CN103134809B - Welded line defect detection method - Google Patents
Welded line defect detection method Download PDFInfo
- Publication number
- CN103134809B CN103134809B CN201310080871.4A CN201310080871A CN103134809B CN 103134809 B CN103134809 B CN 103134809B CN 201310080871 A CN201310080871 A CN 201310080871A CN 103134809 B CN103134809 B CN 103134809B
- Authority
- CN
- China
- Prior art keywords
- image
- shape
- weld
- gray scale
- pixel
- 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.)
- Active
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
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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a welded line defect detection method which comprises the following steps of: judging a pixel proportion and judging an image shape, wherein the pixel proportion judgment comprises the following steps: determining the position of a welded line, acquiring an image of the welded line, locking a rectangular frame at the position of the welded line on the image, calculating the gray scale value of each pixel point on the image in the rectangular frame, dividing the gray scale values into low gray scale values from 0 to 128 and high gray scale values from 128 to 255, when the proportion of the low gray scale values of the pixel points of the image is more than 85 percent, determining that the welded line has defects; and when the proportion is less than 85 percent, judging a shape of the image; and the image shape judgment comprises the following steps: performing binary conversion on the acquired image of the welded line, performing edge extraction on the converted image, extracting the shape of the welded line in the image, judging the shape of the welded line through an eight-communicated graph algorithm, and if the shape of the welded line is irregular, determining that the welded line is defected. By the welded line defect detection method, the detection work finished by a worker can be finished by a computer, so that the labor cost is reduced; and the stability and the high efficiency are realized.
Description
Technical field
the present invention relates to a kind of weld defect detection method.
Background technology
the ladle body of metallic packing pail is generally welded by metal sheet both sides, carries out other operations again, leave weld seam in welding position after forming a columniform tank body.Quality due to weld seam directly can have influence on the quality of pail pack, therefore often needs butt welded seam to detect when completing welding, judges weld seam whether existing defects.Detecting weld seam in industry is generally manual detection, but the detection efficiency of manual detection is lower, cannot detect weld seam slight part, and the mark judged exists deviation, and it is stable that impact judges.
Summary of the invention
the object of the invention is to provide a kind of weld defect detection method.
for achieving the above object, the technical solution used in the present invention is:
a kind of weld defect detection method, comprises pixel ratio judgement, picture shape judgement, wherein:
pixel ratio judges to comprise: determine position while welding, gather weld image, a rectangle frame close to weld shape is locked at the position while welding of image, calculate the gray-scale value on each pixel of image in rectangle frame, gray-scale value is divided into low value gray scale, high level gray scale, wherein: gray-scale value is low value gray scale within the scope of 0-128, gray-scale value is high level gray scale within the scope of 128-255, when the ratio of image each pixel high level gray scale is more than 85%, weld seam existing defects; When image each pixel high level gray scale ratio lower than 85% time, carry out picture shape judgement;
picture shape judges to comprise: carry out binaryzation conversion to the weld image gathered, and carries out edge extracting, extract the shape of weld seam in image to the image after conversion, by eight connectivity nomography, judge the shape of weld seam, when the shape of weld seam is irregular figure, weld seam existing defects.
preferably, determine position while welding, after gathering weld image, judge that the position while welding of image is positioned at product two ends or centre, when image is positioned in the middle of product, carry out pixel ratio judgement.
preferably, when pixel ratio judges, scanned by the weld seam both sides of two sweep traces to image, thus determine the position of weld seam.
because technique scheme is used, the present invention compared with prior art has following advantages and effect:
the present invention, by from the defect that pixel ratio judges, picture shape judges two part comprehensive descision weld seams, carries out image acquisition, defect dipoles to product in real time; By the testing originally needing manually to complete, be transformed into and completed by computing machine, reduce cost of labor; Meanwhile, machine detects manual detection of comparing, and has more stability and high efficiency, this technological improvement, effectively can improve enterprises production efficiency, improves enterprise competitiveness.
Embodiment
below in conjunction with case study on implementation, the invention will be further described:
product line added enter weld defect checkout equipment, checkout equipment comprises at least one industrial camera, capture card, computing machine etc.; Industrial camera is controlled, Real-time Collection weld image data by computing machine; Weld image, by capture card process Primary Stage Data, reaches computing machine, and computing machine receives view data and judges it;
judgement comprises: pixel ratio judges, picture shape judges,
wherein: first need to judge whether image takes from two ends or the centre of product, and judge that image is positioned at welding in-position and still welds away position, record its position mark; When image is positioned in the middle of product, carry out pixel ratio judgement; When image is positioned at product two ends, needs to carry out special judgement to two ends, be not described at this;
pixel ratio judges to comprise: scanned by the weld seam both sides of two sweep traces to image, thus determine the position of weld seam, a rectangle frame close to weld shape is locked at the position while welding of image, calculate the gray-scale value on each pixel of image in rectangle frame, gray-scale value is divided into low value gray scale, high level gray scale, wherein: gray-scale value is low value gray scale within the scope of 0-128, gray-scale value is high level gray scale within the scope of 128-255, when the ratio of image each pixel high level gray scale is more than 85%, weld seam existing defects, product is defective, provides alerting signal; When image each pixel high level gray scale ratio lower than 85% time, carry out picture shape judgement.Because the shape of normal weld is close to a rectangle frame, therefore, in the rectangle frame of locking, low value gray scale (i.e. dark colour) ratio is higher, and at poor weld place, because shape is not too close to a rectangle frame, so in the rectangle frame of locking, must include the high level gray scale (light colour) of a part, therefore the ratio of low value gray scale does not just have the height of normal weld image.
picture shape judges to comprise: carry out binaryzation conversion to the weld image gathered, edge extracting is carried out to the image after conversion, extract the shape of weld seam in image, by eight connectivity nomography (in bianry image, the set of the black pixel interconnected becomes (black) region, by carrying out marking operation to region each in image, try to achieve the number in region, eight connectivity nomography from left to right, from top to bottom, detect each pixel successively, if find that certain pixel pixel value is 0, then detect the upper right of this point successively, just go up, the pixel value of upper left and left front point totally four points, judge their connectedness), judge the shape of weld seam, when the shape of weld seam is regular figure, weld seam is existing defects not, product is qualified, when the shape of weld seam is irregular curved figure, then need to judge that this image is positioned at the position of product further, in the image rule of center section, it is the weld image of specification product, otherwise be substandard product.
after mechanical arm controller receives alerting signal, controller mechanical arm takes out defectiveness product, prevents it from entering next processing link.
in addition, for the erection problem of checkout equipment, because this cover system adopts the method for machine vision to realize the detection of product defects, so higher to the image quality requirements obtained, and the erection of camera light source is most important, accurately need ensure that product, light source, camera are coaxial.
when collection weld image, need to carry out overlap by camera and take pictures (length of overlapped part is the average length of defect), the image so obtained, can ensure that defect part is positioned at the centre of obtained image all the time.
above-described embodiment, only for technical conceive of the present invention and feature are described, its object is to person skilled in the art can be understood content of the present invention and implement according to this, can not limit the scope of the invention with this.All equivalences done according to Spirit Essence of the present invention change or modify, and all should be encompassed within protection scope of the present invention.
Claims (2)
1. a weld defect detection method, is characterized in that: comprise pixel ratio judgement, picture shape judgement, wherein:
Pixel ratio judges to comprise: determine position while welding, gather weld image, judge that the position while welding of image is positioned at product two ends or centre after gathering weld image, when image is positioned in the middle of product, carry out pixel ratio judgement, a rectangle frame close to weld shape is locked at the position while welding of image, calculate the gray-scale value on each pixel of image in rectangle frame, gray-scale value is divided into low value gray scale, high level gray scale, wherein: gray-scale value is low value gray scale within the scope of 0-128, gray-scale value is high level gray scale within the scope of 128-255, when the ratio of image each pixel high level gray scale is more than 85%, weld seam existing defects, when image each pixel high level gray scale ratio lower than 85% time, carry out picture shape judgement,
Picture shape judges to comprise: carry out binaryzation conversion to the weld image gathered, and carries out edge extracting, extract the shape of weld seam in image to the image after conversion, by eight connectivity nomography, judge the shape of weld seam, when the shape of weld seam is irregular figure, weld seam existing defects.
2. weld defect detection method according to claim 1, is characterized in that: when pixel ratio judges, is scanned, thus determine the position of weld seam by the weld seam both sides of two sweep traces to image.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310080871.4A CN103134809B (en) | 2013-03-14 | 2013-03-14 | Welded line defect detection method |
| PCT/CN2013/083509 WO2014139273A1 (en) | 2013-03-14 | 2013-09-13 | Weld seam defect detection method |
| NZ711997A NZ711997A (en) | 2013-03-14 | 2013-09-13 | Weld seam defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310080871.4A CN103134809B (en) | 2013-03-14 | 2013-03-14 | Welded line defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103134809A CN103134809A (en) | 2013-06-05 |
| CN103134809B true CN103134809B (en) | 2015-04-29 |
Family
ID=48494917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310080871.4A Active CN103134809B (en) | 2013-03-14 | 2013-03-14 | Welded line defect detection method |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN103134809B (en) |
| NZ (1) | NZ711997A (en) |
| WO (1) | WO2014139273A1 (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103134809B (en) * | 2013-03-14 | 2015-04-29 | 苏州华源包装股份有限公司 | Welded line defect detection method |
| CN104215638A (en) * | 2013-06-03 | 2014-12-17 | 英业达科技有限公司 | Pin bending detection method |
| CN106290394B (en) * | 2016-09-30 | 2023-04-07 | 华南理工大学 | System and method for detecting aluminum extrusion molding defects of CPU radiator |
| CN109001224B (en) * | 2017-06-07 | 2022-02-18 | 宁德时代新能源科技股份有限公司 | Welding seam detection method and detection device |
| CN108122228A (en) * | 2017-12-21 | 2018-06-05 | 金翰阳科技（大连）股份有限公司 | A kind of polishing putty or lacquer painting detection method |
| CN108665452B (en) * | 2018-05-09 | 2019-06-07 | 广东大鹏液化天然气有限公司 | Pipeline-weld film scanning storage and identification of Weld Defects and its system |
| CN109741311B (en) * | 2018-12-28 | 2022-09-02 | 西南交通大学 | Aluminum alloy fusion welding back face fusion width detection method with false edge |
| CN110751619A (en) * | 2019-08-28 | 2020-02-04 | 中国南方电网有限责任公司超高压输电公司广州局 | Insulator defect detection method |
| CN115210035B (en) * | 2020-03-05 | 2024-06-25 | 松下知识产权经营株式会社 | Bead appearance inspection device, bead appearance inspection method, program, and bead appearance inspection system |
| CN112102255B (en) * | 2020-08-21 | 2024-01-23 | 杭州培慕科技有限公司 | Intelligent defect grading method based on X-ray imaging image in industrial scene |
| CN112730428A (en) * | 2020-12-23 | 2021-04-30 | 联合汽车电子有限公司 | Extension rod weld joint detection system and method |
| CN113160132A (en) * | 2021-03-10 | 2021-07-23 | 上海应用技术大学 | Detection processing method and system for weld defect image |
| CN113610814B (en) * | 2021-08-10 | 2022-11-18 | 广东利元亨智能装备股份有限公司 | Weld quality detection method and device, electronic equipment and storage medium |
| CN113686906A (en) * | 2021-08-27 | 2021-11-23 | 江苏新宏大集团有限公司 | Industrial X-ray flat weld defect positioning method |
| CN114581742B (en) * | 2021-10-26 | 2023-01-24 | 中科慧远视觉技术(北京)有限公司 | Linearity-based connected domain clustering fusion method, device, system and medium |
| CN115018827B (en) * | 2022-08-03 | 2022-11-04 | 山东亿昌装配式建筑科技有限公司 | Automatic detection method for quality of building material weld joint |
| CN115415704B (en) * | 2022-09-23 | 2023-09-22 | 千思跃智能科技(苏州)股份有限公司 | Intelligent welding and 3D camera detection equipment |
| CN115457031A (en) * | 2022-10-27 | 2022-12-09 | 江苏集宿智能装备有限公司 | Method for identifying internal defects of integrated box based on X-ray |
| CN115830013B (en) * | 2023-02-08 | 2023-05-16 | 磐石重工(青岛)股份有限公司 | Pressure vessel weld defect detection method based on machine vision |
| CN116385476B (en) * | 2023-06-05 | 2023-08-18 | 青岛星跃铁塔有限公司 | Iron tower quality analysis method based on visual detection |
| CN116433669B (en) * | 2023-06-14 | 2023-08-18 | 山东兴华钢结构有限公司 | Machine vision-based quality detection method for weld joints of steel frame of anti-seismic structure |
| CN116823756A (en) * | 2023-06-25 | 2023-09-29 | 江苏永康机械有限公司 | Pile leg weld defect detection method |
| CN116503408B (en) * | 2023-06-28 | 2023-08-25 | 曲阜远大集团工程有限公司 | Scanning technology-based steel structure surface defect detection method |
| CN116664554B (en) * | 2023-07-26 | 2023-10-20 | 微山晟轩机械制造有限公司 | Bolt thread defect detection method based on image processing |
| CN117745718B (en) * | 2024-02-19 | 2024-07-02 | 工业云制造(四川)创新中心有限公司 | Information interaction method based on cloud manufacturing |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4531396B2 (en) * | 2001-11-15 | 2010-08-25 | プレシテック ヴィジョン ゲゼルシャフト ミット ベシュレンクテル ハフツング ウント コンパニー コマンディートゲゼルシャフト | Method and apparatus for evaluating workpiece joints |
| JP2004045356A (en) * | 2002-05-20 | 2004-02-12 | Jfe Steel Kk | Surface defect detection method |
| JP2008304312A (en) * | 2007-06-07 | 2008-12-18 | Fuji Xerox Co Ltd | Image processing program and image processor |
| CN101915769B (en) * | 2010-06-29 | 2012-03-28 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN102455171B (en) * | 2010-10-27 | 2014-01-15 | 中国科学院沈阳自动化研究所 | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof |
| CN102830129B (en) * | 2012-08-27 | 2015-07-15 | 山东省特种设备检验研究院 | Quick high-definition digitalized recording device for ray detection negative film for welded joints of pressure-bearing equipment |
| CN103134809B (en) * | 2013-03-14 | 2015-04-29 | 苏州华源包装股份有限公司 | Welded line defect detection method |
-
2013
- 2013-03-14 CN CN201310080871.4A patent/CN103134809B/en active Active
- 2013-09-13 WO PCT/CN2013/083509 patent/WO2014139273A1/en active Application Filing
- 2013-09-13 NZ NZ711997A patent/NZ711997A/en unknown
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
Non-Patent Citations (2)
| Title |
|---|
| X射线焊缝图像中缺陷的实时检测方法;孙怡等;《焊接学报》;20040430;第25卷(第2期);第116页第1栏第2段-第117页第2栏第1段 * |
| 焊缝缺陷图像特征提取研究;杨川;《中国优秀硕士学位论文全文数据库 信息科技辑》;20101215(第12期);第29页倒数第1段-第30页第2段，即第38页第1段第40页倒数第2段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2014139273A1 (en) | 2014-09-18 |
| CN103134809A (en) | 2013-06-05 |
| NZ711997A (en) | 2018-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103134809B (en) | Welded line defect detection method | |
| CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
| CN104504388B (en) | A kind of pavement crack identification and feature extraction algorithm and system | |
| CN109001224B (en) | Welding seam detection method and detection device | |
| KR101256369B1 (en) | Flat display pannel test equipment and test method using multi ccd camera | |
| CN101158650A (en) | On-line detecting method of machine vision system for printed calico flaw | |
| CN104122271A (en) | Automated optical inspection (AOI)-based bullet apparent defect detection method | |
| CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
| CN110405384A (en) | Method and system for real-time detection insufficient (incomplete) penetration during robot welding | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN110376211B (en) | Wet-process-gummed synthetic leather hemming on-line detection device and method | |
| CN115147370A (en) | Battery top cover welding defect detection method and device, medium and electronic equipment | |
| CN115330702A (en) | Beverage bottle filling defect identification method based on deep vision | |
| WO2022222467A1 (en) | Open circular ring workpiece appearance defect detection method and system, and computer storage medium | |
| CN113469991B (en) | Visual online detection method for laser welding spot of lithium battery tab | |
| CN114612423A (en) | Chip packaging defect detection method | |
| CN115239002A (en) | New energy distributed photovoltaic power station monitoring and early warning system and method | |
| CN114943704A (en) | Method, device and equipment for detecting defects of battery electrode die-cut piece | |
| CN113780235A (en) | Icon flaw detection method and system | |
| CN114199127A (en) | Automobile part size detection system and method based on machine vision | |
| CN114565600A (en) | Solar photovoltaic panel surface defect detection method | |
| CN104408727A (en) | Image edge stain detection method and system | |
| CN105092604B (en) | Line information and non-line area information acquisition method and line defect detection method | |
| CN111353974B (en) | Method and device for detecting image boundary defects | |
| US20210383168A1 (en) | Method for labeling image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215236 Suzhou Province, Wujiang City, Taoyuan Town Peach Road, No. 1948, No. Patentee after: Suzhou Huayuan Cmi Holdings Ltd Address before: 215236 Suzhou Province, Wujiang City, Taoyuan Town Peach Road, No. 1948, No. Patentee before: Wujiang Huayuan Tinplate Printing & Tin Making Co Ltd |