CN116823790A - Method for detecting pollution defect of solar cell - Google Patents
Method for detecting pollution defect of solar cell Download PDFInfo
- Publication number
- CN116823790A CN116823790A CN202310829428.6A CN202310829428A CN116823790A CN 116823790 A CN116823790 A CN 116823790A CN 202310829428 A CN202310829428 A CN 202310829428A CN 116823790 A CN116823790 A CN 116823790A
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- function
- defect
- solar cell
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000007619 statistical method Methods 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 64
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000002503 electroluminescence detection Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000011109 contamination Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 5
- 238000010248 power generation Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003860 storage 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
- G01N21/94—Investigating contamination, e.g. dust
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for detecting pollution defects of solar cells, which comprises the steps of carrying out statistical analysis on gray distribution of an image after grid lines are removed, traversing each pixel of the image, counting the number of pixels under each pixel value within a range of 0-255, wherein the number of pixels with gray values below 100 corresponds to the area of the pollution or cold joint dark defects, and when more than 6% of the total number of pixels is selected, the defect detection is carried out by utilizing the statistical method, the robustness is strong, and the detection speed is also higher.
Description
Technical Field
The invention relates to the technical field of pollution defect detection, in particular to a method for detecting pollution defects of solar cells.
Background
The solar cell is a core component of a solar photovoltaic power generation system, and the quality of the solar cell directly influences the power generation efficiency and the service life of the photovoltaic power generation system. In the production process of solar cells, cell pollution is a common defect, which can lead to reduced power generation efficiency of the cells and even to failure of the cells when serious. Therefore, the detection of the defects of the solar cell becomes an important link in the production process of the solar cell.
However, in the production process of solar cells, cell contamination defects are a common problem. At present, the prior art in the aspect of battery piece pollution detection generally uses a traditional algorithm, the robustness is not strong, and the detection speed is relatively slow.
Disclosure of Invention
Aiming at the situation, in order to overcome the defects of the prior art, the invention aims to provide a method for detecting the pollution defects of the solar cell, which utilizes a statistical method to detect the defects, has strong robustness and has higher detection speed.
The technical scheme is that the method for detecting the pollution defect of the solar cell comprises the following steps of S1, converting an EL detection diagram of the solar cell into a two-dimensional matrix;
s2, processing a two-dimensional matrix through a singular value decomposition method, wherein the SVD function in the OpenCv library is used for decomposition, parameters of the SVD function comprise a matrix U to be decomposed, an output matrix V and a singular value matrix W, a diagonal matrix sigma is obtained, elements on the diagonal are singular values, the singular values are arranged from large to small according to the size, the first singular value is largest, and the last singular value is smallest.
S3, taking out 10 singular values, and setting other singular values to 0 to obtain a new singular value matrix W';
s4, reconstructing an original matrix by using a new singular value matrix W', a decomposed matrix U and a transposed matrix Vt of a matrix V to obtain a new image, and obtaining a binarization map only retaining a main grid by using a local self-adaptive binarization operation of opencv;
and S5, performing morphological operation on the battery piece in the horizontal and vertical directions of the binarization graph, and eliminating the grid lines in the image to obtain the image with the grid lines removed.
S6, carrying out statistical analysis on the gray scale distribution of the image after removing the grid lines, traversing each pixel of the image, counting the number of pixels under each pixel value within the range of 0-255, wherein the number of pixels with the gray scale value below 100 is the area of the dirty or cold joint type dark color defect, and when more than 6% of the total number of pixels is selected, indicating that the dirty or cold joint type block defect exists in the battery piece.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages;
1. the defect detection is performed by using a statistical method, so that the robustness is high, and the detection speed is high.
Drawings
Fig. 1 is an original image of a method for detecting a contamination defect of a solar cell according to the present invention.
Fig. 2 is a reconstructed image of a method for detecting a contamination defect of a solar cell according to the present invention.
Fig. 3 is a binary image of a method for detecting a contamination defect of a solar cell according to the present invention.
Fig. 4 is a gray scale image of a method for detecting a contamination defect of a solar cell according to the present invention.
Fig. 5 is an image of a solar cell after removing a grid line according to the method for detecting a contamination defect of the present invention.
Fig. 6 is a statistical analysis image of a method for detecting a pollution defect of a solar cell according to the present invention.
Fig. 7 is a step diagram of a binarized edge image profile of a method for detecting a contamination defect of a solar cell according to the present invention.
Detailed Description
The foregoing and other features, aspects and advantages of the present invention will become more apparent from the following detailed description of the embodiments with reference to the accompanying drawings, 1-7. The following embodiments are described in detail with reference to the drawings.
In the first embodiment, a method for detecting a pollution defect of a solar cell, S1, converts an EL detection map of the solar cell into a two-dimensional matrix;
s2, processing a two-dimensional matrix through a singular value decomposition method, and decomposing by using a cv: SVD function in an OpenCv library, wherein parameters comprise a matrix U to be decomposed, an output matrix V and a singular value matrix W to obtain a diagonal matrix sigma, elements on the diagonal are singular values, the singular values are arranged from large to small according to the size, the first singular value is the largest, and the last singular value is the smallest, so that the singular values can be distinguished through the size of the singular values. In image processing, typically only the first few singular values are retained, the size of which directly affects the reconstructed image quality. Generally, when the number of the retained singular values is large, the image quality after reconstruction is high, but the calculation amount is also large.
Therefore, the singular values are not only used for distinguishing different singular values, but also affect the quality of the reconstructed image after the SVD decomposition, and it is necessary to select which singular values are reserved according to a specific application scene. Singular value decomposition (Singular Value Decomposition, SVD for short) of an image is a mathematical technique that can be used to decompose an image matrix into the product of three matrices, namely: a=uΣvζ where a is the matrix of the original image, U is one orthogonal matrix, Σ is one diagonal matrix, and V is the other orthogonal matrix. U and V are referred to as left singular vector matrices, Σ containing singular values. The singular value is a real number representing the length in space of the row or column vector of the a matrix, which is arranged in order from large to small. Through singular values, important information and structures of the image can be known. SVD is commonly used for image compression and dimension reduction. In image compression, SVD may be used to preserve the largest singular values and corresponding vectors to restore the image, thereby reducing the space required for image storage. In dimension reduction, SVD can be used to reduce the dimension of the image matrix, thereby improving the computational efficiency. In Singular Value Decomposition (SVD) of the EL detection map, for the pixel matrix a of the image, the SVD decomposition thereof yields three matrices: u, W and Vt (transpose of V), where U and Vt are orthogonal matrices and W is a diagonal matrix. The three matrices represent the eigenvectors, singular values, and transposes of the eigenvectors, respectively, of the original matrix. Specifically, the U matrix is an orthogonal matrix composed of left singular vectors of the original matrix a, where each column represents the coordinates of the original matrix in a new coordinate system. The Vt matrix is a transpose of the orthogonal matrix consisting of the right singular vectors of the original matrix a, each row of which also represents the coordinates of the original matrix in a new coordinate system. The W matrix is a diagonal matrix, and elements on the diagonal are singular values of the original matrix, and the singular values are arranged in order from large to small. In practical applications, we will choose a certain number of main components according to the magnitude of the singular value, and set the smaller singular value in the W matrix to 0, so as to obtain a truncated W' matrix. Then the U matrix, the W' matrix and the Vt matrix are multiplied to obtain a new matrix which is used to approximate the original matrix A. Thus, the tasks such as image compression, denoising, feature extraction and the like can be realized.
S3, taking out 10 singular values, and setting other singular values to 0 to obtain a new singular value matrix W';
s4, reconstructing an original matrix by using a new singular value matrix W', a decomposed matrix U and a transposed matrix Vt of a matrix V to obtain a new image, and obtaining a binarization chart only retaining the main grid by using the local self-adaptive binarization operation of opencv, wherein the ordinate of a 255-region gray value in the binarization chart is calculated, so that the ordinate of all the main grids in the battery piece can be determined;
and S5, performing morphological operation on the battery piece in the horizontal and vertical directions of the binarization graph, and eliminating the grid lines in the image to obtain the image with the grid lines removed.
S6, carrying out statistical analysis on the gray scale distribution of the image after removing the grid lines, traversing each pixel of the image, counting the number of pixels under each pixel value within the range of 0-255, wherein the number of pixels with the gray scale value below 100 is the area of the dirty or cold joint type dark color defect, and when more than 6% of the total number of pixels is selected, indicating that the dirty or cold joint type block defect exists in the battery piece.
Step S5, the specific steps of eliminating the grid lines in the image are as follows;
a, reading a binarization map and converting the binarization map into a gray image by using a cvtColor function;
b, performing Gaussian blur processing on the gray level image by using a Gaussian Blur function;
c, binarizing the image by using a threshold function to obtain a binary image, and performing adaptive thresholding by using a THRESH_OTSU mark in the step;
d, using a getstructureelement function to create two structural elements, one for processing horizontal lines and one for processing vertical lines;
e, performing morphological processing on the binary image by using an error function and a dialite function to remove horizontal and vertical lines;
f, displaying the image after removing the grid lines.
In the second embodiment, the EL detection image of the solar cell is subjected to downsampling, upsampling and gaussian blur for a plurality of times, so that only dark defect areas are reserved in the image, the gray level image is subjected to filtering processing to reduce noise, and gaussian blur is performed by using a gaussian blue function, wherein downsampling refers to reducing the original image, namely generating a thumbnail of a corresponding image, and upsampling refers to amplifying the image, so that the image can be displayed on a display device with higher resolution;
removing the main grid by morphological operation, enhancing the contrast of the image, and performing binarization treatment; contours in the binarized edge image are found using a findContours function. After determining the outline, judging whether the battery piece is symmetrical along the main grid, if not, indicating that the battery piece has dirt or cold joint type block defects.
While the invention has been described in connection with certain embodiments, it is not intended that the invention be limited thereto; for those skilled in the art to which the present invention pertains and the related art, on the premise of based on the technical scheme of the present invention, the expansion, the operation method and the data replacement should all fall within the protection scope of the present invention.
Claims (3)
1. A method for detecting pollution defects of solar cells is characterized in that S1, an EL detection diagram of the solar cells is converted into a two-dimensional matrix;
s2, processing a two-dimensional matrix through a singular value decomposition method, wherein the SVD function in the OpenCv library is used for decomposition, parameters of the SVD function comprise a matrix U to be decomposed, an output matrix V and a singular value matrix W to obtain a diagonal matrix sigma, elements on the diagonal are singular values, the singular values are arranged from large to small according to the size, the first singular value is the largest, and the last singular value is the smallest;
s3, taking out 10 singular values, and setting other singular values to 0 to obtain a new singular value matrix W';
s4, reconstructing an original matrix by using a new singular value matrix W', a decomposed matrix U and a transposed matrix Vt of a matrix V to obtain a new image, and obtaining a binarization map only retaining a main grid by using a local self-adaptive binarization operation of opencv;
s5, performing morphological operation on the battery piece in the horizontal and vertical directions of the binarization graph, eliminating grid lines in the image, and obtaining the image with the grid lines removed;
s6, carrying out statistical analysis on the gray scale distribution of the image after removing the grid lines, traversing each pixel of the image, counting the number of pixels under each pixel value within the range of 0-255, wherein the number of pixels with the gray scale value below 100 is the area of the dirty or cold joint type dark color defect, and when more than 6% of the total number of pixels is selected, indicating that the dirty or cold joint type block defect exists in the battery piece.
2. The method for detecting the pollution defect of the solar cell according to claim 1, wherein the step S5 of eliminating the grid line in the image comprises the following steps of;
a, reading a binarization map and converting the binarization map into a gray image by using a cvtColor function;
b, performing Gaussian blur processing on the gray level image by using a Gaussian Blur function;
c, binarizing the image by using a threshold function to obtain a binary image;
d, using a getstructureelement function to create two structural elements, one for processing horizontal lines and one for processing vertical lines;
e, performing morphological processing on the binary image by using an error function and a dialite function to remove horizontal and vertical lines;
f, displaying the image after removing the grid lines.
3. The method for detecting the pollution defect of the solar cell according to claim 1, further comprising the steps of firstly performing downsampling, upsampling and Gaussian blur operations on an EL detection image of the solar cell for a plurality of times, so that only dark defect areas are reserved in the image, performing filtering processing on a gray level image to reduce noise through filtering processing, and then performing Gaussian blur by using a Gaussian Blur function, wherein downsampling refers to reducing the original image, namely generating a thumbnail of a corresponding image, and upsampling refers to amplifying the image, so that the image can be displayed on a display device with higher resolution;
removing the main grid by morphological operation, enhancing the contrast of the image, and performing binarization treatment; contours in the binarized edge image are found using a findContours function. After determining the outline, judging whether the battery piece is symmetrical along the main grid, if not, indicating that the battery piece has dirt or cold joint type block defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310829428.6A CN116823790A (en) | 2023-07-07 | 2023-07-07 | Method for detecting pollution defect of solar cell |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310829428.6A CN116823790A (en) | 2023-07-07 | 2023-07-07 | Method for detecting pollution defect of solar cell |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116823790A true CN116823790A (en) | 2023-09-29 |
Family
ID=88120111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310829428.6A Pending CN116823790A (en) | 2023-07-07 | 2023-07-07 | Method for detecting pollution defect of solar cell |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823790A (en) |
-
2023
- 2023-07-07 CN CN202310829428.6A patent/CN116823790A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022170706A1 (en) | Defect detection method and apparatus for mold monitoring, and device and medium | |
| CN114937055A (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN110346699B (en) | Insulator discharge information extraction method and device based on ultraviolet image processing technology | |
| CN113837991B (en) | Image processing method, device, equipment and storage medium | |
| CN112508090A (en) | External package defect detection method | |
| CN111680690A (en) | Character recognition method and device | |
| CN114495098B (en) | Diaxing algae cell statistical method and system based on microscope image | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN111476758A (en) | Defect detection method and device for AMO L ED display screen, computer equipment and storage medium | |
| CN114463280A (en) | Chip surface defect parallel detection method based on improved convolution variational self-encoder | |
| CN110889374A (en) | Seal image processing method and device, computer and storage medium | |
| CN113505622A (en) | Test system and method for automatically identifying multiple bar codes and LED lamps | |
| CN114792310A (en) | Mura defect detection method for edge blurring in LCD screen | |
| CN103106663B (en) | Realize the method for SIM card defects detection based on image procossing in computer system | |
| CN112561949A (en) | Fast moving target detection algorithm based on RPCA and support vector machine | |
| CN116823790A (en) | Method for detecting pollution defect of solar cell | |
| CN111611783A (en) | Positioning and dividing method and device for graphic table | |
| CN116823775A (en) | Display screen defect detection method based on deep learning | |
| CN116071307A (en) | Pavement defect detection model building method, detection method, storage medium and equipment | |
| CN115661156A (en) | Image generation method, image generation device, storage medium, equipment and computer program product | |
| CN115619796A (en) | Method and device for obtaining photovoltaic module template and nonvolatile storage medium | |
| CN114820379A (en) | Image rain layer removing method for generating countermeasure network based on attention dual residual error | |
| CN110570437B (en) | Electric power channel automatic inspection data processing method based on boundary identification | |
| CN114359414A (en) | Lens smudge identification method and device, computer equipment and storage medium |
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 |