CN104122265B - Panel beating screw hole screw thread disappearance inspection method and system thereof - Google Patents

Panel beating screw hole screw thread disappearance inspection method and system thereof Download PDF

Info

Publication number
CN104122265B
CN104122265B CN201310154924.2A CN201310154924A CN104122265B CN 104122265 B CN104122265 B CN 104122265B CN 201310154924 A CN201310154924 A CN 201310154924A CN 104122265 B CN104122265 B CN 104122265B
Authority
CN
China
Prior art keywords
workpiece
screw hole
image
screw thread
vibrating disk
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.)
Expired - Fee Related
Application number
CN201310154924.2A
Other languages
Chinese (zh)
Other versions
CN104122265A (en
Inventor
王忠勇
马超
宋豫全
邓计才
高向川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou University
Original Assignee
Zhengzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhengzhou University filed Critical Zhengzhou University
Priority to CN201310154924.2A priority Critical patent/CN104122265B/en
Publication of CN104122265A publication Critical patent/CN104122265A/en
Application granted granted Critical
Publication of CN104122265B publication Critical patent/CN104122265B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a kind of method and system thereof checking whether metal plate punching part screw hole screw thread exist, the present invention comprises the following steps: (1) puts the workpiece in vibrating disk, and vibrating disk starts vibration, and conveyer belt starts running simultaneously;The discharging opening started from vibrating disk when workpiece to be detected is sent, and workpiece is transported to detect region by conveyer belt;(2) screw hole diameter checks that camera and the reflective amount of screw hole check that workpiece is taken pictures by camera simultaneously, and is respectively sent in each Video Decoder by the image of gained of taking pictures, to sending into picture processing chip after picture decoding;(3) image received processed and analyze, extracting the feature to be compared of workpiece for measurement, and compare with the feature of normal workpiece template;(4) if comparison result is normal, the most qualified, if comparison result is abnormal, then stops and reporting to the police.The present invention can judge whether metal plate punching part screw hole screw thread exists fast and accurately, easy to operate, cheap, False Rate is low.

Description

Panel beating screw hole screw thread disappearance inspection method and system thereof
Technical field
The present invention relates to a kind of method and system thereof checking whether metal plate punching part screw hole screw thread exist, specifically one Plant Embedded Image Processing System with presence or absence of tapping hole screw thread on judgement metal plate punching part based on computer vision technique.
Background technology
Metal plate punching part has feature frivolous, uniform, that intensity is high and precision is high, processing cost is low, specification is consistent, extensively The general every field being applied in productive life, such as instrument and meter, household electrical appliances, office machinery, auto parts machinery, ornament materials Deng.Assembling to metal plate punching part, more uses the screw hole connected mode of punching tapping on stamping parts, this mode The screw thread processed is the most tiny, it is judged that it is extremely difficult whether it processes.Traditional inspection method is to utilize artificial meat Eye is observed, and the most not only working strength is big, and as easy as rolling off a log appearance erroneous judgement.Occur in recent years utilizing visual system, by measuring The number of screw hole area light reflection amount is as the foundation judging whether screw hole exists, and the reflective amount in threaded hole is many, non-threaded The reflective amount in hole few.Set a threshold value, more than the judgement of threshold value for there being screw thread, be non-threaded less than the judgement of threshold value.So Mode there are two shortcomings: the mode False Rate one, utilizing merely reflective amount is the highest, because the reflective amount in indivedual threaded holes Seldom, and the most reflective amount in indivedual threadless holes is a lot;Two, relatively costly.Visual system often has a lot of function, and uses Family is necessary for using a function therein, i.e. adds up the function of reflective amount, and is that whole system is checked.
Summary of the invention
The technical problem to be solved in the present invention is to judge whether metal plate punching part screw hole screw thread processes more at present Difficulty, workload is big, False Rate is high, relatively costly, it is provided that a kind of cheap, easy to operate, panel beating screw that False Rate is low Hole screw thread disappearance inspection method and system thereof.
For achieving the above object, the present invention uses following technical proposals: a kind of panel beating screw hole screw thread lacks inspection method, It comprises the following steps: 1. put into workpiece to be checked in the hopper of vibrating disk, presses power on button, and vibrating disk starts to shake Dynamic, conveyer belt starts running simultaneously;The discharging opening started from vibrating disk when workpiece to be detected is sent, and workpiece is transported to by conveyer belt Detection region, at this moment, conveyer belt operation suspension;2., after workpiece for measurement enters detection region, screw hole diameter checks camera and spiral shell The reflective amount in silk hole checks that workpiece is taken pictures by camera simultaneously, and the image of gained of taking pictures is respectively sent to corresponding video solution In code device, each Video Decoder is sent in picture processing chip after being decoded image;3. picture processing chip is to reception To image process and analyze, extract the feature to be compared of workpiece for measurement, and by feature to be compared and normal workpiece template Feature compare;If 4. comparison result is normal, then workpiece is qualified, and equipment works on, if comparison result occurs abnormal, then The equipment that sends stops signal and reports to the police.
The template of described normal workpiece obtains in the following manner: use classification mode method to know normal workpiece Not, described classification mode is neural network classifier.
The image received is processed and analyzes by described picture processing chip, and wherein the process to image includes: Image noise reduction process, image histogram equilibrium or image sharpening in any one.
Described image noise reduction processes and refers to: remove salt-pepper noise kind by the method for medium filtering or average value filtering Picture noise pollutes;Image sharpening uses mask convolution and frequency domain filtering method.
A kind of panel beating screw hole screw thread disappearance inspection system, it includes the screw hole diameter taking pictures workpiece to be detected Check that camera and the reflective amount of screw hole check that camera, described screw hole diameter check that camera and the reflective amount of screw hole check camera The picture of shooting is respectively fed to the Video Decoder in master control caseAnd Video DecoderIn, Video DecoderAnd video DecoderBeing connected with picture processing chip, picture processing chip connects MCU, MCU and memorizer, man-machine interface, proximity switch Sensor, vibrating disk are connected with conveyer belt.
Described each Video Decoder is all connected with Logic control module, crystal oscillator, power supply and corresponding inspection camera.
Described memorizer uses FLASH and SRAM, SRAM to be that picture processing chip is shared with MCU.
Described MCU connects the light source irradiating workpiece for measurement, and light source is at least a LED.
Described MCU connects alarm, and alarm is trichroism audible-visual annunciator.
Use the present invention of technique scheme, it is possible to judge whether metal plate punching part screw hole screw thread is deposited fast and accurately , easy to operate, cheap, False Rate is low.
Accompanying drawing explanation
Fig. 1 is the device structure schematic diagram of the present invention.
Fig. 2 is that master control case built-in system of the present invention constitutes schematic diagram.
Fig. 3 is main program flow chart of the present invention.
Fig. 4 is that the present invention checks algorithm flow chart.
Fig. 5 is that the present invention uses flow chart.
Detailed description of the invention
The present invention is a kind of panel beating screw hole screw thread disappearance inspection method, and it comprises the following steps: 1. by work to be checked Part is put in the hopper of vibrating disk, presses power on button, and vibrating disk starts vibration, and conveyer belt starts running simultaneously;When to be detected The discharging opening that workpiece starts from vibrating disk is sent, and workpiece is transported to detect region, at this moment, conveyer belt operation suspension by conveyer belt; 2., after workpiece for measurement enters detection region, screw hole diameter checks that camera and the reflective amount of screw hole check that workpiece is entered by camera simultaneously Row is taken pictures, and is respectively sent in corresponding Video Decoder by the image of gained of taking pictures, and image is entered by each Video Decoder Send in picture processing chip after row decoding;3. the image received is processed and analyzes by picture processing chip, and extraction is treated Survey the feature to be compared of workpiece, and the feature of feature to be compared with normal workpiece template is compared;If 4. comparison result is just Often, then workpiece is qualified, and equipment works on, if comparison result occurs abnormal, then the equipment that sends stops signal and reports to the police.
The template of described normal workpiece obtains in the following manner: use classification mode method to know normal workpiece Not, described classification mode is neural network classifier.
The image received is processed and analyzes by described picture processing chip, and wherein the process to image includes: Image noise reduction process, image histogram equilibrium or image sharpening in any one.
Described image noise reduction processes and refers to: remove salt-pepper noise kind by the method for medium filtering or average value filtering Picture noise pollutes;Image sharpening uses mask convolution and frequency domain filtering method.
As depicted in figs. 1 and 2, the present invention includes a kind of panel beating screw hole screw thread disappearance inspection system, and it includes to be checked Survey screw hole diameter inspection camera 3 and screw hole reflective amount inspection camera 4, described screw hole diameter that workpiece 11 carries out taking pictures Check that camera 3 and the reflective amount of screw hole check that the picture of shooting is respectively fed to the Video Decoder in master control case 2 by camera 4 And Video DecoderIn, Video DecoderAnd Video DecoderBeing connected with picture processing chip, picture processing chip connects MCU, MCU are connected with memorizer, man-machine interface, approach switch sensor, vibrating disk and conveyer belt.
Described each Video Decoder is all connected with Logic control module, crystal oscillator, power supply and corresponding inspection camera.
Described memorizer uses FLASH and SRAM, SRAM to be that picture processing chip is shared with MCU.
Described MCU connects the light source 6 irradiating workpiece for measurement, a light source 6 at least LED, it is provided that camera needs Illuminating ray, it usually needs use multiple LED according to practical situation.
It is trichroism audible-visual annunciator that described MCU connection has alarm 5, alarm 5.
Screw hole diameter checks that camera 3 is that the diameter to the screwed hole arriving the workpiece to be detected 11 detecting region 10 is carried out Check.Its process is to arrive the picture of detection zone territory workpiece from the shooting of the surface of vertical workpiece, and picture is sent to master control Case 2 processed does further image procossing.
The reflective amount of screw hole checks that camera 4 is the reflective amount of the screwed hole to the workpiece to be detected 11 arriving detection region 10 Check.Its process is the picture photographing from workpiece side and reaching detection region workpiece, and picture is sent to master control case 2 Do further image procossing.
Vibrating disk 7 is a kind of automatically workpiece 11 to be detected to be transported to the device on conveyer belt 9, need to be according to different types of Workpiece specific customization.Its operation principle is: have individual impulse mgnet below vibrating disk hopper, and hopper can be made to make vertical direction Vibration, is driven hopper to rock vibration around its vertical axis by the spring leaf tilted.Workpiece in hopper, due to by this vibration Rise along helical orbit.Through screening or the attitudes vibration of a series of tracks during rising, workpiece can be on request In unified state automatically into conveyer belt 9.
Conveyer belt 9 is driven it to operate by motor 8.When a workpiece enters into detection position, stepping electricity Machine 8 suspends rotation, and now conveyer belt is static, completes the detection of workpiece screw hole.When workpiece screw hole is qualified, motor continues Rotate, make next workpiece enter detection region and continue detection.If workpiece is defective, motor does not continues to rotate, simultaneously Trichroism audible-visual annunciator is become the redness of abnormality by the green of normal condition, and sends chimes of doom.
Below in conjunction with Fig. 3, Fig. 4, Fig. 5, the present invention is described further:
As it is shown in figure 5, need before Shi Yonging equipment first carries out overall inspection, the scope of examination includes: watch power line and letter Number line the most correctly connects, and whether especially power line has broken skin, checks whether are the motor of vibrating disk 7 and conveyer belt 9 and circuit Have and burn part.Whether inspection equipment all parts and screw have loosening phenomenon.If all gone well, device power supply (DPS) can be opened, Enter user setup pattern.
Being put into detection region by a sample workpiece to be checked, regulation light source 6, screw hole diameter check that camera 3 and screw hole are anti- Light quantity checks the position of camera 4, makes the sample workpiece of display on monitor 1 the most clear.
Under user setup pattern, the classification mode used due to the present invention is neural network classifier, belongs to and has supervision Classification, the to the effect that training grader that therefore user need to be arranged, concrete operations are: prepare substantial amounts of qualified workpiece and do not conform to Lattice workpiece, is placed into detection region 10 one by one by workpiece.After placing qualified workpiece, treat that system extracts screw hole diameter and reflective amount After information, it is qualified to be set to by work status, after placing defective workpiece, treats that system extracts screw hole diameter and anti-light amount information After, work status is set to defective, completes the setting of criterion.
Being put into workpiece to be checked in the hopper of vibrating disk 7, press power on button, vibrating disk 7 starts vibration, passes simultaneously Band 9 is sent to start running.When workpiece to be detected starts to send from the discharging opening of vibrating disk 7, and workpiece is transported to detection zone by conveyer belt 9 Territory 10, at this moment, conveyer belt 9 operation suspension, screw hole diameter checks that camera 3 and the reflective amount of screw hole check that camera 4 shoots simultaneously Workpiece, and two pictures obtained are sent to master control case 2.
Fig. 4 is the detection algorithm flow chart of two pictures of the master control case 2 same workpiece to obtaining, and becomes at master control case After merit reads two pictures, two pictures obtained are processed, it is therefore an objective to for preferably carrying out subsequent characteristics extraction and knowledge Do not lay the first stone.Process to image specifically includes: image noise reduction processes, and removes by the method such as medium filtering, average value filtering The picture noise of the kinds such as salt-pepper noise pollutes;Image histogram equalizes, and makes original image rectangular histogram be transformed to have uniform density The rectangular histogram of distribution, to increase the global contrast of acquired image;Image sharpening, by mask convolution and the method for frequency domain filtering, Strengthen edge and the part of Gray Level Jump of image, make image be apparent from.
After process terminates, extract screw hole diameter and check screw hole diameter data and the spiral shell of workpiece in camera 3 acquired image The reflective amount in silk hole checks the screw hole reflective amount data of workpiece in camera 4 acquired image, and by both information fusion to Individual data structure, i.e. differentiates in array.
Utilize the nearest neighbor classifier trained in the user mode, to differentiating that array carries out pattern classification, obtain work to be checked The judgement of part acceptance or rejection.
When workpiece is certified products, again make conveyer belt operate, allow next workpiece enter detection region, repeat the above steps Carry out the detection of a new round.When workpiece is defective work, conveyer belt does not continues to run, and suspends vibrating disk, the most trichroism sound Light crossing-signal flashes the redlight, and sends chimes of doom.Until after pressing reset key, detection just proceeds.

Claims (4)

1. a panel beating screw hole screw thread disappearance inspection method, it is characterised in that: it comprises the following steps: 1. by work to be checked Part is put in the hopper of vibrating disk, presses power on button, and vibrating disk starts vibration, and conveyer belt starts running simultaneously;When to be detected The discharging opening that workpiece starts from vibrating disk is sent, and workpiece is transported to detect region, at this moment, conveyer belt operation suspension by conveyer belt; 2., after workpiece for measurement enters detection region, screw hole diameter checks that camera and the reflective amount of screw hole check that workpiece is entered by camera simultaneously Row is taken pictures, and is respectively sent in corresponding Video Decoder by the image of gained of taking pictures, and image is entered by each Video Decoder Send in picture processing chip after row decoding;3. the image received is processed and analyzes by picture processing chip, and extraction is treated Survey the feature to be compared of workpiece, and the feature of feature to be compared with normal workpiece template is compared;If 4. comparison result is just Often, then workpiece is qualified, and equipment works on, if comparison result occurs abnormal, then the equipment that sends stops signal and reports to the police.
Panel beating screw hole screw thread the most according to claim 1 disappearance inspection method, it is characterised in that: described normal workpiece Template obtain in the following manner: using classification mode method to be identified normal workpiece, described classification mode be refreshing Through network classifier.
Panel beating screw hole screw thread the most according to claim 1 disappearance inspection method, it is characterised in that: described image procossing The image received is processed and analyzes by chip, and wherein the process to image includes: image noise reduction processes, image histogram Equilibrium or image sharpening in any one.
Panel beating screw hole screw thread the most according to claim 3 disappearance inspection method, it is characterised in that: described image noise reduction Process refers to: the picture noise removing salt-pepper noise kind by the method for medium filtering or average value filtering pollutes;Image sharpening Middle employing mask convolution and frequency domain filtering method.
CN201310154924.2A 2013-04-28 2013-04-28 Panel beating screw hole screw thread disappearance inspection method and system thereof Expired - Fee Related CN104122265B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310154924.2A CN104122265B (en) 2013-04-28 2013-04-28 Panel beating screw hole screw thread disappearance inspection method and system thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310154924.2A CN104122265B (en) 2013-04-28 2013-04-28 Panel beating screw hole screw thread disappearance inspection method and system thereof

Publications (2)

Publication Number Publication Date
CN104122265A CN104122265A (en) 2014-10-29
CN104122265B true CN104122265B (en) 2016-12-28

Family

ID=51767761

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310154924.2A Expired - Fee Related CN104122265B (en) 2013-04-28 2013-04-28 Panel beating screw hole screw thread disappearance inspection method and system thereof

Country Status (1)

Country Link
CN (1) CN104122265B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104990511A (en) * 2015-07-21 2015-10-21 苏州佳祺仕信息科技有限公司 Threaded hole structure quality detection method
CN105466336B (en) * 2015-12-25 2018-09-18 深圳格兰达智能装备股份有限公司 One kind being suitable for industrial metal plate vision testing machine and its detection method
CN105783730B (en) * 2016-03-01 2018-08-07 珠海格力电器股份有限公司 Detection method, device, system and the detection machine of screw
CN107741606B (en) * 2017-08-31 2019-02-22 江苏宜润智能装备产业创新研究院有限公司 A kind of plastics hot riveting assembling monitoring method and device
CN108593653A (en) * 2017-12-31 2018-09-28 芜湖哈特机器人产业技术研究院有限公司 A kind of screw classification of view-based access control model and damage detection device and method
CN109520553A (en) * 2018-11-14 2019-03-26 深圳市铭利达精密机械有限公司 A kind of threaded hole Laser scanning inspection device
CN110595745B (en) * 2019-04-26 2021-05-07 深圳市豪视智能科技有限公司 Detection method for abnormality of fixing screw of equipment and related product
CN110434678A (en) * 2019-07-25 2019-11-12 上海拓璞数控科技股份有限公司 Metal foil wall pieces thickness real-time detecting system and method
CN113319378A (en) * 2020-02-28 2021-08-31 高桥金属制品(苏州)有限公司 Full-automatic tapping and conveying method of integrated assembly line
CN111551552B (en) * 2020-05-18 2023-06-13 湘潭大学 Appearance quality detection method for round hole punching net
CN112845136A (en) * 2021-01-29 2021-05-28 珠海迪沃航空工程有限公司 Intelligent correction, detection and classification device and method for aircraft engine bolt
CN115575158A (en) * 2022-10-08 2023-01-06 江阴市浩盛电器线缆制造有限公司 Low-loss phase-stable coaxial cable layered structure layout judgment system and method

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203216863U (en) * 2013-04-28 2013-09-25 郑州大学 Inspection system for thread deficiency in sheet-metal screw holes

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7364043B2 (en) * 2003-12-30 2008-04-29 Zen Voce Manufacturing Pte Ltd Fastener inspection system
JP5017628B2 (en) * 2008-09-30 2012-09-05 株式会社ユタカ Side inspection device
CN101738165A (en) * 2008-11-14 2010-06-16 吴圣茂 Screw detecting device and method using same
CN201488952U (en) * 2009-07-09 2010-05-26 精湛机械有限公司 Detection device
JP5471477B2 (en) * 2010-01-15 2014-04-16 ウシオ電機株式会社 Thread inspection equipment
CN103328958B (en) * 2010-11-25 2015-10-14 (株)首尔金属 Component supply system and part checkout facility
CN202404036U (en) * 2011-11-25 2012-08-29 上海安字实业有限公司 Camera imaging detection device for fastener
CN102513819B (en) * 2011-12-21 2013-09-04 中国计量学院 Right angle type expansion bolt and screw automatic assembly device and defect detection method thereof
CN102840826B (en) * 2012-08-23 2014-12-03 华南理工大学 Accurate screw high-speed detection device capable of feeding materials through glass rotary plate

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203216863U (en) * 2013-04-28 2013-09-25 郑州大学 Inspection system for thread deficiency in sheet-metal screw holes

Also Published As

Publication number Publication date
CN104122265A (en) 2014-10-29

Similar Documents

Publication Publication Date Title
CN104122265B (en) Panel beating screw hole screw thread disappearance inspection method and system thereof
CN101696945B (en) On-line detection method of machine vision system to photovoltaic glass flaws
CN101509766B (en) On-line detecting method for spring end plane angle by machine vision system
CN104117876B (en) A kind of method and its equipment for checking cutting tool and whether breaking or wearing out
CN104441526B (en) Mould in-service monitoring protection system and method based on appearance profile coupling
CN112036755B (en) Supervision method and system for quality detection of building engineering
CN101807061B (en) Vision detection control system and method for integrated circuit tendon-cut system
CN205538710U (en) Inductance quality automatic check out system based on machine vision
CN204564599U (en) A kind of glass tube outward appearance automatic detection system
CN101726265A (en) Online detection method of parallelism of spring by machine vision system
CN110146520A (en) A kind of detection device and its detection method of printed wiring board
CN101696877A (en) On-line detection method of machine vision system to spring verticality
CN203390656U (en) Device for examining if cutting tool is ruptured or worn
CN102303018B (en) Method for automatically detecting burrs of injector steel needles by using machine vision system
CN203216863U (en) Inspection system for thread deficiency in sheet-metal screw holes
CN108288274A (en) Mold detection method, device and electronic equipment
CN208000606U (en) Magnetic shoe surface microdefect vision inspection apparatus
CN108776966A (en) A kind of method and system of magnet appearance defect detection
CN109870463A (en) A kind of electronic chip fault detection means
CN103616386A (en) Engineering machinery as well as tool damage detection system and method thereof
CN102305603B (en) Method for automatically detecting inclination of steel needle of injector by machine vision system
CN103453840B (en) The automatic testing method of lock core precision of cylinder lock
Lin et al. Defect detection system for optical element surface based on machine vision
CN203772754U (en) Equipment for detecting true or false appearance of cigarette
CN102495077A (en) Automatic detecting method of machine vision system for detecting flaws of infusion bottle

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20161228

Termination date: 20170428