CN109579735A - Piston ring contour detecting method for identifying and classifying and its device based on machine vision - Google Patents
Piston ring contour detecting method for identifying and classifying and its device based on machine vision Download PDFInfo
- Publication number
- CN109579735A CN109579735A CN201811467726.0A CN201811467726A CN109579735A CN 109579735 A CN109579735 A CN 109579735A CN 201811467726 A CN201811467726 A CN 201811467726A CN 109579735 A CN109579735 A CN 109579735A
- Authority
- CN
- China
- Prior art keywords
- piston ring
- module
- machine vision
- contour detecting
- classifying
- 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
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
Piston ring contour detecting method for identifying and classifying and its device based on machine vision, it is characterised in that including guiding mechanism, visual mechanisms, light source mechanism, inflatable body, diversion mechanism；Wherein piston ring is placed in detection zone, visual mechanisms in the side of piston ring, light source mechanism visual mechanisms opposite side and and its on same central axes, inflatable body is at the top of piston ring detection zone, exit of the diversion mechanism in contour detecting region.The present invention passes through the non-contacting Detection & Controling method and apparatus based on machine vision, replace tradition is pure manually to identify the accurate operation classified to piston ring excircle configuration feature to realize with full-automatic mode, can the various diameters of flexible adaptation, diameter thickness piston ring detection, structure is simple, easy to operate.
Description
Technical field
The present invention is piston ring contour detecting method for identifying and classifying and its device based on machine vision, is belonged to based on machine
A kind of completely new innovative technology of the piston ring contour detecting method for identifying and classifying and its device of vision.
Background technique
It is needed in piston ring production process to the excircle configuration asymmetry bucket face of piston ring compressed in ring and scraping ring, outer circle
The conical surface, outer circle are the detection that part cylindrical surface etc. carries out front and back sides differentiation and oil ring scraping land, such as compression ring and scraping ring are divided into just
Reverse side, oil ring are divided into qualified unqualified etc., and current operation is which kind of above-mentioned class belonged to by visual inspection piston ring
Type, and sorted out manually, but the radial dimension range of piston ring excircle configuration is very narrow, from a few tenths of a mm to two millimeters
It differs, and one day yield of piston ring manufacturing enterprise is more than 10,000 at present, so big workload leads to pure artificial eye
It is easy to appear erroneous judgements, misclassification for operation, to influence the operation correctness of the next process of piston ring.Machine Vision Detection is
A kind of very outstanding energy replace human eye is completed in complex environment high-intensitive, high duplication, fine visual field high-precision oneself
Dynamic detection method.
Summary of the invention
The piston ring contour detecting method for identifying and classifying that the present invention, aiming to the above problems, provides a kind of based on machine vision and
Its device, the invention be it is a kind of can substitution be accomplished manually the efficient non-of most of conventional piston ring excircle configuration detection and classification
Contact automatically detects and recognition methods and its detection device.
Piston ring contour detecting identification device based on machine vision of the invention, including guiding mechanism, visual mechanisms, light
Source mechanism, inflatable body, diversion mechanism；Wherein piston ring is placed in detection zone, and visual mechanisms are in the side of piston ring, light
Source mechanism visual mechanisms opposite side and and its on same central axes, inflatable body at the top of piston ring detection zone, shunt machine
Exit of the structure in contour detecting region；
Piston ring contour detecting method for identifying and classifying based on machine vision of the invention includes the following steps:
(1) piston ring is pushed to outline identification detection zone from prime station by guiding mechanism；
(2) inflatable body clears up piston ring surface dust；
(3) visual mechanisms start, and triggering light source mechanism work acquires piston ring image data；
(4) image data calculate and analysis includes: image filtering module, image enhancement module, binary conversion treatment
Module, Morphological scale-space module, edge detection module, calculated result module；
(5) according to image analysis data, judging result identifies piston ring excircle configuration type, passes through the control of sorter
Piston ring is transported to diversion mechanism according to types of profiles and specifies region by system processed.
The image filtering module of the step of above-mentioned piston ring contour detecting method for identifying and classifying based on machine vision (4),
Using sharp filtering method, median filtering method；
The binary processing module of above-mentioned steps (4), using domain division method, object extraction method, local binarization processing
Method；
The Morphological scale-space module of above-mentioned steps (4) using etching operation, opens operation, closed operation；
The edge detection module of above-mentioned steps (4), using SOBEL Operator Method, Roberts operator, Median operator；
The calculated result module of above-mentioned steps (4) is combined using edge coordinate and least square method fitting surface mode；
The of the invention recognition methods of piston ring contour detecting and its device based on machine vision, due to using Guiding machine
Structure, visual mechanisms, light source mechanism, the composite structure of inflatable body, diversion mechanism, wherein piston ring is placed in detection zone,
Visual mechanisms in the side of piston ring, light source mechanism visual mechanisms opposite side and and its on same central axes, inflatable body exists
At the top of piston ring detection zone, diversion mechanism makes piston ring in detection, identification and classification in the exit in contour detecting region
It is injury-free in whole process.Meanwhile by the non-contacting Detection & Controling method based on machine vision, pointedly use
Image processing techniques is detected automatically, identified and is classified to the incomprehensive sheet type piston ring excircle configuration of field of detection,
It is more than the excircle configuration quality inspection of 10,000 plate sheet piston rings the artificial eye completion that needs daily of this process traditional approach
The highly intensive labour of survey upgrades as the detection of full-automatic excircle configuration, identification, mode classification.This method and its equipment can be real
Now precisely operation, it is high-efficient, ensure that product testing identification classification accuracy while, production lines matching can be greatly reduced
The quantity of worker reduces labor intensity of workers.Simultaneously this method and the various diameters of device energy flexible adaptation, diameter thickness piston ring
Detection, structure are simple, easy to operate.
Detailed description of the invention
Fig. 1 is main view of the invention.
Fig. 2 is top view of the invention.
Fig. 3 is the flow chart of the method for the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Embodiment:
Structural schematic diagram of the invention as shown in Figure 1, the piston ring contour detecting identification device based on machine vision, including
Guiding mechanism, visual mechanisms, light source mechanism, inflatable body, diversion mechanism；Wherein piston ring is placed in detection zone, vision
Mechanism in the side of piston ring, light source mechanism visual mechanisms opposite side and and its on same central axes, inflatable body is in piston
At the top of ring detection zone, exit of the diversion mechanism in contour detecting region；
Structural schematic diagram of the invention is as shown in figure 3, the piston ring contour detecting identification of the invention based on machine vision
Classification method includes the following steps:
(1) piston ring is pushed to outline identification detection zone from prime station by guiding mechanism；
(2) inflatable body clears up piston ring surface dust；
(3) visual mechanisms start, and triggering light source mechanism work acquires piston ring image data；
(4) image data calculate and analysis includes: image filtering module, image enhancement module, binary conversion treatment
Module, Morphological scale-space module, edge detection module, calculated result module；
(5) according to image analysis data, judging result identifies piston ring excircle configuration type, passes through the control of sorter
Piston ring is transported to diversion mechanism according to types of profiles and specifies region by system processed.
In this example, the image filtering of (4) the step of piston ring contour detecting method for identifying and classifying based on machine vision
Module, using sharp filtering method, median filtering method；
The binary processing module of above-mentioned steps (4), using domain division method, object extraction method, local binarization processing
Method；
The Morphological scale-space module of above-mentioned steps (4) using etching operation, opens operation, closed operation；
The edge detection module of above-mentioned steps (4), using SOBEL Operator Method, Roberts operator, Median operator；
The calculated result module of above-mentioned steps (4) calculates edge coordinate, using least square method fitting surface；
The recognition methods of piston ring contour detecting and its device the present invention is based on machine vision are for piston ring excircle wheel
Wide radial dimension is very narrow and field range is in the case where millimeter class precision, and contactless machine vision is used to examine to it
Survey mode and device complete high-intensitive detection and classification task.For the high dimensional profile shape of piston ring ring, synthesis is selected
Image filtering, image enhancement, image binaryzation, morphological image process, Image Edge-Detection combination come complete calculate data,
Complete detection, identification and the tagsort of piston ring excircle configuration.
