CN106248680A - A kind of engine commutator quality detecting system based on machine vision and detection method - Google Patents
A kind of engine commutator quality detecting system based on machine vision and detection method Download PDFInfo
- Publication number
- CN106248680A CN106248680A CN201610393245.4A CN201610393245A CN106248680A CN 106248680 A CN106248680 A CN 106248680A CN 201610393245 A CN201610393245 A CN 201610393245A CN 106248680 A CN106248680 A CN 106248680A
- Authority
- CN
- China
- Prior art keywords
- detection
- shape
- parameter
- learning
- examination criteria
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 163
- 238000007689 inspection Methods 0.000 claims abstract description 32
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000004441 surface measurement Methods 0.000 claims description 27
- 239000000284 extract Substances 0.000 claims description 11
- 239000011148 porous material Substances 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000010205 computational analysis Methods 0.000 claims description 2
- 238000007493 shaping process Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 abstract description 2
- 230000006978 adaptation Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000010354 integration Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan 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
- G01N2021/8887—Scan 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
- G01N2021/8893—Scan 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 providing a video image and a processed signal for helping visual decision
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention is a kind of engine commutator quality detecting system based on machine vision and detection method.It is connected with examination criteria model learning system (1) with data-interface (9) by image acquisition including examination criteria model learning system (1), shape and upper and lower end face detecting system (2), side inspection system (3), feeding system (4), gripping conveyor structure (5), upper and lower end face detection platform (6), side detection platform (7) and product sorting mechanism (8), shape and upper and lower end face detecting system (1) and side inspection system (2).The present invention uses machine vision technique, and design the detection pattern first learning to detect afterwards, this system is made to possess self study, self adaptation and dynamically adjust the abilities such as examination criteria, realize diverter shape, end face and side automatically to detect, improve production efficiency, ensure the concordance of product quality detection, solve engine commutator product quality test problems, practical.
Description
Technical field
The present invention is the vision detection system of a kind of product quality, a kind of engine commutator based on machine vision
Quality detecting system and detection method, belong to engine commutator product quality vision detection system and the innovative technology of method.
Background technology
Motor is as important basic equipment indispensable in industry, traffic, national defence and daily life.Diverter is as electricity
One of core devices of machine, its quality has a strong impact on the quality of motor.The appearance quality detection of diverter is that diverter is raw
Produce an important operation in line.At present, the quality testing of diverter still uses the mode of manual detection, and this may result in inspection
Survey efficiency is low, False Rate and loss high, and have artificial interference, also the dimensional accuracy measured can be produced impact.Additionally,
Manual detection needs substantial amounts of labour force, and the quality testing operation of diverter accounts for the 20%-30% of full scale production labour force, Er Qieren
Work detection is the most tired, and Detection accuracy is low, and cost is high, and the concordance of product is poor.Therefore, advanced machine vision skill is used
Art, artificial intelligence technology, automatic technology and electromechanical integration technology, design and develop diverter quality visual and automatically detect system
System is an inevitable choice, is also the urgent needs of Vehicles Collected from Market.
Summary of the invention
A kind of accuracy of detection that it is an object of the invention to consider to solve the problems referred to above is high, loss is low, detection speed is fast,
Practical by force, and can substitute for the engine commutator quality detecting system based on machine vision of manual detection mode.This
The bright non-contact vision detection realizing diverter shape, end face and side, automatic sorting faulty goods, improve detection speed and
Precision, improves production efficiency.
Another object of the present invention is to provide a kind of motor commutation based on machine vision simple to operate, convenient and practical
The detection method of device quality detecting system.
The technical scheme is that the engine commutator quality detecting system based on machine vision of the present invention, including
Examination criteria model learning system, shape and upper and lower end face detecting system, side inspection system, feeding system, gripping conveyor
Structure, upper and lower end face detection platform, side detection platform and product sorting mechanism, wherein shape and upper and lower end face detecting system and side
Surface detection system is connected with examination criteria model learning system with data-interface by image acquisition, examination criteria model learning system
System is by various detection criteria parameter needed for study and artificial setting offer native system.
The detection method of present invention engine commutator based on machine vision quality detecting system, comprises the steps:
1) learning process: first examination criteria model learning system passes through learning algorithm, obtains various detection criteria parameter;
2) detection process: the various detection criteria parameter that examination criteria model learning system is obtained by learning algorithm pass through image
Gather and be transferred to shape and upper and lower end face detecting system and side inspection system, shape and upper and lower end face detection system with data-interface
System and side inspection system, by calculating relative analysis, obtain testing result.
Above-mentioned learning algorithm comprises the following steps:
1) Image semantic classification;
2) examination criteria feature extraction, for the different test problems in shape, end face and side, is respectively adopted based on geometric properties side
Method extracts SHAPE DETECTION characteristic parameter, extracts end surface measurement characteristic parameter and base based on gray-scale statistical characteristics data and Energy-Entropy
Side detection characteristic parameter is extracted in geometric properties and gray-scale statistical characteristics;
3) statistical calculation method combination supporting vector machine is used to set up detection criteria parameter.
Above-mentioned Image semantic classification includes image segmentation, filters noise and contours extract step.
The present invention comprehensively uses optical, mechanical and electronic integration and machine vision technique, and the exploitation online vision-based detection of diverter quality is certainly
Dynamicization equipment, is used for realizing comprehensive detection and the sorting of the shape to diverter, groove, upper and lower end face and side.This system
Use image processing techniques and machine vision technique, the real defect diverter that identifies, and combine electromechanical equipment and sort, Ke Yidai
For existing manual detection pattern, get rid of manual detection interference caused by subjective factors, improve detection efficiency, accuracy rate and automatization's journey
Degree, reduces production cost, and product quality is more stable.Solve that the quality that manual detection brought is unstable, testing cost is high,
The problems such as inefficiency.
Accompanying drawing explanation
Fig. 1 is embodiment of the present invention system diagram;
Fig. 2 is examination criteria model learning system construction drawing in the embodiment of the present invention;
Fig. 3 is shape and end surface measurement system construction drawing in the embodiment of the present invention;
Fig. 4 is side inspection system structure chart in the embodiment of the present invention.
Detailed description of the invention
The system structure schematic diagram of the present invention is as it is shown in figure 1, present invention engine commutator based on machine vision quality is examined
Examining system, including examination criteria model learning system 1, shape and upper and lower end face detecting system 2, side inspection system 3, feeding system
System 4, gripping conveyor structure 5, upper and lower end face detection platform 6, side detection platform 7 and product sorting mechanism 8, wherein shape and upper
Lower surface detecting system 2 and side inspection system 3 are by image acquisition and data-interface 9 and examination criteria model learning system 1
Connecting, examination criteria model learning system 1 is passed through study and manually sets various detection criteria parameter needed for offer native system.
Above-mentioned examination criteria model learning system 1 obtains various detection criteria parameter by learning algorithm, and these detect mark
Quasi-parameter is transferred to shape and upper and lower end face detecting system 2 and side inspection system 3, shape by image acquisition and data-interface 9
Shape and upper and lower end face detecting system 2 and side inspection system 3, by calculating relative analysis, obtain testing result.
Fig. 2 is the schematic diagram of examination criteria model learning system 1, including image capture interface 11, SHAPE DETECTION parametrics
Learning system 12, end surface measurement parameter learning system 13, side detection parameter learning system 14, examination criteria learning model storehouse 15,
Data-interface 16 and artificial setting examination criteria model library 17;Wherein SHAPE DETECTION parameter learning system 12, end surface measurement parameter
Learning system 13 and side detection parameter learning system 14, by image capture interface 11, obtain non-defective unit diverter view data,
Extract diverter shape, end face and the canonical parameter of side through learning algorithm, and be saved in examination criteria learning model storehouse 15;With
Time, according to the Heuristics of manual detection, set the examination criteria of different size diverter, be saved in and manually set examination criteria
Model library 17;Examination criteria learning model storehouse 15 and artificial setting are connected by data-interface 16 between examination criteria model library 17
Connect, the detection criteria parameter needed for various detections provide.Examination criteria model learning system 1 of the present invention is by learning and artificial
Set and various detection criteria parameter needed for native system are provided.Examination criteria model learning system 1 is when study, and diverter is up and down
On end surface measurement platform, obtain corresponding detection criteria parameter by image acquisition, shape and end surface measurement parameter learning, and protect
It is stored to examination criteria learning model storehouse;When diverter is in the detection platform of side, by image acquisition, side detection parameter learning
Obtain corresponding detection criteria parameter, and be saved in examination criteria learning model storehouse;Meanwhile, the Heuristics of manual detection also
Artificial setting examination criteria model library can be saved in;By data-interface, provide detection criteria parameter for various detections.
The schematic diagram of above-mentioned shape and upper and lower end face detecting system 2 as it is shown on figure 3, include shape visual light origin system 21,
SHAPE DETECTION image capturing system 22, aperture detection system 23, shape detection system 24, end surface measurement light-source system 25, end face
Detection image capturing system 26 and upper and lower end face detecting system 27;The end needed for wherein SHAPE DETECTION light-source system 21 provides detection
Light source;SHAPE DETECTION image capturing system 22 utilizes the online image obtaining diverter, passes to aperture detection system 23 and carries out
Commutator bore detects, and Pore Diameter Detection algorithm utilizes the standard detection parameter in examination criteria model learning system, and actual inspection
Measured value contrasts, and draws qualified, the bigger than normal and less than normal result in aperture and exports;Meanwhile, SHAPE DETECTION image capturing system 22 collection
Image pass to shape detection system 24, SHAPE DETECTION algorithm is to outward appearance shapes such as the hook and slot of diverter, indexing, external diameter, hooks
Shape carries out computational analysis, and and examination criteria model learning system in standard detection parameter comparison, it is judged that be non-defective unit or lack
Fall into product and output result;End surface measurement light-source system more than 25 light source mode provides light source needed for detection end face;End surface measurement
Image capturing system 26 gathers diverter upper and lower end face image, and passes to upper and lower end face detecting system 27 and detect, this calculation
Method utilizes examination criteria model learning system.
Above-mentioned shape and upper and lower end face detecting system 2 are when detecting diverter, and shape visual light origin system 21 top is laid
Diverter to be checked, is in diverter both sides with SHAPE DETECTION image capturing system 22, carries for SHAPE DETECTION image capturing system 22
For bias light;SHAPE DETECTION image capturing system 22 utilizes face battle array industrial camera, obtains the image of diverter to be checked, and is transferred to
Shape detection system 24, shape detection system 24 calls master die relevant with SHAPE DETECTION in examination criteria Template Learning system 1
Shape parameter, is analyzed contrast, determines that testing result exports;Meanwhile, the image transmitting of collection is to aperture detection system 23, aperture
Detecting system 23 calls canonical parameter relevant with Pore Diameter Detection in examination criteria Template Learning system 1, is analyzed contrast, determines
Testing result exports.End surface measurement light-source system 25 uses annular light source, is in homonymy with end surface measurement image capturing system 26,
Front light source is provided for end face image acquisition;End surface measurement image capturing system 26 utilizes face battle array industrial camera, obtains to be checked changing
To the end view drawing picture of device, and it is transferred to upper and lower end face detecting system 27, calls in examination criteria Template Learning system 1 and examine with end face
Survey relevant master pattern parameter, be analyzed contrast, determine that testing result exports.
The schematic diagram of above-mentioned side inspection system 3 as shown in Figure 4, including side vision light-source system 31, side automatic rotary
Rotation structure 32, side image acquisition system 33 and side inspection system 34;Wherein side vision light-source system provides side detection
Required linear light sorurce, side detection image capturing system 33 utilizes linear array industrial camera, with line scan mode, obtains side certainly
Multiple diverter images to be checked at the uniform velocity rotated on dynamic rotational structure 32, and pass to side inspection system 34;Meanwhile, side inspection
Examining system 34 obtains the canonical parameter of side detection in examination criteria model learning system by data access interface, contrasts
Analyze, obtain testing result.
Above-mentioned side vision light-source system 31 uses linear light sources, multiple diverters to be arranged on side automatic rotation structure,
And constant speed rotates, side image collection and utilization linear array industrial camera, with line scan mode, obtain side image;Gathered image
It is transferred to side detection, side detection calls master pattern relevant with side detection ginseng in examination criteria Template Learning system 1
Number, is analyzed contrast, determines that testing result exports.
Additionally, present invention additionally comprises feeding system 4, gripping conveyor structure 5, upper and lower end face detection platform 6, side detection
Platform 7 and product sorting mechanism 8.
The detection method of present invention engine commutator based on machine vision quality detecting system, comprises the steps:
1) learning process: first examination criteria model learning system 1 is by learning algorithm, obtains various detection criteria parameter;
2) detection process: the various detection criteria parameter that examination criteria model learning system 1 is obtained by learning algorithm pass through figure
It is transferred to shape and upper and lower end face detecting system 2 and side inspection system 3, shape and upper and lower end face with data-interface 9 as gathering
Detecting system 2 and side inspection system 3, by calculating relative analysis, obtain testing result.
Above-mentioned learning algorithm comprises the following steps:
1) Image semantic classification;
2) examination criteria feature extraction, for the different test problems in shape, end face and side, is respectively adopted based on geometric properties side
Method extracts SHAPE DETECTION characteristic parameter, extracts end surface measurement characteristic parameter and base based on gray-scale statistical characteristics data and Energy-Entropy
Side detection characteristic parameter is extracted in geometric properties and gray-scale statistical characteristics;
3) statistical calculation method combination supporting vector machine is used to set up detection criteria parameter.
Above-mentioned Image semantic classification includes image segmentation, filters noise and contours extract step.
The operation principle of the present invention is as follows: described diverter quality visual detecting system, is divided into two processes: learning process
With detection process.When study, by feeding structure auto-sequencing and carry the diverter fixing jack-up position to diverter, then by
Capture structure for conveying, capture diverter one by one and be transported to upper and lower end face detection platform and side detection platform with this;Shape with
End surface measurement system and the canonical parameter of side inspection system study non-defective unit diverter, and passed with data-interface by image acquisition
It is defeated by examination criteria Template Learning system to preserve;When detection, by feeding structure auto-sequencing and carry diverter to diverter
Fixing jack-up position, then by capture structure for conveying, one by one capture diverter and with this be transported to upper and lower end face detection platform and
Side detection platform;Shape obtains detection mark with end surface measurement system and side inspection system by image acquisition and data-interface
Canonical parameter in quasi-mode plate learning system, is then analyzed contrast, output detections result;According to testing result, then by producing
Product sorting structure sorts.
Described figure examination criteria model learning system, when study, diverter is placed on one by one in upper and lower end face detection platform
With side detection platform, by image acquisition, parametrics is detected in SHAPE DETECTION parameter learning, end surface measurement parameter learning and side
Practise, calculate corresponding detection criteria parameter, and be saved in examination criteria learning model storehouse;Meanwhile, manual detection
Heuristics can also be saved in artificial setting examination criteria model library;By data-interface, provide detection mark for various detections
Quasi-parameter.
Described shape and end surface measurement system, when diverter detects, be placed in upper and lower end face detection platform, image one by one
Collection and utilization face battle array industrial camera, obtains the image of diverter to be checked, and is transferred to SHAPE DETECTION, and SHAPE DETECTION calls detection mark
Master pattern parameter relevant with SHAPE DETECTION in quasi-mode plate learning system 1, is analyzed contrast, determines that testing result exports;With
Time, the image transmitting of collection is to Pore Diameter Detection, and Pore Diameter Detection calls in examination criteria Template Learning system 1 relevant with Pore Diameter Detection
Canonical parameter, is analyzed contrast, determines that testing result exports;When detecting in upper and lower end face, end view drawing is as collection and utilization face battle array
Industrial camera, obtains the end view drawing picture of diverter to be checked, and is transferred to upper and lower end face detection, calls examination criteria Template Learning system
Master pattern parameter relevant with end surface measurement in system 1, is analyzed contrast, determines that testing result exports.
Described side inspection system, when diverter detects, multiple diverters are arranged on side automatic rotation structure, and fixed
Speed rotates, side image collection and utilization linear array industrial camera, with line scan mode, obtains side image;Gathered image transmitting
Detect to side, side detection call master pattern parameter relevant with side detection in examination criteria Template Learning system 1, enter
Row analyzes contrast, determines that testing result exports.
This system is with skills such as machine vision technique, distributed control technology, electromechanical integration, oriented object development
Art achieves the functions such as the image acquisition of whole system, shape and end surface measurement, side detection and product feeding, sorting;This is
The system method of operation is: first learn examination criteria, builds examination criteria learning template storehouse, then recycling study gained canonical parameter
Carry out shape, end face and side detection.
Claims (8)
1. an engine commutator quality detecting system based on machine vision, it is characterised in that include examination criteria model learning
System (1), shape and upper and lower end face detecting system (2), side inspection system (3), feeding system (4), gripping conveyor structure
(5), upper and lower end face detection platform (6), side detection platform (7) and product sorting mechanism (8), wherein shape and upper and lower end face inspection
Examining system (2) and side inspection system (3) are by image acquisition and data-interface (9) and examination criteria model learning system (1)
Connecting, examination criteria model learning system (1) passes through study and manually sets various detection criteria parameter needed for offer native system.
The engine commutator quality detecting system of view-based access control model the most according to claim 1, it is characterised in that above-mentioned detection
Master pattern learning system (1) obtains various detection criteria parameter by learning algorithm, and these detection criteria parameter pass through image
Gathering and be transferred to shape and upper and lower end face detecting system (2) and side inspection system (3) with data-interface (9), shape is with upper and lower
End surface measurement system (2) and side inspection system (3), by calculating relative analysis, obtain testing result.
Engine commutator quality detecting system based on machine vision the most according to claim 1, it is characterised in that above-mentioned
Examination criteria model learning system (1) includes image capture interface (11), SHAPE DETECTION parameter learning system (12), end surface measurement
Parameter learning system (13), side detection parameter learning system (14), examination criteria learning model storehouse (15), data-interface (16)
Examination criteria model library (17) is set with artificial;Wherein SHAPE DETECTION parameter learning system (12), end surface measurement parameter learning system
System (13) and side detection parameter learning system (14), by image capture interface (11), obtain non-defective unit diverter view data,
Extract diverter shape, end face and the canonical parameter of side through learning algorithm, and be saved in examination criteria learning model storehouse (15);
Meanwhile, according to the Heuristics of manual detection, set the examination criteria of different size diverter, be saved in artificial setting and detect mark
Quasi-model library (17);Examination criteria learning model storehouse (15) and artificial setting are connect by data between examination criteria model library (17)
Mouth (16) connects, the detection criteria parameter needed for various detections provide.
4. according to the engine commutator quality detecting system based on machine vision described in any one of claims 1 to 3, its feature
It is that above-mentioned shape and upper and lower end face detecting system (2) include shape visual light origin system (21), SHAPE DETECTION image acquisition system
System (22), aperture detection system (23), shape detection system (24), end surface measurement light-source system (25), end surface measurement image are adopted
Collecting system (26) and upper and lower end face detecting system (27);Bottom season needed for wherein SHAPE DETECTION light-source system (21) provides detection
Source;SHAPE DETECTION image capturing system (22) utilizes the online image obtaining diverter, passes to aperture detection system (23) and enters
Row commutator bore detects, and Pore Diameter Detection algorithm utilizes the standard detection parameter in examination criteria model learning system, and actual
Detected value contrasts, and draws qualified, the bigger than normal and less than normal result in aperture and exports;Meanwhile, SHAPE DETECTION image capturing system (22)
The image gathered passes to shape detection system (24), and SHAPE DETECTION algorithm is to the hook and slot of diverter, indexing, external diameter, hook etc.
Face shaping carries out computational analysis, and and examination criteria model learning system in standard detection parameter comparison, it is judged that be non-defective unit
Or faulty goods and output result;End surface measurement light-source system (25) above light source mode provides light source needed for detection end face;
End surface measurement image capturing system (26) gathers diverter upper and lower end face image, and passes to upper and lower end face detecting system (27) and enter
Row detection, this algorithm utilizes examination criteria model learning system.
