CN109444144A - Cylinder holes hole wall defects detection detection method - Google Patents
Cylinder holes hole wall defects detection detection method Download PDFInfo
- Publication number
- CN109444144A CN109444144A CN201811008095.6A CN201811008095A CN109444144A CN 109444144 A CN109444144 A CN 109444144A CN 201811008095 A CN201811008095 A CN 201811008095A CN 109444144 A CN109444144 A CN 109444144A
- Authority
- CN
- China
- Prior art keywords
- cylinder holes
- hole wall
- detection
- image
- carried 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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8822—Dark field detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8858—Flaw counting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
Landscapes
- 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)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Cylinder holes hole wall defects detection detection method of the present invention, include the following steps: that 1) camera and light source are gradually coaxial right above cylinder holes under the control of mechanical arm and gos deep into cylinder holes, it is taken pictures according to the segmentation that cylinder holes depth carries out overlapping, radial distortion can be eliminated and obtain the high-definition picture of each hole wall, during taking pictures, with reference to artificial range estimation, the mode of dark field polishing is taken；2) image converts: 21) circle positioning；Circle detection is carried out to image, determines center location and radius；22) circle expansion；Rectangle is expanded into, the rectangular image for intercepting fixed height is detected；3) defects detection: prospect, background separation are carried out using artificial intelligence to expanded view, detailed analysis is carried out to prospect the characteristics of further according to different defect types.
Description
Technical field
The present invention relates to automatic detection system and test technique automatics, specifically, it shows that a kind of cylinder holes hole wall lacks
Fall into detection detection method.
Background technique
The detection of cylinder hole wall appearance is a part of cylinder block detection, cylinder holes aperture generally in 60mm-80mm,
Depth is 140mm, the minimum 0.5mm of the defects with diameters for needing to detect；
Cylinder holes hole wall detection method at this stage includes: human eye visual detection, non-vision method and visible sensation method.
Manually visualize there are two types of polishing mode, one is light to beat from upper end to hole wall, a kind of mode be light from it is following beat to
Hole wall, human eye are observed above checked always；Human eye visual detection large labor intensity, higher cost, and human eyesight
It is limited, can not observe tiny defect, certainly also can not quantitative inspection result；Non-vision method time-consuming, low precision
And mechanism is complicated；Visible sensation method is taken pictures in hole, is obtained hole wall image and is detected, accuracy is clear dependent on image
Degree.
Existing visible sensation method disposably obtains entire cylinder holes hole wall image directly to cylinder polishing, be in fact difficult by
Hole wall all illuminates simultaneously, it is limited to be similarly subjected to the image resolution ratio that the limitation of the camera depth of field obtains, it is difficult to meet detection accuracy
It is required that.
Therefore, it is necessary to provide a kind of cylinder holes hole wall defects detection detection method to solve the above problems.
Summary of the invention
The object of the present invention is to provide a kind of cylinder holes hole wall defects detection detection methods.
Technical solution is as follows:
A kind of cylinder holes hole wall defects detection detection method, includes the following steps:
1) camera and light source are gradually coaxial right above cylinder holes under the control of mechanical arm gos deep into cylinder holes, according to cylinder holes depth
The segmentation that degree carries out overlapping is taken pictures, and can be eliminated radial distortion and be obtained the high-definition picture of each hole wall, during taking pictures,
With reference to artificial range estimation, the mode of dark field polishing is taken；
2) image converts:
21) circle positioning；Circle detection is carried out to image, determines center location and radius；
22) circle expansion；Rectangle is expanded into, the rectangular image for intercepting fixed height is detected；
3) defects detection: prospect, background separation are carried out using artificial intelligence to expanded view, further according to different defect types
Feature carries out detailed analysis to prospect.
Further, each cylinder holes is clapped six times in step 1), obtains the image of six hole wall different height ranges, neighbor map
Between have a repeat region, guarantee without missing inspection region.
Further, step 3) specifically includes:
31) sand hole detects: sand hole is detected according to the contrast of foreground and background, area, clear-cut margin degree, shape, growth
The features such as property carry out judging whether there is husky hole；
32) casting skin detects: prospect background separation is first carried out, then judges the following conditions, meeting then is casting skin:
A plurality of horizontal stripe；Parallel and total length is more than threshold value；
33) band detects: first carrying out foreground and background separation, following 3 conditions is then judged in judgement prospect: parallel；
Spacing is consistent；Length is more than threshold value.
Compared with prior art, the present invention takes the mode of dark field polishing to obtain for visible detection method with reference to artificial range estimation
High-resolution cylinder holes inner wall image is taken to provide good shooting condition；Judge whether cylinder holes hole wall is defective, is lacked if so, determining
It falls into type and obtains the information such as defective locations, area, quantity and distance.
Detailed description of the invention
Fig. 1 is one of structural schematic diagram of the invention.
Fig. 2 is second structural representation of the invention.
Fig. 3 is third structural representation of the invention.
Fig. 4 is the four of structural schematic diagram of the invention.
Fig. 5 is the five of structural schematic diagram of the invention.
Fig. 6 is the six of structural schematic diagram of the invention.
Specific embodiment
Embodiment:
The present embodiment shows a kind of cylinder holes hole wall defects detection detection method, includes the following steps:
1) camera and light source are gradually coaxial right above cylinder holes under the control of mechanical arm gos deep into cylinder holes, according to cylinder holes depth
The segmentation that degree carries out overlapping is taken pictures, and can be eliminated radial distortion and be obtained the high-definition picture of each hole wall, during taking pictures,
With reference to artificial range estimation, the mode of dark field polishing is taken；
Each cylinder holes claps six times, and referring to Fig.1, the cylinder holes shown is taken pictures gained image, obtains six hole wall differences
The image of altitude range has repeat region between neighbor map, guarantees without missing inspection region；
2) image converts:
21) referring to Fig. 2, round positioning is carried out；Circle detection is carried out to image, determines center location and radius；
22) referring to Fig. 3, round expansion is carried out；Rectangle is expanded into, the rectangular image for intercepting fixed height is detected；
3) defects detection: prospect, background separation are carried out using artificial intelligence to expanded view, further according to different defect types
Feature carries out detailed analysis to prospect.
Step 3) specifically includes:
31) referring to Fig. 4, a kind of sand hole detection scene is shown: contrast of the sand hole detection according to foreground and background, face
The features such as product, clear-cut margin degree, shape, growth property carry out judging whether there is husky hole；
32) it referring to Fig. 5, shows a kind of casting skin detection scene: first carrying out prospect background separation, then judge following item
Part, meeting then is casting skin:
A plurality of horizontal stripe；Parallel and total length is more than threshold value；
33) it referring to Fig. 6, shows a kind of band detection scene: foreground and background separation is first carried out, then in judgement prospect
Judge following 3 conditions: parallel；Spacing is consistent；Length is more than threshold value.
Compared with prior art, the present invention takes the mode of dark field polishing to obtain for visible detection method with reference to artificial range estimation
High-resolution cylinder holes inner wall image is taken to provide good shooting condition；Judge whether cylinder holes hole wall is defective, is lacked if so, determining
It falls into type and obtains the information such as defective locations, area, quantity and distance.
Above-described is only some embodiments of the present invention.For those of ordinary skill in the art, not
Under the premise of being detached from the invention design, various modifications and improvements can be made, these belong to protection model of the invention
It encloses.
Claims (3)
1. a kind of cylinder holes hole wall defects detection detection method, characterized by the following steps:
1) camera and light source are gradually coaxial right above cylinder holes under the control of mechanical arm gos deep into cylinder holes, according to cylinder holes depth into
Row has the segmentation of overlapping to take pictures, and can eliminate radial distortion and obtain the high-definition picture of each hole wall, during taking pictures, reference
Artificial range estimation, takes the mode of dark field polishing；
2) image converts:
21) circle positioning；Circle detection is carried out to image, determines center location and radius；
22) circle expansion；Rectangle is expanded into, the rectangular image for intercepting fixed height is detected；
3) defects detection: prospect, background separation are carried out using artificial intelligence to expanded view, the characteristics of further according to different defect types
Detailed analysis is carried out to prospect.
2. a kind of cylinder holes hole wall defects detection detection method according to claim 1, it is characterised in that: each in step 1)
Cylinder holes is clapped six times, and the image of six hole wall different height ranges is obtained, and has repeat region between neighbor map, is guaranteed without missing inspection area
Domain.
3. a kind of cylinder holes hole wall defects detection detection method according to claim 1 or 2, it is characterised in that: step 3) tool
Body includes:
31) sand hole detects: sand hole is detected according to the contrast of foreground and background, area, clear-cut margin degree, shape, growth property etc.
Feature carries out judging whether there is husky hole；
32) casting skin detects: prospect background separation is first carried out, then judges the following conditions, meeting then is casting skin:
A plurality of horizontal stripe；Parallel and total length is more than threshold value；
33) band detects: first carrying out foreground and background separation, following 3 conditions is then judged in judgement prospect: parallel；Spacing
Unanimously；Length is more than threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008095.6A CN109444144A (en) | 2018-08-31 | 2018-08-31 | Cylinder holes hole wall defects detection detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811008095.6A CN109444144A (en) | 2018-08-31 | 2018-08-31 | Cylinder holes hole wall defects detection detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109444144A true CN109444144A (en) | 2019-03-08 |
Family
ID=65532648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811008095.6A Pending CN109444144A (en) | 2018-08-31 | 2018-08-31 | Cylinder holes hole wall defects detection detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109444144A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267452A (en) * | 2021-06-11 | 2021-08-17 | 菲特（天津）检测技术有限公司 | Engine cylinder surface defect detection method and system based on machine vision |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2856994Y (en) * | 2005-07-27 | 2007-01-10 | 福建省建筑科学研究院 | Internal pickup detector for hole of basic pile |
| CN101109716A (en) * | 2007-08-01 | 2008-01-23 | 北京理工大学 | Optical detecting method for internal surface of hole |
| CN101109715A (en) * | 2007-08-01 | 2008-01-23 | 北京理工大学 | Optical method for detecting defect on inner wall of holes |
| CN101206183A (en) * | 2006-12-19 | 2008-06-25 | 财团法人精密机械研究发展中心 | Method and apparatus for viewing hole internal wall image |
| CN101569550A (en) * | 2008-05-01 | 2009-11-04 | 奥林巴斯医疗株式会社 | Endoscope system using manipulator apparatus |
| CN103808730A (en) * | 2013-01-25 | 2014-05-21 | 常州先进制造技术研究所 | Detection method for surface defects of engine cam shaft part |
| CN106979951A (en) * | 2017-04-12 | 2017-07-25 | 青岛北琪实业有限公司 | A kind of multi-functional inner wall surface the cannot-harm-detection device |
| CN206420787U (en) * | 2017-01-16 | 2017-08-18 | 珠海嵘泰有色金属铸造有限公司 | Deep hole internal flaw automatic detecting table |
| CN107238603A (en) * | 2017-07-14 | 2017-10-10 | 深圳市恒工科技有限公司 | A kind of inner hole wall optical detection apparatus and its lamp guide |
-
2018
- 2018-08-31 CN CN201811008095.6A patent/CN109444144A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2856994Y (en) * | 2005-07-27 | 2007-01-10 | 福建省建筑科学研究院 | Internal pickup detector for hole of basic pile |
| CN101206183A (en) * | 2006-12-19 | 2008-06-25 | 财团法人精密机械研究发展中心 | Method and apparatus for viewing hole internal wall image |
| CN101109716A (en) * | 2007-08-01 | 2008-01-23 | 北京理工大学 | Optical detecting method for internal surface of hole |
| CN101109715A (en) * | 2007-08-01 | 2008-01-23 | 北京理工大学 | Optical method for detecting defect on inner wall of holes |
| CN101569550A (en) * | 2008-05-01 | 2009-11-04 | 奥林巴斯医疗株式会社 | Endoscope system using manipulator apparatus |
| CN103808730A (en) * | 2013-01-25 | 2014-05-21 | 常州先进制造技术研究所 | Detection method for surface defects of engine cam shaft part |
| CN206420787U (en) * | 2017-01-16 | 2017-08-18 | 珠海嵘泰有色金属铸造有限公司 | Deep hole internal flaw automatic detecting table |
| CN106979951A (en) * | 2017-04-12 | 2017-07-25 | 青岛北琪实业有限公司 | A kind of multi-functional inner wall surface the cannot-harm-detection device |
| CN107238603A (en) * | 2017-07-14 | 2017-10-10 | 深圳市恒工科技有限公司 | A kind of inner hole wall optical detection apparatus and its lamp guide |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267452A (en) * | 2021-06-11 | 2021-08-17 | 菲特（天津）检测技术有限公司 | Engine cylinder surface defect detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110261410A (en) | A kind of detection device and method of glass lens defect | |
| CN111047568B (en) | Method and system for detecting and identifying steam leakage defect | |
| JP2021043203A (en) | Colony contrast gathering | |
| CN105021628A (en) | Detection method for surface defects of optical fiber image inverter | |
| CN111047655B (en) | High-definition camera cloth defect detection method based on convolutional neural network | |
| CN111527396A (en) | System and method for setting production line inspection | |
| CN106162124A (en) | The calibration steps of scialyscope output image | |
| KR20160090359A (en) | Surface defect detection method and surface defect detection device | |
| CN105812790B (en) | Method for evaluating verticality between photosensitive surface and optical axis of image sensor and optical test card | |
| CN108445010B (en) | Automatic optical detection method and device | |
| JP7514259B2 (en) | System and method for determining whether a camera component is damaged - Patents.com | |
| JPWO2016208626A1 (en) | Surface defect detection method, surface defect detection apparatus, and steel material manufacturing method | |
| CN109801322A (en) | A kind of light leak test method and device | |
| TW201741649A (en) | Defect detection method and defect detection system easily and reliably detecting a defect of an object to be inspected with a simple structure | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN111292228A (en) | Lens defect detection method | |
| CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
| JP6434249B2 (en) | Concrete evaluation apparatus and evaluation method | |
| CN105181713A (en) | Detection device used for optical fiber image inverter surface defects | |
| CN107271445A (en) | Defect detection method and device | |
| CN115931912A (en) | Fresnel lens appearance defect detection method, device, equipment and medium | |
| CZ146195A3 (en) | Method of checking eye lenses and apparatus for making the same | |
| CN109444144A (en) | Cylinder holes hole wall defects detection detection method | |
| CN106973290A (en) | A kind of camera module stain method of testing and device | |
| CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |