CN103808730B - Engine cam component surface defect inspection method - Google Patents
Engine cam component surface defect inspection method Download PDFInfo
- Publication number
- CN103808730B CN103808730B CN201310033740.0A CN201310033740A CN103808730B CN 103808730 B CN103808730 B CN 103808730B CN 201310033740 A CN201310033740 A CN 201310033740A CN 103808730 B CN103808730 B CN 103808730B
- Authority
- CN
- China
- Prior art keywords
- detection algorithm
- anchor ring
- circle
- defect
- face
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of engine cam component surface defect inspection method, comprise that upper and lower end face anchor ring defects detection algorithm, bottom thread have or not detection algorithm and bottom outlet to have or not residual scrap iron detection algorithm, described upper and lower end face anchor ring defects detection algorithm adopts the location, the center of circle of carrying out upper and lower end face in conjunction with the Probabilistic Hough Transform method of gradient information, get rid of center hole, adopt homomorphic filtering to carry out pretreatment to the image of upper end anchor ring and lower surface again, remove picture noise with opening operation, to defect area cluster, judge defect type. The present invention adopts coaxial light source, annular light source, spot light and area array cameras end face and the bottom outlet to parts to carry out polishing and IMAQ. The intermittent rotating machinery structure of utilizing dispenser and optoelectronic switch control disk, realizes resolution ratio and is better than 0.1mm, and single-piece is less than surface of the work crackle, cut, the spot of 3 seconds detection time, the whether automatic detection of residual scrap iron in parts bottom outlet screw thread, hole.
Description
Technical field
The invention belongs to machine components detection field, be specifically related to a kind of engine cam parts tablePlanar defect detection method.
Background technology
Camshaft is parts in piston engine, can control the opening and closing action of valve.Valve motion rule is related to power and the service performance of an engine, and therefore camshaft is at engineUpper in occupation of consequence very. Camshaft parts may cause Lou and add in process of manufactureWork, collide with, the problem such as casting skin, rust staining, be the quality that ensures camshaft, need to ensure to dispatch from the factory zeroParts must be qualified. The small workpiece goods of at present domestic most enterprises to production in enormous quantitiesBlemish, still adopts artificial visually examine's method. Artificial visually examine is subject to physiology and psychological factor impactCause undetectedly, a large amount of human resources of need of work that simultaneously greatly repeat, have increased the life of productProduce and processing cost. Therefore, rational blemish noncontact automatic checkout system is to industrial automationQuality control has important practical value. The present invention is on the basis of original production process, increasesOne platform convex wheel shaft parts certified products detect and are very important. For avoiding parts contact detection to causeCollide with, adopt machine vision technique be rational.
Summary of the invention
(1) technical problem that will solve
The technical problem to be solved in the present invention is to provide a kind of engine cam component surface defect inspectionSurvey method, has solved the inefficiency of artificial visually examine's method, easily the problem such as undetected, false retrieval.
(2) technical scheme
For solving the problems of the technologies described above, the technical solution adopted in the present invention is:
A kind of engine cam component surface defect inspection method, comprises that upper and lower end face anchor ring lacksSunken detection algorithm, bottom thread have or not detection algorithm and bottom outlet to have or not residual scrap iron detection algorithm, instituteState upper and lower end face anchor ring defects detection algorithm and adopt the Probabilistic Hough Transform method in conjunction with gradient informationCarry out the center of circle location of upper and lower end face, get rid of center hole, then figure to upper end anchor ring and lower surfacePicture adopts homomorphic filtering to carry out pretreatment, removes picture noise with opening operation, to defect area cluster,Judge defect type.
Wherein, also comprise that bottom thread has or not detection algorithm, it first utilizes the oval circle in marginal information locationThe heart, the polling place in the position fixing process of the recycling center of circle adopts the method for ellipse fitting to obtain elliptic parameter,Then utilize the oval anchor ring forming of surface defects detection Algorithm Analysis.
Wherein, also comprise that bottom thread has or not detection algorithm, it first utilizes the oval circle in marginal information locationThe heart, the polling place in the position fixing process of the recycling center of circle adopts the method for ellipse fitting to obtain elliptic parameter,By workpiece size Information locating screw position, utilize the marginal information analysis of screw thread whether to have screw thread.
Wherein, also comprise that bottom outlet has or not residual scrap iron detection algorithm, first it locate bottom surface excircle configurationPosition, then utilizes cylindrical information in appointed area, to locate inner circle position, within the scope of inner circle, utilizesThreshold values method two value inner circle region.
(3) beneficial effect
The present invention is compared to prior art, has following beneficial effect: the present invention adopt coaxial light source,Annular light source, spot light and area array cameras end face and the bottom outlet to parts carries out polishing and IMAQ.The intermittent rotating machinery structure of utilizing dispenser and optoelectronic switch control disk, realizes resolution ratio and is better than0.1mm, single-piece is less than surface of the work crackle, cut, the spot of 3 seconds detection time, at the bottom of partsThe whether automatic detection of residual scrap iron in hole screw thread, hole. And can carry out control cylinder by testing resultMove and can repair the sorting of parts and unrepairable parts. Ensure to be installed to engineThe quality of the parts on camshaft, thus the traffic accident causing because of engine cam reduced.
Brief description of the drawings
Fig. 1 is the location schematic diagram of workpiece of the present invention upper end anchor ring;
Fig. 2 is that the certified products of workpiece of the present invention upper end anchor ring detect intention;
Fig. 3 is the location schematic diagram of workpiece of the present invention lower surface;
Fig. 4 is the defects detection schematic diagram of workpiece of the present invention lower surface;
Fig. 5 is the location schematic diagram of workpiece bottom outlet screw thread of the present invention;
Fig. 6 is the detection schematic diagram of workpiece bottom outlet screw thread of the present invention;
Fig. 7 is the location schematic diagram of workpiece bottom outlet of the present invention;
Fig. 8 is the detection schematic diagram of workpiece bottom outlet residual scrap iron of the present invention.
Detailed description of the invention
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used for illustrating the present invention, but are not used for limiting the scope of the invention.
Determining that parts detect on the basis of station and defect, select to adopt revolving being convenient to up and downThe Machine Design thinking of material, utilizes the intermittent dispenser of driven by motor and optoelectronic switch to carry out machine to diskTool control. Adopt two coaxial red light sources, a spot light and an annular light source respectively to partsUpper end anchor ring, lower surface, bottom outlet screw thread and bottom outlet in carry out polishing, utilize four area array cameras to enterThe IMAQ of the corresponding station of row. Select two cylinders to sort respectively the parts of defect unrepairableWith recoverable parts. By ADT-8940A1PCI bus four-axis movement control card withADT-9162 binding post is controlled motor and cylinder. At the VS2005 of WindowsXP environmentIn development platform, utilize MFC, OpenCV, Blepo, the dynamic link of camera and motion control cardProcess the image collecting in storehouses etc.
Upper and lower end face anchor ring defects detection algorithm:
Will use circle location for the detection of upper and lower end face, conventional round location algorithm comprises HoughThe method of conversion or edge fitting. Edge fitting algorithm is subject to Clutter edge and disturbs, and causes result notStable, Clutter edge can be effectively got rid of in Hough conversion, but traditional Hough change detection circle is calculatedMethod is more time-consuming, can adopt a kind of Probabilistic Hough Transform method of combination gradient information for this reason, largeThe large detection speed that improves. To the marginal point in image, calculate respectively the gradient d of its x direction and y directionxAnd dy, the gradient intensity of this pointBallot direction θ=tan-1(ay/dx). This point is in θ sideUpwards to [r between given radial regionsmin，rmax] vote, the peak point finally obtaining is exactly requiredSphere center position.
Compare with the 21HT algorithm of OpenCV, the efficiency of this algorithm is greatly improved. ?CPU is in 2.4G situation, and size is 7ms for the image of 640*120 adopts this algorithm process time,And the processing time of realizing of identical image employing OpenCV is 80ms.
Obtaining behind upper and lower end face circle position, owing to upper surface not being required and lower surface existence circleThe reason in hole, need to get rid of center, and pending image is exactly upper and lower end face circle eliminating centerThe annulus forming behind position. Algorithm will utilize in this region surface defects detection Algorithm Analysis fixedPosition defective locations.
For upper end anchor ring and the lower surface of the parts that collect, adopt homomorphic filtering to carry out imagePretreatment, the problem such as image blurring of removing that the factors such as polishing is inhomogeneous and backlight cause. Pass through SobelEdge detection operator and improved Hough conversion circle detection algorithm by upper end anchor ring and lower surface from imageIn extract. Then separately image dividing processing is carried out to, the district being partitioned in the effective coverage of extractingTerritory can be subject to the impact of edge and noise conventionally. Noise main manifestations is the region that some areas are very little,Can operate removal by morphologic opening. Open the rectangular configuration parameter that operation setting size is less, canConnect very little region to keep apart some in denoising, be convenient to follow-up connected region and extract.
Behind filtering noise region, binary image is carried out to connected region processing, defect pixel is communicated withForm defect area. In this process, may, due to the interference of noise, cause defect area to be cut apartBecome some zonules. Therefore, need to after processing, connected region carry out cluster to defect area. ClusterCriterion according to the distance of defect area, be a large region by the region clustering of close together.After above-mentioned processing, in image, be only left defect area to be determined. For the defect area in imageTerritory cut apart the dynamic threshold segmentation algorithm adopting on gray level image.
In thread defect to peel off defect generally larger, be shaped as bulk, therefore can be according to defectRegion area size is directly identified. Scratch region generally shows as the intensive polymerization of some zonules,General defect area extraction algorithm is more difficult to get accurate region. Due in this project, carry at defect areaIn getting, adopt region clustering algorithm, therefore can accurately obtain the polymerized area of zonule, therefore also canSo that scratch defect is identified. For slit region, the feature being reflected on image due to crackle is:Region is elongated continuously; Circularity is very little; Area is much bigger with respect to system noise. And systemThe feature of image of noise is to be spot distribution; Discontinuous; Circularity is very large; A single point area is very little.Therefore, we adopt two parameters to judge whether tested part exists crackle, and one is defect areaCircularity C, another is the area S of defect area.
Fig. 1 and Fig. 3 are respectively the location schematic diagrames of workpiece upper end anchor ring and lower surface surveyed area, figure2 with Fig. 4 be respectively the schematic diagram of workpiece upper end anchor ring and lower surface defects detection result. Fig. 4 showsUpper end anchor ring does not have defect, and Fig. 4 shows that lower surface exists the defect of serious unrepairable, must quiltSort out.
Bottom outlet screw thread has or not detection algorithm:
Have or not and add man-hour when detecting bottom outlet screw thread, employing be spot light polishing, camera tilts to gather figurePicture. In order to extract screw thread position in bottom outlet, need to use oval location algorithm. Oval location is logicalThe normal Hough of employing converts, but because ellipse has 5 parameters, adopts the time of classical Hough transformsCost is too large, so adopt improved random Hough transformation in native system. But improvement algorithmComputing time is still long, and for this reason, first algorithm utilizes the method similar to circle location, utilizes limitThe oval center of circle of edge Information locating, then utilizes polling place in the position fixing process of the center of circle to adopt ellipse fittingMethod obtains elliptic parameter, thereby averages out in robustness and time efficiency. Practice shows, is somebody's turn to doAlgorithm has been obtained good effect.
Obtain behind oval position, can utilize the oval anchor ring forming of surface defects detection Algorithm Analysis.Also can pass through workpiece size Information locating screw position, utilize the marginal information analysis of screw thread to be simultaneouslyThe no screw thread that exists. If there is screw thread, the edge in this region is more intense, and exists rule to distribute.
Fig. 5 is the location schematic diagram of bottom outlet screw thread, and Fig. 6 detects the signal whether bottom outlet screw thread is processedFigure. From figure, can find, the be positioned edge feature in region of the workpiece of processing screw thread is very obvious.
Bottom outlet has or not residual scrap iron detection algorithm:
Bottom hole location is equally based on circle location algorithm. Because the edge of inner circle is not obvious, directly locationThe effect of inner circle is unsatisfactory, therefore first locates the obvious cylindrical in edge, then utilizes cylindrical information,In appointed area, locate inner circle position.
Be mainly whether to detect residual scrap iron for bottom outlet, under the light source designing irradiates, iron filings existIn image, be all generally to show as black block, therefore within the scope of inner circle, utilize in threshold method binaryzationCircle region, obtains bottom hole whether you exists iron filings thereby can obtain analyzing.
Fig. 7 is the schematic diagram of location bottom outlet, and Fig. 8 is the testing result schematic diagram of bottom hole iron chip. From figureIn can find, at the inner residual bar shaped iron filings of bottom outlet, be defective work. But this workpieceBe recoverable, can repair in product therefore need to be sorted into.
The above is only the preferred embodiment of the present invention, it should be pointed out that for the artThose of ordinary skill, not departing under the prerequisite of the technology of the present invention principle, can also make someImprovements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (3)
1. an engine cam component surface defect inspection method, is characterized in that:Comprise that upper and lower end face anchor ring defects detection algorithm, bottom thread have or not detection algorithm and bottom outletHave or not residual scrap iron detection algorithm, described upper and lower end face anchor ring defects detection algorithm adopts combinationThe Probabilistic Hough Transform method of gradient information is carried out the location, the center of circle of upper and lower end face, gets rid ofCenter hole, then adopt homomorphic filtering to carry out pretreatment to the image of upper end anchor ring and lower surface,Remove picture noise with opening operation, to defect area cluster, judge defect type; Also comprise the endPortion's screw thread has or not detection algorithm, and it first utilizes marginal information to locate the oval center of circle, the recycling center of circlePolling place in position fixing process adopts the method for ellipse fitting to obtain elliptic parameter, then utilizes tablePlanar defect detection algorithm is analyzed the oval anchor ring forming.
2. engine cam component surface according to claim 1 defects detection sideMethod, is characterized in that: also comprise that bottom thread has or not detection algorithm, it first utilizes marginal informationLocate the oval center of circle, the polling place in the position fixing process of the recycling center of circle adopts the method for ellipse fittingObtain elliptic parameter, by workpiece size Information locating screw position, utilize the edge letter of screw threadWhether breath analysis there is screw thread.
3. engine cam component surface according to claim 1 defects detection sideMethod, is characterized in that: also comprise that bottom outlet has or not residual scrap iron detection algorithm, first it locate at the endFace excircle configuration position, then utilizes cylindrical information in appointed area, to locate inner circle position,Within the scope of inner circle, utilize threshold values method two value inner circle region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310033740.0A CN103808730B (en) | 2013-01-25 | 2013-01-25 | Engine cam component surface defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310033740.0A CN103808730B (en) | 2013-01-25 | 2013-01-25 | Engine cam component surface defect inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103808730A CN103808730A (en) | 2014-05-21 |
| CN103808730B true CN103808730B (en) | 2016-05-25 |
Family
ID=50705814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310033740.0A Active CN103808730B (en) | 2013-01-25 | 2013-01-25 | Engine cam component surface defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103808730B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104390589B (en) * | 2014-11-20 | 2017-02-22 | 景德镇陶瓷大学 | Anti-dazzle circular daily ceramic device applique out-of-bound detection method |
| CN105160656B (en) * | 2015-08-05 | 2017-11-03 | 哈尔滨工业大学 | A kind of pipe fitting internal thread visual identifying system and method based on gray level co-occurrence matrixes |
| CN106127100B (en) * | 2016-01-08 | 2019-04-09 | 宁夏巨能机器人系统有限公司 | A kind of robot vision identifying system and its image processing method |
| CN108230388B (en) * | 2018-02-06 | 2021-04-23 | 广西艾盛创制科技有限公司 | Recognition and positioning method for welding spot image of white car body |
| CN109444144A (en) * | 2018-08-31 | 2019-03-08 | 苏州巨能图像检测技术有限公司 | Cylinder holes hole wall defects detection detection method |
| CN109461141A (en) * | 2018-10-10 | 2019-03-12 | 重庆大学 | A kind of workpiece starved detection method |
| CN110006911B (en) * | 2019-04-19 | 2021-07-27 | 天津工业大学 | Method for detecting multiple scratches on metal surface containing screw |
| CN110378902B (en) * | 2019-09-11 | 2019-12-20 | 征图新视(江苏)科技股份有限公司 | Scratch detection method under high noise background |
| CN114152997B (en) * | 2021-12-14 | 2023-10-27 | 东阳(吴江)汽车部件有限公司 | Device and method for detecting scrap iron residues in turbine flange groove |
| CN114549403B (en) * | 2022-01-07 | 2024-05-14 | 中国地质大学（武汉） | Method for detecting intelligent precise geometrical circle centers of multiple monomers of side section of mechanical part |
| CN116703925B (en) * | 2023-08-08 | 2023-10-31 | 菲特（天津）检测技术有限公司 | Bearing defect detection method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054174A (en) * | 2009-10-30 | 2011-05-11 | 佳能株式会社 | Method and system for positioning licence plate |
| CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
| CN102621156A (en) * | 2012-03-07 | 2012-08-01 | 武汉理工大学 | Image-processing-based automatic micro part sorting system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001101417A (en) * | 1999-09-30 | 2001-04-13 | Canon Inc | Device, system and method for detecting defect and storage medium |
-
2013
- 2013-01-25 CN CN201310033740.0A patent/CN103808730B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054174A (en) * | 2009-10-30 | 2011-05-11 | 佳能株式会社 | Method and system for positioning licence plate |
| CN102393961A (en) * | 2011-06-29 | 2012-03-28 | 山东电力研究院 | Computer vision-based real-time detecting and tracking method for electric power transmission circuit of aircraft |
| CN102621156A (en) * | 2012-03-07 | 2012-08-01 | 武汉理工大学 | Image-processing-based automatic micro part sorting system |
Non-Patent Citations (2)
| Title |
|---|
| 乔闹生等.《PCB 显微图像缺陷圆孔检测方法研究》.《光电子• * |
| 激光》.2009,第20卷(第7期),第964-966、982页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103808730A (en) | 2014-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103808730B (en) | Engine cam component surface defect inspection method | |
| CN103090804B (en) | Automatic detection system and detection method of finished product magnet ring image | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN105334219A (en) | Bottleneck defect detection method adopting residual analysis and dynamic threshold segmentation | |
| Liu et al. | Automatic detection technology of surface defects on plastic products based on machine vision | |
| CN105403147A (en) | Embedded bottle pre-form detection system and detection method | |
| CN103308525B (en) | A kind of online test method for metal wire rod production and device | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN102628854A (en) | Automobile instrument board detection system and method | |
| CN106372667A (en) | Method for detecting adverse state of inclined sleeve part screws of high-speed train overhead line system | |
| CN109540904A (en) | A kind of detection of substrate surface gross imperfection and categorizing system | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN106018422A (en) | Matching-based visual outline defect inspection system and method for specially-shaped stamping parts | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN106353340A (en) | Surface defect detection method for rod-like high-reflectance part | |
| CN102129685A (en) | Method for detecting irregular circle based on Gauss pyramid decomposition | |
| Li et al. | The method for glass bottle defects detecting based on machine vision | |
| CN110060239B (en) | Defect detection method for bottle opening of bottle | |
| WO2022222467A1 (en) | Open circular ring workpiece appearance defect detection method and system, and computer storage medium | |
| Kamani et al. | Automatic paint defect detection and classification of car body | |
| CN103308593A (en) | Defect intelligent identification detection system for magnetic powder welding flaw detection | |
| CN205786374U (en) | Special-shaped stamping parts profile defects vision detection system based on coupling | |
| CN105405137B (en) | Axoplasm quantity measuring method based on machine vision |
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 |