The image of acquisition is carried out data screening by image filtering module, and picture noise is removed, and leaving facilitates profile knowledge
Other main feature information, this is the key that the outline identification correctness first step.
Image binaryzation module is clearly divided into image 0 and 1 liang of class by given threshold according to the gray value information of image,
Objective extraction profile and background information are clearly distinguished, this is the key that outline identification correctness second step.
Morphological image process module is by etching operation, opens operation and closed operation combination, in conjunction with edge detection mould
Block further extracts profile framework characteristic, this is the third step of outline identification correctness.
It should be pointed out that for those of ordinary skill in the art, without departing from the inventive concept of the premise,
Various modifications and improvements can be made, and these are all within the scope of protection of the present invention.Therefore, the scope of protection of the patent of the present invention
It should be determined by the appended claims.
Claims (2)
1. piston ring contour detecting method for identifying and classifying and its device based on machine vision, wherein the work based on machine vision
Plug ring contour detecting identifies sorter, including guiding mechanism, visual mechanisms, light source mechanism, inflatable body, diversion mechanism；Its
Middle piston ring is placed in detection zone, visual mechanisms in the side of piston ring, light source mechanism visual mechanisms opposite side and and its
On same central axes, inflatable body is at the top of piston ring detection zone, exit of the diversion mechanism in contour detecting region；Base
Include the following steps: in the piston ring contour detecting method for identifying and classifying of machine vision
(1) piston ring is pushed to outline identification detection zone from prime station by guiding mechanism；
(2) inflatable body clears up piston ring surface dust；
(3) visual mechanisms start, and triggering light source mechanism work acquires piston ring image data；
(4) to image data carry out calculate and analysis include: image filtering module, image enhancement module, binary processing module,
Morphological scale-space module, edge detection module, calculated result module；
(5) according to image analysis data, judging result identifies piston ring excircle configuration type, passes through the control system of sorter
Piston ring is transported to diversion mechanism according to types of profiles and specifies region by system.
2. the piston ring contour detecting method for identifying and classifying and its device according to claim 1 based on machine vision,
The image filtering module of above-mentioned steps (4) is characterized in that, using sharp filtering method, median filtering method；
The binary processing module of above-mentioned steps (4), using domain division method, object extraction method, local binarization facture；
The Morphological scale-space module of above-mentioned steps (4) using etching operation, opens operation, closed operation；
The edge detection module of above-mentioned steps (4), using SOBEL Operator Method, Roberts operator, Median operator；
The calculated result module of above-mentioned steps (4) is combined using edge coordinate and least square method fitting surface mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467726.0A CN109579735A (en) | 2018-12-03 | 2018-12-03 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811467726.0A CN109579735A (en) | 2018-12-03 | 2018-12-03 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109579735A true CN109579735A (en) | 2019-04-05 |
Family
ID=65926802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811467726.0A Pending CN109579735A (en) | 2018-12-03 | 2018-12-03 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109579735A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111678450A (en) * | 2020-05-09 | 2020-09-18 | 东华大学 | Visual detection method and device for precision part |
| CN111735409A (en) * | 2020-06-04 | 2020-10-02 | 深圳职业技术学院 | Soft robot arm shape measuring method, system and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU814488A1 (en) * | 1975-04-25 | 1981-03-23 | Грузинский Ордена Ленина И Ордена Тру-Дового Красного Знамени Политехничес-Кий Институт Им. B.И.Ленина | Monitoring mechanism to apparatus for sorting piston rings |
| SU1026846A1 (en) * | 1981-09-23 | 1983-07-07 | Пермское производственное объединение "Моторостроитель" им.Я.М.Свердлова | Apparatus for automatic sorting of piston rings by clearance |
| CN104239950A (en) * | 2014-09-02 | 2014-12-24 | 广州沧恒自动控制科技有限公司 | Piston ring counting system based on machine vision and counting method of piston ring counting system based on machine vision |
| CN204101439U (en) * | 2014-09-22 | 2015-01-14 | 南京信息工程大学 | A kind of piston ring automatic detecting platform |
| CN204276375U (en) * | 2014-11-14 | 2015-04-22 | 广州沧恒自动控制科技有限公司 | A kind of piston ring excircle inclined-plane checkout gear |
| CN207658681U (en) * | 2017-12-26 | 2018-07-27 | 广州沧恒自动控制科技有限公司 | The feed device of piston ring detection device |
-
2018
- 2018-12-03 CN CN201811467726.0A patent/CN109579735A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SU814488A1 (en) * | 1975-04-25 | 1981-03-23 | Грузинский Ордена Ленина И Ордена Тру-Дового Красного Знамени Политехничес-Кий Институт Им. B.И.Ленина | Monitoring mechanism to apparatus for sorting piston rings |
| SU1026846A1 (en) * | 1981-09-23 | 1983-07-07 | Пермское производственное объединение "Моторостроитель" им.Я.М.Свердлова | Apparatus for automatic sorting of piston rings by clearance |
| CN104239950A (en) * | 2014-09-02 | 2014-12-24 | 广州沧恒自动控制科技有限公司 | Piston ring counting system based on machine vision and counting method of piston ring counting system based on machine vision |
| CN204101439U (en) * | 2014-09-22 | 2015-01-14 | 南京信息工程大学 | A kind of piston ring automatic detecting platform |
| CN204276375U (en) * | 2014-11-14 | 2015-04-22 | 广州沧恒自动控制科技有限公司 | A kind of piston ring excircle inclined-plane checkout gear |
| CN207658681U (en) * | 2017-12-26 | 2018-07-27 | 广州沧恒自动控制科技有限公司 | The feed device of piston ring detection device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111678450A (en) * | 2020-05-09 | 2020-09-18 | 东华大学 | Visual detection method and device for precision part |
| CN111678450B (en) * | 2020-05-09 | 2022-01-11 | 东华大学 | Visual detection method and device for precision part |
| CN111735409A (en) * | 2020-06-04 | 2020-10-02 | 深圳职业技术学院 | Soft robot arm shape measuring method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| CN109141232B (en) | Online detection method for disc castings based on machine vision | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN109822398B (en) | Numerical control machine tool broken cutter detection system and method based on deep learning | |
| CN110220917A (en) | A kind of crown plug surface defect online test method based on image procossing | |
| CN105069790A (en) | Rapid imaging detection method for gear appearance defect | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN103868935A (en) | Cigarette appearance quality detection method based on computer vision | |
| CN105548212A (en) | System and method for online automatically detecting defects on glass surface of touch screen | |
| CN104794491A (en) | Fuzzy clustering steel plate surface defect detection method based on pre classification | |
| CN110111303A (en) | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image | |
| CN103808730B (en) | Engine cam component surface defect inspection method | |
| CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
| CN109087286A (en) | A kind of detection method and application based on Computer Image Processing and pattern-recognition | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN110096980A (en) | Character machining identifying system | |
| CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
| CN110349125A (en) | A kind of LED chip open defect detection method and system based on machine vision | |
| CN109579735A (en) | Piston ring contour detecting method for identifying and classifying and its device based on machine vision | |
| CN109358067A (en) | Motor ring varistor defect detecting system based on computer vision and method | |
| CN107421955A (en) | A kind of ceramic defective vision detection method | |
| CN112067618A (en) | Product quality defect acquisition and analysis system based on imaging | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN113588656A (en) | Novel bolt appearance size detection method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190405 |
|
| WD01 | Invention patent application deemed withdrawn after publication |