows into a spinneret plate barrel located right below the spinneret plate; the detection method comprises the following steps:
the first step is as follows: in the process of moving the tows from top to bottom, a camera is firstly inserted into a spinneret barrel, then an online image of a spinneret plate is shot from an upward view angle, a light source irradiates the spinneret plate while shooting, and then the online image is sent to an industrial personal computer;
the second step is that: after receiving the online image, the industrial personal computer firstly preprocesses the online image, then carries out image fusion on the preprocessed image, then reads the image after image fusion, then carries out algorithm processing on the image, and then carries out noise elimination and edge detection in sequence, wherein, when the edge detection is carried out, if an area different from a normal gray value exists in the image, the area is a defect area, thereby judging that the defects exist.
The algorithm processing in the second step refers to a Gabor filter and a Gaussian mixture clustering algorithm.
In the second step, after finding the defect area:
firstly, eliminating noise again in a defect area, then carrying out image subtraction operation with images in a standard image library, and then judging the defect type existing on the spinneret plate as crystalline agglomeration if a part with a pixel value of 1 exists in a spinneret area; if a part with a pixel value of 0 exists in the wall area of the spinneret barrel, the defect type existing on the spinneret plate is judged to be black agglomeration.
The images in the standard image library are clean images of the spinneret plate under the upward viewing angle.
The spinning area is a circular area with the radius value of 28 mm to 35 mm on the spinneret plate, and the spinneret barrel wall area is a circular area with the radius value of 15 mm to 30 mm on the spinneret plate.
The noise elimination again refers to the elimination of the noise which cannot be completely eliminated in the algorithm processing by using expansion corrosion.
The preprocessing in the second step refers to image filtering, gray level transformation and histogram equalization operations which are sequentially performed.
In the first step, light sources irradiate light with different colors to a spinneret plate at intervals, and meanwhile, a camera shoots online images of the spinneret plate under different light irradiation and sends each image to an industrial personal computer in sequence;
the light with different colors comprises white light, red light, orange light, yellow light, green light, cyan light, blue light and purple light.
The selection rule of the color of the light is: if the defect of which the type is black agglomeration needs to be seen clearly, selecting blue light; if the type of defects needs to be clearly seen as crystal agglomeration defects, selecting white light; and if the panoramic view of the spinneret plate needs to be seen clearly, yellow light is selected.
The bottom of the camera is connected with the top of the cloud deck, the bottom of the camera is annularly provided with a light source, the bottom of the cloud deck is connected with the top of the supporting plate, the supporting plate is connected with the moving vehicle through a bracket, the moving vehicle is provided with an industrial personal computer, the industrial personal computer is in signal connection with the cloud deck and the camera, and meanwhile, the industrial personal computer is in signal connection with an external industrial personal computer outside a production site through an industrial network;
the industrial personal computer or the external industrial personal computer sends a signal to the holder to rotate the camera, so that the shooting angle of the camera is adjusted.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention relates to a spinneret plate defect detection method, under the irradiation of a light source, firstly shooting an online image by a camera, then sending the online image to an industrial personal computer, then sequentially carrying out pretreatment, image fusion, algorithm processing, noise elimination and edge detection on the online image by the industrial personal computer, finally, if an area different from a normal gray value exists in the image during the edge detection, the area is a defect area so as to judge that defects exist, the whole operation process is based on the online image shot by the camera, not only manual visual observation is not needed, the safety is higher, but also a plurality of online images can be shot on line so as to be used for the industrial personal computer to carry out image processing, thereby obtaining an accurate defect area and further accurately judging the existence of the defects, in addition, the method is carried out while the production, and the spinneret plate defect detection can be carried out under the condition of not influencing the original factory production at all, and (4) nondestructive testing technology. Therefore, the invention has the advantages of higher reliability and stronger safety, and can carry out nondestructive detection without interfering the smooth production.
2. In the spinneret plate defect detection method, after the defect area is found, the noise in the defect area can be eliminated again, and then the subtraction operation of the image and the image in the standard image library is carried out, so that the types of the defects, such as crystalline agglomeration, black agglomeration and the like, can be further determined, and the defect judgment accuracy is improved. Therefore, the invention can detect the types of the defects with higher accuracy.
3. In the spinneret plate defect detection method, the camera shoots an online image of the spinneret plate from an upward viewing angle, and the light source irradiates the spinneret plate while shooting, wherein the light sources are various, and different light sources can be selected according to the types of the defects during application, so that the quality of the online image is improved, the observation effect is clearer, and the accuracy of detecting the defects is more facilitated. Therefore, the invention can improve the detection accuracy by switching the light source.
4. The invention relates to a spinneret plate defect detection method, wherein a camera is arranged on a cradle head, the cradle head is sequentially connected with a mobile vehicle (the mobile vehicle is arranged to ensure that a target spinneret plate barrel to be detected can be replaced at any time, the operation is convenient and simple) through a supporting plate and a bracket, an industrial personal computer is arranged on the mobile vehicle, the industrial personal computer is in signal connection with the cradle head and the camera, and is in signal connection with an external industrial personal computer outside a production site through an industrial network Images for facilitating subsequent observation), and setting a corresponding alarm program, and can also display the online detection data of the defects on an external large screen, thereby improving the overall monitoring effect of defect detection. Therefore, the invention has the advantages of good defect detection effect, simple and convenient operation, high safety and high comfort level.
Drawings
Fig. 1 is a bottom view of a clean spinneret in the present invention.
Fig. 2 is a schematic diagram of the online image of the present invention after image fusion.
Fig. 3 is a schematic diagram of the present invention in the case of online image edge detection.
Fig. 4 is a schematic view of the connection between the camera and the support plate according to the present invention.
Fig. 5 is a top view of the light source of fig. 4.
Fig. 6 is a schematic diagram showing the relative positions of the moving vehicle and the spinneret plate in the present invention.
In the figure: the spinning device comprises an industrial personal computer 1, an external industrial personal computer 2, a support 3, a support plate 4, a holder 5, a camera 6, a light source 7, a moving vehicle 8, a spinneret plate 9, a spinning area 91 and a spinning barrel wall area 92.
Detailed Description
The present invention will be described in further detail with reference to the following description and embodiments in conjunction with the accompanying drawings.
Referring to fig. 1 to 6, in a method for detecting defects of a spinneret plate, the spinneret plate 9 ejects filament bundles into a filament ejection barrel located right below the spinneret plate; the detection method comprises the following steps:
the first step is as follows: in the process of moving the tows from top to bottom, the camera 6 is firstly inserted into the spinneret barrel, then the online image of the spinneret plate 9 is shot from the upward view angle, the light source 7 irradiates the spinneret plate 9 during shooting, and then the online image is sent to the industrial personal computer 1;
the second step is that: after receiving the online image, the industrial personal computer 1 firstly preprocesses the online image, then performs image fusion on the preprocessed image, then reads the image after image fusion, then performs algorithm processing on the image, and then sequentially performs noise elimination and edge detection, wherein, when the edge detection is performed, if an area different from a normal gray value exists in the image, the area is a defect area, thereby judging that defects exist.
The algorithm processing in the second step refers to a Gabor filter and a Gaussian mixture clustering algorithm.
In the second step, after finding the defect area:
firstly, eliminating noise again in a defect area, then carrying out image subtraction operation with images in a standard image library, and then judging that the defect type existing on the spinneret plate 9 is a crystalline agglomeration if a part with a pixel value of 1 exists in a spinneret plate area 91; if a portion having a pixel value of 0 exists in the wall region 92 of the spinneret, it is determined that the type of the defect existing on the spinneret 9 is a black lump.
The images in the standard image library are clean images of the spinneret plate 9 at the upward viewing angle.
The spinning zone 91 is a circular area on the spinneret 9 with a radius of 28 mm to 35 mm, and the spinneret barrel wall zone 92 is a circular area on the spinneret 9 with a radius of 15 mm to 30 mm.
The noise elimination again refers to the elimination of the noise which cannot be completely eliminated in the algorithm processing by using expansion corrosion.
The preprocessing in the second step refers to image filtering, gray level transformation and histogram equalization operations which are sequentially performed.
In the first step, the light source 7 irradiates light with different colors to the spinneret plate 9 at intervals, and meanwhile, the camera 6 shoots online images of the spinneret plate 9 under different light irradiation and sends each image to the industrial personal computer 1 in sequence;
the light with different colors comprises white light, red light, orange light, yellow light, green light, cyan light, blue light and purple light.
The selection rule of the color of the light is: if the defect of which the type is black agglomeration needs to be seen clearly, selecting blue light; if the type of defects needs to be clearly seen as crystal agglomeration defects, selecting white light; if the panorama of the spinneret plate 9 needs to be seen clearly, yellow light is selected.
The bottom of the camera 6 is connected with the top of the cloud deck 5, a light source 7 is annularly arranged at the bottom of the camera 6, the bottom of the cloud deck 5 is connected with the top of the supporting plate 4, the supporting plate 4 is connected with the moving vehicle 8 through the bracket 3, the moving vehicle 8 is provided with the industrial personal computer 1, the industrial personal computer 1 is in signal connection with the cloud deck 5 and the camera 6, and meanwhile, the industrial personal computer 1 is in signal connection with the external industrial personal computer 2 outside a production site through an industrial network;
the industrial personal computer 1 or the external industrial personal computer 2 sends a signal to the cloud platform 5 to rotate the camera 6, thereby adjusting the shooting angle of the camera 6.
The principle of the invention is illustrated as follows:
the online image of the spinneret plate in the invention refers to a picture of the spinneret plate in the production process.
Example 1:
referring to fig. 1 to 6, in a method for detecting defects of a spinneret plate, the spinneret plate 9 ejects filament bundles into a filament ejection barrel located right below the spinneret plate; the detection method comprises the following steps:
the first step is as follows: in the process of moving the filament bundles from top to bottom, a camera 6 is firstly inserted into a filament spraying barrel, then an online image of a spinneret plate 9 is shot from an upward viewing angle, and simultaneously, a light source 7 irradiates the spinneret plate 9 (if the defects of black agglomeration type need to be seen clearly, blue light is selected; if the defects of crystalline agglomeration type need to be seen clearly, white light is selected; if the full view of the spinneret plate 9 needs to be seen clearly, yellow light is selected, and when the filament bundles are used, different light colors can be continuously switched at fixed intervals for shooting), and then the online image is sent to an industrial personal computer 1;
the second step is that: after receiving the online image, the industrial personal computer 1 first performs preprocessing on the online image (i.e., sequentially performs image filtering, gray level transformation, and histogram equalization operations), then performs image fusion on the preprocessed image, then reads the image after image fusion (as shown in fig. 2), then performs algorithm processing on the image, and then sequentially performs noise elimination and edge detection, wherein, during edge detection (as shown in fig. 3), if an area different from a normal gray level value exists in the image, the area is a defect area, thereby determining that a defect exists.
Example 2:
the basic contents are the same as example 1, except that:
in the second step, after finding the defect area: firstly, removing noise in the defect area again (for example, removing the noise which cannot be completely removed in the algorithm processing by using expansion corrosion), then performing image subtraction with the image in the standard image library (namely, the clean image of the spinneret plate 9 under the view angle, as shown in fig. 1), and then, if a part with a pixel value of 1 exists in the spinneret area 91, judging that the type of the defect existing on the spinneret plate 9 is a crystalline agglomeration; if a portion having a pixel value of 0 exists in the wall region 92 of the spinneret, it is determined that the type of the defect existing on the spinneret 9 is a black lump.
The above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above embodiment, but equivalent modifications or changes made by those skilled in the art according to the present disclosure should be included in the scope of the present invention as set forth in the appended claims.
Claims (10)
1. A spinneret plate defect detection method is characterized in that a spinneret plate (9) sprays tows into a spinneret plate barrel located right below the spinneret plate, and the method comprises the following steps: the detection method comprises the following steps:
the first step is as follows: in the process of moving the tows from top to bottom, a camera (6) is firstly inserted into a spinneret barrel, then an online image of a spinneret plate (9) is shot from an upward viewing angle, a light source (7) irradiates the spinneret plate (9) during shooting, and then the online image is sent to an industrial personal computer (1);
the second step is that: after receiving the online image, the industrial personal computer (1) preprocesses the online image, then performs image fusion on the preprocessed image, then reads the image after image fusion, then performs algorithm processing on the image, and then sequentially performs noise elimination and edge detection, wherein when the edge detection is performed, if a region different from a normal gray value exists in the image, the region is a defect region, so that the defect is judged to exist.
2. A spinneret plate defect detection method according to claim 1, wherein: the algorithm processing in the second step refers to a Gabor filter and a Gaussian mixture clustering algorithm.
3. A spinneret defect detection method according to claim 1 or claim 2 wherein: in the second step, after finding the defect area:
firstly, eliminating noise again in a defect area, then carrying out image subtraction operation with an image in a standard image library, and then judging the defect type existing on the spinneret plate (9) to be crystalline agglomeration if a part with a pixel value of 1 exists in a spinneret plate area (91); if a part having a pixel value of 0 exists in the wall region (92) of the spinning nozzle, the type of the defect existing on the spinning nozzle (9) is judged to be black agglomerate.
4. A spinneret plate defect detection method according to claim 3, wherein: the images in the standard image library are clean images of the spinneret plate (9) at the upward viewing angle.
5. A spinneret plate defect detection method according to claim 3, wherein: the spinning area (91) is a circular area with the upper diameter value of 28 mm-35 mm of the spinning plate (9), and the spinning barrel wall area (92) is a circular area with the upper diameter value of 15 mm-30 mm of the spinning plate (9).
6. A spinneret plate defect detection method according to claim 3, wherein: the noise elimination again refers to the elimination of the noise which cannot be completely eliminated in the algorithm processing by using expansion corrosion.
7. A spinneret defect detection method according to claim 1 or claim 2 wherein: the preprocessing in the second step refers to image filtering, gray level transformation and histogram equalization operations which are sequentially performed.
8. A spinneret defect detection method according to claim 1 or claim 2 wherein: in the first step, a light source (7) irradiates light with different colors to a spinneret plate (9) at intervals, and meanwhile, a camera (6) shoots online images of the spinneret plate (9) under different light irradiation and sends each image to an industrial personal computer (1) in sequence;
the light with different colors comprises white light, red light, orange light, yellow light, green light, cyan light, blue light and purple light.
9. A spinneret plate defect detection method according to claim 8, wherein: the selection rule of the color of the light is: if the defect of which the type is black agglomeration needs to be seen clearly, selecting blue light; if the type of defects needs to be clearly seen as crystal agglomeration defects, selecting white light; if the panorama of the spinneret plate (9) needs to be seen clearly, yellow light is selected.
10. A spinneret defect detection method according to claim 1 or claim 2 wherein: the bottom of the camera (6) is connected with the top of the cloud deck (5), a light source (7) is arranged at the bottom of the camera (6) in a surrounding mode, the bottom of the cloud deck (5) is connected with the top of the supporting plate (4), the supporting plate (4) is connected with the moving vehicle (8) through the support (3), the moving vehicle (8) is provided with an industrial personal computer (1), the industrial personal computer (1) is in signal connection with the cloud deck (5) and the camera (6), and meanwhile the industrial personal computer (1) is in signal connection with an external industrial personal computer (2) located outside a production site through an industrial network;
the industrial personal computer (1) or the external industrial personal computer (2) sends a signal to the holder (5) to rotate the camera (6), so that the shooting angle of the camera (6) is adjusted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935593.6A CN112129762A (en) | 2020-09-08 | 2020-09-08 | Spinneret plate defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935593.6A CN112129762A (en) | 2020-09-08 | 2020-09-08 | Spinneret plate defect detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112129762A true CN112129762A (en) | 2020-12-25 |
Family
ID=73845325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010935593.6A Pending CN112129762A (en) | 2020-09-08 | 2020-09-08 | Spinneret plate defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112129762A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629626A (en) * | 2003-12-15 | 2005-06-22 | 财团法人工业技术研究院 | Insular spinning die detecting device |
| JP2009258069A (en) * | 2008-03-19 | 2009-11-05 | Teijin Techno Products Ltd | Inspection apparatus and inspection method of foreign matters within hole of spinneret |
| JP2010133771A (en) * | 2008-12-03 | 2010-06-17 | Teijin Fibers Ltd | Spinneret inspection apparatus |
| CN101819157A (en) * | 2010-04-27 | 2010-09-01 | 东华大学 | Spinning plate detector |
| CN102141374A (en) * | 2010-12-23 | 2011-08-03 | 苏州天准精密技术有限公司 | Image type spinneret plate automatic detector |
| CN205175927U (en) * | 2015-12-09 | 2016-04-20 | 中国科学院声学研究所东海研究站 | Appearance is examined to spinneret mirror |
| CN105547182A (en) * | 2015-12-09 | 2016-05-04 | 中国科学院声学研究所东海研究站 | Spinneret plate detection equipment and method |
-
2020
- 2020-09-08 CN CN202010935593.6A patent/CN112129762A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1629626A (en) * | 2003-12-15 | 2005-06-22 | 财团法人工业技术研究院 | Insular spinning die detecting device |
| JP2009258069A (en) * | 2008-03-19 | 2009-11-05 | Teijin Techno Products Ltd | Inspection apparatus and inspection method of foreign matters within hole of spinneret |
| JP2010133771A (en) * | 2008-12-03 | 2010-06-17 | Teijin Fibers Ltd | Spinneret inspection apparatus |
| CN101819157A (en) * | 2010-04-27 | 2010-09-01 | 东华大学 | Spinning plate detector |
| CN102141374A (en) * | 2010-12-23 | 2011-08-03 | 苏州天准精密技术有限公司 | Image type spinneret plate automatic detector |
| CN205175927U (en) * | 2015-12-09 | 2016-04-20 | 中国科学院声学研究所东海研究站 | Appearance is examined to spinneret mirror |
| CN105547182A (en) * | 2015-12-09 | 2016-05-04 | 中国科学院声学研究所东海研究站 | Spinneret plate detection equipment and method |
Non-Patent Citations (1)
| Title |
|---|
| 刘贵林: "喷丝板光电检测系统的研究与设计", 《硕士电子期刊》, no. 09, pages 15 - 70 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10026162B2 (en) | Method and device for sealant coating inspection | |
| CN103743761B (en) | A kind of eyeglass watermark defect image detection device | |
| US10794838B2 (en) | Method and device for detecting defect of cover lens in laser welding system on automobile production line | |
| EP1503206A1 (en) | Systems and methods for identifying foreign objects and debris and defects during fabrication of a composite structure | |
| CN102590330A (en) | Image processing-based magnetic particle inspection defect intelligent identification detection system | |
| WO2014139273A1 (en) | Weld seam defect detection method | |
| CN105891228A (en) | Optical fiber appearance defect detecting and outer diameter measuring device based on machine vision | |
| CN109932369B (en) | Method and device for detecting special-shaped display panel | |
| CN104345481A (en) | Liquid crystal display quality inspection method, device and equipment | |
| CN113592867A (en) | Detection method based on residual binding yarns on carbon fiber cloth cover | |
| CN113592852A (en) | Carbon fiber carbon wire quality online detection system and method | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN116908107A (en) | Paint surface flaw detection system based on machine vision | |
| CN205449822U (en) | A polyphaser image mosaicking device for belted steel surface is detected | |
| CN113610843B (en) | Real-time defect identification system and method for optical fiber braiding layer | |
| CN112129762A (en) | Spinneret plate defect detection method | |
| US9652842B2 (en) | Method, apparatus and equipment of inspecting quality of LCD | |
| CN117554387A (en) | Transparent semitransparent wafer flaw detection equipment | |
| CN112461846A (en) | Workpiece defect detection method and device | |
| CN113567447A (en) | Synthetic leather hemming online detection method | |
| JP4146678B2 (en) | Image inspection method and apparatus | |
| CN111077162A (en) | Glass bottle defect detecting system | |
| JPH04238592A (en) | Automatic bundled bar steel tally device | |
| CN205665178U (en) | Optic fibre appearance imperfections detects and external diameter measuring device based on machine vision | |
| CN110857919A (en) | Tail yarn defect detection method for package filament |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |