CN109596621A - A kind of carbon brush abrasion detection method and detection device - Google Patents
A kind of carbon brush abrasion detection method and detection device Download PDFInfo
- Publication number
- CN109596621A CN109596621A CN201811344674.8A CN201811344674A CN109596621A CN 109596621 A CN109596621 A CN 109596621A CN 201811344674 A CN201811344674 A CN 201811344674A CN 109596621 A CN109596621 A CN 109596621A
- Authority
- CN
- China
- Prior art keywords
- carbon brush
- surface image
- image
- brush surface
- segmentation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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
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)
Abstract
The embodiment of the present application shows a kind of carbon brush abrasion detection method and detection device, comprising: detects whether that there are carbon brush to be measured；If there is carbon brush to be measured, the illumination of carbon determination brush is treated, carbon brush surface image is obtained；Carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；Pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；Enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；Extract the characteristic quantity of segmentation carbon brush surface image；The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of segmentation carbon brush surface image；Carbon brush surface image defect is weighted and is compared with preset threshold, if the weighting of carbon brush surface image defect is greater than preset threshold, for defective products, if the weighting of carbon brush surface image defect less than preset threshold, for non-defective unit.Carbon brush abrasion detection method of the present invention, detection efficiency is high, and detection accuracy is high, meets the testing requirements of carbon brush product surface wear-out defect.
Description
Technical field
The present invention relates to carbon brush abrasion detection technique field, in particular to a kind of carbon brush abrasion detection method and detection dress
It sets.
Background technique
Carbon brush is widely used a kind of product in many electrical equipments, substantially various commutating machines and direct current
Machine, which all lacks, can't do without carbon brush, complete signal transmitting or energy transmission inside various rotating machineries as slide contact member,
Play the role of extremely important.Especially some accurate electric equipment products or automobile etc. are to the higher product of security requirement, carbon
The quality of brush will directly affect the performance and operational safety of these staple products.Therefore, right in carbon brush production process
Carbon brush is detected to guarantee that product quality is particularly important.Currently, since the factors such as technique lead to carbon brush in carbon brush manufacturing process
Surface haves the defects that abrasion, and mainly carbon brush surface abrasion is detected and selected with naked eyes by producing line worker.It is artificial long
Time easily generates fatigue by naked eyes detection carbon brush product, while also will appear erroneous judgement, and omission factor and fallout ratio are relatively high, carbon
Brush quality of finished cannot be effectively ensured, in addition, it is that efficiency is too low that artificial detection, which has another then, after visual fatigue
Cause detection speed slower, so the detection that manual detection mode cannot meet carbon brush product surface wear-out defect is wanted at all
It asks.
Summary of the invention
To overcome the problems in correlation technique, the present invention provides a kind of carbon brush abrasion detection method and detection device,
Detection efficiency is high, and detection accuracy is high, meets the testing requirements of carbon brush product surface wear-out defect.
First aspect of the embodiment of the present invention discloses a kind of carbon brush abrasion detection method, the carbon brush abrasion detection method packet
Include following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Optionally, the light source illuminated by light source to carbon brush is strip source.
It is optionally, described that the carbon brush surface image is carried out pretreatment includes: clarity processing, at mathematical morphology
Reason, image filtering processing, Boundary Extraction processing, greyscale transform process and binary conversion treatment.
Optionally, it is described by the pretreatment carbon brush surface image progress image enhancement include: noise filtering and mask mark
Note.
Optionally, described image segmentation includes: Threshold segmentation.
Optionally, the characteristic quantity for extracting the characteristic quantity of the segmentation carbon brush surface image includes: abrasion length, wearing depth
And wear area.
Using a kind of carbon brush abrasion detection method that first aspect provides, detect whether that there are carbon brush to be measured；If there is
Carbon brush to be measured is treated carbon determination brush by light source and is illuminated, and carbon brush surface image is obtained；The carbon brush surface image is carried out pre-
Processing obtains pretreatment carbon brush surface image；The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush
Surface image；The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；Extract the segmentation
The characteristic quantity of carbon brush surface image；Carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image
Weighting；The carbon brush surface image defect is weighted and is compared with preset threshold, if the carbon brush surface image defect weights
It is then defective products greater than the preset threshold, if carbon brush surface image defect weighting is less than the preset threshold, for
Non-defective unit.The embodiment of the present invention provides a kind of carbon brush abrasion detection method, and detection efficiency is high, and detection accuracy is high, meets carbon brush product
The testing requirements of surface abrasion defect.
According to the second aspect of the disclosure, a kind of carbon brush slide plate detection device is provided, described device includes: LED light source, light
System, feed system, image capture module and image processing module, the optical system respectively with the LED light source and
The electrical connection of described image acquisition module, the data acquisition module are electrically connected with described image processing module；
The LED light source is illuminated for treating carbon determination brush；
The optical system controls opening for the LED light source and image capture module for detecting whether there are carbon brush to be measured
It opens；
The feed system is for conveying carbon brush to be measured；
Described image acquisition module is for obtaining carbon brush surface image；
Described image processing module analyzes carbon brush abrasion amount for handling the carbon brush surface image.
Optionally, described image processing module is also electrically connected with sorting unit, and the sorting unit is for receiving the carbon
Brush wear amount, judges whether the carbon brush abrasion amount exceeds preset threshold, and sorts carbon brush according to judging result.
A kind of carbon brush abrasion detection device shown in second aspect, described device described device include: LED light source, optics
System, feed system, image capture module and image processing module, the optical system respectively with the LED light source and institute
Image capture module electrical connection is stated, the data acquisition module is electrically connected with described image processing module；The LED light source is used for
Carbon determination brush is treated to be illuminated；The optical system is for detecting whether there are carbon brush to be measured, and control the LED light source and figure
As the unlatching of acquisition module；The feed system is for conveying carbon brush to be measured；Described image acquisition module is for obtaining carbon brush table
Face image；Described image processing module analyzes carbon brush abrasion amount for handling the carbon brush surface image.Shown in second aspect
A kind of carbon brush abrasion detection device detection efficiency is high, and detection accuracy is high, meets the testing requirements of carbon brush product surface wear-out defect.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without creative efforts, also
Other drawings may be obtained according to these drawings without any creative labor.
Fig. 1 is a kind of flow diagram of carbon brush abrasion detection method provided in an embodiment of the present invention；
Fig. 2 is a kind of overall schematic of carbon brush slide plate detection device provided in an embodiment of the present invention.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, below in conjunction with of the invention real
The attached drawing in example is applied, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work, all should belong to protection of the present invention
Range.
Embodiment one
It is a kind of carbon brush abrasion detection method provided in an embodiment of the present invention, which is characterized in that the carbon brush abrasion referring to Fig. 1
Detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
After the bad image of the alligatoring of carbon brush workpiece is taken pictures by smart camera to be collected, because of carbon brush work piece production system
The bright dark degree of light at the scene of making, some disturbing factors of periphery cause in addition to carbon brush workpiece self reason and existing interference is special
Sign all brings certain influence by the judgement of camera acquired image to carbon brush workpiece.Therefore, to workpiece image collected
Before formal processing, the bad defect image of carbon brush workpiece surface slight crack collected in advance to smart camera is needed to carry out
Pretreatment.The enhancing of workpiece surface image can aid in the processing and judgement that system carries out fast accurate to the image of workpiece.
When workpiece to be detected is taken pictures using smart camera and extract its image after next need using vision processor come pair
The collected workpiece image of institute is handled, and generally all be unableing to do without an important processing means is exactly image segmentation.It is using
When such image processing techniques, it to be able to confirm that the value region of acquired workpiece image, the region can thus be carried out special
Sign is extracted, and so-called valuable region is exactly usually described area-of-interest, and remaining region of loseing interest in is then without exception as figure
The background of picture is handled.Smart camera can be taken pictures by dividing processing and extract institute's acquired image and distinguished wherein
The data in general characteristic of so-called valuable value part is made of shape, gray scale, these parts of profile, most occasions
Under, most often adopted method is spatial domain and two kinds of frequency domain.
The carbon brush abrasion detection method that embodiment one provides, first detects whether that there are carbon brush to be measured；If there is to be measured
Carbon brush is treated carbon determination brush by light source and is illuminated, and carbon brush surface image is obtained；The carbon brush surface image is located in advance
Reason obtains pretreatment carbon brush surface image；The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush table
Face image；The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；Extract the segmentation carbon
The characteristic quantity of brush surface image；Carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image to add
Power；The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.The embodiment of the present invention provides a kind of carbon brush abrasion detection method, and detection efficiency is high, and detection accuracy is high, meets carbon brush product table
The testing requirements of surface wear defect.
