CN106290394A - A kind of cpu heat aluminium extruded forming defect detecting system and detection method - Google Patents
A kind of cpu heat aluminium extruded forming defect detecting system and detection method Download PDFInfo
- Publication number
- CN106290394A CN106290394A CN201610877132.1A CN201610877132A CN106290394A CN 106290394 A CN106290394 A CN 106290394A CN 201610877132 A CN201610877132 A CN 201610877132A CN 106290394 A CN106290394 A CN 106290394A
- Authority
- CN
- China
- Prior art keywords
- image
- aluminium extruded
- computer
- industrial camera
- shaped article
- 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
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 75
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 75
- 239000004411 aluminium Substances 0.000 title claims abstract description 71
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 230000007547 defect Effects 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 21
- 101000857682 Homo sapiens Runt-related transcription factor 2 Proteins 0.000 claims description 20
- 102100025368 Runt-related transcription factor 2 Human genes 0.000 claims description 20
- 238000007599 discharging Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000002950 deficient Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000006835 compression Effects 0.000 claims 1
- 238000007906 compression Methods 0.000 claims 1
- 238000012797 qualification Methods 0.000 abstract description 3
- 235000012438 extruded product Nutrition 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 3
- 238000000465 moulding Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 230000009931 harmful effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of cpu heat aluminium extruded forming defect detecting system, including image collecting device, computer picture recognition device and COMPUTER DETECTION display device；The invention also discloses a kind of detection method being applied to cpu heat aluminium extruded forming defect detecting system, comprise the following steps: A, aluminium extruded shaped article is carried out image acquisition；B, by view data send to computer；C, image is filtered pretreatment；D, image is carried out greyscale transform process；E, the image after gray proces is carried out Classification and Identification；F, display recognition result；I, storage recognition result.The present invention has and substantially increases the accuracy of detection, reliability and efficiency, the advantage such as qualification rate that improve product.
Description
Technical field
The present invention relates to a kind of cpu heat aluminium extruded forming defect detecting system and method, especially a kind of based on machine
The cpu heat aluminium extruded forming defect detecting system of vision and method, use the method for machine vision to become cpu heat aluminium extruded
Type product detects, by template matching algorithm to the surface flatness of cpu heat aluminium extruded shaped article, bubble and curved
Curvature is identified, and adjusts aluminium extruded template according to recognition result, improves the qualification rate of aluminium extruded shaped article.
Background technology
Computer is in running, and CPU can produce substantial amounts of heat, if heat is not got rid of work in time that reduce CPU
Make temperature, then the runnability of computer can be produced harmful effect.Along with the lifting of CPU speed, the heat radiation to radiator needs
Asking and also improve constantly, radiator develops progressively towards the direction of close tooth, high tooth.Cpu heat typically uses aluminium extruded template legal system
Standby Al squeezing material, traditional aluminium extruded template reaches to control the mesh of aluminum stream flowing speed by height and the width of regulation work strip
, there is the closeest gear piece and will result in the problem that steel material support strength is not enough, tooth height maximum with the ratio of gear piece spacing
15 times can be reached.Aluminum extrusion mould without working zones occurs the most again, substantially increases gear piece density, and by between tooth height and gear piece
Away from ratio increase to more than 20 times, but during aluminium extruded, easily occur that aluminium extruded product distortion deforms, and occur absorption
Grain, bubble, metallic bur power and the surface defect such as rough, these defects all can affect the heat dispersion of radiator.And
Showing from disclosed data, at present in aluminium extruded molding process, the defects detection overwhelming majority of aluminium extruded shaped article is all adopted
By the means of manual detection, detect product by eye-observation and experience the most defective, there is the strongest subjectivity, lack
Accuracy and reliability, and inefficiency, it is impossible to realize Aulomatizeted Detect.Therefore take technological means accurately to carry out detection to be
The most necessary.
Summary of the invention
The primary and foremost purpose of the present invention is that the shortcoming overcoming prior art is with not enough, it is provided that a kind of cpu heat aluminium extruded becomes
Type defect detecting system, the Efficiency and accuracy of this detecting system defects detection is high, and the reliability of detection is high.
The primary and foremost purpose of the present invention is that the shortcoming overcoming prior art is with not enough, it is provided that one is applied to cpu heat
The detection method of aluminium extruded forming defect detecting system, this detection method uses the method for machine vision to lack aluminium extruded shaped article
It is trapped into row vision-based detection, reaches automatically to detect the purpose of defective aluminium extruded shaped article.The primary and foremost purpose of the present invention is by following
Technical scheme realizes: a kind of cpu heat aluminium extruded forming defect detecting system, knows including image collecting device, computer picture
Other device and COMPUTER DETECTION display device, image collecting device is connected with computer picture recognition device, and computer picture is known
Other device is connected with COMPUTER DETECTION display device, and described image collecting device includes CCD1 industrial camera, CCD2 industry phase
Machine, the first image pick-up card and the second image pick-up card, described computer picture recognition device include image processing module and
Template matching module, described computer picture recognition device has been used for the pretreatment of image, greyscale transformation and template
Joining identification, described COMPUTER DETECTION display device includes detecting display module and memory module, and described COMPUTER DETECTION shows
Showing device is used for carrying out showing and storing by testing result, the outfan of described CCD1 industrial camera and the first image pick-up card
Input connect, the input connection of the outfan of described CCD2 industrial camera and the second image pick-up card, the first image
The outfan of capture card and the outfan of the second image pick-up card are all connected with the RS232 serial ports input of computer；First figure
As capture card combines CCD1 industrial camera, and the surface image data of aluminium extruded shaped article that will be collected by RS232 serial ports
Reaching computer picture recognition device, the second image pick-up card combines CCD2 industrial camera, and will be collected by RS232 serial ports
The strain image data of aluminium extruded shaped article reach computer picture recognition device, computer picture recognition device will receive
View data process and identify, and image recognition result is sent to COMPUTER DETECTION display device, described detection shows
Showing that surface image recognition result and strain image recognition result are shown by module, described memory module is by surface image identification
Result and strain image recognition result store.
Described CCD1 industrial camera is for detecting the surface defect of aluminium extruded shaped article, and CCD2 industrial camera is used for detecting
The deformation of aluminium extruded shaped article.
Also include that the Aluminum-Extruding Die, described the Aluminum-Extruding Die include aluminium extruded steel body, charging aperture, empty knife-band and discharging opening,
Described charging aperture, empty knife-band and discharging opening are arranged in order through aluminium extruded steel body, and described CCD1 industrial camera is arranged on discharging opening
Top, CCD2 industrial camera is arranged on the dead ahead of discharging opening.
Another object of the present invention is achieved through the following technical solutions: a kind of be applied to described cpu heat aluminium extruded
The detection method of type defect detecting system, comprises the following steps:
H. aluminium extruded shaped article is carried out image acquisition；
I. view data is sent to computer；
J. image is filtered pretreatment；
K. image is carried out greyscale transform process；
L. the image after gray proces is carried out Classification and Identification；
M. recognition result is shown；
N. recognition result is stored.
In step, the first image pick-up card by CCD1 industrial camera from top complete aluminium extruded shaped article on regard
Image acquisition, the second image pick-up card faces image acquisition by what CCD2 industrial camera completed aluminium extruded shaped article from front.
In stepb, use RS232 serial ports that view data is reached computer.
In step C, gaussian filtering method is used to complete the Filtering Processing of two width images.
In step E, using template matching algorithm to complete the Classification and Identification of image, the identification step of described Classification and Identification is such as
Under:
D. choose a width standard, do not have defective aluminium extruded shaped article image as matches criteria template image；
E. the image collected is carried out location matches, be allowed to complete with the position of the matches criteria template image in step a
Complete corresponding；
F. the matches criteria template image that the image collected is chosen with step a is mated, use correlation coefficient
Join method, calculate the correlation coefficient of image and the matches criteria template image collected, by calculated correlation coefficient to relevant
Coefficient threshold compares and determines whether aluminium extruded shaped article is faulty goods；Computing formula particularly as follows:
Assume that gathering image and matches criteria template image is owned by m × n pixel, use following formula weigh gather image and
The cross correlation of matches criteria template image, D represents degree of association:
Wherein, m represents collection image and total pixel in matches criteria template image abscissa direction, and n represents collection figure
Picture and total pixel in matches criteria template image vertical coordinate direction, i point represents abscissa, and i represents vertical in the range of 1 to m, j
Coordinate, j represents matches criteria template image in the range of 1 to n, T, and (i j) represents that in matches criteria template image, coordinate exists to T
(i, j) gray value of place's pixel, S represents collection image, and (i j) represents that in matches criteria template image, coordinate is at (i, j) place to S
The gray value of pixel；
Will after its normalization the correlation coefficient of template matching, wherein, R represents correlation coefficient:
Above-mentioned formula is used to be calculated the correlation coefficient of template matching, then the correlation coefficient by coefficient R Yu setting
Relatively, if coefficient R is more than correlation coefficient threshold, then the match is successful for threshold ratio, represents that product is qualified, is otherwise considered as coupling and loses
Lose, represent that product is defective.
The detection device of the present invention includes: image collecting device, computer picture recognition device and COMPUTER DETECTION show
Device, described image collecting device includes two CCD industrial cameras and two panels image pick-up card, the aluminium extruded molding that will collect
The image of product reaches computer picture recognition device, and described computer picture recognition device includes that one is provided with at image
Reason and the computer analyzing software, carry out image processing and analysis, described COMPUTER DETECTION display dress by the image received
Put and carry out showing and storing by testing result.Native system uses mechanical vision inspection technology, to the aluminium extruded shaped article collected
Image carries out pretreatment, uses image template matching technology to complete the detection to aluminium extruded shaped article, substantially increases detection
Accuracy, reliability and efficiency, and utilize the testing result display system of native system, operator can according to testing result
In time aluminium extruded mould is carried out detection process, it is ensured that the quality of follow-up aluminium extruded shaped article, improve the qualification rate of product.
In the present invention, CCD camera, image pick-up card, computer are linked in sequence and constitute a control system, CCD industry
Camera includes CCD1 industrial camera and CCD2 industrial camera, and CCD1 industrial camera is arranged on above the Aluminum-Extruding Die discharging opening, uses
In the surface defect of detection aluminium extruded shaped article, CCD2 industrial camera is arranged on the front of the Aluminum-Extruding Die discharging opening, is used for examining
Survey whether aluminium extruded product is distorted deformation.Image pick-up card includes the first image pick-up card and the second image pick-up card, respectively
The collection that realize image supporting with CCD1 industrial camera and CCD2 industrial camera, the image of collection includes image 1 and image 2, figure
As 1 is the top view picture of aluminium extruded shaped article, image 2 is the front view picture of aluminium extruded shaped article.Image pick-up card passes through RS232
View data is reached computer picture recognition device by serial ports, and the image received is filtered pre-by computer picture recognition device
Process, greyscale transform process, and use template matching algorithm, first choose a width standard, do not have defective aluminium extruded molding to produce
Product image, as matches criteria template image, then carries out location matches to the image gathered, is allowed to and matches criteria Prototype drawing
The position of picture is the most corresponding, after location matches completes, uses correlation coefficient process to calculate and gathers image and matches criteria template image
Correlation coefficient, concrete calculating formula is as follows:
Assume to gather image and matches criteria template image is owned by m × n pixel, matches criteria template image T table
Show, T (i, j) represent in matches criteria template image (i, j) gray value of place's pixel, the image S collected represents, S (i,
J) represent that in matches criteria template image, (i, j) gray value of place's pixel use following formula to weigh and gather image and matches criteria
The cross correlation of template image:
Will after its normalization the correlation coefficient of template matching:
Above-mentioned formula is used to be calculated the phase relation of template matching
Number, then it is compared with the correlation coefficient threshold arranged, if more than correlation coefficient threshold, then the match is successful, and product is qualified, otherwise
Being considered as that it fails to match, product is defective.After identification completes, matching result is sent to COMPUTER DETECTION display device to show inspection
Surveying result, substandard product is sorted out by staff according to testing result, it is ensured that the quality of product.
The invention has the beneficial effects as follows: Machine Vision Detection aluminium extruded shaped article can be passed through, use template matching algorithm to sentence
Other product is the most defective, and testing result is shown in COMPUTER DETECTION display device and store, and improves product
The efficiency of quality testing, accuracy and reliability, it is ensured that the quality of cpu heat.
Accompanying drawing explanation
Fig. 1 is the system construction drawing of the present invention.
Fig. 2 is the system schematic of the present invention.
Fig. 3 is the template matching algorithm flow chart of the present invention；Wherein, 1 represents aluminium extruded steel body；2 represent empty knife-band；3 represent
Charging aperture；4 represent discharging opening；5 represent CCD2 industrial camera；6 represent CCD1 industrial camera；7 represent the second image pick-up card；8
Represent the first image pick-up card；9 represent computer.
Detailed description of the invention
The present invention is described in more detail below in conjunction with the accompanying drawings.
Embodiment
As it is shown in figure 1, cpu heat aluminium extruded forming defect detecting system includes that image collecting device, computer picture are known
Other device and COMPUTER DETECTION display device, wherein, described image collecting device includes CCD1 industrial camera and CCD2 work
Industry camera two CCD industrial cameras the first image pick-up card and the second image pick-up card, CCD1 industrial camera is arranged on aluminum
Squeezing the top view picture gathering aluminium extruded product above model discharging opening, CCD2 industrial camera is arranged on the front of aluminium extruded model discharging opening
Gather the front view picture of aluminium extruded product, the image of the aluminium extruded shaped article collected is reached computer picture recognition device, meter
Calculation machine pattern recognition device includes a computer being provided with image processing and analysis software, is entered by the image received
Row filter preprocessing and gray processing process, and use template matching algorithm to be identified image, COMPUTER DETECTION display dress
Put and carry out showing and storing by image testing result.
As in figure 2 it is shown, aluminum stream enters empty knife-band (2) from charging aperture (3), the aluminium extruded product after cooling goes out from discharging opening (4)
Going, at discharging opening (4) CCD1 installed above industrial camera (6), CCD2 industrial camera (5), the first image pick-up card are installed in front
(8) utilizing CCD1 industrial camera (6) to gather the top view picture of aluminium extruded product, the second image pick-up card (7) utilizes CCD2 industry phase
Machine (5) gathers the front view picture of aluminium extruded product, and sends to computer (9), the two width images collected by computer picture
Identify that device carries out pretreatment, greyscale transform process, and use template matching algorithm that image is identified, finally image is examined
Survey result is delivered to COMPUTER DETECTION display device and is carried out showing and storing.
As it is shown on figure 3, template matching algorithm concretely comprises the following steps: the view data collected is delivered to computer picture by first-selection
Identify device, then image is carried out gaussian filtering pretreatment, and image is carried out greyscale transform process, then choose a width mark
Quasi-matching template image, carries out position standard by the image gathering band with matches criteria template image, then uses correlation coefficient
Method calculates the coefficient R gathering image with matching template image, according to coefficient R and correlation coefficient threshold RSetSize
Compare to determine template matching the most successful, thus detect that aluminium extruded product is the most qualified.
Above-described embodiment is the present invention preferably embodiment, but embodiments of the present invention are not by above-described embodiment
Limit, the change made under other any spirit without departing from the present invention and principle, modify, substitute, combine, simplify,
All should be the substitute mode of equivalence, within being included in protection scope of the present invention.
Claims (8)
1. a cpu heat aluminium extruded forming defect detecting system, it is characterised in that: include image collecting device, computer graphic
As identifying device and COMPUTER DETECTION display device, image collecting device is connected with computer picture recognition device, computer graphic
As identifying that device is connected with COMPUTER DETECTION display device, described image collecting device includes CCD1 industrial camera, CCD2 work
Industry camera, the first image pick-up card and the second image pick-up card, described computer picture recognition device includes image procossing mould
Block and template matching module, described computer picture recognition device has been used for the pretreatment of image, greyscale transformation and mould
Plate match cognization, described COMPUTER DETECTION display device includes detecting display module and memory module, described calculating machine examination
Surveying display device to be used for carrying out showing and storing by testing result, outfan and first image of described CCD1 industrial camera are adopted
The input of truck connects, and the outfan of described CCD2 industrial camera and the input of the second image pick-up card connect, and first
The outfan of image pick-up card and the outfan of the second image pick-up card are all connected with the RS232 serial ports input of computer；The
One image pick-up card combines CCD1 industrial camera, and the surface image of aluminium extruded shaped article that will be collected by RS232 serial ports
Data reach computer picture recognition device, and the second image pick-up card combines CCD2 industrial camera, and will be adopted by RS232 serial ports
Collect to the strain image data of aluminium extruded shaped article reach computer picture recognition device, computer picture recognition device will connect
The view data received processes and identifies, and image recognition result is sent to COMPUTER DETECTION display device, described inspection
Surveying display module surface image recognition result and strain image recognition result to be shown, described memory module is by surface image
Recognition result and strain image recognition result store.
Cpu heat aluminium extruded forming defect detecting system the most according to claim 1, it is characterised in that: described CCD1
Industrial camera is for detecting the surface defect of aluminium extruded shaped article, and CCD2 industrial camera is for detecting the shape of aluminium extruded shaped article
Become.
Cpu heat aluminium extruded forming defect detecting system the most according to claim 1, it is characterised in that: also include aluminium extruded
Compression mould, described the Aluminum-Extruding Die includes aluminium extruded steel body, charging aperture, empty knife-band and discharging opening, described charging aperture, empty knife-band and
Discharging opening is arranged in order through aluminium extruded steel body, and described CCD1 industrial camera is arranged on the top of discharging opening, CCD2 industrial camera
It is arranged on the dead ahead of discharging opening.
4. it is applied to a detection method for cpu heat aluminium extruded forming defect detecting system described in claim 1, its feature
It is, comprises the following steps:
A. aluminium extruded shaped article is carried out image acquisition；
B. view data is sent to computer；
C. image is filtered pretreatment；
D. image is carried out greyscale transform process；
E. the image after gray proces is carried out Classification and Identification；
F. recognition result is shown；
G. recognition result is stored.
Detection method the most according to claim 4, it is characterised in that: in middle step A, the first image pick-up card passes through CCD1
Industrial camera completes the top view picture collection of aluminium extruded shaped article from top, the second image pick-up card by CCD2 industrial camera from
What front completed aluminium extruded shaped article faces image acquisition.
Detection method the most according to claim 4, it is characterised in that: in stepb, use RS232 serial ports by picture number
According to reaching computer.
Detection method the most according to claim 4, it is characterised in that: in step C, use gaussian filtering method to complete two
The Filtering Processing of width image.
Detection method the most according to claim 4, it is characterised in that: in step E, use template matching algorithm to complete figure
The Classification and Identification of picture, the identification step of described Classification and Identification is as follows:
A. choose a width standard, do not have defective aluminium extruded shaped article image as matches criteria template image；
B. the image collected is carried out location matches, be allowed to the most right with the position of the matches criteria template image in step a
Should；
C. the matches criteria template image that the image collected is chosen with step a is mated, uses Relative coefficient,
Calculate the correlation coefficient of image and the matches criteria template image collected, by calculated correlation coefficient and correlation coefficient threshold
Value compares and determines whether aluminium extruded shaped article is faulty goods；Computing formula particularly as follows:
Assume to gather image and matches criteria template image is owned by m × n pixel, use following formula to weigh and gather image and standard
The cross correlation of matching template image, D represents degree of association:
Wherein, m represents collection image and total pixel in matches criteria template image abscissa direction, n represent collection image and
Total pixel in matches criteria template image vertical coordinate direction, i point represents abscissa, and i represents vertical coordinate in the range of 1 to m, j,
J represents matches criteria template image in the range of 1 to n, T, and (i j) represents that in matches criteria template image, coordinate is at (i, j) place to T
The gray value of pixel, S represents collection image, and (i j) represents that in matches criteria template image, coordinate is at (i, j) place's pixel to S
Gray value；
Will after its normalization the correlation coefficient of template matching, wherein, R represents correlation coefficient:
Above-mentioned formula is used to be calculated the correlation coefficient of template matching, then the correlation coefficient threshold by coefficient R Yu setting
Relatively, if coefficient R is more than correlation coefficient threshold, then the match is successful, represents that product is qualified, is otherwise considered as that it fails to match, table
Show that product is defective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610877132.1A CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610877132.1A CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106290394A true CN106290394A (en) | 2017-01-04 |
| CN106290394B CN106290394B (en) | 2023-04-07 |
Family
ID=57716764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610877132.1A Expired - Fee Related CN106290394B (en) | 2016-09-30 | 2016-09-30 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106290394B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146704A (en) * | 2017-07-10 | 2017-09-08 | 河南远中电力设备有限公司 | A kind of transformer processing unit (plant) and production technology |
| CN108508021A (en) * | 2018-03-28 | 2018-09-07 | 中山市剑鸿电子科技有限公司 | A kind of failure detector for die quality monitoring |
| CN108956095A (en) * | 2018-05-17 | 2018-12-07 | 北京风云天地信息科技有限公司 | A kind of optical lens pollution level measurement method and device |
| CN110046630A (en) * | 2018-01-16 | 2019-07-23 | 上海电缆研究所有限公司 | Defect mode identification method/the systems/devices and readable storage medium storing program for executing of object |
| CN112082946A (en) * | 2019-06-13 | 2020-12-15 | 撼讯科技股份有限公司 | Automatic detection system and method thereof |
| CN112465809A (en) * | 2020-12-15 | 2021-03-09 | 北京市计算中心 | Mold defect detection method based on image recognition, computer-readable storage medium and device |
| CN114378546A (en) * | 2022-01-05 | 2022-04-22 | 江苏蔚联精密科技有限公司 | Novel aluminum extruded cavity special-shaped radiating fin manufacturing process |
| CN116500086A (en) * | 2023-06-28 | 2023-07-28 | 深圳市鑫典金光电科技有限公司 | Deep learning-based copper complex aluminum heat dissipation bottom plate production evaluation method and system |
| CN116843680A (en) * | 2023-08-29 | 2023-10-03 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN116930196A (en) * | 2023-09-18 | 2023-10-24 | 山东卓越精工集团有限公司 | Machine vision-based aluminum profile production defect analysis processing method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107512A (en) * | 2005-01-28 | 2008-01-16 | Ykk株式会社 | Article visual inspection device |
| CN102183524A (en) * | 2011-01-10 | 2011-09-14 | 哈尔滨工业大学 | Double-CCD (Charge Coupled Device) detecting method and system for apparent defect assessment of civil engineering structure |
| CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
-
2016
- 2016-09-30 CN CN201610877132.1A patent/CN106290394B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101107512A (en) * | 2005-01-28 | 2008-01-16 | Ykk株式会社 | Article visual inspection device |
| CN102183524A (en) * | 2011-01-10 | 2011-09-14 | 哈尔滨工业大学 | Double-CCD (Charge Coupled Device) detecting method and system for apparent defect assessment of civil engineering structure |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN103593670A (en) * | 2013-10-14 | 2014-02-19 | 浙江工业大学 | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine |
| WO2015055060A1 (en) * | 2013-10-16 | 2015-04-23 | 湖南镭目科技有限公司 | Online detecting method for continuous casting slab surface quality |
| CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
Non-Patent Citations (1)
| Title |
|---|
| 严俊龙等: "磁瓦表面缺陷自动检测系统的研究", 《计算机工程与应用》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146704A (en) * | 2017-07-10 | 2017-09-08 | 河南远中电力设备有限公司 | A kind of transformer processing unit (plant) and production technology |
| CN110046630A (en) * | 2018-01-16 | 2019-07-23 | 上海电缆研究所有限公司 | Defect mode identification method/the systems/devices and readable storage medium storing program for executing of object |
| CN108508021B (en) * | 2018-03-28 | 2021-07-30 | 健特(浙江)交通器材股份有限公司 | Flaw detection device for monitoring quality of die |
| CN108508021A (en) * | 2018-03-28 | 2018-09-07 | 中山市剑鸿电子科技有限公司 | A kind of failure detector for die quality monitoring |
| CN108956095A (en) * | 2018-05-17 | 2018-12-07 | 北京风云天地信息科技有限公司 | A kind of optical lens pollution level measurement method and device |
| CN112082946A (en) * | 2019-06-13 | 2020-12-15 | 撼讯科技股份有限公司 | Automatic detection system and method thereof |
| CN112465809A (en) * | 2020-12-15 | 2021-03-09 | 北京市计算中心 | Mold defect detection method based on image recognition, computer-readable storage medium and device |
| CN114378546A (en) * | 2022-01-05 | 2022-04-22 | 江苏蔚联精密科技有限公司 | Novel aluminum extruded cavity special-shaped radiating fin manufacturing process |
| CN116500086A (en) * | 2023-06-28 | 2023-07-28 | 深圳市鑫典金光电科技有限公司 | Deep learning-based copper complex aluminum heat dissipation bottom plate production evaluation method and system |
| CN116500086B (en) * | 2023-06-28 | 2023-09-05 | 深圳市鑫典金光电科技有限公司 | Deep learning-based copper complex aluminum heat dissipation bottom plate production evaluation method and system |
| CN116843680A (en) * | 2023-08-29 | 2023-10-03 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN116843680B (en) * | 2023-08-29 | 2023-12-15 | 深圳市华盛源机电有限公司 | IGBT power module radiator surface defect identification method |
| CN116930196A (en) * | 2023-09-18 | 2023-10-24 | 山东卓越精工集团有限公司 | Machine vision-based aluminum profile production defect analysis processing method |
| CN116930196B (en) * | 2023-09-18 | 2023-12-22 | 山东卓越精工集团有限公司 | Machine vision-based aluminum profile production defect analysis processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106290394B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106290394A (en) | A kind of cpu heat aluminium extruded forming defect detecting system and detection method | |
| WO2023168972A1 (en) | Linear array camera-based copper surface defect detection method and apparatus | |
| CN102735695B (en) | Rapid lens flaw detection method and apparatus thereof | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| CN106934813A (en) | A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning | |
| CN109190628A (en) | A kind of plate camber detection method based on machine vision | |
| CN111062915A (en) | Real-time steel pipe defect detection method based on improved YOLOv3 model | |
| CN110033431B (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| CN102589516B (en) | Dynamic distance measuring system based on binocular line scan cameras | |
| CN112862744B (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| CN108921819B (en) | Cloth inspecting device and method based on machine vision | |
| CN103913468A (en) | Multi-vision defect detecting equipment and method for large-size LCD glass substrate in production line | |
| CN107941808A (en) | 3D printing Forming Quality detecting system and method based on machine vision | |
| CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
| CN110503638B (en) | Spiral adhesive quality online detection method | |
| CN113487570B (en) | High-temperature continuous casting billet surface defect detection method based on improved yolov5x network model | |
| CN105388162A (en) | Raw material silicon wafer surface scratch detection method based on machine vision | |
| WO2023134286A1 (en) | Online automatic quality testing and classification method for cathode copper | |
| CN110260818B (en) | Electronic connector robust detection method based on binocular vision | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN106780437A (en) | A kind of quick QFN chips plastic packaging image is obtained and amplification method | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN113536895A (en) | Disc pointer meter identification method | |
| CN112881412A (en) | Method for detecting non-metal foreign bodies in scrap steel products | |
| CN205449822U (en) | Multi-camera image splicing device for strip steel surface detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230407 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |