CN106290375A - Based on selective laser sintering technology contactless in line defect automatic checkout system - Google Patents
Based on selective laser sintering technology contactless in line defect automatic checkout system Download PDFInfo
- Publication number
- CN106290375A CN106290375A CN201610556679.1A CN201610556679A CN106290375A CN 106290375 A CN106290375 A CN 106290375A CN 201610556679 A CN201610556679 A CN 201610556679A CN 106290375 A CN106290375 A CN 106290375A
- Authority
- CN
- China
- Prior art keywords
- defect
- fabrication region
- image
- reference picture
- carry out
- 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
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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
- G01N2021/8893—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques providing a video image and a processed signal for helping visual decision
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Powder Metallurgy (AREA)
Abstract
The present invention discloses a kind of based on selective laser sintering technology contactless in line defect automatic checkout system.The execution of this system is a kind of carries out, in increasing material manufacture, the method that defect detects automatically, including: paver powder also selects fabrication region；According to designing for manufacturing figure, generate zero defect reference picture for selected fabrication region；Manufactured by laser sintered material powder in selected fabrication region；Image acquisition is carried out for fabrication region；Carry out contrasting to identify defect with the zero defect reference picture generated for selected fabrication region by the image of the fabrication region collected；If the defect identified needs to process, then Realtime Alerts, stopping produce, take artificial remedial measure and/or remanufacturing.The present invention automatically detects manufacturing defect based on Computer Image Processing, thus realizes quick, stable, reliable defect Automatic Measurement Technique increasing material manufacture field.
Description
Technical field
The present invention relates to increase material manufacture, be more particularly to based on selective laser sintering (Selective Laser
Melting, SLM) the contactless of technology detect (Auto Defect Detection, ADD) system and side automatically in line defect
Method.
Background technology
Increase material manufacture (Additional Manufacturing, AM), print also known as 3D, i.e. the one of rapid shaping technique
Kind, it is based on mathematical model file, use powdery metal or plastics etc. can jointing material, by the side successively printed
Formula constructs the advanced technology of entity.It is that the method using material gradually to add up manufactures entity component owing to increasing material manufacturing technology
Technology, it is different from traditional material and removes Machining Technology for Cutting, is the manufacture method of a kind of " from bottom to top ".
Tradition 3D print defect detection method, is to cooperate with layering preparation feature and successively takes pictures and achieve.Due to data
Measure huge, carry out Manual Visual Inspection to reach the purpose that defect is reviewed only for inefficacy product at present.
Visual inspection backtracking method lacks ageing, and the 3D printed product only with the method still continues a large amount of after producing defect
Successive process, causes huge time, resource, cost waste.And defect cannot be positioned by the method, quantitatively and classification is ground
Study carefully.
Improve constantly in 3D printed product complexity thus challenge under the background of its quality testing ability further, need
The tradition high cost of 3D print defect retroactive method, the low ageing problems such as Manual Visual Inspection is added, it is proposed that one for successively taking pictures
Plant and can manufacture, increasing material, the defect Automatic Measurement Technique quick, stable, reliable that field realizes.
Summary of the invention
It is an object of the invention to provide a kind of defect automatic checkout system based on Computer Image Processing, fast to realize
Speed, stable, reliable defect intelligent online detection.
According to the first aspect of the invention, it is provided that a kind of carry out the method that defect detects automatically increasing in material manufacture, bag
Include following steps: paver powder also selects fabrication region；According to designing for manufacturing figure, generate intact for selected fabrication region
Fall into reference picture；Manufactured by laser sintered material powder in selected fabrication region；Figure is carried out for fabrication region
As gathering；The image of the fabrication region collected is contrasted with the zero defect reference picture generated for selected fabrication region
To identify defect；If the defect identified needs to process, process the most accordingly.
Preferably, if the defect that (i) is identified is in important area, or the quantity of (ii) defect or size exceed threshold
Value, then confirm that the defect identified needs to process.
Preferably, described respective handling include following at least one: Realtime Alerts, stop produce, take manually to remedy
Measure, remanufacturing.
Preferably, by the image of the fabrication region collected and the zero defect reference picture generated for selected fabrication region
Carry out contrasting to identify that defect includes: by the image of the fabrication region collected and the zero defect generated for selected fabrication region
Reference picture carries out asking poor, based on image difference identification defect.
In method according to the first aspect of the invention, if the defect identified need not process, then continue to lay
Material powder is to prepare the manufacture of next layer.
According to the second aspect of the invention, it is provided that a kind of carry out the system that defect detects automatically increasing in material manufacture, bag
Include: selective laser sintering unit, for paver powder and select fabrication region laser sintered to carry out；Reference picture generates
Unit, for according to designing for manufacturing figure, generating zero defect reference picture for selected fabrication region；Image acquisition units, is used for
Image acquisition is carried out for fabrication region；Defect recognition unit, for the image of fabrication region that will collect with for selected
The zero defect reference picture that fabrication region generates carries out contrasting to identify defect；Defect processing unit, if the defect identified
Need to process, then notify that described selective laser sintering unit carries out respective handling.
Preferably, described defect processing unit is further configured to: if the defect that (i) is identified is in important district
Territory, or the quantity of (ii) defect or size exceed threshold value, then confirm that the defect identified needs to process.
Preferably, described respective handling include following at least one: Realtime Alerts, stop produce, take manually to remedy
Measure, notify that described selective laser sintering unit remanufactures.
Preferably, described defect recognition unit is further configured to: by the image of fabrication region that collects with for institute
The zero defect reference picture that the fabrication region of choosing generates carries out asking poor, based on image difference identification defect.
Preferably, described defect processing unit is further configured to: if the defect identified need not process, then lead to
Know that described selective laser sintering unit continues paver powder to prepare the manufacture of next layer.
Based on selective laser sintering technology contactless in line defect automatic checkout system and method according to the present invention,
Set up system hardware and software design system, in conjunction with Intelligent Measurement algorithms such as image procossing, rapid image contrast and defect demarcation, solve
Mass data real-time processes problem, it is ensured that defects detection reliability and economy.Thus provide one and can increase material system
Make the defect Automatic Measurement Technique quick, stable, reliable that field realizes.
Accompanying drawing explanation
Below with reference to the accompanying drawings the present invention it is described in conjunction with the embodiments.In the accompanying drawings:
Fig. 1 is to illustrate to carry out, in increasing material manufacture, the system that defect detects automatically according to an embodiment of the invention
Block diagram.
Fig. 2 is to illustrate to carry out, in increasing material manufacture, the method that defect detects automatically according to an embodiment of the invention
Flow chart.
Fig. 3 is to illustrate the image of fabrication region collected with the zero defect generated for selected fabrication region with reference to figure
As carrying out contrasting to identify the schematic diagram of an example of defect.
Fig. 4 is the flow chart illustrating the defect need method to be processed that confirmation is identified.
Fig. 5 is to illustrate the schematic diagram of the example that defect detects automatically in 3D print procedure.
Detailed description of the invention
The specific embodiment of the present invention is explained in detail below in conjunction with accompanying drawing.
Fig. 1 is to illustrate to carry out, in increasing material manufacture, the system that defect detects automatically according to an embodiment of the invention
Block diagram.
As it is shown in figure 1, carry out the system 100 that defect detects automatically and wrap increasing in material manufacture according to an embodiment of the invention
Include: selective laser sintering (SLM) unit 101, for paver powder and select fabrication region laser sintered to carry out；Reference
Image generation unit 102, for according to designing for manufacturing figure, generating zero defect reference picture for selected fabrication region；Image is adopted
Collection unit 103, for carrying out image acquisition for fabrication region；Defect recognition unit 104, for by image acquisition units 103
The image of the fabrication region collected and reference picture signal generating unit 102 are that the zero defect of selected fabrication region generation is with reference to figure
As carrying out contrasting to identify defect；Defect processing unit 105, if the defect identified needs to process, locates the most accordingly
Reason, such as Realtime Alerts, stopping produce, take artificial remedial measure and/or notify that described SLM unit 101 is made again
Make.
The defect analysis that defect recognition unit 104 can be identified by defect processing unit 105 in operation.If institute
The defect identified is in important area, then this defect is probably critical defect, and in the case, defect processing unit 105 should be true
Recognize this defect and need processed, i.e. need this layer is remanufactured.Although the defect identified is not at important area, but
It is that then defect processing unit 105 should confirm that such defect needs if the quantity of defect or size exceed predetermined threshold value
To be processed, i.e. need this layer is remanufactured.Otherwise, if the defect identified need not process, then defect processing
Unit 105 can notify that described SLM unit continues paver powder to prepare the manufacture of next layer.
In a preferred embodiment of the invention, described zero defect reference picture and the image of the described fabrication region collected
It is gray level image.Hereinafter it will be described in detail.
In a preferred embodiment of the invention, the figure of fabrication region that described defect recognition unit 104 can will collect
As carrying out asking poor, based on image difference identification defect with the zero defect reference picture generated for selected fabrication region.Below
In it will be described in detail.
Fig. 2 is to illustrate to carry out, in increasing material manufacture, the method that defect detects automatically according to an embodiment of the invention
Flow chart.
As in figure 2 it is shown, carry out the method 200 that defect detects automatically and open increasing in material manufacture according to an embodiment of the invention
Starting from step S201, in this step, paver powder also selects fabrication region.As it has been described above, this step can be by Fig. 1
SLM unit 101 performs.
In step S203, according to designing for manufacturing figure, generate zero defect reference picture for selected fabrication region.As above institute
Stating, this step can be performed by the reference picture signal generating unit 102 in Fig. 1.
In a preferred embodiment of the invention, described zero defect reference picture can be gray level image.
In order to carry out the contrast of image, the segmentation of all image available pixel points is expressed, and every Pixel Information is by quantifying ash
Degree level represents, the most totally 256 grades, referred to as gray level image.
In this step, a series of preferable zero defect successively gray level images, its picture can be exported by 3D printed design software
Prime information is described by the grey level quantified as above.For step S203, it is desirable that current manufacture layer
Preferably zero defect gray level image, such as 256 grades gray level images.
In step S205, manufactured by laser sintered material powder in selected fabrication region.As it has been described above, should
Step still can be performed by the SLM unit 101 in Fig. 1.
In step S207, image acquisition is carried out for fabrication region.As it has been described above, this step can be adopted by the image in Fig. 1
Collection unit 103 performs.
In a preferred embodiment of the invention, the image of the fabrication region collected described in can be gray level image.
For the image comprising defect information photographed in manufacture process, need it is processed, to reach
The program that contrasts can be carried out with zero defect reference picture (such as gray level image).It is the most reasonable that image processing process can include
Select the sampling interval (Down-sampling) to ensure suitable image size, filter (Filter) be added or removed with the most aobvious
Show some defect characteristic, keep rational gray level and resolution to carry out digital-to-analogue conversion, it is achieved pixel digitization.
In step S209, by the image of the fabrication region collected and the zero defect reference generated for selected fabrication region
Image carries out contrasting to identify defect.As it has been described above, this step can be performed by the defect recognition unit 104 in Fig. 1.
In a preferred embodiment of the invention, by the image of fabrication region that collects with for selected fabrication region
The zero defect reference picture generated carries out asking poor, based on image difference identification defect.
Specifically, carry out with the gray value of the image (after suitably processing) gathered in step S207 with reference picture
Comparison pixel-by-pixel asks poor, and the gray scale difference value of same matrix coordinate is determined Defect Edge standardized testing by optimizing threshold value
(Normalization) algorithm.
The difference of gray value may be used for defect quickly position, dimension measurement and classification.Number of pixels shared by defect can table
Levying its size, gray scale peak-valley difference then characterizes the depth.Signal distributions feature according to different defects also can be classified.
Fig. 3 is to illustrate the image of fabrication region collected with the zero defect generated for selected fabrication region with reference to figure
As carrying out contrasting to identify the schematic diagram of an example of defect.In figure 3, left side a figure is reference picture, and middle b figure is to adopt
The image that collection arrives, the right c figure is the result of image comparison, and figure below is then the numeric representation of gray scale.In figure 3, every lattice represent one
Individual pixel.Reference picture can be different due to material and process conditions with the base grey value of the image collected, right
The histogram in c figure is produced than seeking after the recovery.Studied by the piecemeal engineering that 3D is printed, determine layered weighting defect
Different threshold value crucial.If value is the least, superthreshold pixel increases, it is likely that catches and does not too much affect final products
The invalid defect of performance, otherwise, then defect can not be produced effective early warning.According to the feature analysis for defect pixel (such as,
Occur in which kind of position of part, size, length-width ratio, just fluctuating situation etc.) determine its classification and the need of or need what
Plant post processing.Such as shown in Fig. 3, c figure is that image comparison seeks poor gray scale schematic diagram, it is assumed that determine defect threshold value according to technological requirement
Being 5, the most all pixels being more than 5 are defect area, and how many defect size is directly proportional to superthreshold pixel.Individually or minority
Pixel is connected and is identified as point defect, and greater area of most pixels are assembled and are then referred to as area defects (Area Defect).
Being more than certain constant (typically larger than 2) as area defects meets superthreshold pixel length-width ratio, the most this kind of planar defect typically can be assert
For cut, see c and scheme S. frame.As area defects approximation is closed and comprises normality threshold pixel, then can be big according to intensity profile
Cause to judge the situation that defect height rises and falls.The highest then defect of grey level rises and falls the most obvious, sees c and schemes P. frame.Thus, complete right
The identification of defect.
In step S211, the defect identified is judged the need of process.As it has been described above, this judgement step can
Performed by the defect processing unit 105 of Fig. 1.If the defect identified needs to process, i.e. the judged result of step S211 is
"Yes", then Realtime Alerts, stopping produce and judge whether do over again (artificial remedial measure or remanufacturing), it is to avoid continue production and make
The material become and cost loss.In the present invention, typically can stop after warning producing, then need personnel to carry out intervention and sentence
Disconnected, the most manually remedy or remanufacture.Artificial remedial measure includes: such as, adds in the powder of defective locations
A little special composition, sintering temperature adjusts etc..In this example, in the case of the defect needs identified process, by SLM
Unit 101 remanufactures.In the case, method 200 returns to step S201.On the other hand, if identified lacks
Fall into and need not process, i.e. the judged result of step S211 is "No", then method 200 terminates.In other words, in this case,
Can continue next layer is manufactured.
Can launch to be described by step S211 of Fig. 2.According to a preferred embodiment of the present invention, the step of Fig. 2
The execution of S211 can be carried out, the most as shown in Figure 4 by two judgements.
Fig. 4 is the flow chart illustrating the defect need method to be processed that confirmation is identified.
As shown in Figure 4, method 400 is undertaken in step S209 of Fig. 2.In step S401, it is judged that whether the defect identified
It is in important area.As it has been described above, if defect is positioned in important area, the most such defect is probably critical defect.At this
In the case of, when i.e. the judged result of step S401 is "Yes", in step S405, need to process accordingly, i.e. in this example
In remanufacture exactly.On the other hand, if defect is not positioned in important area, i.e. the judged result of step S401 is "No"
Time, then also need to whether step S403 exceedes predetermined threshold value judge for quantity or the size of defect.If
Quantity or the size of defect exceed threshold value, when i.e. the judged result of step S403 is "Yes", with the judged result of step S401 are
The situation of "Yes" is identical, in step S405, needs to process accordingly, remanufactures the most exactly.The opposing party
Face, if the quantity of defect or size are not above threshold value, when i.e. the judged result of step S403 is "No", can not be to defect
Process, and continue next layer is manufactured.
Fig. 5 is to illustrate the schematic diagram of the example that defect detects automatically in 3D print procedure.In the example of hgure 5, right
Part in manufacture carries out real time image collection, contrasts with reference picture, can monitor the situation of defect growth in real time.?
In Fig. 5, Fig. 5 a represents reference pattern, Fig. 5 b, 5c and 5d represent the most respectively defect produce, the situation that grows and expand and defect
Automatically the signal of detection.In the example of Fig. 5, needing the part carrying out 3D printing is a complex parts.When development of defects to Fig. 5 d
During shown situation, need defect is judged the need of carrying out process, to determine whether to proceed next layer
Manufacture, be also by respective handling, such as, manufacture re-started for current layer.
Carrying out the method that defect detects automatically and can also be summarised increasing in material manufacture according to the specific embodiment of the invention
For following steps, including:
1. print Layered manufacturing design drawing according to 3D, generate zero defect reference picture a (x), wherein x for defects detection when layer
For sinter layer sequence number.This step also comprises selection sintering zone and background area；
2. lay when layer material powder and carry out selective laser sintering；
3. pair fabrication region is sintered rear image acquisition, obtains b (x) image；
4. image b (x) of the fabrication region collected with zero defect reference picture a (x) contrast thus is carried out defect knowledge
Not；
5. met specific criteria (can adjust according to the actual requirement of part and technique) such as identification defect, be then identified as
" critical defect " of subsequent production may be affected；
6. " critical defect " produces, then Realtime Alerts, stopping produce and judge whether to do over again, it is to avoid continue what production caused
Material and cost loss.
It should be noted that in above method step, " generating zero defect reference picture " is with " laying is when layer material powder
End also carries out selective laser sintering " between there is no strict sequencing point.Additionally, about the identification of " critical defect ", to the greatest extent
Pipe, in the description of Fig. 4, is judged by the position of defect and quantity or size, but those skilled in the art should manage
Solving, as described in above step 5, the specific criteria that identified defect needs meet can be according to part and the actual requirement of technique
Adjust.
As it has been described above, automatically detect system according to the based on selective laser sintering technology contactless of the present invention in line defect
System and method, set up system hardware and software design system, in conjunction with Intelligent Measurement such as image procossing, rapid image contrast and defect demarcation
Algorithm, solves mass data real-time and processes problem, it is ensured that defects detection reliability and economy.Thus provide one can
The defect Automatic Measurement Technique quick, stable, reliable that field realizes is manufactured increasing material.
It is described above various embodiments of the present invention and implements situation.But, the spirit and scope of the present invention are not
It is limited to this.Those skilled in the art can make more application according to the teachings of the present invention, and these application are all at this
Within the scope of invention.
Claims (10)
1. carry out, in increasing material manufacture, the method that defect detects automatically, comprise the steps:
Paver powder also selects fabrication region；
According to designing for manufacturing figure, generate zero defect reference picture for selected fabrication region；
Manufactured by laser sintered material powder in selected fabrication region；
Image acquisition is carried out for fabrication region；
Carry out the image of the fabrication region collected and the zero defect reference picture generated for selected fabrication region contrasting with
Identify defect；
If the defect identified needs to process, then carry out respective handling.
Method the most according to claim 1, wherein, if
I defect that () is identified is in important area, or
(ii) quantity or the size of defect exceedes threshold value,
Then confirm that the defect identified needs to process.
Method the most according to claim 1, wherein, described respective handling include following at least one: Realtime Alerts, stop
Only produce, take artificial remedial measure, remanufacturing.
Method the most according to claim 1, wherein, by the image of fabrication region that collects with for selected fabrication region
The zero defect reference picture generated carries out contrasting to identify that defect includes:
Carry out seeking gray scale with the zero defect reference picture generated for selected fabrication region by the image of the fabrication region collected
Difference, based on difference identification defect.
Method the most according to claim 1, farther includes: if the defect identified need not process, then continue paving
If material powder is to prepare the manufacture of next layer.
6. carry out, in increasing material manufacture, the system that defect detects automatically, including:
Selective laser sintering unit, for paver powder and select fabrication region laser sintered to carry out；
Reference picture signal generating unit, for according to designing for manufacturing figure, generating zero defect reference picture for selected fabrication region；
Image acquisition units, for carrying out image acquisition for fabrication region；
Defect recognition unit, the image of the fabrication region for collecting is joined with the zero defect generated for selected fabrication region
Examine image to carry out contrasting to identify defect；
Defect processing unit, if the defect identified needs to process, then carries out respective handling.
System the most according to claim 6, wherein, described defect processing unit is further configured to: if
I defect that () is identified is in important area, or
(ii) quantity or the size of defect exceedes threshold value,
Then confirm that the defect identified needs to process.
System the most according to claim 6, wherein, described respective handling include following at least one: Realtime Alerts, stop
Only produce, take artificial remedial measure, notify that described selective laser sintering unit remanufactures.
System the most according to claim 6, wherein, described defect recognition unit is further configured to:
With the zero defect reference picture generated for selected fabrication region, the image of the fabrication region collected is carried out gray scale ask
Difference, based on differential analysis identification defect.
System the most according to claim 6, wherein, described defect processing unit is further configured to: if identified
Defect need not process, then notify described selective laser sintering unit continue paver powder to prepare the system of next layer
Make.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556679.1A CN106290375A (en) | 2016-07-14 | 2016-07-14 | Based on selective laser sintering technology contactless in line defect automatic checkout system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610556679.1A CN106290375A (en) | 2016-07-14 | 2016-07-14 | Based on selective laser sintering technology contactless in line defect automatic checkout system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106290375A true CN106290375A (en) | 2017-01-04 |
Family
ID=57651612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610556679.1A Pending CN106290375A (en) | 2016-07-14 | 2016-07-14 | Based on selective laser sintering technology contactless in line defect automatic checkout system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106290375A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107014821A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of plastics valve bag detecting system and method |
| CN107014822A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of non-woven fabrics gauze mask defective vision detecting system and method |
| CN107402220A (en) * | 2017-07-01 | 2017-11-28 | 华中科技大学 | A kind of selective laser fusing shaping powdering quality vision online test method and system |
| CN107672161A (en) * | 2017-09-06 | 2018-02-09 | 江苏大学 | The method of testing and test platform of a kind of selective laser sintering |
| CN107894425A (en) * | 2017-11-20 | 2018-04-10 | 伟创力电子技术(苏州)有限公司 | The defects of one kind is based on two-dimentional automatic optical detector detects accessory system |
| CN109187755A (en) * | 2018-09-12 | 2019-01-11 | 西安交通大学 | A kind of online supersonic damage-free detection method based on 3D printing |
| CN109304871A (en) * | 2018-09-25 | 2019-02-05 | 湖南华曙高科技有限责任公司 | A kind of powdering control method and its increasing material manufacturing equipment |
| CN109334009A (en) * | 2018-09-25 | 2019-02-15 | 湖南华曙高科技有限责任公司 | A kind of powdering control method, equipment and readable storage medium storing program for executing |
| CN111257335A (en) * | 2020-01-09 | 2020-06-09 | Oppo（重庆）智能科技有限公司 | Method for detecting dust points in electronic equipment |
| CN112819717A (en) * | 2021-01-29 | 2021-05-18 | 山东建筑大学 | Shaving board image gray value correction method and device |
| CN113016004A (en) * | 2018-11-16 | 2021-06-22 | 阿莱恩技术有限公司 | Machine-based three-dimensional (3D) object defect detection |
| CN113358971A (en) * | 2021-04-27 | 2021-09-07 | 国网山东省电力公司淄博供电公司 | Distribution line tree obstacle positioning method and monitoring device based on visible light image analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1482579A (en) * | 2002-09-13 | 2004-03-17 | ��ʿͨ��ʽ���� | Image defect inspecting apparatus and image defect inspecting method |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| US20150177158A1 (en) * | 2013-12-13 | 2015-06-25 | General Electric Company | Operational performance assessment of additive manufacturing |
| CN105081325A (en) * | 2015-08-28 | 2015-11-25 | 许昌学院 | Surface quality control device for three-dimensional (3D) part formed through metal drop printing and control method of surface quality control device |
-
2016
- 2016-07-14 CN CN201610556679.1A patent/CN106290375A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1482579A (en) * | 2002-09-13 | 2004-03-17 | ��ʿͨ��ʽ���� | Image defect inspecting apparatus and image defect inspecting method |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| US20150177158A1 (en) * | 2013-12-13 | 2015-06-25 | General Electric Company | Operational performance assessment of additive manufacturing |
| CN105081325A (en) * | 2015-08-28 | 2015-11-25 | 许昌学院 | Surface quality control device for three-dimensional (3D) part formed through metal drop printing and control method of surface quality control device |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107014822A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of non-woven fabrics gauze mask defective vision detecting system and method |
| CN107014821A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of plastics valve bag detecting system and method |
| CN107402220B (en) * | 2017-07-01 | 2019-07-19 | 华中科技大学 | A kind of selective laser fusing forming powdering quality vision online test method and system |
| CN107402220A (en) * | 2017-07-01 | 2017-11-28 | 华中科技大学 | A kind of selective laser fusing shaping powdering quality vision online test method and system |
| CN107672161A (en) * | 2017-09-06 | 2018-02-09 | 江苏大学 | The method of testing and test platform of a kind of selective laser sintering |
| CN107894425A (en) * | 2017-11-20 | 2018-04-10 | 伟创力电子技术(苏州)有限公司 | The defects of one kind is based on two-dimentional automatic optical detector detects accessory system |
| CN109187755A (en) * | 2018-09-12 | 2019-01-11 | 西安交通大学 | A kind of online supersonic damage-free detection method based on 3D printing |
| CN109187755B (en) * | 2018-09-12 | 2020-05-22 | 西安交通大学 | Online ultrasonic nondestructive testing method based on 3D printing |
| CN109304871A (en) * | 2018-09-25 | 2019-02-05 | 湖南华曙高科技有限责任公司 | A kind of powdering control method and its increasing material manufacturing equipment |
| CN109334009A (en) * | 2018-09-25 | 2019-02-15 | 湖南华曙高科技有限责任公司 | A kind of powdering control method, equipment and readable storage medium storing program for executing |
| CN113016004A (en) * | 2018-11-16 | 2021-06-22 | 阿莱恩技术有限公司 | Machine-based three-dimensional (3D) object defect detection |
| US12073552B2 (en) | 2018-11-16 | 2024-08-27 | Align Technology, Inc. | Automated quality control for three-dimensional (3D) printed mold for orthodontic aligner |
| CN111257335A (en) * | 2020-01-09 | 2020-06-09 | Oppo（重庆）智能科技有限公司 | Method for detecting dust points in electronic equipment |
| CN111257335B (en) * | 2020-01-09 | 2023-01-24 | Oppo（重庆）智能科技有限公司 | Method for detecting dust points in electronic equipment |
| CN112819717A (en) * | 2021-01-29 | 2021-05-18 | 山东建筑大学 | Shaving board image gray value correction method and device |
| CN113358971A (en) * | 2021-04-27 | 2021-09-07 | 国网山东省电力公司淄博供电公司 | Distribution line tree obstacle positioning method and monitoring device based on visible light image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106290375A (en) | Based on selective laser sintering technology contactless in line defect automatic checkout system | |
| CN105976352B (en) | One kind being based on the morphologic face of weld defect characteristic extracting method of gray level image | |
| CN107402220A (en) | A kind of selective laser fusing shaping powdering quality vision online test method and system | |
| CN112036755B (en) | Supervision method and system for quality detection of building engineering | |
| CN112967243A (en) | Deep learning chip packaging crack defect detection method based on YOLO | |
| US20060093082A1 (en) | Method of inspection for inner defects of an object and apparatus for same | |
| CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| TWI642126B (en) | Semiconductor wafer analyzing sytem and method thereof | |
| CN113324864B (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN115797354B (en) | Method for detecting appearance defects of laser welding seam | |
| JP6448065B2 (en) | Image processing system, image processing method, and image processing program | |
| JP2013235578A (en) | Image processing apparatus | |
| CN108492291A (en) | A kind of photovoltaic silicon chip Defect Detection system and method based on CNN segmentations | |
| Dan et al. | Application of deep learning-based image recognition technology to asphalt–aggregate mixtures: Methodology | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN117274258B (en) | Method, system, equipment and storage medium for detecting defects of main board image | |
| CN110378887A (en) | Screen defect inspection method, apparatus and system, computer equipment and medium | |
| CN113139955B (en) | Photovoltaic module fault identification method and system based on double-light image | |
| JP6788929B1 (en) | Image processing device and image processing method for determining the test object | |
| CN105787955A (en) | Sparse segmentation method and device of strip steel defect | |
| JP7404817B2 (en) | Learning device, detection device, learning method, and learning program | |
| CN115830302B (en) | Multi-scale feature extraction fusion power distribution network equipment positioning identification method | |
| CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model | |
| Abdelgaber et al. | A Novel, Image-Based Method for Characterization of the Porosity of Additively Manufactured Bone Scaffolds with Complex Microstructures | |
| CN113970551A (en) | Material surface quality detection method and system and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |