CN108615232A - Method and device for detecting defects of ceramic layer and detection platform - Google Patents
Method and device for detecting defects of ceramic layer and detection platform Download PDFInfo
- Publication number
- CN108615232A CN108615232A CN201810282815.1A CN201810282815A CN108615232A CN 108615232 A CN108615232 A CN 108615232A CN 201810282815 A CN201810282815 A CN 201810282815A CN 108615232 A CN108615232 A CN 108615232A
- Authority
- CN
- China
- Prior art keywords
- photo
- detected
- enamel
- product
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 126
- 238000001514 detection method Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000000919 ceramic Substances 0.000 title 1
- 229910052573 porcelain Inorganic materials 0.000 claims abstract description 21
- 210000003298 dental enamel Anatomy 0.000 claims description 146
- 239000002320 enamel (paints) Substances 0.000 claims description 138
- 230000002950 deficient Effects 0.000 claims description 23
- 238000003860 storage Methods 0.000 claims description 17
- 230000033001 locomotion Effects 0.000 claims description 12
- 230000008439 repair process Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 17
- 239000000037 vitreous enamel Substances 0.000 abstract 1
- 239000000047 product Substances 0.000 description 131
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000006227 byproduct Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method and a device for detecting defects of a porcelain layer and a detection platform. Wherein, the method comprises the following steps: acquiring a photo of a to-be-detected porcelain layer of the porcelain enamel product to obtain the to-be-detected photo; judging whether the porcelain layer to be detected has defects or not according to the photo to be detected, wherein when the porcelain layer to be detected has defects, the photo to be detected carries information different from a target picture, and the target picture is the photo of the porcelain layer without defects; and marking the position of the defect in the picture to be detected under the condition that the defect exists in the porcelain layer to be detected. The invention solves the technical problem of unreliable defect manual inspection.
Description
Technical field
The present invention relates to detection fields, flat in particular to a kind of detection method of enamel coating defect, device and detection
Platform.
Background technology
When detecting enamel inner container, especially enamel inner container surface when, desk checking can only be carried out at present.Sentenced by experience
The enamel coating of disconnected enamel inner container whether there is defect.But since the range for needing to detect is bigger, and there are dead angles for enamel inner container
Region manually can not accurately be judged to whether there is defect, be easy to cause the insecure technical problem of defects detection.
For above-mentioned problem, currently no effective solution has been proposed.
Invention content
An embodiment of the present invention provides a kind of detection method, device and the detection platforms of enamel coating defect, at least to solve people
Work checks the insecure technical problem of defect.
One side according to the ... of the embodiment of the present invention provides a kind of detection method of enamel coating defect, including：Obtain enamel
The photo of the enamel coating to be detected of product, obtains photo to be detected；It is described to judge to compare the photo to be detected and Target Photo
Enamel coating to be detected is with the presence or absence of scarce；In the case where judging the enamel coating existing defects to be detected, in the photo to be detected
In mark the position of the defect.
Optionally, after obtaining the photo of enamel coating to be detected of enamel product, the method further includes：It is warded off described in scanning
The identification code of porcelain products, wherein the identification code is used to indicate the identity information of the enamel product；By the photo to be detected
With the identification code associated storage.
Optionally, the method further includes：Before obtaining the photo of enamel coating to be detected of enamel product, to the enamel
Product is encoded, and product serial number coding is obtained；After obtaining the photo of enamel coating to be detected of enamel product, by the product
Serial number code and the photo associated storage to be detected.
Optionally, the photo to be detected and Target Photo are compared to judge that the enamel coating to be detected whether there is defect packet
It includes：The photo to be detected is compared with the Target Photo, wherein the Target Photo includes the first picture and second
Picture, first picture are the picture of no defective product, and the second picture is the picture of defective product；In the target
In the case that picture is the first picture, if in the case that the photo to be detected is carried with the first picture different characteristic,
Determine the enamel coating existing defects to be detected；In the case where the Target Photo is second picture, if the photo to be detected
In the case of carrying the defect information same characteristic features with the second picture, the enamel coating existing defects to be detected are determined.
Optionally, the enamel product is enamel inner container, obtains the photo of the enamel coating to be detected of enamel product, obtains to be checked
Surveying photo includes：According to the side wall of enamel inner container described in target time interval or target step rotary taking, multiple sides are obtained
Wall picture；After the side wall for completing to shoot the enamel inner container, the bottom cover image of the enamel inner container is shot；It will be the multiple
Side wall picture and the bottom cover image are spliced, and the photo to be detected is obtained.
Optionally, after marking the position of the defect in the photo to be detected, the method further includes：Judge
Whether the type of the defect is that can repair type；In the case where the type of the defect is that can repair type, warded off to described
Porcelain products carry out repair process；In the case where the type of the defect is unrepairable type, the enamel product is carried out
Scrap processing.
One side according to the ... of the embodiment of the present invention provides a kind of detection platform of enamel coating defect, including：Product conveys
Device, for conveying enamel product movement；Detection station is arranged on the transport path of the product conveying device, for setting
Set the equipment for detecting the enamel product；Video camera is arranged in the detection station, described for being moved in enamel product
When detection station, the photo of the enamel coating to be detected of the enamel product is shot, photo to be detected is obtained；Processor is taken the photograph with described
Camera is connected, and is lacked for comparing the photo to be detected and Target Photo to judge that the enamel coating to be detected whether there is,
In the case of judging the enamel coating existing defects to be detected, the position of the defect is marked in the photo to be detected.
Optionally, the detection station is additionally provided with：Servo-drive guide rail is connected with the video camera, for driving
The camera motion controls the video camera and is moved down on the inside of the enamel product to the inside of the enamel product
It is dynamic, or rotation.
Optionally, it is also equipped with light source on the servo-drive guide rail, is moved together with the video camera, for being described
Video camera provides illumination needed for shooting.
Optionally, the detection platform further includes：Clamping device is correspondingly arranged with the detection station, for described
When enamel product moves to the detection station, the enamel product is clamped.
Optionally, the detection platform further includes：Identification device is disposed adjacent with the detection station, for described
When enamel product moves to the detection station, the identification code of the enamel product is identified.
Optionally, the detection platform further includes：Capture apparatus is disposed adjacent with the detection station, is used for from described
The enamel product is grabbed the detection station by product conveying device.
Optionally, the detection platform further includes：Offline robot is disposed adjacent with the detection station, for that will deposit
It is removed from the detection station in the enamel product of defect.
Optionally, the detection platform further includes：Communication device is connected between the processor and the video camera,
Photo for shooting the video camera is transferred to the processor.
One side according to the ... of the embodiment of the present invention provides a kind of detection device of enamel coating defect, including：It obtains single
Member, the photo of the enamel coating to be detected for obtaining enamel product, obtains photo to be detected；Detection unit, for comparing described wait for
Photo and Target Photo are detected to judge that the enamel coating to be detected whether there is defect；Marking unit, for described in judging
In the case of enamel coating existing defects to be detected, the position of the defect is marked in the photo to be detected.
The present embodiment shoots the enamel coating of enamel, and whether the photo for comparing out shooting prompts enamel coating defective,
In the case of prompting enamel coating defective, fall vacant sunken position, convenient for subsequently handling enamel coating, this profit are marked in photo
The scheme for searching enamel coating defect is compared with photo, all enamel coatings of enamel product can be detected, be avoided hand inspection
When missing inspection, solve the insecure technical problem of hand inspection defect.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and is constituted part of this application, this hair
Bright illustrative embodiments and their description are not constituted improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of flow chart of the detection method of enamel coating defect according to the ... of the embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of the detection platform of enamel coating defect according to the ... of the embodiment of the present invention；
Fig. 3 is the schematic diagram of video camera according to the ... of the embodiment of the present invention and product pipeline；
Fig. 4 is the schematic diagram of the detection platform of enamel coating defect according to the ... of the embodiment of the present invention；
Fig. 5 is the schematic diagram of the detection device of enamel coating defect according to the ... of the embodiment of the present invention.
Specific implementation mode
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model that the present invention protects
It encloses.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
It includes to be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment to cover non-exclusive
Those of clearly list step or unit, but may include not listing clearly or for these processes, method, product
Or the other steps or unit that equipment is intrinsic.
According to embodiments of the present invention, a kind of embodiment of the method for the detection method of enamel coating defect is provided, needs to illustrate
It is that step shown in the flowchart of the accompanying drawings can execute in the computer system of such as a group of computer-executable instructions,
Also, although logical order is shown in flow charts, and it in some cases, can be to be executed different from sequence herein
Shown or described step.
Fig. 1 is the detection method of enamel coating defect according to the ... of the embodiment of the present invention, as shown in Figure 1, this method includes following step
Suddenly：
S102 obtains the photo of the enamel coating to be detected of enamel product, obtains photo to be detected.
The shape of enamel product can be planar as, cylindric, cylindric, square tube shape or other irregular shapes.
Enamel coating to be detected can be the inside enamel coating of cylindric enamel product, can also be the outside porcelain of cylindric enamel product
Layer, for flat enamel product, enamel coating to be detected can be the surface enamel coating of enamel product.
Optionally, the enamel product is enamel inner container, obtains the photo of the enamel coating to be detected of enamel product, obtains to be checked
Surveying photo includes：According to the side wall of enamel inner container described in target time interval or target step rotary taking, multiple sides are obtained
Wall picture；After the side wall for completing to shoot the enamel inner container, the bottom cover image of the enamel inner container is shot；It will be the multiple
Side wall picture and the bottom cover image are spliced, and the photo to be detected is obtained.
The photo that the enamel coating to be detected of enamel product is shot using video camera can not be shot when video camera shoots a film,fault
In the case of entire enamel coating to be detected, it can repeatedly be shot using video camera, obtain multiple pictures, then to obtaining
Multiple pictures are spliced, and the photo to be detected of entire enamel coating to be detected is obtained.
For example, for cylindric enamel inner container, enamel coating is located at the inside of enamel inner container.Video camera extend into enamel inner container
Inside rotary taking inner side of liner surface photo, obtain the photo of multiple side walls.When shooting photo every the unit interval
Or rotary distance is taken pictures once, is repeatedly shot according to the length of liner.It, can be first close to liner when liner is longer
The part rotary taking of opening, after completing shooting, then in the position rotary taking close to liner at the bottom, to shoot the whole of liner
A inner surface.When shooting the side wall of liner, controlling any continuous two images has about 1 centimetre of length overlapping, favorably
In defects detection, missing inspection is prevented.In the bottom of the side wall and then shooting liner that have shot liner.The video camera can be high
Speed shooting video camera, reduces influence of the shake caused by camera motion to photo.In camera motion, may be used even
Speed movement.
After the side wall and bottom cover for completing shooting liner, all photos of the enamel inner container are spliced, are waited for
Photo is detected, whether the enamel coating further to judge enamel inner container is defective.
S104 compares the photo to be detected and Target Photo to judge that the enamel coating to be detected whether there is defect.
Image analysis is carried out to photo to be detected, photo and Target Photo to be detected are compared, to find out photo to be detected
In the information different from Target Photo.Since Target Photo is the photo of the enamel coating there is no defect, if photo packet to be detected
The information different from Target Photo is included, illustrates that the photo to be detected is the photo of the enamel coating of existing defects.
Optionally, the photo to be detected and Target Photo are compared to judge that the enamel coating to be detected whether there is defect packet
It includes：The photo to be detected is compared with the Target Photo, wherein the Target Photo includes the first picture and second
Picture, first picture are the picture of no defective product, and the second picture is the picture of defective product；In the target
In the case that picture is the first picture, if in the case that the photo to be detected is carried with the first picture different characteristic,
Determine the enamel coating existing defects to be detected；In the case where the Target Photo is second picture, if the photo to be detected
In the case of carrying the defect information same characteristic features with the second picture, the enamel coating existing defects to be detected are determined.
Can image coding first be carried out to photo to be detected when comparing, then be compared with the image of Target Photo coding
Compared with.When comparing photo and the first picture to be detected, the image coding and the image of the first picture that find out photo to be detected are compiled
The different place of code.If different image codings can be found, it is determined that the corresponding enamel coating existing defects of the photo to be detected,
Defective locations are located at the represented position of the different image coding.When comparing photo to be detected with second picture, find out
The image coding and the image of defect information in second picture of photo to be detected encode identical place.If can find identical
Image coding, it is determined that the corresponding enamel coating existing defects of the photo to be detected, type and the second picture of defect include scarce
Sunken type is identical.
S106 is marked in the case where judging the enamel coating existing defects to be detected in the photo to be detected
The position of the defect.
In the case where determining defect, the position of marking of defects in photo to be detected also just can determine that the defect is being warded off
Position on the enamel coating of porcelain products, convenient for being subsequently further processed to the enamel product.
The present embodiment shoots the enamel coating of enamel, and whether the photo for comparing out shooting prompts enamel coating defective,
In the case of prompting enamel coating defective, fall vacant sunken position, convenient for subsequently handling enamel coating, this profit are marked in photo
The scheme for searching enamel coating defect is compared with photo, all enamel coatings of enamel product can be detected, be avoided hand inspection
When missing inspection cause the insecure technical problem of artificial detection enamel coating defect, reached improve artificial detection enamel coating defect it is reliable
The technique effect of property.
Optionally, in order to be tracked to enamel product, when shooting the photo of enamel coating, by the knowledge of photo and enamel product
Other code is associated, that is, after obtaining the photo of enamel coating to be detected of enamel product, the method further includes：Described in scanning
The identification code of enamel product, wherein the identification code is used to indicate the identity information of the enamel product；By the photograph to be detected
Piece and the identification code associated storage.
In the case where having identification code on enamel product, direct scanning recognition code, and by photo to be detected and identification code
Associated storage.The identification code can be the product serial number coding imprinted on enamel product, and product serial number coding can be item
The product serial number of shape code, Quick Response Code or other forms encodes, and can also be product serial number coding of written form etc..It is scanning
After obtaining identification code, identification code is transferred to computer or server, is stored together with photo to be detected.Wherein, to be checked
It is that splicing obtains to survey photo, and before splicing, video camera can be often to take a picture one photo of transmission to computer or clothes
Business device, is sent to computer after can also all having been shot to the enamel coating whole photo of entire enamel product or server carries out
Storage, in this case, every time send a photo all with identification code associated storage.
