CN114636706A - Comprehensive method and device for image detection of solar cell after film coating - Google Patents
Comprehensive method and device for image detection of solar cell after film coating Download PDFInfo
- Publication number
- CN114636706A CN114636706A CN202210282767.2A CN202210282767A CN114636706A CN 114636706 A CN114636706 A CN 114636706A CN 202210282767 A CN202210282767 A CN 202210282767A CN 114636706 A CN114636706 A CN 114636706A
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- images
- defects
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000007888 film coating Substances 0.000 title claims abstract description 12
- 238000009501 film coating Methods 0.000 title claims abstract description 12
- 230000007547 defect Effects 0.000 claims abstract description 127
- 230000001815 facial effect Effects 0.000 claims abstract description 4
- 239000011248 coating agent Substances 0.000 claims description 14
- 238000000576 coating method Methods 0.000 claims description 14
- 238000005424 photoluminescence Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000000903 blocking effect Effects 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 4
- 238000007747 plating Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 206010027146 Melanoderma Diseases 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000241 photoluminescence detection Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007650 screen-printing Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
- G06T3/147—Transformations for image registration, e.g. adjusting or mapping for alignment of images using affine transformations
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Biology (AREA)
- Power Engineering (AREA)
- Signal Processing (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Textile Engineering (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a comprehensive method and a device for detecting images of solar cells after film coating, wherein products to be detected of the solar cells are horizontally conveyed into an image detection device for detection through a motion track 12 according to a horizontal motion direction 13, positioning judgment is carried out according to a camera comprehensive detection method, when a sensor a14 senses the products, a light source 3 is on, a linear array camera a5 starts to acquire images, a sensor b15 senses the products, a near-infrared laser 9 is on, a linear array camera b6 starts to acquire images, and the front-back interval of the solar cell products is larger than the distance between a5 and a linear array camera b6 for scanning facial lines. The invention combines the appearance defect detection and the internal defect detection, simultaneously collects the appearance image and the internal image of the product in the same set of equipment in terms of hardware, and the collection is carried out by adopting the line scanning camera, thereby greatly reducing the size of the equipment.
Description
Technical Field
The invention relates to the field of industrial visual inspection, in particular to a device and a method for detecting appearance defects, color classification and internal defects of a coated solar cell.
Background
In order to perform quality inspection on solar cell intermediate processes, particularly on solar cells coated before screen printing, defect inspection is generally performed after the process.
The conventional detection mode mainly aims at color sorting and surface dirt detection, and cannot detect internal product defects. Or a photoluminescence detection device is used to detect the internal defects separately, and the method may have more misjudgments. And the internal defect has the condition that the internal defect is repaired by a subsequent process, which can influence the judgment of the internal defect.
Disclosure of Invention
Based on the defects of the prior art, the invention provides a detection device and a detection method for detecting appearance defects, color classification and internal defects of a coated solar cell, and the detection device and the detection method are used for solving the problems that the detection items of the existing equipment are single and the misjudgment of the single equipment is more.
The technical scheme of the invention is as follows: a product to be detected of a solar cell is horizontally conveyed into an image detection device for detection through a motion track 12 according to a horizontal motion direction 13, positioning judgment is carried out according to a camera comprehensive detection method, when a sensor a14 senses the product, a light source 3 is lightened, a linear array camera a5 starts to collect images, a sensor b15 senses the product, a near infrared laser 9 is lightened, a linear array camera b6 starts to collect images, and the front-back interval of the solar cell product is larger than the distance between the linear array camera a5 and the linear array camera b6 for scanning facial lines.
Further, the image detection device comprises a solar cell, a light source 3, an infrared blocking lens 4, a line camera a5, a line camera b6, an infrared anti-reflection lens 7, a high-pass filter 8, a near-infrared laser 9, a sensor a14 and a sensor b 15;
the light source 3 and the near-infrared laser 9 are oppositely arranged at a certain inward included angle, the linear array camera a5 and the linear array camera b6 vertically downwards acquire images, an infrared cut-off lens 4 is arranged below a5, an infrared anti-reflection lens 7 is arranged below b6, a high-pass filter 8 is arranged at the bottom of the infrared anti-reflection lens 7 where the linear array camera b6 is located, the light source 3, the near-infrared laser 9, the linear array camera a5 and the linear array camera b6 are located above the motion track 12, and the sensor a14 and the sensor b15 are located below the motion track 12; the light source 3 and the line camera a5 are directed to the sensor a14 below, and the near infrared laser 9 and the line camera b6 are directed to the sensor b15 below;
further, the line camera b6 is an infrared camera, a phase scan camera with resolution typically 1024 × 1; the line camera a5 is a visible light camera with a resolution of typically 2048 x 3, 4096 x 3.
The invention discloses an image detection method of a solar cell after film coating, which comprises the following specific steps of:
step 1: the linear array camera a5 collects images, transmits the images to computer software for processing, firstly binds a special ID for the images, and finds out the positioning points of corners; the line camera b6 collects photoluminescence images, transmits the photoluminescence images to a computer for processing, firstly binds the same ID for the images, and finds out positioning points of corners;
step 2: carrying out secondary positioning on the image with abnormal positioning;
and step 3: carrying out appearance defect detection and color classification on images collected by the line array camera a5, and carrying out defect detection on photoluminescence images collected by the line array camera b 6;
and 4, step 4: calculating a coordinate transformation matrix between the two images through the positioning points;
and 5: and finally, comprehensively judging the defect areas detected in the two images, giving a detection result, and counting the process sections generated by the defects.
Further, the step 2 comprises the following steps:
step 2.1: judging whether positioning failure exists or not;
step 2.2: judging whether plating leakage exists or not: the method comprises the following steps that (1) battery piece inflow detection is carried out, wherein the battery piece with an uncoated surface is detected, a visible light camera image shows that the whole surface of the battery piece is overexposed, an infrared camera image shows that the whole surface is too dark, because the background of the visible light image is white and the background of the infrared image is black, the finding of an angular point is failed, and the product can be directly judged to be reworkable under the condition;
step 2.3: judging whether the black pieces and the concentric circles exist or not: the visible camera image is a normal image, the infrared camera image is a black film with an excessively dark whole surface, and the infrared camera image has the concentric circle defect of black concentric circles, so that the infrared image fails to find the corner point, and the product can be directly judged to be 'unrepairable';
step 2.4: judging whether the conditions of edge overexposure and dark corners exist: the condition that the edge overexposure can be caused to the product edge coating thickness inequality leads to the colour then to lead to the edge to overexpose in can seeing light camera image, has the condition of dark angle in the infrared camera image, and the angle is too dark promptly, and two kinds of circumstances all can lead to looking for the angular point failure or have the deviation, and this condition then needs fix a position as the angular point through looking for four sides and fitting straight line, with the crossing point of straight line.
Further, the step 4 comprises the following steps:
step 4.1: affine transformation of multi-point positioning is used between images of the linear array camera a5 and the linear array camera b6, sub-pixel coordinates of a plurality of corner points in four corners of the solar cell piece are searched, and the corner points in the two images are set to be corresponding IDs;
step 4.2: considering the factor of point finding failure, the angular points with the same ID need to be discarded at the same time, and the calculated points are all ensured to be corresponding points;
step 4.3: because there is a conversion error when the low pixel is converted to the high pixel, the coordinate conversion is performed by using a conversion matrix for converting the camera coordinate of the high pixel to the camera coordinate of the low pixel, and finally, the affine transformation matrix of the two images is calculated.
Further, the step 5 comprises the following steps:
step 5.1: the black sheets, the concentric circles and the cracks are irreparable defects and are unrepairable, and comprehensive judgment is not needed;
step 5.2: if the same position of the internal defect exists, the contrast, the area and the like of the internal defect need to be judged simultaneously whether to meet the threshold setting, and the classification is carried out by comprehensive judgment. If the same position does not have the defect, judging whether threshold setting is met or not and classifying;
step 5.3: the comprehensive algorithm needs to set three types of thresholds for judging three conditions, namely, the three conditions are that the appearance and the inside of the same position have defects, the appearance has defects and the inside has no defects, and the appearance has no defects and the inside has defects. The process section with the defects can be counted and counted according to the three conditions and the defect types; if the appearance and the interior have mechanical defects, the problem of the mechanical part of the film coating section can be counted to be serious; if the appearance has mechanical defects and the interior has no defects, the mechanical problem of the mechanical part of the coating section can be counted; if the appearance is free of defects and the interior has mechanical defects, judging the process section with problems according to the defect type and the defect position and counting; if the appearance and the interior have process defects, the serious abnormal coating can be counted; if the appearance has a technological defect and the interior has no defect, the film can be counted as a slight film coating technological defect; if the appearance is not defective and the interior has defects, the process section with problems can be judged according to the defect type.
The invention has the following technical effects:
the invention combines the appearance defect detection and the internal defect detection, simultaneously acquires the appearance image and the internal image of the product in the same set of equipment on the aspect of hardware, and the acquisition is carried out by adopting a line scanning camera, thus greatly reducing the size of the equipment.
In the aspect of software, the two images are subjected to coordinate correspondence, so that comprehensive judgment of defects is realized, the characteristic performance of one defect in two types of detection can be counted, the defects can be classified more finely, the misjudgment rate is reduced, and the detection accuracy is improved. And then can reduce the manufacturing cost of producing the line, reduce the use of silver thick liquid in the later process, further reduce the use of manpower resources.
Drawings
FIG. 1 is a schematic diagram of an apparatus according to the present invention;
FIG. 2 is a schematic flow chart of an image positioning and calibration module;
FIG. 3 is a schematic view of a defect comprehensive judgment module;
FIG. 4 is a schematic diagram of the overall flow of a defect detection algorithm;
FIG. 5 is a detailed flow chart of the judgment operator in the comprehensive judgment module.
1. Solar cell sheet a: product to be detected
2. Line light path
3. Light source: white line light source
4. An infrared blocking lens: in order that the visible light image is not affected by infrared light, a lens for blocking infrared light is used
5. Line array camera a
6. Line array camera b
7. An infrared anti-reflection lens: lens used for increasing light transmittance of near infrared part
8. A high-pass filter: is a near-infrared 950nm high-pass filter and a filter for blocking visible light
9. Near-infrared laser: the laser is a near infrared laser with the wavelength of 808nm, and the battery piece generates a photoluminescence effect by utilizing the irradiation of the laser so as to obtain a photoluminescence image;
10. laser light path
11. Solar cell b: inspecting the finished product
12. A motion track: product bearing rail
13. The moving direction is as follows: direction of movement of the product
14. A sensor a: triggering 5, 3 to start collecting image
15. A sensor b: triggering 6, 9 to start collecting image
Detailed Description
As shown in fig. 1, a solar cell a1 is conveyed into a detection mechanism for detection through a movement track 12 according to a horizontal movement direction 13, a sensor a14 senses a solar cell a1 product, a light source 3 lights up, a line camera a5 starts to collect images, a sensor b15 senses a solar cell b11 product, a near-infrared laser 9 lights up, a line camera b6 starts to collect images, and the distance between the front and back of the solar cell a1 and the solar cell b11 product is greater than the distance between the line camera a5 and the line camera b6 for sweeping facial lines.
As shown in fig. 2, the positioning module: a commonly used infrared camera, i.e. line camera b6, is a phase scan camera with a resolution of typically 1024 x 1. The resolution of the visible light camera, i.e. line camera a5, is typically 2048 x 3, 4096 x 3. The method comprises the steps of using multi-point positioning affine transformation between two camera imaging to search sub-pixel coordinates of a plurality of corner points in four corners of a solar cell, setting corresponding IDs (identification) for the corner points in two images, considering the factor of point finding failure, simultaneously discarding the corner points with the same IDs, ensuring that calculated points are all corresponding points, and finally calculating affine transformation matrixes of the two images. Since there is a conversion error in converting the low pixel to the high pixel, the coordinate conversion is performed using a conversion matrix in which the camera coordinate of the high pixel is converted to the camera coordinate of the low pixel. The special case of positioning is described below: 1. plating leakage: the method comprises the steps that battery pieces with uncoated surfaces flow in for detection, visible light camera images show that the whole surfaces of the battery pieces are overexposed, infrared camera images show that the whole surfaces are too dark, and because the background of the visible light images is white and the background of the infrared images is black, the finding of corner points fails, and the product can be directly judged to be reworkable under the condition. 2. Black patch and concentric circles: the visible camera image is a normal image, the infrared camera image is a black image with an excessively dark whole surface, and the infrared camera image has the defect that black concentric circles are concentric circles, so that the infrared image fails to find the corner points, and the product can be directly judged to be 'unrepairable'. 3. Edge overexposure and dark corner: can see in the camera image that the product edge coating thickness inequality leads to the colour then can lead to the condition of edge overexposure, has the condition of vignetting in the infrared camera image, the angle is too dark promptly, and two kinds of conditions all can lead to looking for the angular point failure or have the deviation, and this condition then needs fix a position as the angular point through looking for four sides and fitting straight line, with the crossing point of straight line.
The comprehensive judgment module reviews: the appearance defect classification comprises the following steps: the coating is too thin, the coating is too thick, scratches, sucker marks, belt marks, finger marks, white dots, rainbow pieces, uneven coating, winding coating and the like; the internal defect classification includes: black flakes, concentric circles, white dots, massive shadows, top tooth marks, overruling, black spots, scratches, cracks, pockmarks, friction scratches, belt marks, winding plates, finger marks, water marks, watermarks, medicine watermarks, dirt, boat scratches, boat marks and the like. The product grades are divided into: good products, reworkable and non-reworkable. The defects that can be comprehensively judged are as follows: the internal defects of the scratch board, the sucker seal, the belt seal, the finger print, the white dot, the pockmark, the black spot, the rainbow film and the like do not need comprehensive judgment, and the other defects need joint judgment except the black film, the concentric circle, the crack and the boat scratch.
As shown in fig. 3, the comprehensive judgment logic: the black sheet, the concentric circles and the cracks are irreparable defects and are unrepairable, and comprehensive judgment is not needed. If the same position of the internal defect exists, the contrast, the area and the like of the internal defect need to be judged simultaneously whether to meet the threshold setting, and the classification is carried out by comprehensive judgment. The internal defect also needs to refer to whether a defect exists in the same position, and if the same position does not have the defect, whether the threshold setting is met or not is judged and classified. The comprehensive algorithm needs to set three types of thresholds for judging three conditions, namely, the three conditions are that the appearance and the inside of the same position have defects, the appearance has defects and the inside has no defects, and the appearance has no defects and the inside has defects.
The process section with the defect can be counted and counted through the three conditions and the defect type. If the appearance and the interior have mechanical defects, the problem of the mechanical part of the film coating section can be counted and is serious; if the appearance has mechanical defects and the interior has no defects, the mechanical problem of the mechanical part of the coating section can be counted; if the appearance is not defective and the interior has mechanical defects, the process section with problems can be judged according to the defect type and the defect position and counted. If the appearance and the interior have process defects, the serious abnormal coating can be counted; if the appearance has a technological defect and the interior has no defect, the film can be counted as a slight film coating technological defect; if the appearance is not defective and the interior has defects, the process section with problems can be judged according to the defect types.
As shown in fig. 4, the line camera a5 collects images, transmits the images to computer software for processing, firstly binds unique ID to the images, then performs appearance defect detection and color classification to the images, and finds out the positioning points of the corners. The line camera b6 collects photoluminescence images, transmits the photoluminescence images to a computer for processing, firstly binds the same ID for the images, then carries out defect detection on the images, and finds out positioning points of corners. And calculating a coordinate transformation matrix between the two images through the positioning points. And finally, comprehensively judging the defect areas detected in the two images, giving out a detection result, and counting the process sections generated by the defects.
As shown in FIG. 5, the detailed flow of the judgment operator in the comprehensive judgment module
The algorithm takes the defect information of two pictures of the same product obtained by pre-calculation, respectively retrieves the defect types in the two pictures, and divides the result into two types, one type is directly judging the defect without synthesis, and the other type is the defect needing synthesis. And classifying the defects without integration according to the set threshold value through the position information and Blob analysis. And classifying the defects needing comprehensive judgment according to the position information, wherein the defects are classified into the defects with overlapped parts and the defects without overlapped parts. And classifying the defects of the non-overlapped part according to a set threshold, aligning the local regions of the defect regions in the regions and comparing the outline information of the defect regions for the defects with the overlapped part, and finally classifying the defects according to the set threshold by combining Blob analysis.
Claims (7)
1. A method for detecting images of solar cells after film coating is characterized in that products to be detected of the solar cells are horizontally conveyed into an image detection device for detection through a motion track 12 according to a horizontal motion direction 13, positioning judgment is carried out according to a camera comprehensive detection method, when a sensor a14 senses the products, a light source 3 is turned on, a linear array camera a5 starts to collect images, a sensor b15 senses the products, a near infrared laser 9 is turned on, a linear array camera b6 starts to collect images, and the front-back interval of the solar cell products is larger than the distance between a linear array camera a5 and a linear array camera b6 for scanning facial lines.
2. The image detection method of the solar cell after film coating of claim 1, wherein the image detection device comprises a solar cell, a light source 3, an infrared blocking lens 4, a line camera a5, a line camera b6, an infrared anti-reflection lens 7, a high-pass filter 8, a near-infrared laser 9, a sensor a14 and a sensor b 15;
the light source 3 and the near-infrared laser 9 are oppositely arranged at a certain inward included angle, the linear array camera a5 and the linear array camera b6 vertically downwards acquire images, an infrared cut-off lens 4 is arranged below a5, an infrared anti-reflection lens 7 is arranged below b6, a high-pass filter 8 is arranged at the bottom of the infrared anti-reflection lens 7 where the linear array camera b6 is located, the light source 3, the near-infrared laser 9, the linear array camera a5 and the linear array camera b6 are located above the motion track 12, and the sensor a14 and the sensor b15 are located below the motion track 12; the light source 3 and line camera a5 are directed to the lower sensor a14 and the near infrared laser 9 and line camera b6 are directed to the lower sensor b 15.
3. The method for detecting the image of the solar cell after coating according to claim 2, wherein the line camera b6 is an infrared camera, and the resolution is generally 1024 x 1; the line camera a5 is a visible light camera with a resolution of typically 2048 x 3, 4096 x 3.
4. The method for detecting the image of the solar cell after the film is coated according to claim 2, wherein the specific process of positioning and judging according to the camera comprehensive detection method comprises the following steps:
step 1: the linear array camera a5 collects images, transmits the images to computer software for processing, firstly binds a special ID for the images, and finds out positioning points of corners; the line-scan camera b6 collects photoluminescence images, transmits the photoluminescence images to a computer for processing, firstly binds the same ID for the images, and finds out positioning points of corners;
step 2: carrying out secondary positioning on the image with abnormal positioning;
and step 3: carrying out appearance defect detection and color classification on images collected by the line array camera a5, and carrying out defect detection on photoluminescence images collected by the line array camera b 6;
and 4, step 4: calculating a coordinate transformation matrix between the two images through the positioning points;
and 5: and finally, comprehensively judging the defect areas detected in the two images, giving a detection result, and counting the process sections generated by the defects.
5. The method for detecting the image of the solar cell after being coated according to claim 4, wherein the step 2 comprises the following steps:
step 2.1: judging whether positioning failure exists or not;
step 2.2: judging whether plating leakage exists or not: the method comprises the following steps that (1) battery piece inflow detection is carried out, wherein the battery piece with an uncoated surface is detected, a visible light camera image shows that the whole surface of the battery piece is overexposed, an infrared camera image shows that the whole surface is too dark, because the background of the visible light image is white and the background of the infrared image is black, the finding of an angular point is failed, and the product can be directly judged to be reworkable under the condition;
step 2.3: judging whether the black pieces and the concentric circles exist or not: the visible camera image is a normal image, the infrared camera image is a black film with an excessively dark whole surface, and the infrared camera image has the concentric circle defect of black concentric circles, so that the infrared image fails to find the corner point, and the product can be directly judged to be 'unrepairable';
step 2.4: judging whether the conditions of edge overexposure and dark corners exist: the condition that the edge overexposure can be caused to the product edge coating thickness inequality leads to the colour then to lead to the edge to overexpose in can seeing light camera image, has the condition of dark angle in the infrared camera image, and the angle is too dark promptly, and two kinds of circumstances all can lead to looking for the angular point failure or have the deviation, and this condition then needs fix a position as the angular point through looking for four sides and fitting straight line, with the crossing point of straight line.
6. The method for detecting the image of the solar cell after being coated according to claim 4, wherein the step 4 comprises the following steps:
step 4.1: affine transformation of multi-point positioning is used between images of the linear array camera a5 and the linear array camera b6, sub-pixel coordinates of a plurality of corner points in four corners of the solar cell piece are searched, and the corner points in the two images are set to be corresponding IDs;
step 4.2: considering the factor of point finding failure, angular points with the same ID need to be discarded at the same time, and the calculated points are all corresponding points;
step 4.3: because there is a conversion error when the low pixel is converted to the high pixel, the coordinate conversion is performed by using a conversion matrix for converting the camera coordinate of the high pixel to the camera coordinate of the low pixel, and finally, the affine transformation matrix of the two images is calculated.
7. The method for detecting the image of the solar cell after being coated according to claim 4, wherein the step 5 comprises the following steps:
step 5.1: the black sheets, the concentric circles and the cracks are irreparable defects and are unrepairable, and comprehensive judgment is not needed;
step 5.2: if the same position of the internal defect exists, the contrast, the area and the like of the internal defect need to be judged simultaneously whether to meet the threshold setting, and the classification is carried out by comprehensive judgment. If the same position does not have the defect, judging whether threshold setting is met or not and classifying;
step 5.3: the comprehensive algorithm needs to set three types of thresholds for judging three conditions, namely, the three conditions are that the appearance and the inside of the same position have defects, the appearance has defects and the inside has no defects, and the appearance has no defects and the inside has defects. The process section with the defects can be counted and counted according to the three conditions and the defect types; if the appearance and the interior have mechanical defects, the problem of the mechanical part of the film coating section can be counted and is serious; if the appearance has mechanical defects and the interior has no defects, the mechanical problem of the mechanical part of the coating section can be counted; if the appearance is free of defects and the interior has mechanical defects, judging the process section with problems according to the defect type and the defect position and counting; if the appearance and the interior have process defects, the serious abnormal coating can be counted; if the appearance has a technological defect and the interior has no defect, the film can be counted as a slight film coating technological defect; if the appearance is not defective and the interior has defects, the process section with problems can be judged according to the defect types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210282767.2A CN114636706A (en) | 2022-03-22 | 2022-03-22 | Comprehensive method and device for image detection of solar cell after film coating |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210282767.2A CN114636706A (en) | 2022-03-22 | 2022-03-22 | Comprehensive method and device for image detection of solar cell after film coating |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114636706A true CN114636706A (en) | 2022-06-17 |
Family
ID=81950090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210282767.2A Pending CN114636706A (en) | 2022-03-22 | 2022-03-22 | Comprehensive method and device for image detection of solar cell after film coating |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114636706A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115881573A (en) * | 2023-01-20 | 2023-03-31 | 通威太阳能（成都）有限公司 | Method for detecting surface circuit morphology of solar cell |
| CN116245794A (en) * | 2022-12-02 | 2023-06-09 | 广州市儒兴科技股份有限公司 | Solar cell back surface field appearance test method and device and readable storage medium |
| TWI808009B (en) * | 2022-09-23 | 2023-07-01 | 國立勤益科技大學 | Intelligent detection system |
| CN116626053A (en) * | 2023-07-24 | 2023-08-22 | 宁德微图智能科技有限公司 | Cell blue film defect detection method and device |
| CN117929278A (en) * | 2024-03-19 | 2024-04-26 | 北京博兴远志科技有限公司 | Method and device for detecting coating film of light-splitting sheet |
-
2022
- 2022-03-22 CN CN202210282767.2A patent/CN114636706A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI808009B (en) * | 2022-09-23 | 2023-07-01 | 國立勤益科技大學 | Intelligent detection system |
| CN116245794A (en) * | 2022-12-02 | 2023-06-09 | 广州市儒兴科技股份有限公司 | Solar cell back surface field appearance test method and device and readable storage medium |
| CN115881573A (en) * | 2023-01-20 | 2023-03-31 | 通威太阳能（成都）有限公司 | Method for detecting surface circuit morphology of solar cell |
| CN116626053A (en) * | 2023-07-24 | 2023-08-22 | 宁德微图智能科技有限公司 | Cell blue film defect detection method and device |
| CN116626053B (en) * | 2023-07-24 | 2023-11-03 | 宁德微图智能科技有限公司 | Cell blue film defect detection method and device |
| CN117929278A (en) * | 2024-03-19 | 2024-04-26 | 北京博兴远志科技有限公司 | Method and device for detecting coating film of light-splitting sheet |
| CN117929278B (en) * | 2024-03-19 | 2024-05-31 | 北京博兴远志科技有限公司 | Method and device for detecting coating film of light-splitting sheet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114636706A (en) | Comprehensive method and device for image detection of solar cell after film coating | |
| CN110595999B (en) | Image acquisition system | |
| WO2020248439A1 (en) | Crown cap surface defect online inspection method employing image processing | |
| JP5583102B2 (en) | Glass substrate surface defect inspection apparatus and inspection method | |
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| CN108765416A (en) | PCB surface defect inspection method and device based on fast geometric alignment | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN111398287A (en) | Battery pole piece scratch detection system and detection method | |
| WO2020119246A1 (en) | Highlight object surface defect detection system and method based on reflected light | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| WO2023134286A1 (en) | Online automatic quality testing and classification method for cathode copper | |
| CN112014407A (en) | Method for detecting surface defects of integrated circuit wafer | |
| CN114359253A (en) | Image pollution detection method and system based on convolutional neural network | |
| CN111189854A (en) | Defect layering detection method of automatic glass cover plate detection system | |
| CN107742119A (en) | A kind of contour of object extraction and coalignment and method based on figure viewed from behind imaging | |
| CN102128838A (en) | Internal defect inspection device and method for substrate | |
| CN114359155A (en) | Film laminating method and system | |
| CN114324344A (en) | Non-lambert surface inspection system for line scanning | |
| CN207397296U (en) | A kind of object identification device based on figure viewed from behind imaging | |
| CN117092113A (en) | Camera mould welding quality detection device and system thereof | |
| CN116609349A (en) | Carrier plate glass foreign matter detection equipment and detection method | |
| Boukouvalas et al. | An integrated system for quality inspection of tiles | |
| CN107727654B (en) | Film detection method, device and system | |
| WO2023164809A1 (en) | Bubble detection method and detection system for curved substrate | |
| CN114755236A (en) | System and method for detecting surface defects of electroplated part with revolution curved surface |
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 |