CN101221134A - Method and device for detecting tiny bearing surface defect by computer vision technology - Google Patents
Method and device for detecting tiny bearing surface defect by computer vision technology Download PDFInfo
- Publication number
- CN101221134A CN101221134A CN 200710066671 CN200710066671A CN101221134A CN 101221134 A CN101221134 A CN 101221134A CN 200710066671 CN200710066671 CN 200710066671 CN 200710066671 A CN200710066671 A CN 200710066671A CN 101221134 A CN101221134 A CN 101221134A
- Authority
- CN
- China
- Prior art keywords
- bearing
- image
- micro
- bearing surface
- automatically
- 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
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a computer visual detecting field and provides a method and a device for detecting defects on the surfaces of a micro bearing by adopting computer visual technology. The technical proposal is that: the system for detecting the defects on the surface of the micro bearing works on line in a production line; the micro bearing (4) to be detected is arranged on an automatic line (5) and leading a digital camera (1) to shoot the surface image of the bearing through the control of a sensor when the micro bearing moves to the lower side of the digital camera; a cold light source (2) changes the beams into parallel beams by a telecentric lens (3) to lead the beams to vertically irradiate the surface of the bearing; a dark box (6) is used for insulating the bearing from the outside optical source; the collected gray images are transmitted to the computer through an image collecting card and whether the bearing has defects by using special software is analyzed automatically according to the gray changes of the images; a removing mechanism automatically removes the bearings with defects. The device can be conveniently connected with a bearing production line, has simple structure, is easy to be maintained and has low device investment.
Description
Technical field
The present invention relates to the Computer Vision Detection field, be specifically related to the method and a kind of device that the defective on micro bearing surface are detected by computer vision technique for realizing that this method is invented.
Background technology
In recent years, along with technical merit improves, to the also greatly raising of requirement of product surface quality, because the output of micro bearing is very big, and lip-deep load mould, to scratch its size, the degree of depth and distributing position all be at random, enterprise adopts artificial visually examine's method to finish this work usually at present, and not only the amount of labour used is big, efficient is low, and the loss height, influence the quality of finished product, the thing that often has the user to replace takes place, and not only causes economic loss, and brings negative effect to the user.And adopt the Computer Vision Detection technology to do non-contact detecting, be the preferred approach that addresses this problem.
Micro bearing surface imperfection Automatic Measurement Technique based on the ccd image recognition technology is the comprehensive of optics, Digital image technology, computer technology, software engineering and the multidisciplinary new and high technology of automatic technology.
Computer vision has more and more caused people's attention as a kind of detection means, and it is a kind of based on computer vision methods, the non-contact detection method of technology such as integrated use Flame Image Process, precision measurement and pattern-recognition, artificial intelligence.Its ultimate principle is to analyze by the measured target image that computer vision system is obtained, thereby obtains needed metrical information, and according to existing priori, judges whether compliant of measured target.
Because computer vision is wide to the sensitive range of spectrum, measuring accuracy is high, testing result is more stable, therefore in a lot of fields in to enhancing productivity, guarantee product quality, improving aspect such as product precision and made major contribution.The appliance computer vision detection technology is the occasion that those repeatability detect same parts or product the most widely.As far back as the eighties in last century, abroad just vision detection technology has been carried out extensive studies and obtained developing rapidly the operation market that the U.S. just has company more than 100 to rank among vision detection system, and widespread use in Americanized industry.According to statistics, in the per three cover vision systems of the U.S., it is industrial vision detection systems that two covers are arranged, and in needing the production system of vision-based detection, late nineteen eighties existing at least 25% is replaced by vision detection system fully.To last century end, existing 90% is replaced by vision system fully.Japan successfully has been used for computer vision system the quality testing of printed circuit board (PCB).According to statistics: nineteen eighty-two, the U.S. installed 6301 cover industrial vision systems altogether, and Japan is then more.To 1990 U.S. number is installed and is surpassed 100,000 covers, Japan has surpassed 55.7 ten thousand covers.Sell aspect the gold-sprinkled volume in market, reached 600,000,000 dollars in 1984, reached 1,200,000,000 dollars by 1994 in the U.S..In a word, all developed rapidly at industrially developed country's industrial vision system.
Domestic vision-based detection research since last century the nineties just obtain paying attention to, the development of advancing by leaps and bounds has been arranged recent years.More domestic universities and research institution have successively developed some Computer Vision Detection System.For over ten years, vision detection technology has obtained very big progress, continues to bring out at the new results aspect theory research and the applied research.
Although the Computer Vision Detection technology is used in a lot of fields, be applied to the surface defects detection of micro bearing, do not find report both at home and abroad as yet.
Adopt the Computer Vision Detection technology can make micro bearing surface defects detection operation realize robotization, make the clearance of defect recognition rate, substandard product reach higher level, improve the oeverall quality of the product that dispatches from the factory, avoid actual loss as far as possible, improve the credit worthiness and the modernization level of enterprise.
Problem to be solved by this invention is exactly to overcome bearing to show that the caused efficient of defective employing manual detection is hanged down and the problem of poor reliability.
Summary of the invention
First technical matters solved by the invention provides a kind of reliable, convenient and practical, method of can be used for the micro bearing surface defects detection.
Second technical matters solved by the invention provides a kind of reliable, convenient and practical, device of can be used for the micro bearing surface defects detection.
Technical scheme solved by the invention, its principle of work and process are as described below: 1, micro bearing surface defects detection system works online in production line, and detected bearing moves on conveying belt according to certain beat; 2, when entering the detection operation, detection system adopts the rhythm extracting bearing surface image synchronous with production line by adjusting the CCD camera of position; 3, pass through image pick-up card, institute's images acquired is sent in the computing machine carries out Flame Image Process by special software; 4, analyze the comparison process result, the bearing that will have defective is rejected automatically by mechanism for sorting, and qualified bearing is then proceeded the detection on another surface.
Compare with existing manual detection method, the invention has the advantages that: computer vision technique is applied to the Production of bearing transfer matic neatly, improved automaticity and efficient, alleviated labour intensity.This method can be widely used in the SHAPE DETECTION of other micro parts.This apparatus structure is simple, and system is easy to safeguard that equipment drops into low, the practicality height.
Description of drawings
Fig. 1 is a detection system structural representation of the present invention.
Embodiment
Embodiment describes in further detail the present invention below in conjunction with accompanying drawing.
The device that adopts detecting tiny bearing surface defect by computer vision technology mainly by the support (7) of light source (2), telecentric iris camera lens (3), stationary digital camera and the light source of the digital camera (1) of taking the bearing surface image, illumination bearing, comprise that the micro bearing conveying device (5) of rejecting mechanism, the computer control system etc. that prevents the camera bellows (6) that extraneous light disturbs and whole detection system is implemented control form.
Principle of work and process: micro bearing surface defects detection system works online in production line, the micro bearing (4) that need are detected is placed on the automatic conveyor line (5), transfer matic requires (the present invention is 4 seconds) motion according to certain beat, in the time of under micro bearing moves to digital camera (1), make digital camera (1) take the micro bearing surface image by sensor control; Cold light source (2) changes over directional light by telecentric iris camera lens (3) with light, makes the light vertical irradiation to bearing surface, thereby farthest reduces dark angle; In order not influenced by external environment light source etc., bearing and external light source are completely cut off with camera bellows (6); By image pick-up card, the image that collects is sent in the computing machine, when finding defective bearing, gray scale can change, and analyzes comparison process according to the gradation of image value automatically by special software; Automatically classify according to testing result, rejecting mechanism will have the bearing of defective rejects automatically, otherwise, 180 ° of detections of carrying out another surface of bearing upset.
Claims (4)
1. method and apparatus that computer vision technique is used for the micro bearing surface defects detection, it is characterized in that described method employing image is gathered automatically, surface imperfection is discerned automatically and bearing is rejected automatically, step is as follows: micro bearing surface defects detection system works online in production line, the micro bearing that need are detected is placed on the automatic conveyor line (5), transfer matic requires motion according to certain beat, in the time of under micro bearing moves to digital camera (1), make digital camera (1) take the micro bearing surface image by sensor control; Cold light source (2) changes over directional light by telecentric iris camera lens (3) with light, makes the light vertical irradiation to bearing surface, thereby farthest reduces dark angle; In order not influenced by external environment light source etc., bearing and external light source are completely cut off with camera bellows (6); By image pick-up card, the image that collects is sent in the computing machine, when finding defective bearing, gray scale can change, and analyzes comparison process according to the gradation of image value automatically by special software; Automatically classify according to testing result, rejecting mechanism will have the bearing of defective rejects automatically, otherwise, 180 ° of detections of carrying out another surface of bearing upset.
2. a kind of method according to claim 1 is characterized in that whether described this device adopts computer vision technique to grasp the gray level image of bearing surface automatically, exist defectives such as cut or pit according to the next automatic identified surface of the gray-scale value of image.
3. a kind of method according to claim 1 is characterized in that this method adopts cold light source, and by the telecentric iris camera lens light is changed over directional light, makes the light vertical irradiation to bearing surface, uses the interference of camera bellows shielding surround lighting.
4. a kind of method according to claim 1 is characterized in that this method adopts special rejecting mechanism by software control, makes the rejecting action consistent with productive temp, to guarantee the timely rejecting of defectiveness bearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200710066671 CN101221134A (en) | 2007-01-10 | 2007-01-10 | Method and device for detecting tiny bearing surface defect by computer vision technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200710066671 CN101221134A (en) | 2007-01-10 | 2007-01-10 | Method and device for detecting tiny bearing surface defect by computer vision technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101221134A true CN101221134A (en) | 2008-07-16 |
Family
ID=39631105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200710066671 Pending CN101221134A (en) | 2007-01-10 | 2007-01-10 | Method and device for detecting tiny bearing surface defect by computer vision technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101221134A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526484B (en) * | 2009-04-13 | 2011-05-11 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| CN102183528A (en) * | 2011-01-10 | 2011-09-14 | 宁波工程学院 | Defect detection device and method of duplicate gear |
| CN101793496B (en) * | 2009-04-23 | 2012-01-11 | 杭州新三联电子有限公司 | Precision video mapping analyzer |
| CN102486463A (en) * | 2011-05-25 | 2012-06-06 | 浙江三和机电科技有限公司 | Full-automatic plane bearing appearance visual inspection device |
| CN103364406A (en) * | 2012-09-28 | 2013-10-23 | 洛阳久德轴承模具技术有限公司 | Bearing rolling element detector based on high-resolution CCD (Charge Coupled Device) technology |
| CN103383359A (en) * | 2013-07-22 | 2013-11-06 | 爱彼思（苏州）自动化科技有限公司 | Color difference analytical device based on image recognition technology |
| CN103743745A (en) * | 2013-12-17 | 2014-04-23 | 江苏金发科技新材料有限公司 | Detection method for stain on appearance of modified plastic |
| CN104215642A (en) * | 2013-05-31 | 2014-12-17 | 胡新 | Bearing roller appearance inspection apparatus and method of using same to inspect bearing roller appearance |
| CN104792789A (en) * | 2015-04-08 | 2015-07-22 | 上海常良智能科技有限公司 | Chemical fiber paper tube appearance detection device and method |
| CN106124213A (en) * | 2016-08-12 | 2016-11-16 | 扬州康派尔机械科技有限公司 | A kind of four-way bearing motility visual identity machine |
| CN106290392A (en) * | 2016-08-05 | 2017-01-04 | 宁波达尔机械科技有限公司 | A kind of little micro-bearing surface pitting defects online test method and system thereof |
| CN106908444A (en) * | 2017-03-20 | 2017-06-30 | 辽宁科技大学 | A kind of taper roll bearing end face identifying system and method based on image procossing |
| CN107101926A (en) * | 2017-05-05 | 2017-08-29 | 湖南建研信息技术股份有限公司 | A kind of automatic measurement and the Anti-leakage instrument and impervious detection method of control |
| CN108885168A (en) * | 2018-06-12 | 2018-11-23 | 深圳达闼科技控股有限公司 | A kind of detection system and signal enhancing device |
| CN109100358A (en) * | 2018-10-18 | 2018-12-28 | 深圳市微埃智能科技有限公司 | Vision detection system |
| CN109975307A (en) * | 2019-03-11 | 2019-07-05 | 中国科学院上海技术物理研究所 | Bearing surface defect detection system and detection method based on statistics projection training |
| CN110296995A (en) * | 2019-06-27 | 2019-10-01 | 华东送变电工程有限公司 | Image acquisition device applied to power cable damage detection |
-
2007
- 2007-01-10 CN CN 200710066671 patent/CN101221134A/en active Pending
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526484B (en) * | 2009-04-13 | 2011-05-11 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| CN101793496B (en) * | 2009-04-23 | 2012-01-11 | 杭州新三联电子有限公司 | Precision video mapping analyzer |
| CN102183528A (en) * | 2011-01-10 | 2011-09-14 | 宁波工程学院 | Defect detection device and method of duplicate gear |
| CN102486463A (en) * | 2011-05-25 | 2012-06-06 | 浙江三和机电科技有限公司 | Full-automatic plane bearing appearance visual inspection device |
| CN102486463B (en) * | 2011-05-25 | 2013-09-11 | 浙江三和机电科技有限公司 | Full-automatic plane bearing appearance visual inspection device |
| CN103364406A (en) * | 2012-09-28 | 2013-10-23 | 洛阳久德轴承模具技术有限公司 | Bearing rolling element detector based on high-resolution CCD (Charge Coupled Device) technology |
| CN104215642A (en) * | 2013-05-31 | 2014-12-17 | 胡新 | Bearing roller appearance inspection apparatus and method of using same to inspect bearing roller appearance |
| CN104215642B (en) * | 2013-05-31 | 2017-04-19 | 林丽妹 | Bearing roller appearance inspection apparatus and method of using same to inspect bearing roller appearance |
| CN103383359B (en) * | 2013-07-22 | 2016-06-22 | 爱彼思（苏州）自动化科技有限公司 | Color difference analytical device based on image recognition technology |
| CN103383359A (en) * | 2013-07-22 | 2013-11-06 | 爱彼思（苏州）自动化科技有限公司 | Color difference analytical device based on image recognition technology |
| CN103743745A (en) * | 2013-12-17 | 2014-04-23 | 江苏金发科技新材料有限公司 | Detection method for stain on appearance of modified plastic |
| CN104792789A (en) * | 2015-04-08 | 2015-07-22 | 上海常良智能科技有限公司 | Chemical fiber paper tube appearance detection device and method |
| CN106290392A (en) * | 2016-08-05 | 2017-01-04 | 宁波达尔机械科技有限公司 | A kind of little micro-bearing surface pitting defects online test method and system thereof |
| CN106124213B (en) * | 2016-08-12 | 2019-01-29 | 扬州康派尔机械科技有限公司 | A kind of four-way bearing flexibility visual identity machine |
| CN106124213A (en) * | 2016-08-12 | 2016-11-16 | 扬州康派尔机械科技有限公司 | A kind of four-way bearing motility visual identity machine |
| CN106908444A (en) * | 2017-03-20 | 2017-06-30 | 辽宁科技大学 | A kind of taper roll bearing end face identifying system and method based on image procossing |
| CN106908444B (en) * | 2017-03-20 | 2023-10-10 | 辽宁科技大学 | Tapered roller bearing end face recognition system and method based on image processing |
| CN107101926A (en) * | 2017-05-05 | 2017-08-29 | 湖南建研信息技术股份有限公司 | A kind of automatic measurement and the Anti-leakage instrument and impervious detection method of control |
| CN108885168A (en) * | 2018-06-12 | 2018-11-23 | 深圳达闼科技控股有限公司 | A kind of detection system and signal enhancing device |
| CN108885168B (en) * | 2018-06-12 | 2023-12-01 | 北京云端光科技术有限公司 | Detection system and signal enhancement device |
| CN109100358A (en) * | 2018-10-18 | 2018-12-28 | 深圳市微埃智能科技有限公司 | Vision detection system |
| CN109975307A (en) * | 2019-03-11 | 2019-07-05 | 中国科学院上海技术物理研究所 | Bearing surface defect detection system and detection method based on statistics projection training |
| CN110296995A (en) * | 2019-06-27 | 2019-10-01 | 华东送变电工程有限公司 | Image acquisition device applied to power cable damage detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101221134A (en) | Method and device for detecting tiny bearing surface defect by computer vision technology | |
| CN108332689B (en) | Optical measurement system and method for detecting surface roughness and surface damage | |
| CN201141839Y (en) | Device for detecting tiny bearing surface defect by computer vision technology | |
| CN102221556B (en) | Device and method for online detection on appearance defect of minitype connecting part based on machine vision | |
| CN201218723Y (en) | Optoelectronic non-contact type image detection apparatus | |
| CN102621156B (en) | Image-processing-based automatic micro part sorting system | |
| CN110216080A (en) | Quality monitoring system of PCB processing production line based on image contrast | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| CN105548212A (en) | System and method for online automatically detecting defects on glass surface of touch screen | |
| KR20180106856A (en) | Automatic optical inspection system and operating method thereof | |
| CN106290392A (en) | A kind of little micro-bearing surface pitting defects online test method and system thereof | |
| CN106651802B (en) | Machine vision scolding tin position finding and detection method | |
| CN108844966A (en) | A kind of screen detection method and detection system | |
| CN106353336A (en) | Lens coating automatic detection system | |
| Fan et al. | Development of auto defect classification system on porosity powder metallurgy products | |
| CN106501272A (en) | Machine vision scolding tin position detecting system | |
| CN102303018B (en) | Method for automatically detecting burrs of injector steel needles by using machine vision system | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN205449820U (en) | Machine vision device of detectable ball bearing defect | |
| CN104318249A (en) | Grinding surface roughness grade identification method based on multi-classification support vector machine | |
| CN205786362U (en) | A kind of touch screen glass surface flaw on-line automaticization detecting system | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN109632815A (en) | Surface defect on-line detecting system and method | |
| CN107748897A (en) | Large-size curved part profile quality detection method based on pattern recognition | |
| CN205786374U (en) | Special-shaped stamping parts profile defects vision detection system based on coupling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080716 |