CN107764829A - Solar cell open defect recognition methods - Google Patents
Solar cell open defect recognition methods Download PDFInfo
- Publication number
- CN107764829A CN107764829A CN201610669889.1A CN201610669889A CN107764829A CN 107764829 A CN107764829 A CN 107764829A CN 201610669889 A CN201610669889 A CN 201610669889A CN 107764829 A CN107764829 A CN 107764829A
- Authority
- CN
- China
- Prior art keywords
- solar cell
- image
- cell piece
- open defect
- defects
- 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
-
- 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
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)
- Photovoltaic Devices (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of solar cell open defect recognition methods, by gathering the sample image of solar cell piece and the pretreatment such as distortion correction, rotation, cutting being carried out to image, then edge detection algorithm is passed through, obtain the edge feature of cell piece, according to whether the shape of feature and location determination jagged, whether chipping and cell piece surface have the defects of slurry contamination, then judge whether battery has the defects of disconnected grid by line detection method.The inventive method is based on the principles such as NI Vision Builder for Automated Inspection, image procossing and signature analysis, substitutes manual identified method, realizes the open defect sorting of intelligent solar cell piece, is advantageous to improve the presentation quality of product, reduces cost of labor.
Description
Technical field
The present invention relates to photovoltaic technology, more particularly to a kind of solar cell open defect recognition methods.
Background technology
In process of production, for various reasons, its surface can produce some apparent defects to solar cell piece, these
Defect is very big for apparent influence, influences whether the conversion efficiency of battery what is more, hides some dangers for, it is therefore desirable in battery
Piece produces the later stage or component package early stage sorts to the open defect of cell piece.At present generally using artificial range estimation in industry
Mode solar cell piece open defect is identified, cost of labor is high, low production efficiency, and can produce visual fatigue so as to
Influence recognition effect.Therefore, there is an urgent need to a kind of quick, accurately and efficiently solar cell piece outward appearance for cell piece production enterprise
Defect identification method, to improve production efficiency, reduce production cost.
The content of the invention
The purpose of the present invention, being to overcome in the presence of prior art needs manual identified solar cell piece open defect
Deficiency, there is provided a kind of solar cell open defect recognition methods.
In order to achieve the above object, present invention employs following technical scheme：
A kind of solar cell open defect recognition methods, comprises the following steps：
Step 1, captured image correction template image；
Step 2, the binary image for gathering solar cell piece；
Step 3, the solar cell picture for having barrel-shaped distortion is corrected by image rectification template image, by battery picture
In curve deformation be corrected to straight line；
Step 4, by Karhunen-Loeve transformation by image rotation for just；
Step 5, the solar cell picture progress edge extracting using Boundary extracting algorithm to collection, split from image
Go out the only image containing cell piece；
Step 6, by edge detection algorithm, the edge feature of cell piece is obtained, according to the shape and location determination of feature
Whether cell piece is jagged, chipping or the defects of slurry contamination；
Step 7, by line detection method judge whether cell piece has the defects of disconnected grid.
Described image rectification template has the chessboard grid pattern being made up of multiple lattice proper alignments, each lattice
Filled respectively with black or white, and it is chequered with black and white, grid is closeer, and correction accuracy is higher.
Described edge detection algorithm, detect there are the target edges of color change in cell piece binary image, pass through
The shape at these edges is for example U-shaped or V-type, and these edges where position such as battery edge or battery surface, so that it is determined that
The defects of whether jagged, chipping or slurry contamination.
Compared with prior art, the beneficial effects of the invention are as follows：Using image-recognizing method, to including solar cell piece
Binary image successively carries out the processing such as distortion correction, rotation, cutting, rim detection, straight-line detection and analysis, special according to edge
The defects of whether shape and location determination of sign are jagged, chipping and surface size pollute, and according to the quantity for detecting straight line
To judge whether battery has the defects of disconnected grid.The identification of solar cell piece open defect is carried out using the inventive method, it is only necessary to
Input the binary image for including solar cell piece of collection, you can breach, chipping, slurry are carried out to the solar cell piece in image
The identification of the defects of material pollution, disconnected grid, without manually being sorted by observing blocks of solar cell piece, realizes intellectuality
Open defect identifies, greatly improves the recognition efficiency of open defect, reduces workload, reduces cost of labor.
Brief description of the drawings
Fig. 1 is the flow chart of solar cell open defect recognition methods of the present invention.
Embodiment
With reference to test example and embodiment, the present invention is described in further detail.But this should not be understood
Following embodiment is only limitted to for the scope of the above-mentioned theme of the present invention, it is all that this is belonged to based on the technology that present invention is realized
The scope of invention.
Referring to Fig. 1, solar cell open defect recognition methods provided by the invention, comprise the following steps：
Step 1：The image of captured image correction template is used for image rectification.
Step 2：The binary image of solar cell piece is gathered, and cell piece can be distinguished substantially with background in image.
Step 3：The image for the solar cell piece for having barrel-shaped distortion is corrected by the image of image rectification template, by battery
Curve deformation in piece is corrected to straight line.
Step 4：By Karhunen-Loeve transformation by image rotation for just.
Step 5：Edge extracting is carried out to the solar cell picture of collection using Boundary extracting algorithm, split from image
Go out the only image containing cell piece.
Step 6：By edge detection algorithm, the edge feature of cell piece is obtained, according to the shape and location determination of feature
Whether whether jagged, chipping and cell piece surface have the defects of slurry contamination.
In this step, described edge detection algorithm, it is capable of detecting when there be pair of color change in cell piece bianry image
As edge, pass through position such as battery edge or battery table of the shape at these edges as where U-shaped or V-type and these edges
Face, the defects of so as to determine whether jagged, chipping or slurry contamination.
Step 7：Judge whether battery has the defects of disconnected grid by line detection method.
Claims (3)
1. a kind of solar cell open defect recognition methods, it is characterised in that comprise the following steps：
Step 1, captured image correction template image；
Step 2, the binary image for gathering solar cell piece；
Step 3, the solar cell picture for having barrel-shaped distortion is corrected by image rectification template image, by battery picture
Curve deformation is corrected to straight line；
Step 4, by Karhunen-Loeve transformation by image rotation for just；
Step 5, the solar cell picture progress edge extracting using Boundary extracting algorithm to collection, are partitioned into only from image
Image containing cell piece；
Step 6, by edge detection algorithm, the edge feature of cell piece is obtained, according to the shape of feature and location determination battery
Whether piece is jagged, chipping or the defects of slurry contamination；
Step 7, by line detection method judge whether cell piece has the defects of disconnected grid.
2. solar cell open defect recognition methods as claimed in claim 1, it is characterised in that described image rectification template tool
By the chessboard grid pattern being made up of multiple lattice proper alignments, each lattice is filled with black or white respectively, and black and white
Alternate, grid is closeer, and correction accuracy is higher.
3. solar cell open defect recognition methods as claimed in claim 1, it is characterised in that described rim detection is calculated
Method, detect there are the target edges of color change in cell piece binary image, by the way that the shape at these edges is for example U-shaped or V-type,
And the position where these edges such as battery edge or battery surface, determine whether jagged, chipping or slurry contamination
The defects of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610669889.1A CN107764829A (en) | 2016-08-15 | 2016-08-15 | Solar cell open defect recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610669889.1A CN107764829A (en) | 2016-08-15 | 2016-08-15 | Solar cell open defect recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107764829A true CN107764829A (en) | 2018-03-06 |
Family
ID=61260902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610669889.1A Pending CN107764829A (en) | 2016-08-15 | 2016-08-15 | Solar cell open defect recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107764829A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111229648A (en) * | 2020-01-19 | 2020-06-05 | 青岛滨海学院 | Solar cell panel flaw detection system and detection method based on machine vision |
| CN118279887A (en) * | 2024-05-27 | 2024-07-02 | 佛山隆深机器人有限公司 | Retired battery sorting method and system applied to battery disassembly production line |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830002A (en) * | 2003-07-28 | 2006-09-06 | 奥林巴斯株式会社 | Image processing apparatus, image processing method, and distortion correcting method |
| CN102519365A (en) * | 2011-12-06 | 2012-06-27 | 桂林电子科技大学 | Detector of properties of gate line of solar cell piece |
| CN103033517A (en) * | 2011-07-15 | 2013-04-10 | 株式会社Npc | Defect inspection device for solar cells and inspection method |
| CN103116878A (en) * | 2013-02-25 | 2013-05-22 | 徐渊 | Method and device for correcting image barrel distortion and image processing device |
| CN103489254A (en) * | 2012-06-11 | 2014-01-01 | 深圳信息职业技术学院 | Lottery recognition method and lottery recognition system |
| CN103872983A (en) * | 2014-04-04 | 2014-06-18 | 天津市鑫鼎源科技发展有限公司 | Device and method for detecting defects on surface of solar cell |
| CN104713883A (en) * | 2013-12-11 | 2015-06-17 | 上海空间电源研究所 | Rapid detection and automatic identification method for large-area space solar battery array defects |
-
2016
- 2016-08-15 CN CN201610669889.1A patent/CN107764829A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830002A (en) * | 2003-07-28 | 2006-09-06 | 奥林巴斯株式会社 | Image processing apparatus, image processing method, and distortion correcting method |
| CN103033517A (en) * | 2011-07-15 | 2013-04-10 | 株式会社Npc | Defect inspection device for solar cells and inspection method |
| CN102519365A (en) * | 2011-12-06 | 2012-06-27 | 桂林电子科技大学 | Detector of properties of gate line of solar cell piece |
| CN103489254A (en) * | 2012-06-11 | 2014-01-01 | 深圳信息职业技术学院 | Lottery recognition method and lottery recognition system |
| CN103116878A (en) * | 2013-02-25 | 2013-05-22 | 徐渊 | Method and device for correcting image barrel distortion and image processing device |
| CN104713883A (en) * | 2013-12-11 | 2015-06-17 | 上海空间电源研究所 | Rapid detection and automatic identification method for large-area space solar battery array defects |
| CN103872983A (en) * | 2014-04-04 | 2014-06-18 | 天津市鑫鼎源科技发展有限公司 | Device and method for detecting defects on surface of solar cell |
Non-Patent Citations (3)
| Title |
|---|
| 中华人民共和国工业信息化部: "《中华人民共和国电子行业标准 SJ/T 11631-2016 太阳能电池用硅片外观缺陷测试方法》", 5 April 2016 * |
| 李久芳: "基于标准棋盘格的图像校准方法", 《电子工业专用设备》 * |
| 黄远民 等: "基于Halcon的太阳能硅片缺陷检测", 《机械工程与技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111229648A (en) * | 2020-01-19 | 2020-06-05 | 青岛滨海学院 | Solar cell panel flaw detection system and detection method based on machine vision |
| CN118279887A (en) * | 2024-05-27 | 2024-07-02 | 佛山隆深机器人有限公司 | Retired battery sorting method and system applied to battery disassembly production line |
| CN118279887B (en) * | 2024-05-27 | 2024-08-27 | 佛山隆深机器人有限公司 | Retired battery sorting method and system applied to battery disassembly production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103831253B (en) | Solar silicon wafers surface detection apparatus based on DSP machine vision and method | |
| CN112465809B (en) | Mold defect detection method based on image recognition, computer readable storage medium and device | |
| CN107742286A (en) | A kind of polysilicon solar battery slice EL tests crack defect detection method | |
| CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN108230315B (en) | Mask belt loss detection method based on machine vision | |
| CN109767445B (en) | High-precision PCB defect intelligent detection method | |
| CN103868935A (en) | Cigarette appearance quality detection method based on computer vision | |
| CN102305798A (en) | Method for detecting and classifying glass defects based on machine vision | |
| CN105203543A (en) | Machine vision based whole case red grape fruit size grading device and method | |
| CN103226106A (en) | Machine vision based bearing dust cap quality monitoring system | |
| CN105157563A (en) | Beer bottleneck positioning method based on visual sense of machine | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN113627435B (en) | Defect detection and identification method and system for ceramic tile | |
| CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
| CN111260617A (en) | Solar cell panel defect detection method based on deep learning | |
| CN104952754A (en) | Coated silicon chip sorting method based on machine vision | |
| CN107764829A (en) | Solar cell open defect recognition methods | |
| CN112819844A (en) | Image edge detection method and device | |
| CN106323985B (en) | Solid wood board quality detection method combining computer vision with self-learning behavior | |
| Yang et al. | Wood veneer defect detection system based on machine vision | |
| CN103900499A (en) | Cigarette packing warning zone area measuring method based on computer visual technology | |
| CN117409005A (en) | Defective product detection system and method for plate receiving machine based on image | |
| CN103954627A (en) | Electronic component surface defect detection method based on sample library dictionary | |
| CN106370673A (en) | Automatic lens flaw 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180306 |
|
| RJ01 | Rejection of invention patent application after publication |