Embodiment two is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Wherein, the light source illuminated by light source to carbon brush is strip source.In intelligence machine vision system,
Smart camera takes pictures to workpiece and extracts image to be used for system image procossing and judge, the quality pair of Image Acquisition effect
Final evaluation result has direct influence, is difficult to obtain if institute's acquired image quality is bad or feature extraction is not complete
True processing judging result, to interfere or influence to detection work belt.And can smart camera obtain good image
Effect, whether what light source was selected among these is properly a crucial factor of comparison, therefore, will especially be weighed in system design
The comparison and selection of matched light source depending on camera are mainly based upon workpiece feature and each section relative tertiary location etc. and specifically believe
Breath is to be determined light source.Currently, conventional camera light source mainly includes annular light source, backlight, coaxial light source, strip light
A variety of different light sources such as source, linear light source, these light sources are commonly used in actual vision system, and applicable occasion is main
It is determined according to shape, feature and the measurement of detection workpiece or detection function performance, only selects suitable light source type
The image for meeting detection effect can be acquired out.It is compared by polishing mode, it is contemplated that the present apparatus needs to grind carbon brush product surface
Damage defect has an accurate Image Acquisition, using, to polishing mode, light source is located at carbon brush product and phase before white strip source
Between machine, clearly image effect can be received in this way.
Embodiment three is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Wherein, it is described by the carbon brush surface image carry out pretreatment include: clarity processing, morphology processing,
Image filtering processing, Boundary Extraction processing, greyscale transform process and binary conversion treatment.Mathematical morphology: boundary lines are used for
Overstriking or decrease.Normally due to light source problem, the lines for the image shot with itself have certain gap, number can be passed through
Morphology is learned to adjust.Greyscale transformation: for reaching partially dark or partially bright picture in specified tonal range, to reduce light
The problems such as source caused grayscale shift.
Example IV is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Light filling is carried out to carbon brush sled surface, and obtains carbon brush sled surface original image；
The carbon brush sled surface original image is pre-processed, pretreatment carbon brush sled surface image is obtained；
The pretreatment carbon brush sled surface image is subjected to median filtering, obtains preliminary treatment carbon brush sled surface image；
The preliminary treatment carbon brush sled surface image is subjected to image segmentation, obtains segmentation carbon brush sled surface image；
The edge for extracting the segmentation carbon brush sled surface image, obtains the profile of carbon brush sled surface image；
The profile of the carbon brush sled surface image is positioned, is placed in preset coordinate system diagram, it is sliding with preset carbon brush
The coordinate of the profile of plate surface image is compared analysis, obtains carbon brush abrasion abrasion loss.
Wherein, state to carbon brush sled surface carry out light filling before further include: by be based on 2D plane chessboard target technology
The 3D camera acquisition parameter is demarcated.Vision system is demarcated using 2D plane chessboard target technology, Ke Yifu
Its accurate measurement capability is given, the carbon brush sled surface original image of acquisition is more acurrate.
Embodiment five is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Wherein, described by pretreatment carbon brush surface image progress image enhancement includes: that noise filtering and mask mark.
Noise filtering can use but be not limited to gaussian filtering, and image filtering main function eliminates the non-shooting object sheet shot
The noise spot of body, consequently facilitating feature extraction and differentiation.The most important function of gaussian filtering and effect are exactly to make institute collected
The treatment effect of workpiece image is more smooth.
Embodiment six is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Wherein, described image segmentation includes: Threshold segmentation.Usual thresholding method is namely based in the image of acquisition and carries on the back
Existing grey scale change between scape and characteristic area is divided into multiple gray scale classifications using pixel for threshold value setting means, this
Sample is achieved that the simple and effective segmentation to acquisition image, and the background and segmentation of feature regions in the image of acquisition are obvious, thus
It is analyzed and is handled convenient for characteristic area, that is, target object to acquisition image, and Binarization methods are exactly multiple Threshold segmentations
In algorithm segmentation effect it is relatively good, it is important and use relatively simple one kind.
Embodiment seven is a kind of carbon brush abrasion detection method that the preferred embodiment of the invention provides, which is characterized in that institute
Stating carbon brush abrasion, detection method includes the following steps:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
Wherein, extract it is described segmentation carbon brush surface image characteristic quantity characteristic quantity include: abrasion length, wearing depth with
And wear area.
A kind of carbon brush slide plate detection device shown in second aspect, referring to Fig. 2, described device includes: LED light source 1, light
System 2, feed system 3, image capture module 4 and image processing module 5, the optical system 2 respectively with the LED light
Source 1 and described image acquisition module 4 are electrically connected, and the data acquisition module 4 is electrically connected with described image processing module 5；
The LED light source 1 is illuminated for treating carbon determination brush；
The optical system 2 controls the LED light source 1 and image capture module 4 for detecting whether there are carbon brush to be measured
It opens；
The feed system 3 is for conveying carbon brush to be measured；
Described image acquisition module 4 is for obtaining carbon brush surface image；
Described image processing module 5 analyzes carbon brush abrasion amount for handling the carbon brush surface image.
As preferred embodiment, described image processing module 5 is also electrically connected with sorting unit 6, and the sorting unit 6 is used
In receiving the carbon brush abrasion amount, judge whether the carbon brush abrasion amount exceeds preset threshold, and carbon is sorted according to judging result
Brush.If carbon brush abrasion amount exceeds preset threshold, carbon brush is sorted all defective products areas by sorting unit 6, if carbon brush abrasion amount is not
Beyond preset threshold, carbon brush is sorted into non-defective unit area by sorting unit 6.
Those skilled in the art will readily occur to its of the application after considering specification and practicing application disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by above
Claim is pointed out.
It should be understood that the application is not limited to the accurate process for being described above and being shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
Claims (8)
1. a kind of carbon brush abrasion detection method, which is characterized in that detection method includes the following steps for the carbon brush abrasion:
Detect whether that there are carbon brush to be measured；
If there is carbon brush to be measured, carbon determination brush is treated by light source and is illuminated, obtains carbon brush surface image；
The carbon brush surface image is pre-processed, pretreatment carbon brush surface image is obtained；
The pretreatment carbon brush surface image is subjected to image enhancement, obtains enhancing carbon brush surface image；
The enhancing carbon brush surface image is subjected to image segmentation, obtains segmentation carbon brush surface image；
Extract the characteristic quantity of the segmentation carbon brush surface image；
The weighting of carbon brush surface image defect is calculated according to the characteristic quantity of the segmentation carbon brush surface image；
The carbon brush surface image defect is weighted and is compared with preset threshold, if carbon brush surface image defect weighting is big
Then it is defective products in the preset threshold, is good if carbon brush surface image defect weighting is less than the preset threshold
Product.
2. a kind of carbon brush abrasion detection method according to claim 1, which is characterized in that it is described by light source to carbon brush into
The light source of row illumination is strip source.
3. a kind of carbon brush abrasion detection method according to claim 1, which is characterized in that described by the carbon brush exterior view
It include: clarity processing, morphology processing, image filtering processing, Boundary Extraction processing, greyscale transformation as carrying out pretreatment
Processing and binary conversion treatment.
4. a kind of carbon brush abrasion detection method according to claim 1, which is characterized in that described by the pretreatment carbon brush
It includes: noise filtering and mask label that surface image, which carries out image enhancement,.
5. a kind of carbon brush abrasion detection method according to claim 1, which is characterized in that described image segmentation includes: threshold
Value segmentation.
6. a kind of carbon brush abrasion detection method according to claim 1, which is characterized in that extract the segmentation carbon brush surface
The characteristic quantity of the characteristic quantity of image includes: abrasion length, wearing depth and wear area.
7. a kind of carbon brush abrasion detection device, which is characterized in that described device includes: LED light source (1), optical system (2), send
Material system (3), image capture module (4) and image processing module (5), the optical system (2) respectively with the LED light source
(1) it is electrically connected with described image acquisition module (4) electrical connection, the data acquisition module (4) with described image processing module (5)
It connects；
The LED light source (1) is illuminated for treating carbon determination brush；
The optical system (2) is for detecting whether there are carbon brush to be measured, and control the LED light source (1) and Image Acquisition mould
The unlatching of block (4)；
The feed system (3) is for conveying carbon brush to be measured；
Described image acquisition module (4) is for obtaining carbon brush surface image；
Described image processing module (5) analyzes carbon brush abrasion amount for handling the carbon brush surface image.
8. a kind of carbon brush abrasion detection device according to claim 7, which is characterized in that described image processing module (5)
It is also electrically connected with sorting unit (6), the sorting unit (6) judges the carbon brush abrasion for receiving the carbon brush abrasion amount
Whether amount exceeds preset threshold, and sorts carbon brush according to judging result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811344674.8A CN109596621A (en) | 2018-11-13 | 2018-11-13 | A kind of carbon brush abrasion detection method and detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811344674.8A CN109596621A (en) | 2018-11-13 | 2018-11-13 | A kind of carbon brush abrasion detection method and detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109596621A true CN109596621A (en) | 2019-04-09 |
Family
ID=65958650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811344674.8A Pending CN109596621A (en) | 2018-11-13 | 2018-11-13 | A kind of carbon brush abrasion detection method and detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109596621A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111855796A (en) * | 2020-09-04 | 2020-10-30 | 浙江城建煤气热电设计院有限公司 | Contact surface detection device and method for electric energy conduction of rotating equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204679607U (en) * | 2015-06-24 | 2015-09-30 | 重庆交通大学 | Generator carbon brush condition monitoring system |
| CN105158268A (en) * | 2015-09-21 | 2015-12-16 | 武汉理工大学 | Intelligent online detection method, system and device for defects of fine-blanked parts |
| CN103837097B (en) * | 2012-11-23 | 2016-12-21 | 上海久点触控计算机***股份有限公司 | A kind of workpiece angle self-operated measuring unit based on image procossing and measuring method |
| CN107328342A (en) * | 2017-08-16 | 2017-11-07 | 国家电网公司 | A kind of online square carbon brush abrasion detection means |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
-
2018
- 2018-11-13 CN CN201811344674.8A patent/CN109596621A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103837097B (en) * | 2012-11-23 | 2016-12-21 | 上海久点触控计算机***股份有限公司 | A kind of workpiece angle self-operated measuring unit based on image procossing and measuring method |
| CN204679607U (en) * | 2015-06-24 | 2015-09-30 | 重庆交通大学 | Generator carbon brush condition monitoring system |
| CN105158268A (en) * | 2015-09-21 | 2015-12-16 | 武汉理工大学 | Intelligent online detection method, system and device for defects of fine-blanked parts |
| CN107328342A (en) * | 2017-08-16 | 2017-11-07 | 国家电网公司 | A kind of online square carbon brush abrasion detection means |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
Non-Patent Citations (1)
| Title |
|---|
| 张智勇 等: "《2004版ISO14001标准理解及其在一体化管理体系中的应用》", 31 August 2005, 中国计量出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111855796A (en) * | 2020-09-04 | 2020-10-30 | 浙江城建煤气热电设计院有限公司 | Contact surface detection device and method for electric energy conduction of rotating equipment |
| CN111855796B (en) * | 2020-09-04 | 2023-08-25 | 浙江城建煤气热电设计院股份有限公司 | Contact surface detection device and method for electric energy conduction of rotating equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934802B (en) | Cloth defect detection method based on Fourier transform and image morphology | |
| CN109490316B (en) | Surface defect detection algorithm based on machine vision | |
| CN106053479B (en) | A kind of vision detection system of the workpiece appearance defects based on image procossing | |
| CN109668909A (en) | A kind of glass defect detection method | |
| Liming et al. | Automated strawberry grading system based on image processing | |
| CN115082683A (en) | Injection molding defect detection method based on image processing | |
| CN113781486B (en) | IC card image defect detection method | |
| CN113109348B (en) | Paddle image transfer printing defect identification method based on machine vision | |
| CN110111303A (en) | A kind of large-scale carrier strip tearing intelligent fault detection method based on dynamic image | |
| CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| Samarawickrama et al. | Matlab based automated surface defect detection system for ceremic tiles using image processing | |
| CN110403232A (en) | A kind of cigarette quality detection method based on second level algorithm | |
| CN110096980A (en) | Character machining identifying system | |
| CN108389216A (en) | Local auto-adaptive threshold segmentation method towards on-line ferrograph image wear Particles Recognition | |
| CN109239073A (en) | A kind of detection method of surface flaw for body of a motor car | |
| CN111487192A (en) | Machine vision surface defect detection device and method based on artificial intelligence | |
| CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
| CN115063407A (en) | Scratch and crack identification method for annular copper gasket | |
| CN110060239B (en) | Defect detection method for bottle opening of bottle | |
| CN109596621A (en) | A kind of carbon brush abrasion detection method and detection device | |
| Wu et al. | Fast processing of foreign fiber images by image blocking | |
| CN114155226A (en) | Micro defect edge calculation method | |
| Lin et al. | Defect detection system for optical element surface based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |