CN106057700B - A kind of detection method on red of the side of solar battery sheet - Google Patents
A kind of detection method on red of the side of solar battery sheet Download PDFInfo
- Publication number
- CN106057700B CN106057700B CN201610590513.1A CN201610590513A CN106057700B CN 106057700 B CN106057700 B CN 106057700B CN 201610590513 A CN201610590513 A CN 201610590513A CN 106057700 B CN106057700 B CN 106057700B
- Authority
- CN
- China
- Prior art keywords
- solar battery
- battery sheet
- red
- tone
- cell piece
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
- H01L22/10—Measuring as part of the manufacturing process
- H01L22/12—Measuring as part of the manufacturing process for structural parameters, e.g. thickness, line width, refractive index, temperature, warp, bond strength, defects, optical inspection, electrical measurement of structural dimensions, metallurgic measurement of diffusions
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Engineering (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of red detection methods in the side of solar battery sheet, and using Machine Vision Inspecting System, its step are as follows: acquiring solar battery sheet RGB image by the CCD camera of Machine Vision Inspecting System；Battery panel region is generated by backlight, cell piece grid line is extracted by the channel R；Two steps combine removal periphery and White lnterfere；Finally it is converted into HSV model；Using the detection method identified based on edge tone variance, the tone variance of solar battery sheet is calculated, when solar battery sheet fringe region tone variance
Description
Technical field
The present invention relates to a kind of red detection methods in the side of solar battery sheet, belong to photovoltaic technology field.
Background technique
Currently, the whole world faces serious fossil energy crisis and environmental crisis, solar energy is as a kind of clean, pollution-free and most
Natural energy resources abundant, have been widely used.However, the production technology of solar battery sheet is more complex, cause to produce
The cell piece come is inevitably generated colour deficient problem, such as red of side, grey piece etc..Inspection for cell piece colour deficient
It surveys, most of by the way of artificial detection, personnel's fatiguability after a long time, and each personnel's test stone is inconsistent, meeting
It causes cell piece to mix shelves, while cell piece can be polluted.In a practical situation, the appearance color defect of cell piece, not only will affect
Photovoltaic module presentation quality and service life, and photoelectric conversion efficiency can be reduced.
Summary of the invention
To solve the above-mentioned problems, the present invention provides a kind of detection method on red of the side of solar battery sheet, this hairs
Bright technology contents are as follows:
A kind of detection method on red of the side of solar battery sheet, using Machine Vision Inspecting System, its step are as follows:
(1), solar battery sheet RGB image is acquired by the CCD camera of Machine Vision Inspecting System；
(2), battery panel region is generated by backlight；
(3), cell piece grid line is extracted by the channel R；
(4), step (2) and step (3) combine removal periphery and White lnterfere；
(5), finally it is converted into HSV model, it is containing there are three vector value in the HSV model, i.e. tone H, saturation degree S, bright
Spend V；
(6), using the detection method identified based on edge tone variance, the variance of the tone H of solar battery sheet is calculated,
As the variance > 8 of solar battery sheet fringe region tone H, determine that this piece cell piece edge color is uneven, is red of side.
The method of removal periphery and White lnterfere is as follows in above-mentioned steps (4):
Solar battery sheet RGB image is collected by step (1), the cell piece grid line that step (3) is extracted, with being based on
Periphery and White lnterfere are split removal by the dividing method of threshold value, since amount of image information is larger, therefore from collected figure
Target area is directly acquired as in, and sets periphery and White lnterfere threshold value T value, and divide the image into greater than T pixel by T value
Group is with less than T pixel group, and thresholding input picture F (i, j) is to output image G (x, y) such as down conversion:
The periphery in image is divided away with White lnterfere thus, and excludes its interference to detection.
The method that HSV model is converted into above-mentioned steps (5) is as follows:
R, G, B value of solar battery sheet RGB image are converted into tone H in hsv color model, full by following formula
With degree S, brightness V:
In hsv color model, it is assumed that have N number of pixel, each pixel in one piece of solar battery sheet solid images
Tone H be defined as H (Nn), n=1,2,3 ... N, the Mean Value Formulas of this component of tone H are as follows:
The formula that the variance of tone H is calculated in above-mentioned steps (6) is as follows:
Advantageous effects of the invention:
The present invention utilizes NI Vision Builder for Automated Inspection, using the detection method based on image mean value and variance to solar battery sheet
Red of side sorted, replace traditional artificial detection mode, effectively improve cell piece presentation quality, it is strong to reduce manual work
Degree reduces manual operation fragment rate, reduces artificially to the pollution of cell piece, improves productivity.
Specific embodiment
The present invention will be further described below with reference to examples.Following embodiment is only used for clearly illustrating this hair
Bright technical solution, and not intended to limit the protection scope of the present invention.
A kind of detection method on red of the side of solar battery sheet, using Machine Vision Inspecting System, its step are as follows:
(1), solar battery sheet RGB image is acquired by the CCD camera of Machine Vision Inspecting System；
(2), battery panel region is generated by backlight；
(3), cell piece grid line is extracted by the channel R；
(4), step (2) and step (3) combine removal periphery and White lnterfere；
(5), finally it is converted into HSV model, it is containing there are three vector value in the HSV model, i.e. tone H, saturation degree S, bright
Spend V；
(6), using the detection method identified based on edge tone variance, the variance of the tone H of solar battery sheet is calculated,
As the variance > 8 of solar battery sheet fringe region tone H, determine that this piece cell piece edge color is uneven, is red of side.
The method of removal periphery and White lnterfere is as follows in above-mentioned steps (4):
Solar battery sheet RGB image is collected by step (1), the cell piece grid line that step (3) is extracted, with being based on
Periphery and White lnterfere are split removal by the dividing method of threshold value, since amount of image information is larger, therefore from collected figure
Target area is directly acquired as in, and sets periphery and White lnterfere threshold value T value, and divide the image into greater than T pixel by T value
Group is with less than T pixel group, and thresholding input picture F (i, j) is to output image G (x, y) such as down conversion:
The periphery in image is divided away with White lnterfere thus, and excludes its interference to detection.
The method that HSV model is converted into above-mentioned steps (5) is as follows:
R, G, B value of solar battery sheet RGB image are converted into tone H in hsv color model, full by following formula
With degree S, brightness V:
In hsv color model, it is assumed that have N number of pixel, each pixel in one piece of solar battery sheet solid images
Tone H be defined as H (Nn), n=1,2,3 ... N, the Mean Value Formulas of this component of tone H are as follows:
The formula that the variance of tone H is calculated in above-mentioned steps (6) is as follows:
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (4)
1. a kind of detection method on red of the side of solar battery sheet, it is characterised in that utilize Machine Vision Inspecting System, step
It is rapid as follows:
(1), solar battery sheet RGB image is acquired by the CCD camera of Machine Vision Inspecting System；
(2), battery panel region is generated by backlight；
(3), cell piece grid line is extracted by the channel R；
(4), step (2) and step (3) combine removal periphery and White lnterfere；
(5), HSV model is finally converted into, containing there are three vector value, i.e. tone H, saturation degree S, brightness V in the HSV model；
(6), using the detection method identified based on edge tone variance, the variance of the tone H of solar battery sheet is calculated, when too
When the variance > 8 of positive energy cell piece fringe region tone H, determine that this piece cell piece edge color is uneven, is red of side.
2. a kind of detection method on red of the side of solar battery sheet according to claim 1, it is characterised in that: the step
Suddenly the method for removal periphery and White lnterfere is as follows in (4):
Solar battery sheet RGB image, the cell piece grid line that step (3) is extracted, with based on threshold value are collected by step (1)
Dividing method by periphery and White lnterfere be split removal, since amount of image information is larger, therefore from acquired image
Directly acquire target area, and set periphery and White lnterfere threshold value T value, and divided the image into greater than T pixel group by T value and
Less than T pixel group, thresholding input picture F (i, j) is to output image G (x, y) such as down conversion:
The periphery in image is divided away with White lnterfere thus, and excludes its interference to detection.
3. a kind of detection method on red of the side of solar battery sheet according to claim 1, it is characterised in that: the step
Suddenly the method that HSV model is converted into (5) is as follows:
R, G, B value of solar battery sheet RGB image are converted into tone H in hsv color model, saturation degree by following formula
S, brightness V:
In hsv color model, it is assumed that have N number of pixel, the color of each pixel in one piece of solar battery sheet solid images
H is adjusted to be defined as H (Nn), n=1,2,3 ... N, the Mean Value Formulas of this component of tone H are as follows:
4. a kind of detection method on red of the side of solar battery sheet according to claim 1, it is characterised in that: the step
Suddenly the formula that the variance of tone H is calculated in (6) is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610590513.1A CN106057700B (en) | 2016-07-25 | 2016-07-25 | A kind of detection method on red of the side of solar battery sheet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610590513.1A CN106057700B (en) | 2016-07-25 | 2016-07-25 | A kind of detection method on red of the side of solar battery sheet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106057700A CN106057700A (en) | 2016-10-26 |
| CN106057700B true CN106057700B (en) | 2018-12-21 |
Family
ID=57417001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610590513.1A Active CN106057700B (en) | 2016-07-25 | 2016-07-25 | A kind of detection method on red of the side of solar battery sheet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106057700B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106841211A (en) * | 2016-12-30 | 2017-06-13 | 镇江苏仪德科技有限公司 | Platform and method of a kind of utilization machine vision to cell piece surface defects detection |
| CN107478335B (en) * | 2017-08-08 | 2019-11-08 | 河海大学常州校区 | A kind of method of microdefect solar module hot spot temperature computation |
| CN107843600B (en) * | 2017-10-31 | 2021-01-08 | 河北工业大学 | Method for detecting appearance fingerprint defects of polycrystalline silicon solar cell |
| CN108376398B (en) * | 2018-02-05 | 2022-06-28 | 无锡奥特维科技股份有限公司 | Battery piece detection device and method |
| CN113112445A (en) * | 2020-01-09 | 2021-07-13 | 阿里巴巴集团控股有限公司 | Data processing method, device and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680102A (en) * | 2012-04-28 | 2012-09-19 | 江南大学 | Automatic detection method of solar silicon chip colors based on machine vision |
| CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
| CN203178203U (en) * | 2013-03-06 | 2013-09-04 | 江南大学 | Automatic solar silicon wafer color detection device based on machine vision |
| CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技（杭州）有限公司 | Battery piece chromatism selection control method based on color machine vision |
-
2016
- 2016-07-25 CN CN201610590513.1A patent/CN106057700B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680102A (en) * | 2012-04-28 | 2012-09-19 | 江南大学 | Automatic detection method of solar silicon chip colors based on machine vision |
| CN102974551A (en) * | 2012-11-26 | 2013-03-20 | 华南理工大学 | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy |
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
| CN203178203U (en) * | 2013-03-06 | 2013-09-04 | 江南大学 | Automatic solar silicon wafer color detection device based on machine vision |
| CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技（杭州）有限公司 | Battery piece chromatism selection control method based on color machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106057700A (en) | 2016-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106057700B (en) | A kind of detection method on red of the side of solar battery sheet | |
| WO2021248915A1 (en) | Color difference analysis/detection method and system for fair-faced concrete | |
| CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
| CN103063167B (en) | A kind of method of automatic decision laser cleaning effect | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN106384117B (en) | A kind of vehicle color identification method and device | |
| CN101882315B (en) | The detection method of area of skin color | |
| CN107346429A (en) | The color automatic identification and sorting technique of a kind of polycrystalline battery picture | |
| CN106096603A (en) | A kind of dynamic flame detection method merging multiple features and device | |
| CN108596903A (en) | A kind of defect inspection method of the black surround and fragment of solar battery sheet | |
| CN104166999B (en) | Cloud cluster extracting method based on strength layering of foundation cloud pictures | |
| CN103886565A (en) | Nighttime color image enhancement method based on purpose optimization and histogram equalization | |
| CN102608130A (en) | Smart card stain detecting system based on image feature matching technology and detection and detecting method | |
| CN103780845B (en) | Based on non-width dynamic high light suppressing method and device | |
| CN103302039B (en) | Solar battery wafer color separation method | |
| CN108960259A (en) | A kind of license plate preprocess method based on HSV | |
| CN104021527A (en) | Rain and snow removal method in image | |
| CN105223208A (en) | A kind of circuit board detecting template and preparation method thereof, circuit board detecting method | |
| CN112669306A (en) | Solar cell defect detection method and system based on saliency map | |
| CN104637425A (en) | Assembly-line LED (light emitting diode) display unit uniformity detection method, system and device | |
| CN106327463A (en) | Color identification method for solar cell | |
| CN106298568B (en) | A kind of detection method of the grey piece of solar battery sheet | |
| CN107742283A (en) | A kind of method of cell piece outward appearance grid line thickness inequality defects detection | |
| CN202059518U (en) | System for white balance correction by using color plate | |
| CN106295643A (en) | Automobile license plate automatic recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Bai Jianbo Inventor after: Tao Weidong Inventor after: Li Huafeng Inventor after: Wang Guangqing Inventor after: Chen Jianhao Inventor after: Zhang Zhen Inventor after: Liu Sheng Inventor before: Bai Jianbo Inventor before: Tao Weidong Inventor before: Li Huafeng Inventor before: Wang Guangqing Inventor before: Chen Jianhao Inventor before: Zhang Zhen Inventor before: Liu Sheng |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |