CN108050930A - A kind of bolt visible detection method - Google Patents
A kind of bolt visible detection method Download PDFInfo
- Publication number
- CN108050930A CN108050930A CN201711330338.3A CN201711330338A CN108050930A CN 108050930 A CN108050930 A CN 108050930A CN 201711330338 A CN201711330338 A CN 201711330338A CN 108050930 A CN108050930 A CN 108050930A
- Authority
- CN
- China
- Prior art keywords
- bolt
- data
- gasket
- detection
- detecting system
- 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
-
- 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- 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
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
-
- 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
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
Abstract
The invention discloses a kind of bolt visible detection methods in Data Detection field, detecting system carries out bolt and/or gasket vision-based detection by presentation layer, logical layer and data Layer, and specific detection process includes grassroot project, calls corresponding project, starts to detect, show and check that testing result, data such as preserve and check at the processes.Present invention user interface image-centric, detecting system can detect bolt or gasket automatically according to varying input signal, and input corresponding pass or NG signals according to result, so as to simplify the complexity of system, reduce the technology requirement of operating personnel.The detection method has been obtained for being widely applied in auto-parts industry at present.
Description
Technical field
The present invention relates to Data Detection fields, are to be related to a kind of bolt visible detection method specifically.
Background technology
In modern industry automated production, it is related to various Parts Recognition applications, as auto-parts produce
Process has strict requirements to the Dimension Types of all kinds of bolts and the placement location of gasket, and then needs to bolt and gasket etc.
Product is detected.The testing requirements of the present products such as client's bolt and gasket include：1) whether the type of bolt is correct, including
Whether the height of bolt is correct, and whether bolt is correct with the presence or absence of step and step height；2) type of bolt Upper gasket is
It is no correct, it includes whether as spring washer, whether the diameter and thickness of plain cushion is correct；3) bolt Upper gasket placement order whether with life
Production requirement is consistent.
And producer tests to the assembling quality of bolt and gasket using artificial mode mostly at present, but it is this
The labor intensity of mode is big, and work efficiency is low, and subjectivity is strong, technical quality, experience and the discernable by eye of easy examinate person
The factors such as ability and visual fatigue influence.
Drawbacks described above is worth solving.
The content of the invention
In order to overcome the shortcomings of existing technology, the present invention provides a kind of bolt visible detection method.
Technical solution of the present invention is as described below：
A kind of bolt visible detection method, which is characterized in that detecting system passes through presentation layer, logical layer and data Layer pair
Bolt and/or gasket carry out vision-based detection, wherein, presentation layer provides the interactive interface with user by user interface；It patrols
The service logic that layer controls the detecting system is collected, is the alternation of bed of the presentation layer and the data Layer, effectively described in tissue
The various data of data Layer；The data Layer includes the parameters of the detecting system and the data result of various detections, and
By effective management to data result, data supporting is provided for the detecting system；Specific detection process comprises the following steps：
Step 1, grassroot project are sequentially placed bolt and/or corresponding gasket according to prompting, preserve related data and engineering,
It is directly invoked in detection of the subsequent production with a product；
Step 2, the production requirement according to the bolt and/or the gasket, call corresponding project, proceed by inspection
It surveys；
Step 3, detection when, the detecting system by the input signal of IO control cards detect respectively the bolt and/or
The gasket, real-time display, which goes out testing result and sends corresponding signal by the IO control cards, notifies user, and user passes through
The user interface is checked；
Step 4, the data Layer preserve detection data, and user is checked at any time according to the date.
According to the present invention of said program, which is characterized in that the hardware components of the detecting system include industrial camera, mirror
Head, backlight, light source controller, IO control cards, industrial personal computer and display, the industrial camera and camera lens are connected with industrial personal computer
It connects, for gathering the respective image of respective bolt and/or gasket；The backlight is connected with light source controller, for giving
Bolt and/or gasket polishing, prominent individual features；The IO control cards are connected with industrial personal computer, and bolt is detected for receiving
And/or detection gasket signal, industrial personal computer is detected bolt and/or gasket according to corresponding signal, and the result of detection is led to
IO control cards are crossed to send.
Further, the detecting system is loaded on the industrial personal computer, in the industrial personal computer and the detecting system
Other each several parts are in communication with each other, and according to corresponding I/O port input signal, control industrial camera gathers corresponding picture, and image is carried out
Detection exports pass/NG signals finally by I/O port.
According to the present invention of said program, which is characterized in that when the detecting system is detected for the first time, further include
The step of preparation, specifically includes：
(1) open system；
(2) connect industrial camera and open backlight；
(3) camera parameter of the industrial camera is set, adjusts the brightness of the backlight, it is ensured that communication is normal and described
Industrial camera collects the apparent picture of contrast；
(4) IO control cards are connected, the relevant parameter of IO control cards is set.
Further, in the step (3), the camera parameter includes the bolt and/or the gasket in image
In regional extent, the time for exposure of camera and gain, Gaussian smoothing parameter, minimum edge amplitude and error parameter.
Further, the regional extent of the bolt and/or the gasket in the picture is by interesting image regions
Top left co-ordinate, length and width determine.
According to the present invention of said program, which is characterized in that in the step 1, user is to the bolt and the pad
Piece carries out learning from instruction.
According to the present invention of said program, which is characterized in that in the step 3, the detection process of the detecting system
Comprise the following steps：
The state that step 31, system monitoring IO cards accordingly input, if receiving bolt detection signal, system calls camera mould
Block captures bolt picture；
Step 32, the position according to teaching, corresponding edge in being extracted in bolt picture, if in corresponding region extraction not
Go out edge, then prompt bolt type mistake；If after successfully extracting edge, will bolt/step be calculated according to the position at edge
Height, with reference to the height of teaching and the error of setting, judge whether bolt correct, send out according to testing result pass or
Ng signals；
If step 33 receives gasket detection signal, system calls camera model crawl gasket picture.
Further, in the detection process of the detecting system, have to the edge extracting of the bolt and/or the gasket
Body includes step：
1) following formula are utilized, denoising is carried out by Gaussian filter before edge is extracted：
Wherein σ is Gaussian smoothing parameter；
2) to obtaining relevant marginal position after smooth rear function derivation, the derivative of Gaussian filter is
To function it is smooth after derivation result with first identical to the result that and function convolution obtains again after smoothing filter derivation,
I.e.：(f*h) `=f*h`,
The output of boundary filter is expressed as ei=| f*h |i；
3) non-maxima suppression is finally carried out to the marginal position extracted, the marginal point of final output meets：(ei＞
ei-1)∩(ei＞ ei+1)∩(ei>=t), wherein t is minimum edge amplitude.
Further, in the step 33, including：
If there was only plain cushion in 33-1, detection process, the position of the plain cushion according to teaching, it is 1 to generate a height
The measurement frame of a pixel measures the diameter in the region, and the cycle detection region can obtain the thickness of gasket, with reference to the thickness of teaching
And the error set may determine that whether gasket is correct；
If there are spring washer in 33-2, detection process, first judge whether corresponding region is the spring washer, the concrete foundation area
Whether domain gap and the edge of described spring washer the right and left occurs judges with the presence or absence of certain difference in height, if there are institutes
The gasket situation of the spring washer then spring washer up/down according to teaching is stated, continues to detect corresponding gasket, otherwise prompting mistake is simultaneously
NG signals are sent by IO control cards；
If there are gasket on spring washer in 33-3, detection process, when detection, first extracts the edge of described gasket the right and left, meter
The inclination angle of the gasket is calculated, and affine transformation is carried out to measurement frame according to the angle, is finally detected according to 33-1.
According to the present invention of said program, which is characterized in that in the step 4, user carries out the later stage and transfers, checks
Process specifically includes：
A. data real-time display during producing on the user interface, including：Pass/NG signals close
Lattice number, production sum and qualification rate；
B. user inquires about specific creation data according to the specific date by the user interface；
C. the data Layer automatically saves detection picture and daily record in process of production, and each item data is automatically according to produces day
Phase is stored in corresponding file, and the operating process for having user to the detecting system, relevant device are recorded in journal file
Connection status；
D. the logical layer carries out data processing according to date data input by user and product data, transfers the file
Each item data in folder, and it is shown to the user interface.
According to the present invention of said program, its advantage is：
1st, the present invention calculates the corresponding height of bolt by detecting the respective edges of bolt, so as to detect the class of bolt
Type and relevant parameter can directly invoke after different bolt type teachings, easy to operate.
2nd, the present invention can detect that the relevant parameter (diameter, thickness) of gasket by detecting the respective edges of gasket, different
Gasket teaching after can directly invoke, it is easy to operate.
3rd, the present invention can intelligent decision go out with the presence or absence of spring washer, and detect to tilt on spring washer caused by due to spring washer existing
The relevant parameter of plain cushion, detection data are more comprehensive, reference value higher.
4th, teaching and detection function of the invention can be suitble to the various production requirements of user, and realize and detect
Relevant parameter in production process, system have higher flexibility and adaptability.
Description of the drawings
Fig. 1 is the logic relation picture between presentation layer, logical layer and data Layer in the present invention.
Fig. 2 is the schematic diagram of hardware installation of the present invention.
Fig. 3 is the image that bolt is shot in the present invention.
Fig. 4 is the image that gasket is shot in the present invention.
Fig. 5 is the sequential flowchart that detecting system performs in the present invention.
Fig. 6 is the flow chart of teaching in the present invention.
In the figure 1, backlight；2nd, bolt；3rd, camera lens；4th, industrial camera；5th, step；6th, spring washer；7th, plain cushion.
Specific embodiment
Below in conjunction with the accompanying drawings and the present invention is further described in embodiment：
As shown in Figure 1, a kind of bolt visible detection method, detecting system pass through presentation layer, logical layer and data Layer pair
Bolt and/or gasket carry out vision-based detection, wherein, presentation layer provides the interactive interface with user by user interface；It patrols
The service logic of layer control detecting system is collected, is the alternation of bed of presentation layer and data Layer, effectively organizes the various data of data Layer；
The parameters of data Layer including detecting system and the data result of various detections, and by effective management to data result,
Data supporting is provided for detecting system.
As in Figure 2-4, the hardware components of detecting system include industrial camera 4, camera lens 3, backlight 1, light source controller,
IO control cards, industrial personal computer and display, industrial camera 4 and camera lens 3 are connected with industrial personal computer, for gather respective bolt 2 and/
Or the respective image of gasket；Backlight 1 is connected with light source controller, for bolt 2 and/or gasket polishing, protruding corresponding
Feature；IO control cards are connected with industrial personal computer, and for receiving detection bolt 2 and/or detection gasket signal, industrial personal computer is according to phase
Induction signal is detected bolt 2 and/or gasket, and the result of detection is sent by IO control cards.
Detecting system is loaded on industrial personal computer, and industrial personal computer is in communication with each other with other each several parts in detecting system, according to phase
I/O port input signal is answered, control industrial camera 4 gathers corresponding picture, and image is detected, and is exported finally by I/O port
Pass/NG signals.
After carrying out teaching by the bolt 2 to different production types and requirement, when use, can be according to the result pair of teaching
Bolt 2 is detected, and the result of teaching can automatically save, and user is facilitated to be called at any time, the result and dependency number of detection
According to local can be automatically saved in, finally data interaction is carried out with client.
As seen in figs. 5-6, the present invention passes through the detection module of core and camera model, communication module, data module, user
The vision inspection process of spiral shell inspection 2 can be achieved in interactive module combination.Wherein, user interactive module and communication module correspond to presentation layer,
Data module corresponds to data Layer, and detection module corresponds to logical layer, and camera model is mainly used for driving camera and captures image.
Detection process specifically includes following steps：
1st, when detecting system is detected for the first time, the step of including preparation (subsequent process can directly invoke),
It specifically includes：
(1) open system.
(2) connect industrial camera 4 and open backlight 1.
(3) camera parameter of industrial camera 4 is set, adjusts the brightness of backlight 1, it is ensured that communicates normal and industrial camera 4
Collect the apparent picture of contrast.Camera parameter includes the exposure of the regional extent, camera of bolt 2 and/or gasket in the picture
Between light time and gain, Gaussian smoothing parameter, minimum edge amplitude and error parameter, the area of bolt 2 and/or gasket in the picture
Domain scope is determined by the top left co-ordinate of interesting image regions, length and width.
Top left co-ordinate, length and the width of interesting image regions (ROI) define the substantially area of bolt 2 in the picture
Domain reduces detection range；Time for exposure and gain by adjusting machine obtain the image with fine definition and contrast；It is high
This smoothing parameter, minimum edge amplitude are used for smooth and extract the marginal point of bolt 2 and gasket；Error parameter detects for setting
Permissible error, including height error on bolt 2 and step 5, the diameter and thickness error of spring washer Upper gasket, spring washer lower gasket
Diameter and thickness error.
(4) IO control cards are connected, the relevant parameter of IO control cards is set.
2nd, grassroot project is sequentially placed bolt 2 and/or corresponding gasket according to prompting, and user shows bolt 2 and gasket
Teaching is practised, and is preserved related data and engineering, is directly invoked in detection of the subsequent production with a product.
3rd, according to the production requirement of bolt 2 and/or gasket, corresponding project is called, proceeds by detection.
When the 4th, detecting, detecting system detects bolt 2 and/or gasket respectively by the input signal of IO control cards, aobvious in real time
Testing result is shown and passes through IO control cards and sends corresponding signal to notify user, user is looked by user interface
It sees.
The detection process of detecting system comprises the following steps：
1) state that system monitoring IO cards accordingly input, if receiving bolt 2 detects signal, system calls camera model to grab
Take bolt picture.
2) according to the position of teaching, corresponding edge in being extracted in bolt picture, if can not extract side in corresponding region
Edge then prompts bolt type mistake；If after successfully extracting edge, will 2/ step 5 of bolt be calculated according to the position at edge
Highly, with reference to the height of teaching and the error of setting, judge whether bolt 2 correct, send out according to testing result pass or
NgSignal.In the detection process of detecting system, step is specifically included to the edge extracting of bolt 2 and/or gasket：
A. using following formula, denoising is carried out by Gaussian filter before edge is extracted：
Wherein σ is Gaussian smoothing parameter；
B. to obtaining relevant marginal position after smooth rear function derivation, the derivative of Gaussian filter is
To function it is smooth after derivation result with first identical to the result that and function convolution obtains again after smoothing filter derivation,
I.e.：(f*h) `=f*h`,
The output of boundary filter is expressed as ei=| f*h |i；
C. non-maxima suppression is finally carried out to the marginal position extracted, the marginal point of final output meets：(ei＞
ei-1)∩(ei＞ ei+1)∩(ei>=t), wherein t is minimum edge amplitude.
3) as Figure 2-3, if receiving gasket detection signal, system calls camera model crawl gasket picture.Specifically
Including：
If 3-1) there was only plain cushion 7 in detection process, according to the position of plain cushion in teaching 7, it is 1 picture to generate a height
The measurement frame of element measures the diameter in the region, and the cycle detection region can obtain the thickness of gasket, with reference to teaching thickness and set
The error put may determine that whether gasket is correct；
If 3-2) in detection process there are spring washer 6, first judge whether corresponding region is spring washer 6, the concrete foundation region
The edge for 6 the right and left of gap and spring washer whether occur judges with the presence or absence of certain difference in height, if there are spring washer 6
According to the gasket situation of 6 up/down of spring washer in teaching, continue to detect corresponding gasket, otherwise prompting mistake and pass through IO control cards and send out
Send NG signals；
3-3) if there are gaskets on spring washer 6 in detection process (to detect the plain cushion 7 and bullet of 6 top of spring washer respectively in Fig. 4
The plain cushion 7 of the lower section of pad 6), when detection, first extracts the edge of gasket the right and left, calculates the inclination angle of gasket, and according to the angle
Degree carries out affine transformation to measurement frame, finally according to 3-1) it is detected.
5th, data Layer preserves detection data, and user is checked at any time according to the date.User carry out the later stage transfer,
The process checked specifically includes：
A. data real-time display during producing on user interface, including：Pass/NG signals, passing number,
Production sum and qualification rate；
B. user inquires about specific creation data according to the specific date by user interface；
C. (can be configured in the case of system default by user interface), data Layer automatically saves inspection in process of production
Mapping piece and daily record, each item data are stored according to the date of manufacture in corresponding file automatically, are recorded in journal file useful
Family is to the operating process of detecting system, the connection status of relevant device (industrial camera 4, backlight 1, IO control cards)；
D. logical layer carries out data processing according to date data input by user and product data, transfers each in file
Item data, and it is shown to user interface.
The method integration Many Detection of the present invention is used for detecting the placement of 2 type of bolt, gasket-type and gasket
Sequentially.Detecting system user interface image-centric, detecting system can detect bolt 2 automatically according to varying input signal
Or gasket, and corresponding pass or NG signals are inputted according to result, so as to simplify the complexity of system, reduce operating personnel
Technology requirement.The detection method has been obtained for being widely applied in auto-parts industry at present.
It should be appreciated that for those of ordinary skills, can be improved or converted according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Illustrative description has been carried out to patent of the present invention above in conjunction with attached drawing, it is clear that the realization of patent of the present invention and from
The limitation of aforesaid way, if employ patent of the present invention methodology and technical solution carry out various improvement or without
It improves and the design of patent of the present invention and technical solution is directly applied into other occasions, within the scope of the present invention.
Claims (8)
1. a kind of bolt visible detection method, which is characterized in that detecting system is by presentation layer, logical layer and data Layer to spiral shell
Bolt and/or gasket carry out vision-based detection, wherein, presentation layer provides the interactive interface with user by user interface；Logic
Layer controls the service logic of the detecting system, is the alternation of bed of the presentation layer and the data Layer, effectively organizes the number
According to the various data of layer；The data Layer includes the parameters of the detecting system and the data result of various detections, and leads to
Effective management to data result is crossed, data supporting is provided for the detecting system；Specific detection process comprises the following steps：
Step 1, grassroot project are sequentially placed bolt and/or corresponding gasket according to prompting, related data and engineering are preserved, rear
Continue and directly invoked when producing the detection with a product；
Step 2, the production requirement according to the bolt and/or the gasket, call corresponding project, proceed by detection；
When step 3, detection, the detecting system detects the bolt and/or described respectively by the input signal of IO control cards
Gasket, real-time display, which goes out testing result and sends corresponding signal by the IO control cards, notifies user, and user passes through described
User interface is checked；
Step 4, the data Layer preserve detection data, and user is checked at any time according to the date.
2. bolt visible detection method according to claim 1, which is characterized in that the Hardware Subdivision subpackage of the detecting system
Include industrial camera, camera lens, backlight, light source controller, IO control cards, industrial personal computer and display, the industrial camera and mirror
Head is connected with industrial personal computer, for gathering the respective image of respective bolt and/or gasket；The backlight and and light source controller
It is connected, for bolt and/or gasket polishing, prominent individual features；The IO control cards are connected with industrial personal computer, are used for
It receives detection bolt and/or detection gasket signal, industrial personal computer is detected bolt and/or gasket according to corresponding signal, and will
The result of detection is sent by IO control cards.
3. bolt visible detection method according to claim 2, which is characterized in that the detecting system is loaded into the work
On control machine, the industrial personal computer is in communication with each other with other each several parts in the detecting system, according to corresponding I/O port input signal, control
Industrial camera processed gathers corresponding picture, and image is detected, and pass/NG signals are exported finally by I/O port.
4. bolt visible detection method according to claim 1, which is characterized in that carried out for the first time in the detecting system
During detection, the step of further including preparation, specifically include：
（1）Open system；
（2）Connection industrial camera simultaneously opens backlight；
（3）The camera parameter of the industrial camera is set, adjusts the brightness of the backlight, it is ensured that communicates normal and described industry
Camera collects the apparent picture of contrast；
（4）IO control cards are connected, the relevant parameter of IO control cards is set.
5. bolt visible detection method according to claim 4, which is characterized in that in the step（3）In, the camera
Parameter includes the bolt and/or the gasket regional extent in the picture, the time for exposure of camera and gain, Gaussian smoothing
Parameter, minimum edge amplitude and error parameter.
6. bolt visible detection method according to claim 1, which is characterized in that in the step 1, user is to described
Bolt and the gasket carry out learning from instruction.
7. bolt visible detection method according to claim 1, which is characterized in that in the step 3, the detection system
The detection process of system comprises the following steps：
The state that step 31, system monitoring IO cards accordingly input, if receiving bolt detection signal, system calls camera model to grab
Take bolt picture；
Step 32, the position according to teaching, corresponding edge in being extracted in bolt picture, if can not extract side in corresponding region
Edge then prompts bolt type mistake；If after successfully extracting edge, the height of bolt/step will be calculated according to the position at edge
Degree, with reference to the height of teaching and the error of setting, judges whether bolt is correct, sends out pass or Ng letters according to testing result
Number；
If step 33 receives gasket detection signal, system calls camera model crawl gasket picture.
8. bolt visible detection method according to claim 1, which is characterized in that in the step 4, after user carries out
The process that phase transfers, checks specifically includes：
A. data real-time display during producing on the user interface, including：Pass/NG signals, passing number,
Production sum and qualification rate；
B. user inquires about specific creation data according to the specific date by the user interface；
C. the data Layer automatically saves detection picture in process of production and daily record, each item data are deposited automatically according to the date of manufacture
It is put into corresponding file, record has user to the operating process of the detecting system, the company of relevant device in journal file
Connect state；
D. the logical layer carries out data processing according to date data input by user and product data, transfers in the file
Each item data, and be shown to the user interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330338.3A CN108050930A (en) | 2017-12-13 | 2017-12-13 | A kind of bolt visible detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711330338.3A CN108050930A (en) | 2017-12-13 | 2017-12-13 | A kind of bolt visible detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108050930A true CN108050930A (en) | 2018-05-18 |
Family
ID=62132540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711330338.3A Pending CN108050930A (en) | 2017-12-13 | 2017-12-13 | A kind of bolt visible detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108050930A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109128794A (en) * | 2018-11-01 | 2019-01-04 | 苏州思驼众自动化技术有限公司 | It is a kind of to semi-automatic production and assembly screw technique guidance and fail-safe system |
| CN110294381A (en) * | 2019-08-08 | 2019-10-01 | 湖北江汉建筑工程机械有限公司 | A kind of elevator guide bracket is bolted reliability detecting device and its method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101149254A (en) * | 2007-11-12 | 2008-03-26 | 北京航空航天大学 | High accuracy vision detection system |
| CN102116610A (en) * | 2010-11-29 | 2011-07-06 | 科达斯特恩(常州)汽车塑件系统有限公司 | Automatic on-line detection method and device for size of automobile parts based on machine vision |
| CN103499296A (en) * | 2013-10-21 | 2014-01-08 | 东华大学 | Batch part automatic detection system and method based on machine vision |
| CN203704867U (en) * | 2014-02-19 | 2014-07-09 | 南京蒙渡电子科技有限公司 | Special machine vision system for industrial measurement |
| CN104296665A (en) * | 2014-09-28 | 2015-01-21 | 苏州镭络视觉技术有限公司 | Workpiece size measuring method and system based on machine vision |
| CN105115425A (en) * | 2015-08-31 | 2015-12-02 | 江苏大学 | Vision-based precision measuring instrument of small-size part |
| CN106598622A (en) * | 2016-12-22 | 2017-04-26 | 陕西维视数字图像技术有限公司 | Smart vision inspection platform |
| CN106705843A (en) * | 2016-12-30 | 2017-05-24 | 芜湖哈特机器人产业技术研究院有限公司 | Bolt sorting system and sorting method thereof |
-
2017
- 2017-12-13 CN CN201711330338.3A patent/CN108050930A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101149254A (en) * | 2007-11-12 | 2008-03-26 | 北京航空航天大学 | High accuracy vision detection system |
| CN102116610A (en) * | 2010-11-29 | 2011-07-06 | 科达斯特恩(常州)汽车塑件系统有限公司 | Automatic on-line detection method and device for size of automobile parts based on machine vision |
| CN103499296A (en) * | 2013-10-21 | 2014-01-08 | 东华大学 | Batch part automatic detection system and method based on machine vision |
| CN203704867U (en) * | 2014-02-19 | 2014-07-09 | 南京蒙渡电子科技有限公司 | Special machine vision system for industrial measurement |
| CN104296665A (en) * | 2014-09-28 | 2015-01-21 | 苏州镭络视觉技术有限公司 | Workpiece size measuring method and system based on machine vision |
| CN105115425A (en) * | 2015-08-31 | 2015-12-02 | 江苏大学 | Vision-based precision measuring instrument of small-size part |
| CN106598622A (en) * | 2016-12-22 | 2017-04-26 | 陕西维视数字图像技术有限公司 | Smart vision inspection platform |
| CN106705843A (en) * | 2016-12-30 | 2017-05-24 | 芜湖哈特机器人产业技术研究院有限公司 | Bolt sorting system and sorting method thereof |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109128794A (en) * | 2018-11-01 | 2019-01-04 | 苏州思驼众自动化技术有限公司 | It is a kind of to semi-automatic production and assembly screw technique guidance and fail-safe system |
| CN110294381A (en) * | 2019-08-08 | 2019-10-01 | 湖北江汉建筑工程机械有限公司 | A kind of elevator guide bracket is bolted reliability detecting device and its method |
| CN110294381B (en) * | 2019-08-08 | 2024-03-19 | 湖北江汉建筑工程机械有限公司 | Device and method for detecting reliability of bolted connection of guide rail frame of elevator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913415B (en) | A kind of image sub-pixel edge extracting method with extensive adaptability | |
| CN105453153B (en) | Traffic lights detects | |
| CN108062542B (en) | Method for detecting shielded human face | |
| CN107220649A (en) | A kind of plain color cloth defects detection and sorting technique | |
| CN102297867A (en) | Detection system for assembly quality of wiring harness | |
| CN106226325A (en) | A kind of seat surface defect detecting system based on machine vision and method thereof | |
| DE102007055912A1 (en) | Eyelid detection device, eyelid detection method and associated program | |
| CN106682665B (en) | Seven-segment type digital display instrument number identification method based on computer vision | |
| CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
| Sakhare et al. | Spectral and spatial domain approach for fabric defect detection and classification | |
| CN108050930A (en) | A kind of bolt visible detection method | |
| CN106599890B (en) | digital instrument recognition algorithm for substation inspection robot | |
| CN110363742A (en) | A kind of notch of switch machine detection method based on CNN and image procossing | |
| KR20120019425A (en) | Image processing device, method, and program | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN108921003A (en) | Unmanned plane obstacle detection method based on convolutional neural networks and morphological image | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN110084246A (en) | A kind of yarn dyed fabric fault automatic identifying method | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN109615598A (en) | A kind of power transmission line recognition methods based on the free algorithm of edge mapping parameter | |
| CN109002774A (en) | A kind of fatigue monitoring device and method based on convolutional neural networks | |
| US8817125B2 (en) | Gesture recognition using chroma-keying | |
| CN111665199A (en) | Wire and cable color detection and identification method based on machine vision | |
| CN109636793A (en) | The detection system and its detection method of display | |
| CN107248151B (en) | Intelligent liquid crystal display detection method and system based on machine vision |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180518 |
|
| RJ01 | Rejection of invention patent application after publication |