CN107966099A - A kind of detection method of part defective products - Google Patents
A kind of detection method of part defective products Download PDFInfo
- Publication number
- CN107966099A CN107966099A CN201711261642.7A CN201711261642A CN107966099A CN 107966099 A CN107966099 A CN 107966099A CN 201711261642 A CN201711261642 A CN 201711261642A CN 107966099 A CN107966099 A CN 107966099A
- Authority
- CN
- China
- Prior art keywords
- control unit
- conveyor
- central control
- measured
- image
- 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.)
- Withdrawn
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
-
- 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)
- General 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)
- Immunology (AREA)
- Pathology (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention provides a kind of detection method of part defective products, use the image information of image acquisition device part to be measured, and image information is transmitted to central control unit, marginal information and the standard picture marginal information of part to be measured are compared, it is if consistent, then central control unit control driving motor operation, and motor and striking mechanism are closed, conveyor is by parts transport to be measured to product packing；It is if inconsistent, then central control unit control driving motor operation, and open the laser emitter on striking mechanism, laser pickoff receives laser signal, central control unit control driving motor stops, central control unit control motor driving striking mechanism gets rejected part ready central control unit control driving motor operation after mark, and conveyor is by parts transport to be measured to product rejection.
Description
Technical field
The present invention relates to intelligence test field, more particularly to a kind of detection method of part defective products.
Background technology
Automatic manual transmission refers to the connection that machine components or component are realized according to the technical requirements of design, machine components or portion
Part is combined into machine.Automatic manual transmission is machine manufacture and the important step repaired, particularly for repair of machine, due to providing
The part of assembling is conducive to situation during machine-building, more so that assembly work has particularity.The quality of assembly work is to machine
The efficiency of device, the duration repaired, the labour of work and cost etc. all play very important effect.
With the complication of mechanical structure, it is irregular shape that machine components are also developed by regular shape, and traditional
Standard module is only through to the calibration equipment of regular part to verify part, applied to the part school to irregular shape
It is not high to test middle precision, so as to influence Automatic manual transmission precision.
The content of the invention
In order to overcome the above problem, the present invention provides a kind of detection method of part defective products, uses image collecting device
Gather the image information of part to be measured, and image information is transmitted to central control unit, central control unit is by by image
Information contrasts the detection essence that to judge whether part to be measured is qualified, can not only improve to irregular part with standard picture information
Degree, moreover it is possible to by replacing standard picture information to be applicable in part of different shapes.
The detection method of part defective products according to an embodiment of the invention, wherein, calibration equipment include testboard,
Conveyor, fixed station, part to be measured, image collecting device, testing jig, fixed seat, motor, striking mechanism, center control dress
Put and drive motor；
Conveyor is placed on testboard, and driving motor is placed in the side of testboard, and driving motor drives conveyor along testboard
Upper plane motion, conveyor drive fixed station to move in the horizontal direction, and fixed station is placed in the conveyor, part to be measured
It is fixed in fixed station card slot；
Fixed seat, central control unit and motor are fixedly connected sequentially in testing jig towards the side of conveyor, image collector
Put and be fixedly connected with fixed seat, striking mechanism is fixedly connected with the transmission axle of motor；
Image collecting device is used for the image information for gathering part to be measured, and image information is transmitted to central control unit, in
Control device is entreated by contrasting image information and standard picture information to judge whether part to be measured is qualified, if unqualified,
Central control unit controls the motor driving dotting machine to get rejected part mark ready.
Preferably, central control unit includes image processing apparatus, industrial personal computer, memory and controller, image collector
Put and be connected with image collecting device, image processing apparatus, memory and controller are connected with industrial personal computer respectively, controller, motor
It is sequentially connected with striking mechanism.
Preferably, part to be measured is irregular shape.
Preferably, the marginal information of image processing apparatus extraction image information, to extract image border.
Preferably, the marginal information of image information is obtained using improved Edge extraction algorithm.
Preferably, central control unit by image border compared with the standard picture edge in memory, if unanimously, treating
It is qualified to survey part, if inconsistent, controller control motor driving striking mechanism carries out rejected part to get mark ready.
The method that part defective products detection is carried out using calibration equipment is included the following steps：
Step 1, part to be measured is placed in the card slot of fixed station, and fixed station is placed in conveyor, open the drive
Dynamic motor, makes fixed station be moved with the conveyor；
Step 2, the laser emitter in fixed seat is opened, laser pickoff receives laser signal, central control unit control
Motor is driven to stop, the image information of image acquisition device part to be measured；
Step 3, central control unit obtains the marginal information of image information, image side using improved Edge extraction algorithm
Edge extraction algorithm is：
Ask for the image intensity value of transverse edge detection, two-dimensional function f (x, y) is defined as, wherein x, y is space coordinate, its
In,
=(-2) f(x-1,y-1)+2f(x+1,y-1)-3f(x-1,y)+3f(x+1,y)-2f(x-1,y+1)+2f(x+1,y+
1)；
Ask for the image intensity value of longitudinal edge detection, wherein,=2f(x-1,y-1)+3f(x+1,y-1)+2f(x+1,y-
1) +1f(x+1,y)-2f(x-1,y+1)-2f(x+1,y+1)-3f(x,y+1)；
Ask for the gray value of image；
Judge whether above-mentioned gray value is more than predetermined threshold value, point coordinates during if more than the predetermined threshold value for (,), then
Point (,) it is image border point, wherein n is positive integer；
Step 4：Marginal information and the standard picture marginal information of part to be measured are compared, if unanimously, central control unit control
System driving motor operation, and motor and striking mechanism are closed, conveyor is by parts transport to be measured to product packing；If differ
Cause, then central control unit control driving motor operation, and open the laser emitter on striking mechanism, laser pickoff receives
To laser signal, central control unit control driving motor stops, and central control unit control motor drives striking mechanism to not
Qualified parts get central control unit control driving motor operation after mark ready, and conveyor is by parts transport to be measured to product rejection
Place.
Brief description of the drawings
Fig. 1 is the calibration equipment schematic diagram of the present invention；
Fig. 2 is the functional block diagram of the central control unit of the present invention.
Reference numeral：
1- testboards；2- conveyors；3- fixed stations；4- parts to be measured；5- image collecting devices；6- testing jigs；7- fixed seats；
8- motors；9- striking mechanisms；10- central control units；11- drives motor.
Embodiment
The detection method of part defective products of the present invention is described in detail with reference to the accompanying drawings and examples.
As shown in Figure 1, the present invention provides a kind of calibration equipment, believed using the image of image acquisition device part to be measured
Breath, and image information is transmitted to central control unit, central control unit is by by image information and standard picture information pair
Than to judge whether part to be measured is qualified, can not only improve the accuracy of detection to irregular part, moreover it is possible to pass through the standard of replacing
Image information is with applicable part of different shapes.
Calibration equipment includes testboard（1）, conveyor（2）, fixed station（3）, part to be measured（4）, image collecting device
（5）, testing jig（6）, fixed seat（7）, motor（8）, striking mechanism（9）, central control unit（10）With driving motor（11）；Its
In,
Conveyor（2）It is placed in testboard（1）On, drive motor（11）It is placed in testboard（1）Side, drive motor（11）Driving
Conveyor（2）Along testboard（1）Movement, conveyor（2）Drive fixed station（3）Movement, fixed station（3）It is placed in conveyor
（2）On, part to be measured（4）It is fixed on fixed station（3）In card slot；
Fixed seat（7）, central control unit（10）And motor（8）It is fixedly connected sequentially in testing jig（6）Towards conveyor（2）'s
Side, image collecting device（5）With fixed seat（7）It is fixedly connected, striking mechanism（9）With motor（8）Transmission axle be fixedly connected；
In fixed seat（7）And striking mechanism（9）On be separately installed with laser emitter（Not shown in figure）, fixed station（3）On
Laser pickoff is installed（Not shown in figure）, when laser pickoff receives laser signal, central control unit（10）Control
Drive motor（11）By conveyor（2）Operation suspension 3s.
Image collecting device（5）For gathering part to be measured（4）Image information, and image information is transmitted to central control
Device processed（10）, central control unit（10）By contrasting image information and standard picture information to judge part to be measured（4）
It is whether qualified, if unqualified, central control unit（10）Control motor（8）Drive striking mechanism（9）Rejected part is beaten
Point mark.
As shown in Fig. 2, central control unit（10）Including image processing apparatus, industrial personal computer, memory and controller, image
Harvester（5）It is connected with image collecting device, image processing apparatus, memory and controller are connected with industrial personal computer respectively, control
Device processed, motor（8）And striking mechanism（9）It is sequentially connected.
Part to be measured（4）For irregular shape.
Image processing apparatus extracts the marginal information of image information, to extract image border.
The marginal information of image information is obtained using improved Edge extraction algorithm.
Traditional image edge information extraction algorithm, according to above and below pixel, left and right adjoint point intensity-weighted it is poor, in edge
Reach extreme value this phenomenon detection edge, though there is smoothing effect to noise, it is possible to provide more accurate edge directional information,
Edge precision is not high enough, since the image outline of part to be measured is generally straight line or camber line, it is therefore desirable to continuous to image
The edge of rule change is strengthened, and using above-mentioned improved Edge extraction algorithm, is carried to part edge to be measured
When taking, can obtain become apparent from, accurate image edge information.
Central control unit（10）By image border compared with the standard picture edge in memory, if unanimously, it is to be measured
Part（4）Qualification, if inconsistent, controller control motor（8）Drive striking mechanism（9）Rejected part is carried out to get mark ready
Note.
The method that part defective products detection is carried out using calibration equipment is included the following steps：
Step 1, by part to be measured（4）It is placed in fixed station（3）Card slot in, and by fixed station（3）It is placed in the conveyor
（2）On, driving motor is opened, makes fixed station（3）With conveyor（2）Move together；
Step 2, fixed seat is opened（7）On laser emitter, laser pickoff receives laser signal, central control unit
（10）Control the driving motor（11）Stop, described image harvester（5）Gather the part to be measured（4）Image letter
Breath；
Step 3, the central control unit（10）The side of described image information is obtained using improved Edge extraction algorithm
Edge information, described image Boundary extracting algorithm are：
Ask for the image intensity value of transverse edge detection, two-dimensional function f (x, y) is defined as, wherein x, y is space coordinate, its
In,
=(-2) f(x-1,y-1)+2f(x+1,y-1)-3f(x-1,y)+3f(x+1,y)-2f(x-1,y+1)+2f(x+1,y+
1)；
Ask for the image intensity value of longitudinal edge detection, wherein,=2f(x-1,y-1)+3f(x+1,y-1)+2f(x+1,y-
1) +1f(x+1,y)-2f(x-1,y+1)-2f(x+1,y+1)-3f(x,y+1)；
Ask for the gray value of image；
Judge whether above-mentioned gray value is more than predetermined threshold value, point coordinates during if more than the predetermined threshold value for (,), then
Point (,) it is image border point, wherein n is positive integer；
Step 4：By the marginal information and the part to be measured（4）Standard picture marginal information compare, if unanimously, it is described
Central control unit（10）Control the driving motor（11）Operation, and close motor（8）And striking mechanism（9）, conveyor（2）
By part to be measured（4）It is transmitted at product packing；If inconsistent, central control unit control driving motor（11）Operation, and
Open striking mechanism（9）On laser emitter, laser pickoff receives laser signal, central control unit（10）Control is driven
Dynamic motor（11）Stop, central control unit（10）Control motor（8）Drive striking mechanism（9）Mark is got rejected part ready
Central control unit afterwards（10）Control driving motor（11）Operation, conveyor（2）By part to be measured（4）It is transmitted to product rejection
Place, is rejected labeled part by staff.
It should be noted last that the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted.Although ginseng
The present invention is described in detail according to embodiment, it will be understood by those of ordinary skill in the art that, to the technical side of the present invention
Case technical scheme is modified or replaced equivalently, without departure from the spirit and scope of technical solution of the present invention, it should all cover in the present invention
Right among.
Claims (3)
1. a kind of detection method of part defective products, calibration equipment include testboard（1）, conveyor（2）, fixed station（3）, treat
Survey part（4）, image collecting device（5）, testing jig（6）, fixed seat（7）, motor（8）, striking mechanism（9）, center control dress
Put（10）With driving motor（11）；The conveyor（2）It is placed in the testboard（1）On, the driving motor（11）It is placed in institute
State testboard（1）Side, the driving motor（11）Drive the conveyor（2）Along the testboard（1）Upper plane fortune
It is dynamic, the fixed station（3）It is placed in the conveyor（2）On, the conveyor（2）Drive the fixed station（3）Along level
Direction is moved, the part to be measured（4）It is fixed on the fixed station（3）In card slot；The fixed seat（7）, it is described center control
Device processed（10）With the motor（8）It is fixedly connected sequentially in the testing jig（6）Towards the conveyor（2）Side, institute
State image collecting device（5）With the fixed seat（7）It is fixedly connected, the striking mechanism（9）With the motor（8）Transmission axle
It is fixedly connected, the fixed seat（7）With the striking mechanism（9）On be separately installed with laser emitter, fixed station（3）Upper peace
Equipped with laser pickoff；It is characterized in that, the method for part defective products detection is carried out using above-mentioned calibration equipment includes following step
Suddenly：
Step 1, by the part to be measured（4）It is placed in the fixed station（3）Card slot in, and by the fixed station（3）Put
In the conveyor（2）On, the driving motor is opened, makes the fixed station（3）With the conveyor（2）Move together；
Step 2, the fixed seat is opened（7）On laser emitter, the laser pickoff receives laser signal, in described
Entreat control device（10）Control the driving motor（11）Stop, described image harvester（5）Gather the part to be measured（4）
Image information；
Step 3, the central control unit（10）The side of described image information is obtained using improved Edge extraction algorithm
Edge information, described image Boundary extracting algorithm are：
Ask for the image intensity value of transverse edge detection, two-dimensional function f (x, y) is defined as, wherein x, y is space coordinate, its
In,
=(-2) f(x-1,y-1)+2f(x+1,y-1)-3f(x-1,y)+3f(x+1,y)-2f(x-1,y+1)+2f(x+1,y+
1)；
Ask for the image intensity value of longitudinal edge detection, wherein,=2f(x-1,y-1)+3f(x+1,y-1)+2f(x+1,y-
1) +1f(x+1,y)-2f(x-1,y+1)-2f(x+1,y+1)-3f(x,y+1)；
Ask for the gray value of image；
Judge whether above-mentioned gray value is more than predetermined threshold value, point coordinates during if more than the predetermined threshold value for (,), then
Point (,) it is image border point, wherein n is positive integer；
Step 4：By the marginal information and the part to be measured（4）Standard picture marginal information compare, if unanimously, it is described
Central control unit（10）Control the driving motor（11）Operation, and close the motor（8）With the striking mechanism（9）,
The conveyor（2）By the part to be measured（4）It is transmitted at product packing；If inconsistent, the central control unit control
Make the driving motor（11）Operation, and open the striking mechanism（9）On laser emitter, the laser pickoff receives
To laser signal, the central control unit（10）Control the driving motor（11）Stop, the central control unit（10）
Control the motor（8）Drive the striking mechanism（9）The central control unit mark after is got rejected part ready（10）
Control the driving motor（11）Operation, the conveyor（2）By the part to be measured（4）It is transmitted at product rejection.
2. detection method according to claim 1, it is characterised in that the central control unit（10）Including image procossing
Device, industrial personal computer, memory and controller, described image harvester（5）It is connected with described image harvester, described image
Processing unit, the memory and the controller are connected with the industrial personal computer respectively, the controller, the motor（8）With
The striking mechanism（9）It is sequentially connected.
3. detection method according to claim 1, it is characterised in that the part to be measured（4）For irregular shape.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261642.7A CN107966099A (en) | 2017-12-04 | 2017-12-04 | A kind of detection method of part defective products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261642.7A CN107966099A (en) | 2017-12-04 | 2017-12-04 | A kind of detection method of part defective products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107966099A true CN107966099A (en) | 2018-04-27 |
Family
ID=61997928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711261642.7A Withdrawn CN107966099A (en) | 2017-12-04 | 2017-12-04 | A kind of detection method of part defective products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107966099A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109001222A (en) * | 2018-09-28 | 2018-12-14 | 三诺生物传感股份有限公司 | A kind of AOI looks into enzyme equipment and method automatically |
| CN109239074A (en) * | 2018-08-20 | 2019-01-18 | 中铝国际工程股份有限公司 | A kind of green anode carbon block detection method based on machine vision |
| CN109270067A (en) * | 2018-09-29 | 2019-01-25 | 格力电器（武汉）有限公司 | Detection method, the device and system of equipment appearance |
| CN110288575A (en) * | 2019-06-17 | 2019-09-27 | Oppo（重庆）智能科技有限公司 | Localization method, electronic device, equipment and the storage medium of part bad position |
-
2017
- 2017-12-04 CN CN201711261642.7A patent/CN107966099A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109239074A (en) * | 2018-08-20 | 2019-01-18 | 中铝国际工程股份有限公司 | A kind of green anode carbon block detection method based on machine vision |
| CN109001222A (en) * | 2018-09-28 | 2018-12-14 | 三诺生物传感股份有限公司 | A kind of AOI looks into enzyme equipment and method automatically |
| CN109270067A (en) * | 2018-09-29 | 2019-01-25 | 格力电器（武汉）有限公司 | Detection method, the device and system of equipment appearance |
| CN110288575A (en) * | 2019-06-17 | 2019-09-27 | Oppo（重庆）智能科技有限公司 | Localization method, electronic device, equipment and the storage medium of part bad position |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107966099A (en) | A kind of detection method of part defective products | |
| CN109886298B (en) | Weld quality detection method based on convolutional neural network | |
| CN106952250A (en) | A kind of metal plate and belt detection method of surface flaw and device based on Faster R CNN networks | |
| CN104990926B (en) | A kind of TR elements positioning of view-based access control model and defect inspection method | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN111189837B (en) | Cigarette appearance online detection method and device | |
| CN110473173A (en) | A kind of defect inspection method based on deep learning semantic segmentation | |
| CN106934813A (en) | A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning | |
| CN106952258A (en) | A kind of bottle mouth defect detection method based on gradient orientation histogram | |
| CN106934800A (en) | A kind of metal plate and belt detection method of surface flaw and device based on YOLO9000 networks | |
| CN109683360A (en) | Liquid crystal display panel defect inspection method and device | |
| CN104913739B (en) | Visual measurement method and device for eccentricity of crank throw of crankshaft | |
| CN107876425A (en) | A kind of bearing defect detecting system device of view-based access control model | |
| CN106909909B (en) | Face detection and alignment method based on shared convolution characteristics | |
| CN107677688A (en) | Notebook computer appearance delection device | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN115156093A (en) | Battery shell defect detection method, system and device | |
| CN106875441A (en) | A kind of online PE bottles of recognition positioning method based on machine vision | |
| CN107886131A (en) | One kind is based on convolutional neural networks detection circuit board element polarity method and apparatus | |
| CN107016396A (en) | A kind of assembling connecting piece characteristics of image deep learning and recognition methods | |
| CN107952695A (en) | A kind of method of production line automatic screening defective products | |
| CN110415238A (en) | Diaphragm spots detection method based on reversed bottleneck structure depth convolutional network | |
| CN103310191B (en) | The human motion recognition method of movable information image conversion | |
| CN107717434A (en) | A kind of calibration equipment to irregular part | |
| CN103258218B (en) | Masking-out detects skeleton generating method, device, defect inspection method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180427 |
|
| WW01 | Invention patent application withdrawn after publication |