CN106645174A - Automatic online visual apparent-defect inspection system for general purpose engine - Google Patents

Automatic online visual apparent-defect inspection system for general purpose engine Download PDF

Info

Publication number
CN106645174A
CN106645174A CN201611235626.6A CN201611235626A CN106645174A CN 106645174 A CN106645174 A CN 106645174A CN 201611235626 A CN201611235626 A CN 201611235626A CN 106645174 A CN106645174 A CN 106645174A
Authority
CN
China
Prior art keywords
machine engine
logical machine
camera arrangement
automatic online
algorithm
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
Application number
CN201611235626.6A
Other languages
Chinese (zh)
Inventor
李志远
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.)
Chongqing Fivision Technology Co Ltd
Original Assignee
Chongqing Fivision Technology Co Ltd
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 Chongqing Fivision Technology Co Ltd filed Critical Chongqing Fivision Technology Co Ltd
Priority to CN201611235626.6A priority Critical patent/CN106645174A/en
Publication of CN106645174A publication Critical patent/CN106645174A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Abstract

The invention discloses an automatic online visual apparent-defect inspection system for a general purpose engine, relates to automobile spare parts and aims at solving the problem that an existing inspection device is poor in target edge contrast ratio and easily produces mistaken part identification. The automatic online visual apparent-defect inspection system comprises a general purpose engine operating track, a general purpose engine conveying bracket, a position sensor, a manipulator, a photographing device and a computer and comprises the following steps that S1, an illumination system capable of changing light intensity change is adopted; S2, motion photographing is conducted on corresponding detection points one by one; S3, the manipulator returns to an initial position for repeated motion. By the adoption of the technical scheme, a photographing structure is optimized, the target edge contrast ratio is remarkably improved, and a mistaken part identification phenomenon is eliminated.

Description

Logical machine engine open defect automatic online vision detection system
Technical field
The present invention relates to auto parts machinery, is logical machine engine open defect automatic online vision-based detection system specifically System.
Background technology
The manufacture of old China hand's machine engine has been occupied first of the whole world, but many still manual detections of manufacturing industry, and quality can not It is completely secured, customer complaint rate is very high.Therefore many large-scale Tong Ji manufacturers also appreciate this problem and are located, and have opened Begin the manual detection transition and upgrade of producing line to detect for automatic visual testing equipment, to improve efficiency, it is ensured that quality.Face Such reality, the logical machine open defect on-line detecting system for researching and developing complete set is imperative.
But above-mentioned technical proposal has the following disadvantages, easily there is part misrecognition existing in the poor contrast of object edge As.
The content of the invention
The present invention seeks to aimed to provide a kind of optimization take pictures structure, the contrast of object edge is significantly increased, and is eliminated Part misidentifies the logical machine engine open defect automatic online vision detection system of phenomenon.
To realize above-mentioned technical purpose, the technical solution used in the present invention is as follows:
Logical machine engine open defect automatic online vision detection system, including logical machine engine running track, logical machine Engine transport carrier, position sensor, manipulator, camera arrangement and computer, it is characterised in that:Comprise the following steps,
S1, is placed on logical machine engine running track by logical machine engine first, is sent using logical machine engine transport carrier Take pictures scope to camera arrangement, camera arrangement employing can change the illuminator of light intensity change, by changing light intensity change, ensure There is the good linearity in unsaturation region, picture quality is improved;
S2, logical machine engine running track is made up of three parts, is respectively feeding track, take pictures track and discharging track, When logical machine engine moves to feeding track rear end with the speed of 0.1m/s, position sensor detects logical machine engine in place Afterwards, the manipulator beside producing line is synchronized with the movement, and leads to machine engine and is moved with the speed of 0.02m/s in track of taking pictures, dress of taking pictures Put to move corresponding test point one by one according to the program for setting and take pictures, frequency acquisition is 3D frames/second, and within 8 seconds Necessarily complete all test points to take pictures and detect;Then camera arrangement is transformed into digitized signal picture signal, is sent to meter Calculation machine;
S3, if any bad, machine alarm, operating personnel process in time defective products, such as qualified, and computer can provide action letter Number, manipulator returns initial position, waits next engine to arrive.
Further limit, in S2, camera arrangement is comprised the following steps,
Step one, is arranged with Digital Image Processing algorithm and wants detection zone;
Step 2, carries out position correction, it is ensured that position is accurate to image with digital picture position correction algorithm;
Step 3, with connectivity algorithm, Binarization methods, object creation algorithm, edge object removes algorithm, edge object Insertion algorithm, contours extract algorithm, edge detection algorithm, weighted mean method, image denoising process, image sharpening, medium filtering, The original image for collecting is pre-processed with image processing techniques to improve picture quality, therefrom extracted spy interested The amount of levying;
Step 4, accurately finds out point position to be checked, mark mark, model, and direction is judged, application mode identification Technology to get characteristic quantity carries out taxonomic revision with the detection of completion system.
Further limit, the camera arrangement is arranged on a robotic arm, keeps being synchronized with the movement.
Further limit, the camera arrangement adopts CCD camera, and specific works mode is by the image Jing of subject Lens focus are crossed to CCD chip, CCD accumulates the electric charge of corresponding proportion according to the power of light, the electric charge of each pixel accumulation exists Under the control of video sequential, move outside pointwise, the filtering of Jing capure cards, enhanced processing form vision signal defeated after A/D conversions Go out.
Further limit, the test point that the camera arrangement is completed within 8 seconds there are 6 width figures, due to detect 6 detections Point, so needing to use six road video inputs on hardware, the image of different surfaces is gathered per road.
Further limit, the video input signals of the camera arrangement adopt pal mode, and the picture signal of equipment output is equal Can be used as the input source of the capure card.
Further limit, the video input window of the camera arrangement adopts the pal mode, input window full-size to be 768X576。
Further limit, the modular construction of the camera arrangement possesses alterability, readable and confirmatory.
Further limit, the camera arrangement is provided with stabilization frame.
Compared to existing technology, assembly experiment result shows the present invention, and using camera arrangement is arranged on manipulator, process is quick Accurately, camera arrangement employing can change the illuminator of light intensity change, and the contrast of object edge is notable after structure optimization of taking pictures Strengthen, eliminate part misrecognition phenomenon, meet the requirement of logical machine engine part high accuracy assembly automation.
Specific embodiment
In order that those skilled in the art may be better understood the present invention, with reference to embodiment to the technology of the present invention Scheme is further illustrated.
Embodiment one,
Logical machine engine open defect automatic online vision detection system, including logical machine engine running track, logical machine Engine transport carrier, position sensor, manipulator, camera arrangement and computer, comprise the following steps,
S1, is placed on logical machine engine running track by logical machine engine first, is sent using logical machine engine transport carrier Take pictures scope to camera arrangement, camera arrangement employing can change the illuminator of light intensity change, by changing light intensity change, ensure There is the good linearity in unsaturation region, picture quality is improved;
S2, logical machine engine running track is made up of three parts, is respectively feeding track, take pictures track and discharging track, When logical machine engine moves to feeding track rear end with the speed of 0.1m/s, position sensor detects logical machine engine in place Afterwards, the manipulator beside producing line is synchronized with the movement, and leads to machine engine and is moved with the speed of 0.02m/s in track of taking pictures, dress of taking pictures Put to move corresponding test point one by one according to the program for setting and take pictures, frequency acquisition is 3D frames/second, and within 8 seconds Necessarily complete all test points to take pictures and detect;Then camera arrangement is transformed into digitized signal picture signal, is sent to meter Calculation machine;
S3, if any bad, machine alarm, operating personnel process in time defective products, such as qualified, and computer can provide action letter Number, manipulator returns initial position, waits next engine to arrive.
In S2, camera arrangement is comprised the following steps,
Step one, is arranged with Digital Image Processing algorithm and wants detection zone;
Step 2, carries out position correction, it is ensured that position is accurate to image with digital picture position correction algorithm;
Step 3, with connectivity algorithm, Binarization methods, object creation algorithm, edge object removes algorithm, edge object Insertion algorithm, contours extract algorithm, edge detection algorithm, weighted mean method, image denoising process, image sharpening, medium filtering, The original image for collecting is pre-processed with image processing techniques to improve picture quality, therefrom extracted spy interested The amount of levying;
Step 4, accurately finds out point position to be checked, mark mark, model, and direction is judged, application mode identification Technology to get characteristic quantity carries out taxonomic revision with the detection of completion system.
The camera arrangement is arranged on a robotic arm, keeps being synchronized with the movement.
The camera arrangement adopts CCD camera, and specific works mode is through lens focus by the image of subject To in CCD chip, according to the electric charge of the strong and weak accumulation corresponding proportion of light, the electric charge of each pixel accumulation is in video sequential for CCD Under control, move outside pointwise, the filtering of Jing capure cards, enhanced processing form vision signal output after A/D conversions.
The test point that the camera arrangement is completed within 8 seconds has 6 width figures, due to detect 6 test points, so needing Six road video inputs are used on hardware, the image of different surfaces is gathered per road.
The video input signals of the camera arrangement adopt the picture signal of pal mode, equipment output can regard as this Frequency catches the input source of card.
The video input window of the camera arrangement adopts pal mode, and input window full-size is 768X 576.
The modular construction of the camera arrangement possesses alterability, readable and confirmatory.
Embodiment two,
Logical machine engine open defect automatic online vision detection system, including logical machine engine running track, logical machine Engine transport carrier, position sensor, manipulator, camera arrangement and computer, comprise the following steps,
S1, is placed on logical machine engine running track by logical machine engine first, is sent using logical machine engine transport carrier Take pictures scope to camera arrangement, camera arrangement employing can change the illuminator of light intensity change, by changing light intensity change, protect Barrier has the good linearity in unsaturation region, improves picture quality;
S2, logical machine engine running track is made up of three parts, is respectively feeding track, take pictures track and discharging track, When logical machine engine moves to feeding track rear end with the speed of 0.1m/s, position sensor detects logical machine engine in place Afterwards, the manipulator beside producing line is synchronized with the movement, and leads to machine engine and is moved with the speed of 0.02m/s in track of taking pictures, dress of taking pictures Put to move corresponding test point one by one according to the program for setting and take pictures, frequency acquisition is 3D frames/second, and within 8 seconds Necessarily complete all test points to take pictures and detect;Then camera arrangement is transformed into digitized signal picture signal, is sent to meter Calculation machine;
S3, if any bad, machine alarm, operating personnel process in time defective products, such as qualified, and computer can provide action letter Number, manipulator returns initial position, waits next engine to arrive.
In S2, camera arrangement is comprised the following steps,
Step one, is arranged with Digital Image Processing algorithm and wants detection zone;
Step 2, carries out position correction, it is ensured that position is accurate to image with digital picture position correction algorithm;
Step 3, with connectivity algorithm, Binarization methods, object creation algorithm, edge object removes algorithm, edge object Insertion algorithm, contours extract algorithm, edge detection algorithm, weighted mean method, image denoising process, image sharpening, medium filtering, The original image for collecting is pre-processed with image processing techniques to improve picture quality, therefrom extracted spy interested The amount of levying;
Step 4, accurately finds out point position to be checked, mark mark, model, and direction is judged, application mode identification Technology to get characteristic quantity carries out taxonomic revision with the detection of completion system.
The camera arrangement is arranged on a robotic arm, keeps being synchronized with the movement.
The camera arrangement adopts CCD camera, and specific works mode is through lens focus by the image of subject To in CCD chip, according to the electric charge of the strong and weak accumulation corresponding proportion of light, the electric charge of each pixel accumulation is in video sequential for CCD Under control, move outside pointwise, the filtering of Jing capure cards, enhanced processing form vision signal output after A/D conversions.
The test point that the camera arrangement is completed within 8 seconds has 6 width figures, due to detect 6 test points, so needing Six road video inputs are used on hardware, the image of different surfaces is gathered per road.
The video input signals of the camera arrangement adopt the picture signal of pal mode, equipment output can regard as this Frequency catches the input source of card.
The video input window of the camera arrangement adopts pal mode, and input window full-size is 768X 576.
The modular construction of the camera arrangement possesses alterability, readable and confirmatory.
The camera arrangement is provided with stabilization frame.
The difference of embodiment one and embodiment two is, in embodiment two, sets up stabilization frame, it is ensured that image clearly, reduces Error.By following table as can be seen that the recall rate of embodiment two is up to 90.2%~90.6%.
Open defect vision detection system result
The logical machine engine open defect automatic online vision detection system that the present invention is provided has been carried out in detail above Introduce.The explanation of specific embodiment is only intended to help and understands the method for the present invention and its core concept.It should be pointed out that for this For the those of ordinary skill of technical field, under the premise without departing from the principles of the invention, the present invention can also be carried out some Improve and modify, these are improved and modification is also fallen into the protection domain of the claims in the present invention.

Claims (9)

1. machine engine open defect automatic online vision detection system is led to, including logical machine engine running track, logical machine are sent out Motivation transport carrier, position sensor, manipulator, camera arrangement and computer, it is characterised in that:Comprise the following steps,
S1, is placed on logical machine engine running track by logical machine engine first, and using logical machine engine transport carrier bat is delivered to Take pictures scope according to device, camera arrangement employing can change the illuminator of light intensity change, by changing light intensity change, ensure non- There is the good linearity in zone of saturation, picture quality is improved;
S2, logical machine engine running track is made up of three parts, is respectively feeding track, take pictures track and discharging track, when logical Machine engine moves to feeding track rear end with the speed of 0.1m/s, after position sensor detects logical machine engine in place, Manipulator beside producing line is synchronized with the movement, and leads to machine engine and is moved with the speed of 0.02m/s in track of taking pictures, camera arrangement root Corresponding test point is moved one by one according to the program for setting is taken pictures, frequency acquisition is 3D frames/second, and it is certain within 8 seconds Complete all test points to take pictures and detect;Then camera arrangement is transformed into digitized signal picture signal, is sent to computer;
S3, if any bad, machine alarm, operating personnel process in time defective products, and such as qualified, computer can provide action signal, Manipulator returns initial position, waits next engine to arrive.
2. logical machine engine open defect automatic online vision detection system according to claim 1, it is characterised in that: In S2, camera arrangement is comprised the following steps,
Step one, is arranged with Digital Image Processing algorithm and wants detection zone;
Step 2, carries out position correction, it is ensured that position is accurate to image with digital picture position correction algorithm;
Step 3, with connectivity algorithm, Binarization methods, object creation algorithm, edge object removes algorithm, the insertion of edge object Algorithm, contours extract algorithm, edge detection algorithm, weighted mean method, image denoising process, image sharpening, medium filtering is used Image processing techniques is pre-processed to improve picture quality to the original image for collecting, and therefrom extracts feature interested Amount;
Step 4, accurately finds out point position to be checked, mark mark, model, and direction is judged, application mode technology of identification To get characteristic quantity carries out taxonomic revision with the detection of completion system.
3. logical machine engine open defect automatic online vision detection system according to claim 1 and 2, its feature exists In:The camera arrangement is arranged on a robotic arm, keeps being synchronized with the movement.
4. logical machine engine open defect automatic online vision detection system according to claim 3, it is characterised in that: The camera arrangement adopts CCD camera, and specific works mode is to CCD chip by the image of subject through lens focus On, CCD according to the electric charge of the strong and weak accumulation corresponding proportion of light, the electric charge of each pixel accumulation under the control of video sequential, by Point is outer to be moved, and the filtering of Jing capure cards, enhanced processing form vision signal output after A/D conversions.
5. logical machine engine open defect automatic online vision detection system according to claim 4, it is characterised in that: The test point that the camera arrangement is completed within 8 seconds has 6 width figures, due to detect 6 test points, so needing to be made on hardware With six road video inputs, the image of different surfaces is gathered per road.
6. logical machine engine open defect automatic online vision detection system according to claim 5, it is characterised in that: The video input signals of the camera arrangement adopt pal mode, and the picture signal of equipment output can be used as the capure card Input source.
7. logical machine engine open defect automatic online vision detection system according to claim 6, it is characterised in that: The video input window of the camera arrangement adopts pal mode, and input window full-size is 768X 576.
8. logical machine engine open defect automatic online vision detection system according to claim 7, it is characterised in that: The modular construction of the camera arrangement possesses alterability, readable and confirmatory.
9. logical machine engine open defect automatic online vision detection system according to claim 8, it is characterised in that: The camera arrangement is provided with stabilization frame.
CN201611235626.6A 2016-12-28 2016-12-28 Automatic online visual apparent-defect inspection system for general purpose engine Pending CN106645174A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611235626.6A CN106645174A (en) 2016-12-28 2016-12-28 Automatic online visual apparent-defect inspection system for general purpose engine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611235626.6A CN106645174A (en) 2016-12-28 2016-12-28 Automatic online visual apparent-defect inspection system for general purpose engine

Publications (1)

Publication Number Publication Date
CN106645174A true CN106645174A (en) 2017-05-10

Family

ID=58831880

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611235626.6A Pending CN106645174A (en) 2016-12-28 2016-12-28 Automatic online visual apparent-defect inspection system for general purpose engine

Country Status (1)

Country Link
CN (1) CN106645174A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108020555A (en) * 2017-11-23 2018-05-11 苏州艺力鼎丰智能技术有限公司 A kind of carbon fiber surface of automobile part prints volume defect intelligent detecting method
CN109164113A (en) * 2018-11-14 2019-01-08 武汉万安智能技术有限公司 A kind of handset port circuit board vision automatic checkout system and its detection method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101762460A (en) * 2009-07-02 2010-06-30 长沙楚天科技有限公司 Image synchronous tracking and collecting method and device for automatic lamp inspector
CN102226688A (en) * 2011-04-12 2011-10-26 翁瑜 Automatic detection system of engine piston ring
CN202196021U (en) * 2011-06-01 2012-04-18 苏州优纳科技有限公司 Automated optical inspection system
CN103512897A (en) * 2013-09-10 2014-01-15 上海东富龙科技股份有限公司 Baseless light inspection machine for freeze-dried vials
CN104698006A (en) * 2015-02-11 2015-06-10 湖南正中制药机械有限公司 Machine for automatically checking foreign bodies in soft bag preparation drugs
CN105651782A (en) * 2015-12-12 2016-06-08 机械科学研究总院先进制造技术研究中心 Engine cylinder cover defect automatic detection equipment based on machine vision

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101762460A (en) * 2009-07-02 2010-06-30 长沙楚天科技有限公司 Image synchronous tracking and collecting method and device for automatic lamp inspector
CN102226688A (en) * 2011-04-12 2011-10-26 翁瑜 Automatic detection system of engine piston ring
CN202196021U (en) * 2011-06-01 2012-04-18 苏州优纳科技有限公司 Automated optical inspection system
CN103512897A (en) * 2013-09-10 2014-01-15 上海东富龙科技股份有限公司 Baseless light inspection machine for freeze-dried vials
CN104698006A (en) * 2015-02-11 2015-06-10 湖南正中制药机械有限公司 Machine for automatically checking foreign bodies in soft bag preparation drugs
CN105651782A (en) * 2015-12-12 2016-06-08 机械科学研究总院先进制造技术研究中心 Engine cylinder cover defect automatic detection equipment based on machine vision

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108020555A (en) * 2017-11-23 2018-05-11 苏州艺力鼎丰智能技术有限公司 A kind of carbon fiber surface of automobile part prints volume defect intelligent detecting method
CN109164113A (en) * 2018-11-14 2019-01-08 武汉万安智能技术有限公司 A kind of handset port circuit board vision automatic checkout system and its detection method

Similar Documents

Publication Publication Date Title
CN104749184B (en) Automatic optical detection method and system
CN102621156B (en) Image-processing-based automatic micro part sorting system
CN104835166B (en) Liquid medicine bottle foreign matter detecting method based on machine vision detection platform
CN102020036A (en) Visual detection method for transparent paper defect of outer package of strip cigarette
CN101324427A (en) Device and method for automatically measuring greenery area
CN105388162A (en) Raw material silicon wafer surface scratch detection method based on machine vision
CN106501272A (en) Machine vision scolding tin position detecting system
CN104483320A (en) Digitized defect detection device and detection method of industrial denitration catalyst
CN106645174A (en) Automatic online visual apparent-defect inspection system for general purpose engine
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN106824806A (en) The detecting system and detection method of the low module plastic gear based on machine vision
CN108765416A (en) PCB surface defect inspection method and device based on fast geometric alignment
CN108344743A (en) One kind being based on machine vision drug blister package defect inspection method and system
CN108982512A (en) A kind of circuit board detecting system and method based on machine vision
CN106645189A (en) Automatic commutator appearance defect online visual detection system
CN102854195B (en) Method for detecting defect coordinates on color filter
CN106651802B (en) Machine vision scolding tin position finding and detection method
CN102879404B (en) System for automatically detecting medical capsule defects in industrial structure scene
CN104103069B (en) Image processing apparatus, image processing method and recording medium
CN206470210U (en) Machine vision scolding tin position detecting system
CN104677906A (en) Image information detecting method
CN106442536A (en) Machine-vision-based IC card automatic thread take-up device and method
CN104749801B (en) High Precision Automatic optical detecting method and system
CN105445286A (en) Method and device for detecting quality defects of mark on glass fuse tube products
CN110514668A (en) A kind of small-sized forging post treatment production line product defects detection device and detection method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170510

WD01 Invention patent application deemed withdrawn after publication