Engine commutator quality detecting system based on machine vision the most according to claim 4, it is characterised in that above-mentioned
Side inspection system (3) includes side vision light-source system (31), side automatic rotation structure (32), side image acquisition system
And side inspection system (34) (33);Linear light sorurce needed for wherein side vision light-source system provides side detection, side is examined
Altimetric image acquisition system (33) utilizes linear array industrial camera, with line scan mode, obtains side automatic rotation structure (32) upper many
The individual diverter image to be checked at the uniform velocity rotated, and pass to side inspection system (34);Meanwhile, side inspection system (34) passes through
Data access interface obtains the canonical parameter of side detection in examination criteria model learning system, is analyzed, is examined
Survey result.
6. a detection method for engine commutator quality detecting system based on machine vision according to claim 1,
It is characterized in that comprising the steps:
1) learning process: first examination criteria model learning system (1) passes through learning algorithm, obtains various detection criteria parameter;
2) detection process: the various detection criteria parameter that examination criteria model learning system (1) is obtained by learning algorithm are passed through
Image acquisition and data-interface (9) are transferred to shape and upper and lower end face detecting system (2) and side inspection system (3), shape and
Upper and lower end face detecting system (2) and side inspection system (3), by calculating relative analysis, obtain testing result.
The detection method of engine commutator quality detecting system based on machine vision the most according to claim 6, it is special
Levy and be that above-mentioned learning algorithm comprises the following steps:
1) Image semantic classification;
2) examination criteria feature extraction, for the different test problems in shape, end face and side, is respectively adopted based on geometric properties side
Method extracts SHAPE DETECTION characteristic parameter, extracts end surface measurement characteristic parameter and base based on gray-scale statistical characteristics data and Energy-Entropy
Side detection characteristic parameter is extracted in geometric properties and gray-scale statistical characteristics;
3) statistical calculation method combination supporting vector machine is used to set up detection criteria parameter.
The detection method of engine commutator quality detecting system based on machine vision the most according to claim 7, it is special
Levy and be that above-mentioned Image semantic classification includes image segmentation, filters noise and contours extract step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610393245.4A CN106248680A (en) | 2016-06-03 | 2016-06-03 | A kind of engine commutator quality detecting system based on machine vision and detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610393245.4A CN106248680A (en) | 2016-06-03 | 2016-06-03 | A kind of engine commutator quality detecting system based on machine vision and detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106248680A true CN106248680A (en) | 2016-12-21 |
Family
ID=57613529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610393245.4A Pending CN106248680A (en) | 2016-06-03 | 2016-06-03 | A kind of engine commutator quality detecting system based on machine vision and detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106248680A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106645189A (en) * | 2016-12-28 | 2017-05-10 | 重庆远创光电科技有限公司 | Automatic commutator appearance defect online visual detection system |
CN107340294A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of engine commutator automatic visual detecting system |
CN107340299A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of image capture instrument of engine commutator vision-based detection |
CN107340295A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of motor commutator detection device |
CN107727146A (en) * | 2017-10-12 | 2018-02-23 | 重庆远创光电科技有限公司 | Engine commutator open defect automatic visual detection means |
CN108120721A (en) * | 2017-12-21 | 2018-06-05 | 重庆晓微城企业孵化器有限公司 | A kind of engine commutator automatic visual detecting system |
CN109047035A (en) * | 2018-08-03 | 2018-12-21 | 华侨大学 | A kind of composite polycrystal-diamond surface defect automatic detection device |
CN109387152A (en) * | 2018-11-28 | 2019-02-26 | 无锡威孚奥特凯姆精密机械有限公司 | Visual detection equipment |
CN109387152B (en) * | 2018-11-28 | 2024-05-31 | 无锡威孚奥特凯姆精密机械有限公司 | Visual inspection apparatus |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735287A (en) * | 2012-06-19 | 2012-10-17 | 周仲华 | Method and equipment for fully-automatically detecting motor commutator |
CN103090804A (en) * | 2013-01-15 | 2013-05-08 | 中国计量学院 | Automatic detection system and detection method of finished product magnet ring image |
CN103411974A (en) * | 2013-07-10 | 2013-11-27 | 杭州赤霄科技有限公司 | Cloud big data-based planar material detection remote system and cloud big data-based planar material detection method |
CN103868934A (en) * | 2014-01-21 | 2014-06-18 | 图灵视控(北京)科技有限公司 | Glass lamp cup detection system and method based on machine vision |
CN104597053A (en) * | 2014-10-28 | 2015-05-06 | 北京鸿浩信达技术有限公司 | Miniature workpiece surface defect and size out-of-tolerance automatic detector |
CN105004731A (en) * | 2015-07-14 | 2015-10-28 | 南京工程学院 | Column capacitance appearance automatic detection device and method |
CN105044122A (en) * | 2015-08-25 | 2015-11-11 | 安徽工业大学 | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model |
CN208125628U (en) * | 2016-06-03 | 2018-11-20 | 广州恺煜兴智能科技有限公司 | A kind of engine commutator quality detecting system based on machine vision |
-
2016
- 2016-06-03 CN CN201610393245.4A patent/CN106248680A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735287A (en) * | 2012-06-19 | 2012-10-17 | 周仲华 | Method and equipment for fully-automatically detecting motor commutator |
CN103090804A (en) * | 2013-01-15 | 2013-05-08 | 中国计量学院 | Automatic detection system and detection method of finished product magnet ring image |
CN103411974A (en) * | 2013-07-10 | 2013-11-27 | 杭州赤霄科技有限公司 | Cloud big data-based planar material detection remote system and cloud big data-based planar material detection method |
CN103868934A (en) * | 2014-01-21 | 2014-06-18 | 图灵视控(北京)科技有限公司 | Glass lamp cup detection system and method based on machine vision |
CN104597053A (en) * | 2014-10-28 | 2015-05-06 | 北京鸿浩信达技术有限公司 | Miniature workpiece surface defect and size out-of-tolerance automatic detector |
CN105004731A (en) * | 2015-07-14 | 2015-10-28 | 南京工程学院 | Column capacitance appearance automatic detection device and method |
CN105044122A (en) * | 2015-08-25 | 2015-11-11 | 安徽工业大学 | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model |
CN208125628U (en) * | 2016-06-03 | 2018-11-20 | 广州恺煜兴智能科技有限公司 | A kind of engine commutator quality detecting system based on machine vision |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107340294A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of engine commutator automatic visual detecting system |
CN107340299A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of image capture instrument of engine commutator vision-based detection |
CN107340295A (en) * | 2016-12-24 | 2017-11-10 | 重庆都英科技有限公司 | A kind of motor commutator detection device |
CN106645189A (en) * | 2016-12-28 | 2017-05-10 | 重庆远创光电科技有限公司 | Automatic commutator appearance defect online visual detection system |
CN107727146A (en) * | 2017-10-12 | 2018-02-23 | 重庆远创光电科技有限公司 | Engine commutator open defect automatic visual detection means |
CN108120721A (en) * | 2017-12-21 | 2018-06-05 | 重庆晓微城企业孵化器有限公司 | A kind of engine commutator automatic visual detecting system |
CN108120721B (en) * | 2017-12-21 | 2020-04-28 | 重庆晓微城企业孵化器有限公司 | Automatic vision detection system of motor commutator |
CN109047035A (en) * | 2018-08-03 | 2018-12-21 | 华侨大学 | A kind of composite polycrystal-diamond surface defect automatic detection device |
CN109387152A (en) * | 2018-11-28 | 2019-02-26 | 无锡威孚奥特凯姆精密机械有限公司 | Visual detection equipment |
CN109387152B (en) * | 2018-11-28 | 2024-05-31 | 无锡威孚奥特凯姆精密机械有限公司 | Visual inspection apparatus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
CN105388162B (en) | Raw material silicon chip surface scratch detection method based on machine vision | |
Liming et al. | Automated strawberry grading system based on image processing | |
CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
CN104198324B (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
CN110403232A (en) | A kind of cigarette quality detection method based on second level algorithm | |
CN104197836A (en) | Vehicle lock assembly size detection method based on machine vision | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
CN112893159B (en) | Coal gangue sorting method based on image recognition | |
CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
CN112268910A (en) | Visual detection system and method for cigarette appearance defects | |
CN104952754B (en) | Silicon chip method for separating after plated film based on machine vision | |
CN110096980A (en) | Character machining identifying system | |
CN109115775B (en) | Betel nut grade detection method based on machine vision | |
CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161221 |
|
RJ01 | Rejection of invention patent application after publication |