The product serial number of enamel product is encoded and is associated storage with corresponding defective locations and defect type, so as to right
Enamel product is tracked.For example, when enamel product occurs damaged, the defective locations and defect class of the product can be recalled
Type, and then judge damaged Producing reason.Production line can also be optimized according to damaged reason so that the enamel product of production
No longer there is similar defect or damaging problem no longer occurs.
Optionally, the method further includes：Before obtaining the photo of enamel coating to be detected of enamel product, to the enamel
Product is encoded, and product serial number coding is obtained；After obtaining the photo of enamel coating to be detected of enamel product, by the product
Serial number code and the photo associated storage to be detected.
Can be enamel product when shooting the photo of enamel coating to be detected in the case where there is no identification code on enamel product
The product serial number is encoded the identity coding as product, to be subsequently tracked to the product by serial number code.When storage,
Using coding storage is associated with photo.Associated storage is identical in the associated storage of above-mentioned identification code, and details are not described herein again.
If there are after-market products exception occurs, can database liner enamel coating number be called according to identification code or coding at any time
According to analyzing enamel coating quality, realize quality tracing, while according to quality tracing situation, carry out process optimization and change with quality
It is kind.
Intelligent measurement may be implemented in the present embodiment, following scheme can be used：
When liner (enamel product) runs to station, clamping device clamps liner, avoids shaking.
Machine Vision Detection camera is moved by servo-drive guide rail along liner central axes, while driving imaging institute light requirement
Source enters liner inside photographing image.
Servo guide rail drives light source and camera at the uniform velocity to enter liner.Combined light source is opened during entrance, Mei Gedan
Bit length is taken pictures once, is repeatedly shot according to the length of liner.Controlling any continuous two images has about 1 centimetre simultaneously
Length overlapping, be conducive to defects detection, prevent missing inspection.
The high speed of camera, which is taken pictures, can effectively reduce guide rail movement and shake influence to generation of taking pictures.
Camera is often shot once, and the image of acquisition is transferred to computer immediately via data line, is completed at the same time the image
On defect inspection and mark.After the multiple shooting for completing each liner.Computer is by multiple collected image mosaics
And it is launched into a complete liner image, and carry out qualification determination.
When reaching upper cover position, continues to shoot bottom cover image, and be transferred to computer, complete defect inspection and mark
Know.
After the completion of all taking pictures, servo guide rail, which quickly exits, exits machine vision camera, completes primary complete bat
Take the photograph process.
The present embodiment can utilize manual intervention pattern and artificial teaching mould when judging whether photo to be detected is defective
Formula is combined.Since photo detection depends on huge database, need manually to impart knowledge to students when database is complete：Setting
Manual intervention pattern, artificial teaching pattern.After the liner component global image of shooting, abnormal position is marked, by manually carrying out
Judgement；Database learns the result manually judged.After database preserves data, and reach high in the clouds backup, it is ensured that data are protected
Deposit reliability.
Optionally, after marking the position of the defect in the photo to be detected, the method further includes：Judge
Whether the type of the defect is that can repair type；In the case where the type of the defect is that can repair type, warded off to described
Porcelain products carry out repair process；In the case where the type of the defect is unrepairable type, the enamel product is carried out
Scrap processing.
The type of defect includes lacking porcelain, burst porcelain and pin hole etc..Be in the type for detecting defect it is recoverable, can
With by the enamel product it is offline arrive pending district, waiting be further processed the case where the type for detecting defect is unrepairable
Under, which can be carried out scrapping processing.
The embodiment of the present invention also provides a kind of detection platform of enamel coating defect.As shown in Fig. 2, the detection of the enamel coating defect is flat
Platform includes：
Product conveying device 22 is moved for conveying enamel product 20；The shape of enamel product can be planar as, cylinder
Shape, cylindric, square tube shape or other irregular shapes.Enamel coating to be detected can be the inside porcelain of cylindric enamel product
Layer can also be the outside enamel coating of cylindric enamel product, and for flat enamel product, enamel coating to be detected can be with
It is the surface enamel coating of enamel product.
Product conveying device 22 can be assembly line, and conveying enamel product moves on assembly line.The product conveying device
22 can be carrier chain 31 shown in Fig. 3, and enamel product 20 is workpiece 32 shown in Fig. 3.
Detection station 24 is arranged on the transport path of the product conveying device, and the enamel production is detected for being arranged
The equipment of product；
Detection station 24 can be the position being oppositely arranged with product conveying device 22, station 33 as shown in Figure 3.
Video camera 26 is arranged in the detection station, for when enamel product moves to the detection station, shooting
The photo of the enamel coating to be detected of the enamel product, obtains photo to be detected.
Video camera is vision-based detection camera 34 shown in Fig. 3, is arranged in station 33 shown in Fig. 3.The vision-based detection
Camera 34 can be moved up and down or be rotated in station 33, so that the enamel coating to enamel product is shot.
It should be noted that Fig. 2 only schematically illustrates the relationship between each location component, component is not limited
Size relationship.
Processor 28 is connected with the video camera 26, judges for comparing the photo to be detected and Target Photo
The enamel coating to be detected is with the presence or absence of lacking, in the case where judging the enamel coating existing defects to be detected, described to be detected
The position of the defect is marked in photo.
Image analysis is carried out to photo to be detected, photo and Target Photo to be detected are compared, to find out photo to be detected
In the information different from Target Photo.
Can image coding first be carried out to photo to be detected when comparing, then be compared with the image of Target Photo coding
Compared with.When comparing photo and the first picture to be detected, the image coding and the image of the first picture that find out photo to be detected are compiled
The different place of code.If different image codings can be found, it is determined that the corresponding enamel coating existing defects of the photo to be detected,
Defective locations are located at the represented position of the different image coding.When comparing photo to be detected with second picture, find out
The image coding and the image of defect information in second picture of photo to be detected encode identical place.If can find identical
Image coding, it is determined that the corresponding enamel coating existing defects of the photo to be detected, type and the second picture of defect include scarce
Sunken type is identical.
In the case where determining defect, the position of marking of defects in photo to be detected also just can determine that the defect is being warded off
Position on the enamel coating of porcelain products, convenient for being subsequently further processed to the enamel product.
The present embodiment shoots the enamel coating of enamel, and whether the photo for comparing out shooting prompts enamel coating defective,
In the case of prompting enamel coating defective, fall vacant sunken position, convenient for subsequently handling enamel coating, this profit are marked in photo
The scheme for searching enamel coating defect is compared with photo, all enamel coatings of enamel product can be detected, be avoided hand inspection
When missing inspection, solve the prior art detection enamel coating defect when be easy missing inspection the technical issues of.
Optionally, as shown in figure 4, the detection station is additionally provided with：Servo-drive guide rail 44 is connected with the video camera
It connects, for driving the camera motion to the inside of the enamel product, and controls the video camera in the enamel product
Inside move up and down, or rotation.
Optionally, it is also equipped with light source on the servo-drive guide rail, is moved together with the video camera, for being described
Video camera provides illumination needed for shooting.
Optionally, the detection platform further includes：Clamping device is correspondingly arranged with the detection station, for described
When enamel product moves to the detection station, the enamel product is clamped.Clamping device (being not shown in Fig. 3) is warded off to be measured
Porcelain products clamp, and avoid shaking.
Optionally, detection platform further includes：Identification device 41 is disposed adjacent with the detection station, for being warded off described
When porcelain products move to the detection station, the identification code 45 of the enamel product is identified.
As shown in figure 4, being provided with identification device 41 on the adjacent position of detection station, which can scan and ward off
Identification code on porcelain products.The identification code can be transferred to processor by identification device, so that processor utilizes identification code pair
Enamel product and photo to be detected are associated storage.
Optionally, the detection platform further includes：Capture apparatus is disposed adjacent with the detection station, is used for from described
The enamel product is grabbed the detection station by product conveying device.
Capture apparatus can capture enamel product from assembly line, and enamel product is put into detection work and is detected, or
Person is put into test station and carries out qualification testing.
Optionally, the detection platform further includes：Offline robot 42 is disposed adjacent with the detection station, and being used for will
The enamel product of existing defects is removed from the detection station.
As shown in figure 4, being provided with offline robot 42 on the adjacent position of detection station, which can incite somebody to action
Defective enamel product is mobile from detection station to be managed region or scraps region everywhere.Wherein, recoverable enamel product
It is moved to processing region, it is not possible to which the enamel product of reparation, which is moved to, scraps region.
Optionally, the detection platform further includes：Communication device is connected between the processor and the video camera,
Photo for shooting the video camera is transferred to the processor.
Communication device can be wired or wireless communication line, for carrying out communication link between processor and video camera
It connects.The processor can be computer 43 shown in Fig. 4.After the computer receives photo, cloud can be saved the data in
Client database ensures the reliability of data, convenient for subsequently being tracked after sale enamel product.For example, occurring in enamel product
After problem, the photo of database is inquired, and the reason of according to photo decision problem, and production procedure is updated with this, avoid having
The enamel product of same problem is in market circulation.
The embodiment of the present invention additionally provides a kind of detection device of enamel coating defect.Fig. 5 is enamel coating according to embodiments of the present invention
The schematic diagram of the detection device of defect.As shown in figure 5, the detection device of the enamel coating defect includes：
Acquiring unit 52 is used to obtain the photo of the enamel coating to be detected of enamel product, obtains photo to be detected；
The shape of enamel product can be planar as, cylindric, cylindric, square tube shape or other irregular shapes.
Enamel coating to be detected can be the inside enamel coating of cylindric enamel product, can also be the outside porcelain of cylindric enamel product
Layer, for flat enamel product, enamel coating to be detected can be the surface enamel coating of enamel product.
Detection unit 54 is for comparing the photo to be detected and Target Photo to judge whether the enamel coating to be detected is deposited
In defect；
The photo that the enamel coating to be detected of enamel product is shot using video camera can not be shot when video camera shoots a film,fault
In the case of entire enamel coating to be detected, it can repeatedly be shot using video camera, obtain multiple pictures, then to obtaining
Multiple pictures are spliced, and the photo to be detected of entire enamel coating to be detected is obtained.
For example, for cylindric enamel inner container, enamel coating is located at the inside of enamel inner container.Video camera extend into enamel inner container
Inside rotary taking inner side of liner surface photo, obtain the photo of multiple side walls.When shooting photo every the unit interval
Or rotary distance is taken pictures once, is repeatedly shot according to the length of liner.It, can be first close to liner when liner is longer
The part rotary taking of opening, after completing shooting, then in the position rotary taking close to liner at the bottom, to shoot the whole of liner
A inner surface.When shooting the side wall of liner, controlling any continuous two images has about 1 centimetre of length overlapping, favorably
In defects detection, missing inspection is prevented.In the bottom of the side wall and then shooting liner that have shot liner.The video camera can be high
Speed shooting video camera, reduces influence of the shake caused by camera motion to photo.In camera motion, may be used even
Speed movement.
After the side wall and bottom cover for completing shooting liner, all photos of the enamel inner container are spliced, are waited for
Photo is detected, whether the enamel coating further to judge enamel inner container is defective.
Image analysis is carried out to photo to be detected, photo and Target Photo to be detected are compared, to find out photo to be detected
In the information different from Target Photo.Since Target Photo is the photo of the enamel coating there is no defect, if photo packet to be detected
The information different from Target Photo is included, illustrates that the photo to be detected is the photo of the enamel coating of existing defects.
Can image coding first be carried out to photo to be detected when comparing, then be compared with the image of Target Photo coding
Compared with.When comparing photo and the first picture to be detected, the image coding and the image of the first picture that find out photo to be detected are compiled
The different place of code.If different image codings can be found, it is determined that the corresponding enamel coating existing defects of the photo to be detected,
Defective locations are located at the represented position of the different image coding.When comparing photo to be detected with second picture, find out
The image coding and the image of defect information in second picture of photo to be detected encode identical place.If can find identical
Image coding, it is determined that the corresponding enamel coating existing defects of the photo to be detected, type and the second picture of defect include scarce
Sunken type is identical.
Marking unit 56 is used in the case where judging the enamel coating existing defects to be detected, in the photo to be detected
In mark the position of the defect.
In the case where determining defect, the position of marking of defects in photo to be detected also just can determine that the defect is being warded off
Position on the enamel coating of porcelain products, convenient for being subsequently further processed to the enamel product.
The present embodiment shoots the enamel coating of enamel, and whether the photo for comparing out shooting prompts enamel coating defective,
In the case of prompting enamel coating defective, fall vacant sunken position, convenient for subsequently handling enamel coating, this profit are marked in photo
The scheme for searching enamel coating defect is compared with photo, all enamel coatings of enamel product can be detected, be avoided hand inspection
When missing inspection, solve the prior art detection enamel coating defect when be easy missing inspection the technical issues of.
In the above embodiment of the present invention, all emphasizes particularly on different fields to the description of each embodiment, do not have in some embodiment
The part of detailed description may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, for example, the unit division, Ke Yiwei
A kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
It connects, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
On unit.Some or all of unit therein can be selected according to the actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can to store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (15)
1. a kind of detection method of enamel coating defect, which is characterized in that including：
The photo for obtaining the enamel coating to be detected of enamel product, obtains photo to be detected；
The photo to be detected and Target Photo are compared to judge that the enamel coating to be detected whether there is defect；
In the case where judging the enamel coating existing defects to be detected, the defect is marked in the photo to be detected
Position.
2. according to the method described in claim 1, it is characterized in that, obtain enamel product enamel coating to be detected photo it
Afterwards, the method further includes：
Scan the identification code of the enamel product, wherein the identification code is used to indicate the identity information of the enamel product；
By the photo to be detected and the identification code associated storage.
3. according to the method described in claim 1, it is characterized in that, the method further includes：
Before obtaining the photo of enamel coating to be detected of enamel product, the enamel product is encoded, product serial number is obtained
Coding；
After obtaining the photo of enamel coating to be detected of enamel product, product serial number coding and the photo to be detected are closed
Connection storage.
4. according to the method described in claim 1, it is characterized in that, comparing the photo to be detected and Target Photo to judge
State enamel coating to be detected includes with the presence or absence of defect：
The photo to be detected is compared with the Target Photo, wherein the Target Photo includes the first picture and the
Two pictures, first picture are the picture of no defective product, and the second picture is the picture of defective product；
The Target Photo be the first picture in the case of, if the photo to be detected carry it is different from first picture
In the case of feature, the enamel coating existing defects to be detected are determined；
The Target Photo be second picture in the case of, if the photo to be detected carry with the second picture lack
In the case of falling into information same characteristic features, the enamel coating existing defects to be detected are determined.
5. according to the method described in claim 1, it is characterized in that, the enamel product be enamel inner container, obtain enamel product
Enamel coating to be detected photo, obtaining photo to be detected includes：
According to the side wall of enamel inner container described in target time interval or target step rotary taking, multiple side wall pictures are obtained；
After the side wall for completing to shoot the enamel inner container, the bottom cover image of the enamel inner container is shot；
The multiple side wall picture and the bottom cover image are spliced, the photo to be detected is obtained.
6. according to the method described in claim 1, it is characterized in that, marking the position of the defect in the photo to be detected
After setting, the method further includes：
Judge whether the type of the defect is that can repair type；
In the case where the type of the defect is that can repair type, repair process is carried out to the enamel product；
In the case where the type of the defect is unrepairable type, the enamel product is carried out to scrap processing.
7. a kind of detection platform of enamel coating defect, which is characterized in that including：
Product conveying device, for conveying enamel product movement；
Detection station is arranged on the transport path of the product conveying device, and setting for the enamel product is detected for being arranged
It is standby；
Video camera is arranged in the detection station, for when enamel product moves to the detection station, being warded off described in shooting
The photo of the enamel coating to be detected of porcelain products, obtains photo to be detected；
Processor is connected with the video camera, described to be checked to judge for comparing the photo to be detected and Target Photo
It surveys enamel coating and whether there is defect, in the case where judging the enamel coating existing defects to be detected, in the photo to be detected
Mark the position of the defect.
8. detection platform according to claim 7, which is characterized in that the detection station is additionally provided with：
Servo-drive guide rail is connected with the video camera, for driving the camera motion to the interior of the enamel product
Portion, and control the video camera and moved up and down in the inside of the enamel product, or rotation.
9. detection platform according to claim 8, which is characterized in that it is also equipped with light source on the servo-drive guide rail,
It is moved with together with the video camera, for providing illumination needed for shooting for the video camera.
10. detection platform according to claim 7, which is characterized in that the detection platform further includes：
Clamping device is correspondingly arranged with the detection station, for when the enamel product moves to the detection station, inciting somebody to action
The enamel product clamps.
11. detection platform according to claim 7, which is characterized in that the detection platform further includes：
Identification device is disposed adjacent with the detection station, for when the enamel product moves to the detection station, knowing
The identification code of the not described enamel product.
12. detection platform according to claim 7, which is characterized in that the detection platform further includes：
Capture apparatus is disposed adjacent with the detection station, for being captured from the product conveying device by the enamel product
To the detection station.
13. detection platform according to claim 7, which is characterized in that the detection platform further includes：
Offline robot is disposed adjacent with the detection station, for there will be the enamel products of defect from the detection station
Upper removal.
14. detection platform according to claim 7, which is characterized in that the detection platform further includes：
Communication device is connected between the processor and the video camera, the photo transmission for shooting the video camera
To the processor.
15. a kind of detection device of enamel coating defect, which is characterized in that including：
Acquiring unit, the photo of the enamel coating to be detected for obtaining enamel product, obtains photo to be detected；
Detection unit judges the enamel coating to be detected with the presence or absence of scarce for comparing the photo to be detected and Target Photo
It falls into；
Marking unit, in the case where judging the enamel coating existing defects to be detected, getting the bid in the photo to be detected
Remember the position for the defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282815.1A CN108615232B (en) | 2018-04-02 | 2018-04-02 | Method, device and platform for detecting defects of porcelain layer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282815.1A CN108615232B (en) | 2018-04-02 | 2018-04-02 | Method, device and platform for detecting defects of porcelain layer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108615232A true CN108615232A (en) | 2018-10-02 |
| CN108615232B CN108615232B (en) | 2024-09-24 |
Family
ID=63659385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810282815.1A Active CN108615232B (en) | 2018-04-02 | 2018-04-02 | Method, device and platform for detecting defects of porcelain layer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108615232B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109900794A (en) * | 2019-04-18 | 2019-06-18 | 深圳市神视检验有限公司 | Fault detection system, method and computer readable storage medium |
| CN111008968A (en) * | 2019-12-04 | 2020-04-14 | 深圳科瑞技术股份有限公司 | Picture processing method and device and storage medium |
| CN114043151A (en) * | 2021-11-29 | 2022-02-15 | 国网四川省电力公司映秀湾水力发电总厂 | A system, method and welding robot for automatic and rapid generation of welding trajectory |
| CN114283269A (en) * | 2021-12-30 | 2022-04-05 | 深圳志涯科技有限公司 | A method for automatically grabbing and detecting clothing label information based on image recognition technology |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11326235A (en) * | 1998-05-06 | 1999-11-26 | Ntt Fanet Systems Kk | Appearance inspection method and device for inspection object |
| JP2000180382A (en) * | 1998-12-11 | 2000-06-30 | Mitsubishi Nuclear Fuel Co Ltd | Visual examination apparatus |
| CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
| CN105572137A (en) * | 2015-12-15 | 2016-05-11 | 重庆瑞阳科技股份有限公司 | Appearance defect test method |
| CN106525873A (en) * | 2016-10-25 | 2017-03-22 | 广州市申发机电有限公司 | Machine vision based full-automatic rotation printed product defect detection device |
| CN106646137A (en) * | 2016-12-28 | 2017-05-10 | 国网通用航空有限公司 | Method of detecting defect of power transmission line, defect detecting device, and defect detecting system |
| CN208092793U (en) * | 2018-04-02 | 2018-11-13 | 珠海格力电器股份有限公司 | Detection platform for ceramic layer defects |
-
2018
- 2018-04-02 CN CN201810282815.1A patent/CN108615232B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11326235A (en) * | 1998-05-06 | 1999-11-26 | Ntt Fanet Systems Kk | Appearance inspection method and device for inspection object |
| JP2000180382A (en) * | 1998-12-11 | 2000-06-30 | Mitsubishi Nuclear Fuel Co Ltd | Visual examination apparatus |
| CN103439337A (en) * | 2013-08-29 | 2013-12-11 | 华南理工大学 | Automatic detection device and method for apparent defects of piezoelectric ceramic buzzers |
| CN105572137A (en) * | 2015-12-15 | 2016-05-11 | 重庆瑞阳科技股份有限公司 | Appearance defect test method |
| CN106525873A (en) * | 2016-10-25 | 2017-03-22 | 广州市申发机电有限公司 | Machine vision based full-automatic rotation printed product defect detection device |
| CN106646137A (en) * | 2016-12-28 | 2017-05-10 | 国网通用航空有限公司 | Method of detecting defect of power transmission line, defect detecting device, and defect detecting system |
| CN208092793U (en) * | 2018-04-02 | 2018-11-13 | 珠海格力电器股份有限公司 | Detection platform for ceramic layer defects |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109900794A (en) * | 2019-04-18 | 2019-06-18 | 深圳市神视检验有限公司 | Fault detection system, method and computer readable storage medium |
| CN111008968A (en) * | 2019-12-04 | 2020-04-14 | 深圳科瑞技术股份有限公司 | Picture processing method and device and storage medium |
| CN111008968B (en) * | 2019-12-04 | 2024-04-12 | 深圳科瑞技术股份有限公司 | Picture processing method, device and storage medium |
| CN114043151A (en) * | 2021-11-29 | 2022-02-15 | 国网四川省电力公司映秀湾水力发电总厂 | A system, method and welding robot for automatic and rapid generation of welding trajectory |
| CN114283269A (en) * | 2021-12-30 | 2022-04-05 | 深圳志涯科技有限公司 | A method for automatically grabbing and detecting clothing label information based on image recognition technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108615232B (en) | 2024-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208092793U (en) | Detection platform for ceramic layer defects | |
| CN108615232A (en) | Method and device for detecting defects of ceramic layer and detection platform | |
| CN111814850B (en) | Defect detection model training method, defect detection method and related device | |
| CN109724984B (en) | Device and method for defect detection and identification based on deep learning algorithm | |
| CN107179324B (en) | Method, device and system for detecting product package | |
| CN106153639B (en) | Circuit board detecting method based on artificial intelligence and its detection device | |
| CN108872265A (en) | Detection method, device and system | |
| CN109685789A (en) | The battery core surface gummed paper detection method and device of view-based access control model detection | |
| JP4747313B2 (en) | Inspection method and inspection equipment for thin plate parts | |
| CN113189109A (en) | Flaw judgment system and flaw judgment method based on artificial intelligence | |
| CN117124302A (en) | Part sorting method and device, electronic equipment and storage medium | |
| CN208333374U (en) | Pipe inner stuffing position detecting device | |
| CN110956285A (en) | Deep learning-based assembly and maintenance construction normative detection method and system | |
| KR20210053509A (en) | Structure defect detecting system using drone | |
| CN111223081A (en) | Part hole opening recognition and detection method and system based on deep learning | |
| CN114501980A (en) | Device and method for pin detection and automatic insertion of special-shaped components | |
| CN118823018A (en) | A method and system for automatic detection of wine box anomalies based on deep learning | |
| KR102766273B1 (en) | Apparatus and method for inspecting nozzles using a rotating method | |
| CN115753782B (en) | Engine cylinder block detection equipment, detection method and detection system | |
| CN114273261B (en) | Simultaneous detection method and system for multiple workpiece suites of automotive interior parts | |
| KR102679611B1 (en) | Apparatus and method for inspecting a nozzle using an image | |
| CN113042397A (en) | System for real wood appearance detection | |
| CN118961585B (en) | An automated visual inspection device | |
| CN111711814A (en) | Camera module defect detection method | |
| TWI833471B (en) | Defect detection method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |