CN113155847A - Oil smoke cover surface defect detecting system based on AI 3D vision - Google Patents
Oil smoke cover surface defect detecting system based on AI 3D vision Download PDFInfo
- Publication number
- CN113155847A CN113155847A CN202110443640.XA CN202110443640A CN113155847A CN 113155847 A CN113155847 A CN 113155847A CN 202110443640 A CN202110443640 A CN 202110443640A CN 113155847 A CN113155847 A CN 113155847A
- Authority
- CN
- China
- Prior art keywords
- camera
- surface defect
- detection
- vision
- box body
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 65
- 230000004438 eyesight Effects 0.000 title claims abstract description 32
- 239000000779 smoke Substances 0.000 title description 4
- 238000001514 detection method Methods 0.000 claims abstract description 113
- 238000012546 transfer Methods 0.000 claims abstract description 23
- 238000005507 spraying Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 15
- 239000006233 lamp black Substances 0.000 claims abstract description 9
- 238000003384 imaging method Methods 0.000 claims description 32
- 239000013589 supplement Substances 0.000 claims description 20
- 238000011179 visual inspection Methods 0.000 claims description 15
- 239000003517 fume Substances 0.000 claims description 10
- 230000001502 supplementing effect Effects 0.000 claims description 5
- 230000008878 coupling Effects 0.000 claims description 4
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 238000013016 damping Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000006378 damage Effects 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 14
- 238000000034 method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 238000010191 image analysis Methods 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 230000002950 deficient Effects 0.000 description 3
- 230000003760 hair shine Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01N2021/8858—Flaw counting
Abstract
The invention discloses an AI 3D vision-based lampblack hood surface defect detection system which comprises a vision detection station, a transfer robot arranged near the vision detection station, a code spraying device arranged in the working range of the transfer robot and an industrial personal computer, wherein the industrial personal computer is electrically connected with the vision detection station, the transfer robot and the code spraying device. According to the invention, the visual detection station is arranged, and the visual detection technology is used for replacing manual detection, so that the system can effectively improve the detection efficiency and the detection stability, and avoid the damage of long-time naked eye detection to the eyesight of workers.
Description
Technical Field
The invention belongs to the technical field of visual defect detection, and particularly relates to an AI 3D vision-based lampblack hood surface defect detection system.
Background
With the rapid development of computer technology and the widespread use in the industrial field, a great deal of industrial technology has revolutionized the development of modern process automation involving a variety of inspection, production monitoring and part identification applications.
In many industrial fields, manual identification is often used for defect detection, surface defects such as pits and scratches of an object to be detected are judged and identified through human eyes, or the object to be detected is detected by means of a measuring tool, and the traditional manual detection has the following problems: manual identification wastes time and energy, and the manual identification result receives the influence of monitoring person human factor easily, like tired, detection person personal knowledge level etc. and artifical detection efficiency and quality are lower simultaneously, and long-time work leads to the fact workman's eyesight.
Disclosure of Invention
The invention provides an AI 3D vision-based lampblack hood surface defect detection method for overcoming the defects of the prior art.
In order to solve the problem that the manual identification result is easily influenced by human factors of a monitor in the detection process of a workpiece, the invention aims to provide the detection method for the surface defects of the oil smoke cover based on the AI 3D vision.
An AI 3D vision-based oil smoke cover surface defect detection method comprises the following steps:
s01: providing a workpiece to be detected;
s02: acquiring an image and surface characteristic data of a workpiece to be detected;
s03: image analysis, namely performing 3D computational imaging and AI defect identification and positioning on the acquired image;
s04: judging defects, namely extracting the image analysis result and judging whether the workpiece has defects or not;
s05: and (4) carrying out classification treatment, wherein the qualified products are transferred to a good product area, and the unqualified products are transferred to an unqualified product area after defect marking.
Optionally, the image analysis result in S03 shows a normal vector diagram of the workpiece marking the defect position, an enlarged view of the defect, a count of the current workpiece, a qualification judgment of the current workpiece, and log information of the detection process.
Optionally, the detection method further includes automatically counting the number of defective products, the types of defects, the positions of defects, and the number of defects, and feeding back the information to the product design and production processes.
In order to implement the AI 3D vision-based lampblack hood surface defect detection system provided by the first aspect, the second aspect of the invention provides a lampblack hood surface defect detection system.
The utility model provides a lampblack cover surface defect detecting system, includes the visual detection station, locates near the visual detection station the transfer robot, locate the yard device, the industrial computer of spouting of transfer robot work scope, the industrial computer with the visual detection station, transport the robot, spout the equal electric connection of yard device.
Optionally, the transfer robot is equipped with two at least, and two transfer robots alternately absorb or snatch the work piece to the visual inspection station.
Optionally, the code spraying device is associated with the transfer robot, and after the transfer robot aligns the defect position of the workpiece to be detected with the code spraying device, the code spraying device marks the detected defects one by one.
Optionally, the code spraying device is installed on the outer wall of the visual inspection station or is arranged near the visual inspection station.
Optionally, the detection system further comprises a feeding conveyor line for conveying the workpiece to the gripping position, and the transfer robot is arranged at the tail end of the feeding conveyor line.
The visual inspection has higher requirement on the light irradiation of a detection scene, the part is reflected and the defects are covered due to overlarge illumination intensity, and the part with a special structure is not easy to identify if the part is too small, so that the adjustment of the illumination is very critical. In a third aspect, the present invention is directed to an omnidirectional visual inspection station.
The utility model provides an all-round vision inspection station, includes the box that has the feed inlet, locates the first imaging module at box top, at least two sets of locating second imaging module on the box lateral wall, locate the jacking subassembly of bottom half, it is two sets of the second imaging module sets up about the feed inlet symmetry.
Optionally, the first imaging module includes a first camera disposed at the top of the box and a plurality of first light supplement lamps for supplementing light to shooting positions, and the plurality of first light supplement lamps surround the first camera.
Optionally, the first camera is connected with the box body through a mechanical arm, an installation part is arranged at one end of the mechanical arm, and the camera is detachably arranged on the installation part.
Optionally, the first light supplement lamp is fixed to the mounting part through the first light source support, the first light source support comprises a hanging lug and a hanging piece, the hanging lug is fixed to the mounting part, the first light supplement lamp is fixed to the hanging piece, the hanging piece and the hanging lug are rotatably connected, and damping is arranged between the hanging piece and the hanging lug.
Optionally, the hanging lug is provided with an ear part extending in a direction away from the mounting part, the hanging part is provided with a beam and a connecting part extending in a direction close to the mounting part, and the first light supplement lamp is fixed on the beam; the connecting part is overlapped with the ear part, a light source rotating shaft is arranged between the connecting part and the ear part, and the light source rotating shaft is fixed with the connecting part or the light source rotating shaft is fixed with the ear part; the irradiation area of the first light supplement lamp on the workpiece to be measured can be adjusted through the rotating beam.
Optionally, the light source rotating shaft is fixed to the connecting portion, and the light source rotating shaft is connected with an output shaft of the light source driving motor.
Optionally, the second imaging module includes a second camera disposed on the side wall of the box and a second light supplement lamp for supplementing light to a shooting position of the second camera.
Optionally, the second imaging module further includes a slide rail horizontally disposed on the inner wall of the box body, and a sliding member slidably connected to the slide rail, and the second camera is mounted on the sliding member.
Optionally, the number of the second light supplement lamps is at least two, the two second light supplement lamps are symmetrically arranged on two sides of the second camera, and the second light supplement lamps are mounted on the sliding piece through the second light source support.
Optionally, the second imaging module includes a slide rail and a detection device slidably disposed on the slide rail; the detection device is provided with an upper detection unit, a middle detection unit and a lower detection unit, and each detection unit is provided with a third camera, a point light source and a light source controller.
Optionally, a third camera axis of the upper detection unit is inclined downwards relative to the horizontal plane, a third camera axis of the middle detection unit is parallel to the horizontal plane, and a third camera axis of the lower detection unit is inclined upwards relative to the horizontal plane.
Optionally, the detection device further includes a back plate, the upper detection unit, the middle detection unit and the lower detection unit are respectively mounted on the back plate through respective position adjustment mechanisms, the back plate includes a main plate, an upper wing plate and a lower wing plate, and the main plate is parallel to the height direction of the box body; the upper wing plate is intersected with the main plate, and the top of the upper wing plate is closer to a workpiece to be measured than the bottom of the upper wing plate; the lower wing plate is intersected with the main plate, and the top of the lower wing plate is farther away from a workpiece to be measured than the bottom of the lower wing plate.
Optionally, the third camera of the upper detection unit is close to an intersecting area of the upper wing plate and the main board, a part of light sources of the upper detection unit is disposed in an area covered by the upper wing plate, and another part of light sources of the upper detection unit is disposed in an area covered by the main board.
Optionally, the third camera of the middle detection unit and the light source thereof are disposed in an area covered by the main board.
Optionally, the third camera of the lower detection unit and the light source thereof are disposed in the area covered by the lower wing plate.
Optionally, the jacking module comprises a bracket capable of moving up and down and a driving piece arranged on the box body and connected with the bracket at an output end.
Optionally, the bracket is connected with a guide pillar, the box body is provided with a fixing plate for the guide pillar to pass through, and the fixing plate is provided with a guide sleeve slidably connected with the guide pillar.
Optionally, the fine-tuning piece is screwed at a corner of one side of the box body facing the ground.
In summary, the invention has the advantages that:
1. through using visual detection technique to replace artifical the detection, effectively improve detection efficiency, promote detection stability to avoid long-time naked eye detection to the injury of workman's eyesight.
2. The method adopts a 3D vision calculation imaging technology and an AI defect identification technology to perform ultrahigh-precision three-dimensional imaging and identification positioning on tiny flaws on the surface of the complex and bright metal, has high running speed, high reliability and high identification accuracy, and meets the requirements of high-efficiency and high-reliability detection of surface defects of complex sheet metal parts in the household appliance industry.
3. The automatic statistics of defect types, positions and quantities can provide a large amount of statistical data for the optimized product design and the technological process of enterprises, and the intelligent manufacturing level of the enterprises is improved.
4. Through two transfer robots alternate work, improve the utilization efficiency to the visual inspection station, detection efficiency is high.
5. The angle of first light filling lamp is adjustable, carries out corresponding adjustment according to the shooting position difference of first camera, and real time control light shines the position, avoids appearing the light and shines the dead angle, improves and shoots the image quality.
Drawings
FIG. 1 is a flow chart of the detection method of the present invention.
FIG. 2 is a schematic view of an operation interface of an industrial personal computer.
Fig. 3 is a perspective view of the vision inspection station of the present invention.
Fig. 4 is a left side view of fig. 3.
Fig. 5 is a cross-sectional perspective view of fig. 4 taken along a-a.
Fig. 6 is a perspective view of fig. 5 with the cover removed.
Fig. 7 is a perspective view of the first imaging module of fig. 3.
Fig. 8 is an enlarged view at B in fig. 7.
Fig. 9 is a perspective view of another embodiment of the second imaging module of fig. 3.
Fig. 10 is a perspective view of the detection device of fig. 9.
Fig. 11 is a perspective view of fig. 3 from another perspective.
Fig. 12 is a front view of fig. 3.
Fig. 13 is an enlarged view at C in fig. 12.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
As shown in fig. 1, an AI 3D vision-based surface defect detection system for a cooking fume hood includes the following steps:
s01: providing a workpiece to be detected;
s02: acquiring an image and surface characteristic data of a workpiece to be detected;
s03: image analysis, namely performing 3D computational imaging and AI defect identification and positioning on the acquired image;
s04: judging defects, namely extracting the image analysis result and judging whether the workpiece has defects or not;
s05: and (4) carrying out classification treatment, wherein the qualified products are transferred to a good product area, and the unqualified products are transferred to an unqualified product area after defect marking.
In the practical application process, the S01-S05 is executed by a lampblack cover surface defect detection system, and the lampblack cover surface defect detection system comprises a feeding conveying line, a transfer robot, a visual detection station, a code spraying device and an industrial personal computer.
In some embodiments, the feeding conveyor line is located near the visual inspection station, the number of the feeding conveyor lines is arranged according to specific situations, and can be one or more, after the workpiece is placed on the feeding conveyor line and the sensor is triggered, the feeding conveyor line starts to move, the workpiece to be detected is moved to the grabbing position, the sensor is triggered when the workpiece is moved to the grabbing position, and the feeding conveyor line stops moving; furthermore, a feeding device is arranged at the feeding end of the feeding conveying line and used for grabbing the workpiece to the feeding conveying line.
In some embodiments, the transfer robot is arranged at the tail end of the feeding conveying line and is responsible for grabbing or sucking a workpiece from the conveying line to move to the visual detection station, a sensor on the visual detection station sends a trigger signal to the control circuit board after monitoring that the workpiece reaches a detection position, and a forming image is obtained after the workpiece to be detected is detected; and after the detection is finished, the defective workpiece is moved to a code spraying device for marking, and the detected workpiece is stacked to a corresponding position according to the model and whether the workpiece is qualified.
In some embodiments, the transfer robots are at least two, the two transfer robots alternately grab the workpiece from the corresponding feeding conveying lines to the visual inspection station, utilization efficiency of the AI 3D visual inspection station is improved, and work efficiency is high. The working cycle of the detection system is shown in table 1, and the detection cycle can reach 2 workpieces to be detected every 18 seconds, namely 9 seconds per workpiece on average.
TABLE 1
In some embodiments, the code spraying device is arranged on one side of the visual inspection station or on the outer wall of the visual inspection station and can spray a monochromatic mark with a fixed shape, and further, the code spraying device can spray different shapes or colors according to different defect types, so that rapid identification can be conveniently carried out during subsequent repair; the code spraying device is associated with the transfer robot, and after the transfer robot aligns the defect position of the workpiece to be detected with the code spraying device, the detected defects are marked one by one, so that the defects can be repaired conveniently in subsequent processes.
In some embodiments, the industrial personal computer is provided with a GTX1080Ti high-performance computing card for 3D computing imaging and AI defect identification and positioning of workpieces, and is electrically connected with the visual detection station, the transfer robot and the code spraying device; as shown in fig. 2, each time a workpiece is detected, the main window of the operation interface of the industrial personal computer displays a normal vector diagram of the workpiece, and marks the defect position in a square frame form, however, in other embodiments, a circular frame, a polygonal frame or other figures are used to highlight the defect position; the system comprises a main window, a first sliding window and a second sliding window, wherein the main window is provided with a plurality of enlarged images with defects, the first sliding window is used for displaying the enlarged images with defects, the second sliding window is used for displaying log information in the detection process, counting values of current workpieces are displayed between the first sliding windows and between the second sliding windows, whether the workpieces are qualified or not is represented in a red fork and green hook mode, a system operation interface is concise, and operation is facilitated.
In some embodiments, the detection system automatically counts information such as the total number of detected workpieces, the number of defective products, the types of defects, the positions of defects, the number of defects and the like, and automatically uploads the data to the MES system, so that a large amount of statistical data is provided for an enterprise to optimize product design and a technological process, and the improvement of the intelligent manufacturing level of the enterprise is assisted.
In some embodiments, the detection system is suitable for a workpiece with a length range of 825 and 1225mm and a width range of 775 and 960 mm; the defect types detectable by the detection system comprise concave-convex points and scratches, the detection range of the diameter D of the concave-convex points is larger than or equal to 0.5mm, the detection range of the width B and the length L of the scratches is larger than or equal to 0.5mm, and the detection range of the L is larger than or equal to 2 mm.
In some embodiments, the vision inspection station adopts a 3D vision calculation imaging technology and an AI defect recognition technology, the imaging technology and the defect recognition technology adopt the existing products of Shanghai intelligent array information technology company, ultra-high-precision three-dimensional imaging and recognition positioning can be carried out on tiny flaws on complex and bright metal surfaces, the detection method has the characteristics of high running speed, high reliability, high recognition accuracy and the like, and the detection requirements of high efficiency and high reliability of surface defects of complex sheet metal parts in the household appliance industry are met.
The visual inspection has higher requirement on the light irradiation of a detection scene, the part is reflected and the defects are covered due to overlarge illumination intensity, and the part with a special structure is not easy to identify if the part is too small, so that the adjustment of the illumination is very critical. The present invention provides an omni-directional vision inspection station to obtain a panoramic image of a workpiece.
Referring to fig. 3-6, in some embodiments, the vision inspection station includes a tank 10, a first imaging module 20, a second imaging module 30, and a jacking assembly 40; the box body 10 comprises a frame 11 and a cover shell 12 covering the frame 11, the frame 11 is fixed on the ground or a corresponding base, and the frame 11 is formed by splicing a plurality of sectional materials, so that the strength of the visual detection station is improved; a cushion block 13 is arranged on one side, facing the ground, of the box body 10, a fine adjusting piece 14 is arranged on the cushion block 13, and the fine adjusting piece 14 is in threaded connection with the cushion block 13 and used for adjusting the integral level of the box body 10; a feeding hole 121 is formed in the housing 12, and a workpiece to be detected is placed into the visual inspection station through the feeding hole 121.
Referring to fig. 5 to 7, in some embodiments, the first imaging module 20 is disposed on the top of the box 10 and includes a first camera 21, a robot arm 22, a mounting member 23, and a first fill-in light 24; the first camera 21 is 2000 ten thousand pixel industrial cameras and is arranged in the box body 10, and the first camera 21 is arranged at the top of the box body 10 through a mechanical arm 22 and is used for detecting the upper surface of a workpiece; the mechanical arm 22 is a six-axis industrial robot and is detachably arranged at the top of the box body 10, when a workpiece is detected, the mechanical arm 22 drives the first camera 21 to move, and the shooting angle of the first camera 21 is adjusted to obtain a panoramic image of the workpiece; the mounting member 23 is provided at one end of the robot arm 22, the mounting member 23 is formed in a disk shape, and the first camera 21 is mounted on the mounting member 23; first light filling lamp 24 is set as LED lamp pearl, and is equipped with a plurality ofly, and a plurality of first light filling lamps 24 encircle first camera 21 arranges for carry out the light filling to the shooting position of first camera 21.
Referring to fig. 7 and 8, in some embodiments, the first supplementary lighting lamp 24 is fixed to the mounting member 23 through the first light source bracket 25, one first supplementary lighting lamp 24 is disposed on each light source bracket 50, the first light source bracket 25 includes a hanging lug 251 and a hanging part 252, the hanging lug 251 is fixed to the mounting member, the supplementary lighting lamp is fixed to the hanging part 252, the hanging part 252 is rotatably connected to the hanging lug 251, and a damper is disposed between the hanging part 252 and the hanging lug 252. The angle of light filling lamp is conveniently adjusted according to operating condition, avoids appearing the light and shines the dead angle, improves and shoots the image quality.
Referring to fig. 7 and 8, in some embodiments, the hanging lug 252 has an ear portion 2521 extending away from the mounting member 23, the hanging member 251 has a beam and a connecting portion 2511 extending toward the mounting member 23, and the first fill light 24 is fixed to the beam; coupling portion 2511 overlaps with ear portion 2521, and a light source shaft is provided between coupling portion 2511 and ear portion 2521, and is fixed to coupling portion 2511 or fixed to ear portion 2521. The irradiation area of the first light supplement lamp 24 on the workpiece to be measured can be adjusted by the rotating beam.
In some embodiments, the light source rotating shaft is fixed to the connection portion 2511, and the light source rotating shaft is connected to an output shaft of the light source driving motor. The position of first light filling lamp 24 can be adjusted in the existence of light source pivot, and is different according to the shooting position of first camera 21, finely tunes the angle of first light filling lamp 24, improves the shooting effect.
Referring to fig. 5 and 6, in some embodiments, the second imaging modules 30 are provided in at least two groups, two groups of the second imaging modules 30 are symmetrically disposed on the inner side of the frame 11 about the feeding opening 121, and cooperate with the second imaging modules 30 to perform overall detection on the workpiece, where the second imaging modules 30 include a slide rail 31, a sliding member 32, a second camera 33, and a second fill light 34; the slide rails 31 are electric slide rails 31 and are horizontally arranged on the inner wall of the box body 10, and at least two slide rails 31 are symmetrically arranged on two sides of the feed port 121; the sliding part 32 is connected with the sliding rail 31 in a sliding way; the second camera 33 is 2000 ten thousand pixel industrial cameras, is arranged on the sliding part 32 and is used for detecting the side face of the workpiece; the second light supplement lamps 34 are LED lamp beads, are arranged on the sliding member 32, and are at least two, and the two second light supplement lamps 34 are symmetrically arranged on two sides of the second camera 33, and are used for supplementing light to the shooting position of the second camera 33. Further, the second light supplement lamp 34 is mounted on the sliding member 32 through a second light source bracket 35, and the second light source bracket 35 has the same structure as the first light source bracket 25, so that the angle of the second light supplement lamp 34 is adjustable, and the second light supplement lamp is correspondingly adjusted according to different shooting positions of the first camera 21.
Of course, referring to fig. 9 and 10, in other embodiments, the second imaging module 30 includes a slide rail 31a and a detecting device 36 slidably disposed on the slide rail 31 a; the detection device 36 has an upper detection unit 361, a middle detection unit 362 and a lower detection unit 363, each having a third camera 371, a point light source 372 and a light source controller; the axis of the third camera 371 of the upper detection unit 361 is inclined downward with respect to the horizontal plane, the axis of the third camera 371 of the middle detection unit 362 is parallel to the horizontal plane, and the axis of the third camera 371 of the lower detection unit 363 is inclined upward with respect to the horizontal plane. According to different detection positions on the workpiece, the jacking assembly 40 drives the workpiece to move to the position corresponding to the detection unit, and the dead angle position of the workpiece is detected.
Referring to fig. 9 and 10, the detecting device 36 includes a back plate 364, the upper detecting unit 361, the middle detecting unit 362 and the lower detecting unit 363 are respectively mounted on the back plate 364 through respective position adjusting mechanisms, the back plate 364 includes a main plate 3641, an upper wing plate 3642 and a lower wing plate 3643, and the main plate 3641 is disposed in parallel to the height direction of the frame; the upper wing plate 3642 is intersected with the main plate 3641, the top of the upper wing plate 3642 is closer to a workpiece to be measured than the bottom of the upper wing plate 3642, the lower wing plate 3643 is intersected with the main plate 3641, and the top of the lower wing plate 3643 is farther from the workpiece to be measured than the bottom of the lower wing plate 3643.
Referring to fig. 10, in some embodiments, the third camera 371 of the upper detection unit 361 is close to a region where the upper wing plate 3642 and the main plate 3641 intersect, a part of light sources of the upper detection unit 361 are disposed in a region covered by the upper wing plate 3642, and another part of light sources of the upper detection unit 361 are disposed in a region covered by the main plate 3641.
Referring to fig. 10, in some embodiments, the third camera 371 of the middle detection unit 362 and its light source are disposed in an area covered by the main board 3641.
Referring to fig. 10, in some embodiments, the third camera 371 of the lower detection unit 363 and its light source are disposed within an area covered by the lower wing panel 3643.
Referring to fig. 5, 6, 12 and 13, in particular, the jacking assembly 40 includes the bracket 41, a driving member 42, a fixing plate 43 and a guide post 44; the bracket 41 can move up and down and is arranged in the box body 10 and is formed by splicing a plurality of sectional materials, and a workpiece is supported after being placed in the box body 10; the driving part 42 is a cylinder or an oil cylinder, and one end of the driving part is detachably arranged on the frame 11 and is used for driving the bracket 41 to move; the fixing plate 43 is fixedly arranged on the frame 11 and fixes the other end of the driving part 42; the guide posts 44 are rod bodies, symmetrically arranged on two sides of the driving member 42, and slidably arranged on the fixing plate 43 to support the bracket 41, so that the bracket 41 is prevented from shaking, and the stability is improved; the fixed plate 43 is detachably connected with a guide sleeve 45, and the guide post 44 penetrates through the guide sleeve 45, so that the guide post 44 is prevented from being directly contacted with the fixed plate 43 to cause abrasion.
The above-described embodiments do not limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the above-described embodiments should be included in the protection scope of the technical solution.
Claims (10)
1. The utility model provides a lampblack cover surface defect detecting system based on AI 3D vision, its characterized in that, include the visual detection station, locate near the visual detection station transport the robot, locate transport the robot work scope spout a yard device, industrial computer and visual detection station, transport the robot, spout the equal electric connection of yard device.
2. The AI 3D vision based fume hood surface defect detection system of claim 1, wherein: the transfer robot is at least provided with two transfer robots, and the two transfer robots alternately absorb or grab the workpiece to the visual inspection station.
3. The AI 3D vision based fume hood surface defect detection system of claim 1, wherein: the code spraying device is associated with the transfer robot, and after the transfer robot aligns the defect position of the workpiece to be detected with the code spraying device, the code spraying device marks the detected defects one by one.
4. The AI 3D vision based fume hood surface defect detection system of claim 1, wherein: the visual inspection station comprises a box body with a feed inlet, a first imaging module arranged at the top of the box body, at least two groups of second imaging modules arranged on the side wall of the box body and a jacking assembly arranged at the bottom of the box body, wherein the second imaging modules are symmetrically arranged around the feed inlet.
5. The AI 3D vision based fume hood surface defect detection system of claim 4, wherein: the first imaging module comprises a first camera arranged at the top of the box body and a plurality of first light supplement lamps used for supplementing light to shooting positions, and the first light supplement lamps are arranged around the first camera.
6. The AI 3D vision based fume hood surface defect detection system of claim 5, wherein: first light filling lamp is fixed in the installed part through first light source support, and this first light source support includes hangers and pendant, and the hangers is fixed with the installed part, fixed first light filling lamp on the pendant, pendant and hangers rotatable coupling have the damping between pendant and the hanger.
7. The AI 3D vision based fume hood surface defect detection system of claim 4, wherein: the second imaging module comprises a second camera arranged on the side wall of the box body and a second light supplement lamp used for supplementing light for the shooting position of the second camera.
8. The AI 3D vision based fume hood surface defect detection system of claim 7, wherein: the second imaging module further comprises a sliding rail horizontally arranged on the inner wall of the box body and a sliding part in sliding connection with the sliding rail, and the second camera and the second light supplement lamp are mounted on the sliding part.
9. The AI 3D vision based fume hood surface defect detection system of claim 4, wherein: the second imaging module comprises a slide rail and a detection device which can be arranged on the slide rail in a sliding mode, the detection device is provided with an upper detection unit, a middle detection unit and a lower detection unit, and each detection unit is provided with a third camera, a point light source and a light source controller.
10. The AI 3D vision based fume hood surface defect detection system of claim 9, wherein: the third camera axis of the middle detection unit is parallel to the horizontal plane, and the third camera axis of the lower detection unit is inclined upwards relative to the horizontal plane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110443640.XA CN113155847A (en) | 2021-04-23 | 2021-04-23 | Oil smoke cover surface defect detecting system based on AI 3D vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110443640.XA CN113155847A (en) | 2021-04-23 | 2021-04-23 | Oil smoke cover surface defect detecting system based on AI 3D vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113155847A true CN113155847A (en) | 2021-07-23 |
Family
ID=76870023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110443640.XA Pending CN113155847A (en) | 2021-04-23 | 2021-04-23 | Oil smoke cover surface defect detecting system based on AI 3D vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113155847A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201464382U (en) * | 2009-07-13 | 2010-05-12 | 郑州市华熙系统信息有限公司 | Aluminum foil defect detecting system based on computer vision |
| CN207114442U (en) * | 2017-09-08 | 2018-03-16 | 深圳力普尔智能科技有限公司 | A kind of diaphragm open defect detection means |
| CN109375573A (en) * | 2018-11-22 | 2019-02-22 | 南通科技职业学院 | A kind of industrial machine vision system image processing method |
| US20190064254A1 (en) * | 2017-08-28 | 2019-02-28 | Teradyne, Inc. | Automated test system employing robotics |
| CN109896233A (en) * | 2019-02-01 | 2019-06-18 | 上海电机学院 | Drug freeze dryer automatic cycle feeding system |
| CN110082357A (en) * | 2019-05-05 | 2019-08-02 | 苏州艾科瑞思智能装备股份有限公司 | Circuit lead frame defect detecting device |
| CN209853315U (en) * | 2019-04-26 | 2019-12-27 | 合刃科技（武汉）有限公司 | Reciprocating type transmission device |
| CN111229642A (en) * | 2020-01-20 | 2020-06-05 | 江清林 | Automatic change building material optics letter sorting system |
| CN211393009U (en) * | 2019-12-11 | 2020-09-01 | 杭州勇成机械有限公司 | Automatic feeding platform of duplex position robot |
| CN212622266U (en) * | 2020-07-23 | 2021-02-26 | 苏州风向标金属制品有限公司 | Sheet metal visual detection device |
-
2021
- 2021-04-23 CN CN202110443640.XA patent/CN113155847A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201464382U (en) * | 2009-07-13 | 2010-05-12 | 郑州市华熙系统信息有限公司 | Aluminum foil defect detecting system based on computer vision |
| US20190064254A1 (en) * | 2017-08-28 | 2019-02-28 | Teradyne, Inc. | Automated test system employing robotics |
| CN207114442U (en) * | 2017-09-08 | 2018-03-16 | 深圳力普尔智能科技有限公司 | A kind of diaphragm open defect detection means |
| CN109375573A (en) * | 2018-11-22 | 2019-02-22 | 南通科技职业学院 | A kind of industrial machine vision system image processing method |
| CN109896233A (en) * | 2019-02-01 | 2019-06-18 | 上海电机学院 | Drug freeze dryer automatic cycle feeding system |
| CN209853315U (en) * | 2019-04-26 | 2019-12-27 | 合刃科技（武汉）有限公司 | Reciprocating type transmission device |
| CN110082357A (en) * | 2019-05-05 | 2019-08-02 | 苏州艾科瑞思智能装备股份有限公司 | Circuit lead frame defect detecting device |
| CN211393009U (en) * | 2019-12-11 | 2020-09-01 | 杭州勇成机械有限公司 | Automatic feeding platform of duplex position robot |
| CN111229642A (en) * | 2020-01-20 | 2020-06-05 | 江清林 | Automatic change building material optics letter sorting system |
| CN212622266U (en) * | 2020-07-23 | 2021-02-26 | 苏州风向标金属制品有限公司 | Sheet metal visual detection device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106895961B (en) | A kind of detection device and its detection method of backlight module | |
| CN104764750B (en) | Elevator balanced compensated chain automatic detection device for quality and method based on machine vision | |
| CN106770331B (en) | Workpiece defect detection system based on machine vision | |
| CN108380509B (en) | Machine vision-based LED lamp panel sorting and detecting system | |
| CN109060827A (en) | A kind of intelligent visual detection identification equipment | |
| CN205650478U (en) | Switch outward appearance check out test set and system | |
| CN109142381B (en) | High-speed visual detection and identification equipment | |
| CN210742146U (en) | Multi-station and multi-angle visual surface defect detection system | |
| CN111069078B (en) | Multifunctional visual detection platform | |
| CN112691926A (en) | Automatic quality detection device based on machine vision and working method thereof | |
| CN112170248A (en) | L-shaped steel plate visual detection equipment with bending angle detection function | |
| CN110877151A (en) | Vision-guided engine cylinder unstacking detection robot equipment and method thereof | |
| CN114705693A (en) | AI visual inspection device and system for shell structure defect detection | |
| CN113911729A (en) | Electric toothbrush electric control part automatic assembly system and method based on vision | |
| CN206959802U (en) | A kind of non-contact type high-precision optical measuring equipment for curved surface mouse base | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN111232592B (en) | Black paint detection and paint removal device of radiator | |
| CN113155847A (en) | Oil smoke cover surface defect detecting system based on AI 3D vision | |
| CN219608806U (en) | Appearance detection equipment for lens cambered surface product | |
| CN209408173U (en) | A kind of robot polishing system | |
| CN116008294B (en) | Key cap surface particle defect detection method based on machine vision | |
| CN218331280U (en) | Cylinder inner hole flaw detection equipment | |
| CN216728343U (en) | Multistation automobile chassis foundry goods defect automatic check out system | |
| CN206178859U (en) | Spout a yard detection and identification device | |
| CN114354633B (en) | Ceramic bathroom appearance quality detection system and detection method |
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 |