CN117525192B - Photovoltaic panel gluing control method, system and device based on visual detection - Google Patents
Photovoltaic panel gluing control method, system and device based on visual detection Download PDFInfo
- Publication number
- CN117525192B CN117525192B CN202410022967.3A CN202410022967A CN117525192B CN 117525192 B CN117525192 B CN 117525192B CN 202410022967 A CN202410022967 A CN 202410022967A CN 117525192 B CN117525192 B CN 117525192B
- Authority
- CN
- China
- Prior art keywords
- glued
- glass panel
- image information
- data
- determining
- 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
- 238000004026 adhesive bonding Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 230000000007 visual effect Effects 0.000 title claims abstract description 23
- 239000011521 glass Substances 0.000 claims abstract description 145
- 230000002159 abnormal effect Effects 0.000 claims abstract description 116
- 230000007547 defect Effects 0.000 claims abstract description 96
- 239000003292 glue Substances 0.000 claims abstract description 50
- 238000001931 thermography Methods 0.000 claims abstract description 47
- 239000011248 coating agent Substances 0.000 claims description 18
- 238000000576 coating method Methods 0.000 claims description 18
- 238000005452 bending Methods 0.000 claims description 12
- 238000004886 process control Methods 0.000 claims description 6
- 238000011179 visual inspection Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000003892 spreading Methods 0.000 claims description 4
- 230000007480 spreading Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 2
- 238000002372 labelling Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 9
- 238000003860 storage Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L31/00—Semiconductor devices sensitive to infrared radiation, light, electromagnetic radiation of shorter wavelength or corpuscular radiation and specially adapted either for the conversion of the energy of such radiation into electrical energy or for the control of electrical energy by such radiation; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof
- H01L31/04—Semiconductor devices sensitive to infrared radiation, light, electromagnetic radiation of shorter wavelength or corpuscular radiation and specially adapted either for the conversion of the energy of such radiation into electrical energy or for the control of electrical energy by such radiation; Processes or apparatus specially adapted for the manufacture or treatment thereof or of parts thereof; Details thereof adapted as photovoltaic [PV] conversion devices
- H01L31/042—PV modules or arrays of single PV cells
- H01L31/048—Encapsulation of modules
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C—APPARATUS FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C11/00—Component parts, details or accessories not specifically provided for in groups B05C1/00 - B05C9/00
- B05C11/10—Storage, supply or control of liquid or other fluent material; Recovery of excess liquid or other fluent material
- B05C11/1002—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves
- B05C11/1015—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves responsive to a conditions of ambient medium or target, e.g. humidity, temperature ; responsive to position or movement of the coating head relative to the target
-
- 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
-
- 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
- H01L22/20—Sequence of activities consisting of a plurality of measurements, corrections, marking or sorting steps
Abstract
The invention discloses a photovoltaic panel gluing control method, a photovoltaic panel gluing control system and a photovoltaic panel gluing control device based on visual detection, belonging to the technical field of visual detection, wherein the photovoltaic panel gluing control method comprises the following steps: acquiring first image information of a glass panel to be glued, and determining thermal imaging data of the glass panel to be glued according to the first image information; acquiring second image information of the glass panel to be glued, and determining first defect data of the glass panel to be glued according to the second image information; acquiring third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information; a glue application scheme is determined based on the thermal imaging data, the first defect data, and the second defect data. According to the method, abnormal points of the convex points and the concave points of the glass panel to be glued are detected based on visual detection, the gluing process is optimized based on detection results, one-time gluing film forming is ensured, and the gluing and bonding stability is improved.
Description
Technical Field
The application relates to the technical field of visual detection, in particular to a photovoltaic panel gluing processing control method, system and device based on visual detection.
Background
In the production process of the solar cell panel assembly, after all solar cells are attached to the templates, the glass cover plate is required to be attached to the cells, and glue coating is required to be carried out on the glass plate before the glass cover plate is attached.
In the prior art, with the development of automation, the step of gluing on the glass cover plate replaces manual gluing by an automation device. However, when the glass cover plate enters the gluing area, due to the defect of the surface of the glass cover plate, uneven areas exist, so that the gluing thickness of the fixing process can cause different gluing strength of certain areas of the glass cover plate after gluing, even the positions of the glass cover plate deviate and fall off during use, and the stable use and the power generation efficiency of the photovoltaic panel are affected.
Therefore, how to optimize the processing technology, especially control the glue outlet technology, in the photovoltaic gluing process is a technical problem to be solved by the person skilled in the art.
Disclosure of Invention
In view of the above problems, the invention aims to provide a photovoltaic panel gluing control method, a photovoltaic panel gluing control system and a photovoltaic panel gluing control device based on visual detection, which are used for detecting abnormal points of convex points and concave points of a glass panel to be glued based on the visual detection, optimizing a gluing process based on a detection result, ensuring one-time gluing film forming and improving gluing and bonding stability.
The first aspect of the invention provides a photovoltaic panel gluing processing control method based on visual detection, which comprises the following steps:
acquiring first image information of a glass panel to be glued, and determining thermal imaging data of the glass panel to be glued according to the first image information;
acquiring second image information of a glass panel to be glued, and determining first defect data of the glass panel to be glued according to the second image information;
acquiring third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information;
a glue application scheme is determined based on the thermal imaging data, the first defect data, and the second defect data.
Preferably, the method for obtaining first image information of the glass panel to be glued and determining thermal imaging data of the glass panel to be glued according to the first image information includes:
acquiring first image information of the glass panel to be glued, and establishing a coordinate system based on any two adjacent sides of the first image information as an X axis and a Y axis respectively;
converting the first image information into a thermographic image;
defining an isothermal line of the glass panel to be glued based on the thermal imaging image, and determining coordinates of a highest temperature point and a lowest temperature point;
and marking the highest temperature point and the lowest temperature point as abnormal points, and determining thermal imaging data of the glass panel to be glued.
Preferably, the method for obtaining second image information of the glass panel to be glued and determining first defect data of the glass panel to be glued according to the second image information includes:
acquiring at least a first transverse cross-sectional image and a second transverse cross-sectional image of the glass panel to be glued;
marking the abnormal points on the first transverse cross-sectional image and the second transverse cross-sectional image according to the obtained abnormal point coordinates;
determining whether the abnormal point protrudes out of the plane of the glass panel to be glued, and determining that the abnormal point is a salient point abnormal point when the abnormal point protrudes out of the plane of the glass panel to be glued;
and acquiring the height data of the abnormal points of the convex points to determine first defect data.
Preferably, the acquiring the height data of the bump abnormal point to determine the first defect data includes:
acquiring first height data of abnormal points of the salient points and surrounding areas on a first transverse cross-sectional image;
acquiring second height data of the abnormal points of the salient points and the surrounding areas on a second transverse cross-sectional image;
and drawing abnormal points of the salient points and surrounding area images to serve as first defect data by combining the first height data and the second height data and based on isothermal lines of the glass panel to be glued, which are defined by the thermal imaging images.
Preferably, the obtaining third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information includes:
obtaining the reflection image of the first incident light irradiated on the glass panel to be glued as third image information;
based on the determined convex point abnormal points, the rest abnormal points are marked as concave point abnormal points;
and marking the pit abnormal points on the third image information, and determining second defect data based on a pit defect model.
Preferably, the marking the pit anomaly point on the third image information and determining the second defect data based on a pit defect model includes:
determining the relation between the reflection bending rate of the glass panel to be glued on the third image information and the pit depth value based on machine learning, and forming a depth lookup table;
acquiring the reflection bending rate of the pit abnormal point on the third image, and determining depth values corresponding to coordinates of the pit abnormal point and surrounding areas based on a depth lookup table;
and outlining the pit abnormal point and surrounding area image as second defect data based on the obtained depth values corresponding to the coordinates of the pit abnormal point and surrounding area.
Preferably, the method further comprises:
acquiring the height value of the abnormal point of the convex point;
comparing the height value of the abnormal point of the convex point with a preset gluing thickness threshold value;
and when the height value of the abnormal points of the convex points is larger than a preset gluing thickness threshold value, judging that the glass panel to be glued is unqualified.
Preferably, the determining a glue coating scheme based on the thermal imaging data, the first defect data and the second defect data includes:
adjusting the coating glue outlet temperature based on the thermal imaging data;
and determining the glue spreading amount based on the first defect data and the second defect data.
The second aspect of the present invention provides a photovoltaic panel gluing control system based on visual detection, which is applied to the photovoltaic panel gluing control method based on visual detection as described above, and comprises the following steps:
the first data acquisition module is used for acquiring first image information of the glass panel to be glued and determining thermal imaging data of the glass panel to be glued according to the first image information;
the second data acquisition module is used for acquiring second image information of the glass panel to be glued and determining first defect data of the glass panel to be glued according to the second image information;
the third data acquisition module is used for acquiring third image information of the glass panel to be glued and determining second defect data of the glass panel to be glued according to the third image information;
and the glue coating determining module is used for determining a glue coating scheme based on the thermal imaging data, the first defect data and the second defect data.
The third aspect of the invention provides a photovoltaic panel gluing control device based on visual detection, which is applied to a gluing device, wherein a gluing head is arranged on the gluing device, and the photovoltaic panel gluing control device further comprises a gluing controller, program codes of a photovoltaic panel gluing control method based on visual detection are embedded in the gluing controller, and the gluing controller is used for calling the program codes to execute the method.
The invention discloses a photovoltaic panel gluing processing control method, a photovoltaic panel gluing processing control system and a photovoltaic panel gluing processing control device based on visual detection, wherein the method comprises the following steps: acquiring first image information of a glass panel to be glued, and determining thermal imaging data of the glass panel to be glued according to the first image information; acquiring second image information of the glass panel to be glued, and determining first defect data of the glass panel to be glued according to the second image information; acquiring third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information; a glue application scheme is determined based on the thermal imaging data, the first defect data, and the second defect data. According to the method, abnormal points of the convex points and the concave points of the glass panel to be glued are detected based on visual detection, the gluing process is optimized based on detection results, one-time gluing film forming is ensured, and the gluing and bonding stability is improved.
Drawings
FIG. 1 shows a flow chart of a photovoltaic panel gumming process control method based on visual inspection of the present invention;
FIG. 2 shows a flow chart of the invention for acquiring thermal imaging data of a glass panel to be glued;
FIG. 3 is a flow chart of the invention for obtaining first defect data for a glass panel to be glued;
FIG. 4 is a flow chart of the invention for obtaining second defect data for a glass panel to be glued;
FIG. 5 shows a flow chart of the present invention for determining a glue application scheme;
fig. 6 shows a block diagram of a photovoltaic panel rubberizing process control system based on visual inspection of the invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
In the prior art, when the production process of the photovoltaic panel is carried out, the glass panel is required to be subjected to glue coating treatment, but the defects such as bulges or depressions possibly existing on the glass panel to be glued affect the performance of the final photovoltaic panel. Specifically, as shown in fig. 1, the method comprises the following steps:
step 100, acquiring first image information of a glass panel to be glued, and determining thermal imaging data of the glass panel to be glued according to the first image information;
step 200, obtaining second image information of the glass panel to be glued, and determining first defect data of the glass panel to be glued according to the second image information;
step 300, obtaining third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information;
step 400, wherein a glue application scheme is determined based on the thermal imaging data, the first defect data and the second defect data.
Based on the steps, the photovoltaic panel gluing processing control method based on visual detection is used for gluing the glass panel, so that other glass panels can be conveniently pasted and a photovoltaic panel can be formed. Specifically, first image information of the glass panel to be glued is obtained through shooting by a thermal imaging camera, second image information of the glass panel to be glued is obtained through shooting by a CCD camera, and third image information of the glass panel to be glued is obtained through shooting by the CCD camera, further thermal imaging data, first defect data and second defect data of the glass panel to be glued are respectively obtained through the first image information, the second image information and the third image information, and a glue coating scheme is determined based on the thermal imaging data, the first defect data and the second defect data. The glue coating scheme in the embodiment mainly aims at controlling the glue outlet temperature, the unit glue outlet amount, the glue outlet thickness and the like of the glue outlet head so as to realize uniform glue thickness on the glass panel to be glued, ensure one-time glue coating and film forming and improve the stability of glue coating and bonding. Based on the above step 100, wherein the first image information of the glass panel to be glued is obtained, and the thermal imaging data of the glass panel to be glued is determined according to the first image information, as shown in fig. 2, the method comprises the following steps:
step 101, obtaining first image information of a glass panel to be glued, and establishing a coordinate system based on any two adjacent sides of the first image information as an X axis and a Y axis respectively. Firstly, shooting a glass panel to be glued, which enters a gluing station, by a thermal imaging camera to obtain a first image, simultaneously obtaining length and width data of four sides of the first image to form first image information, then selecting any one angle in the first image information as an origin based on the determined first image information, establishing a coordinate system by taking two sides which are connected with the origin and are vertical to the origin as an X axis and a Y axis respectively, and enabling the first image information to be in a first quadrant.
Step 102, converting the first image information into a thermal imaging image, and converting the thermal imaging image into a non-uniform image based on the first image captured by the thermal imaging camera if a defect area such as a recess or a protrusion exists on the glass panel to be glued.
And 103, defining an isothermal line of the glass panel to be glued based on the thermal imaging image, and determining coordinates of a highest temperature point and a lowest temperature point. Specifically, the thermal imaging image has been obtained in the above step 102, in which the isotherm is defined based on the thermal imaging image, and therefore, the temperature maximum point and the temperature minimum point can be determined through the process of defining the isotherm. It was determined that most of the area on the glass panel to be glued was uniformly distributed on the thermographic image, and that the highest and lowest temperature points could be either raised or recessed points.
And 104, marking the highest temperature point and the lowest temperature point as abnormal points, and determining thermal imaging data of the glass panel to be glued.
Through the steps, the thermal imaging data are determined based on the thermal imaging image, and the abnormal points are marked, so that the control system can optimize the gluing scheme based on the information of the abnormal points, and uniform gluing is realized. Based on the above step 100, it has been determined that the abnormal point information on the glass panel to be glued is possible to be a bump or a depression point, and therefore, it is necessary to further determine whether the abnormal point is a bump or a depression point, so that the amount of glue to be produced is controlled to be reduced when the bump is made, and the amount of glue to be produced is controlled to be increased when the depression point is made, in order to achieve uniform film formation once, and secondary repair is not required.
In order to identify the abnormal points, specifically, the protruding points or the recessed points, further, in step 200, second image information of the glass panel to be glued is obtained, and first defect data of the glass panel to be glued is determined according to the second image information, as shown in fig. 3, including the following steps:
step 201, obtaining at least a first transverse cross-sectional image and a second transverse cross-sectional image of a glass panel to be glued; in this step 201, shooting is performed from the side of the glass panel to be glued by using a CCD camera, specifically, in order to better identify defects on the glass panel to be glued, shooting is performed from at least two adjacent sides to obtain a first transverse cross-sectional image and a second transverse cross-sectional image, and from the first transverse cross-sectional image and the second transverse cross-sectional image, a salient point on the glass panel to be glued can be seen. Of course, in order to better realize the identification of the abnormal points on the glass panel to be glued, shooting is performed from four sides of the glass panel to be glued, and a third transverse cross-sectional image and a fourth transverse cross-sectional image are further obtained.
Step 202, marking abnormal points on the first transverse section image and the second transverse section image according to the obtained abnormal point coordinates; in step 104, coordinates of abnormal points on the glass panel to be glued are determined, and the abnormal points are marked on the first transverse cross-sectional image and the second transverse cross-sectional image according to the coordinates, and which abnormal points are visible as salient points on the first transverse cross-sectional image and the second transverse cross-sectional image. Of course, in order to better identify the abnormal point, the abnormal points may be marked on the third transverse cross-sectional image and the fourth transverse cross-sectional image at the same time, and further, the abnormal points on the 4 images may be compared, and when the abnormal points marked on the first transverse cross-sectional image and the second transverse cross-sectional image are identified as the same abnormal point, the abnormal points may be marked by the same color, so as to distinguish from other abnormal points.
Step 203, determining whether the abnormal point protrudes out of the plane of the glass panel to be glued, and determining that the abnormal point is a salient point abnormal point when the abnormal point protrudes out of the plane of the glass panel to be glued; since the abnormal points have been marked in the above step 202, in this step, it is possible to identify which abnormal points protrude from the plane of the glass panel to be glued by the abnormal point marking on the first transverse cross-sectional image and the second transverse cross-sectional image, and thus determine as salient abnormal points. As described above, when the abnormal points of the bumps are determined, the thickness of the removed paste is required to be adjusted according to the height data of the abnormal points of the bumps and the size of the surrounding area when the paste is applied.
Step 204, obtaining the height data of abnormal points of the convex points to determine first defect data, and optimizing a gluing scheme according to the first defect data when gluing, so as to ensure one-time film forming of gluing and stability after gluing. The method for acquiring the height data of the abnormal points of the salient points to determine the first defect data comprises the following steps:
acquiring first height data of abnormal points of the salient points and surrounding areas on a first transverse cross-sectional image; the height data of the abnormal points of the convex points in the steps can be determined through the first transverse section image shot by the CCD camera, and meanwhile, the heights of the areas around the abnormal points of the convex points gradually decrease along the extending directions of the two sides and are flush with the surface of the glass panel to be glued, so that the data are determined to be the first height data.
Acquiring second height data of abnormal points of the salient points and surrounding areas on a second transverse cross-sectional image; the height data of the abnormal points of the convex points in the steps can be determined through the second transverse cross-sectional image shot by the CCD camera, and meanwhile, the heights of the areas around the abnormal points of the convex points gradually decrease along the extending directions of the two sides and are flush with the surface of the glass panel to be glued, so that the data are determined to be the second height data.
Therefore, by the above steps, it is possible to determine the height data of the same bump anomaly point in four extension directions.
Meanwhile, combining the first height data and the second height data, and outlining abnormal points of the salient points and surrounding area images based on isotherms of the glass panel to be glued defined by the thermal imaging image to serve as first defect data.
If the abnormal point A of the bump is selected, first defect data of the abnormal point A of the bump is obtained, and specifically:
the coordinate height value of the first point in the extending direction of the left side of the bump abnormal point A determined by the first height data is H1, and the coordinate height value of the second point in the extending direction of the right side of the bump abnormal point A determined by the first height data is H2;
the coordinate height value of the third point in the extending direction of the left side of the bump abnormal point A determined by the second height data is H3, and the coordinate height value of the fourth point in the extending direction of the right side of the bump abnormal point A determined by the second height data is H4;
and the points are points on the same isotherm, then the height value of a first interval point between a first point and a third point is obtained through interpolation operation, and likewise, the height value of a second interval point between a second point and the third point is obtained through interpolation operation, the height value of a third interval point between the second point and a fourth point is obtained through interpolation operation, and the height value of a fourth interval point between the fourth point and the first point is obtained through difference operation;
further sequentially connecting a first point, a first interval point, a third point, a second interval point, a second point, a third interval point, a fourth interval point and a first point on the isotherm in series, thereby outlining points with different heights on the same isotherm;
the steps are repeated, so that the height data on the plurality of isotherms with the abnormal points of the salient points as the center can be obtained, and the abnormal points of the salient points and the surrounding area images are further outlined to serve as first defect data.
As described above, in order to avoid errors (such as abnormal point shielding, etc.) and higher accuracy, by adding the third height data of the third transverse cross-sectional image and the fourth height data of the fourth transverse cross-sectional image, the error data can be removed by combining the third height data with the first height data and the second height data, so as to ensure accuracy.
Meanwhile, in the above steps, the height of the abnormal points of the salient points on the glass panel to be glued is also required to be measured, so that the defective glass is prevented from being continuously processed, and the method specifically comprises the following steps:
acquiring the height value of abnormal points of the salient points; as already obtained in step 204 above.
Comparing the height value of the abnormal point of the salient point with a preset gluing thickness threshold; according to industry rules, a glue thickness threshold value is preset, and whether the height value of the abnormal point of the convex point exceeds a specified glue thickness value is determined by comparing the height value of the abnormal point of the convex point with the preset glue thickness threshold value. Specific:
and when the height value of the abnormal points of the convex points is smaller than a preset gluing thickness threshold value, judging that the glass panel to be glued is qualified, and continuing to glue.
When the height value of the abnormal points of the convex points is larger than a preset gluing thickness threshold value, judging that the glass panel to be glued is unqualified, and replacing the glass panel to be glued with the qualified glass panel for further processing.
In the above step, the first defect data of the abnormal points of the bumps have been determined, and the glue spreading control scheme is optimized during the glue spreading process. In step 300, third image information of the glass panel to be glued is obtained, and second defect data of the glass panel to be glued is determined according to the third image information, as shown in fig. 4, including the following steps:
step 301, obtaining a reflection image of the first incident light irradiated on the glass panel to be glued as third image information; specifically, a light source forming a certain angle with the glass panel to be glued is introduced to irradiate the glass panel to be glued, and the formed reflective image is recorded as third image information.
Step 302, based on the determined abnormal points of the convex points, the rest abnormal points are marked as abnormal points of the concave points; in general, the outliers are mainly a convex outlier and a concave outlier, and when the convex outlier among the outliers has been determined through step 200, the remaining outliers are concave outliers.
In step 303, pit outliers are marked on the third image information, and second defect data is determined based on the pit defect model. In this step, the second defect data, mainly pit data, is determined mainly according to the pit defect model.
Step 303, wherein the third image information is marked with pit anomaly points, and the second defect data is determined based on the pit defect model, comprising the following specific steps:
determining the relation between the reflection bending rate of the glass panel to be glued on the third image information and the pit depth value based on machine learning, and forming a depth lookup table; in the step, a plurality of measured reflection bending rates and corresponding measured pit depth values are used as input items and input into a machine learning model for learning training, a pit defect model is obtained, a depth lookup table is formed, and depth data in the depth lookup table and the reflection bending rates correspond to each other. It should be noted that, the reflective bending rate is that when the strip light source irradiates on the glass panel to be glued, bending is generated around the abnormal points of the pits, and the bending size is recorded as the reflective bending rate.
Acquiring the reflection bending rate of the pit abnormal point on the third image, and determining depth values corresponding to coordinates of the pit abnormal point and surrounding areas based on a depth lookup table; thus, similar to the above-described step of the bump anomaly A, the height data of the pit anomaly and the like are obtained.
And outlining the pit outlier and the surrounding area image as second defect data based on the depth values corresponding to the obtained coordinates of the pit outlier and the surrounding area. This step can be performed in a similar manner to the above-described step of the bump anomaly A, to obtain the height data of the pit anomaly, thereby forming second defect data. The above steps are already clear and will not be described in detail here.
Wherein, in step 400, a glue coating scheme is determined based on the thermal imaging data, the first defect data and the second defect data, as shown in fig. 5, comprising the steps of:
step 401, adjusting the coating glue outlet temperature based on thermal imaging data; before specific gluing, the whole temperature value of the glass panel to be glued can be obtained through thermal imaging data, and the glue outlet temperature can be finely adjusted according to the temperature of the glass panel to be glued because the glass panel to be glued needs to be pre-cured and then baked in the gluing processing process. Specifically, when the temperature of the glass panel to be glued is higher, the glue outlet temperature is properly lowered, and when the temperature of the glass panel to be glued is lower, the glue outlet temperature is properly raised.
Step 402, determining the glue dispensing amount based on the first defect data and the second defect data. The first defect data of the abnormal points of the convex points and the second defect data of the abnormal points of the concave points are already determined through the steps, so that the glue outlet amount of the abnormal points of the convex points is adjusted based on the first defect data in the gluing process, and the glue outlet amount of the abnormal points of the concave points is adjusted based on the second defect data. Specifically, the glue outlet amount is properly reduced at abnormal points of the convex points, and the glue outlet amount is properly increased at abnormal points of the concave points, so that the effect of leveling is achieved after primary film forming, and secondary repairing is not needed. Therefore, the glue coating processing control is realized through the steps, the quality consistency of the photovoltaic panel is improved, and the stability of the use effect of the photovoltaic panel is ensured.
A second aspect of the present invention provides a photovoltaic panel gluing process control system based on visual inspection, which is applied to the above photovoltaic panel gluing process control method based on visual inspection, as shown in fig. 6, and includes:
the first data acquisition module 500 is configured to acquire first image information of a glass panel to be glued, and determine thermal imaging data of the glass panel to be glued according to the first image information;
the second data obtaining module 600 is configured to obtain second image information of the glass panel to be glued, and determine first defect data of the glass panel to be glued according to the second image information;
the third data obtaining module 700 is configured to obtain third image information of the glass panel to be glued, and determine second defect data of the glass panel to be glued according to the third image information;
the glue application determination module 800 is configured to determine a glue application scheme based on the thermal imaging data, the first defect data, and the second defect data.
The third aspect of the invention provides a photovoltaic panel gluing control device based on visual detection, which is applied to a gluing device, wherein a gluing head is arranged on the gluing device, and the photovoltaic panel gluing control device further comprises a gluing controller, program codes of a photovoltaic panel gluing control method based on visual detection are embedded in the gluing controller, and the gluing controller is used for calling the program codes to execute the method.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (7)
1. The photovoltaic panel gluing control method based on visual detection is characterized by comprising the following steps of:
acquiring first image information of a glass panel to be glued, and determining thermal imaging data of the glass panel to be glued according to the first image information;
acquiring second image information of a glass panel to be glued, and determining first defect data of the glass panel to be glued according to the second image information;
acquiring third image information of the glass panel to be glued, and determining second defect data of the glass panel to be glued according to the third image information;
determining a glue coating scheme based on the thermal imaging data, the first defect data, and the second defect data;
the method for obtaining the first image information of the glass panel to be glued, and determining the thermal imaging data of the glass panel to be glued according to the first image information comprises the following steps:
acquiring first image information of the glass panel to be glued, and establishing a coordinate system based on any two adjacent sides of the first image information as an X axis and a Y axis respectively;
converting the first image information into a thermographic image;
defining an isothermal line of the glass panel to be glued based on the thermal imaging image, and determining coordinates of a highest temperature point and a lowest temperature point;
marking the highest temperature point and the lowest temperature point as abnormal points, and determining thermal imaging data of the glass panel to be glued;
the method for obtaining the second image information of the glass panel to be glued, and determining the first defect data of the glass panel to be glued according to the second image information comprises the following steps:
acquiring at least a first transverse cross-sectional image and a second transverse cross-sectional image of the glass panel to be glued;
marking the abnormal points on the first transverse cross-sectional image and the second transverse cross-sectional image according to the obtained abnormal point coordinates;
determining whether the abnormal point protrudes out of the plane of the glass panel to be glued, and determining that the abnormal point is a salient point abnormal point when the abnormal point protrudes out of the plane of the glass panel to be glued;
acquiring height data of abnormal points of the salient points to determine first defect data;
the method for obtaining the third image information of the glass panel to be glued, and determining the second defect data of the glass panel to be glued according to the third image information comprises the following steps:
obtaining the reflection image of the first incident light irradiated on the glass panel to be glued as third image information;
based on the determined convex point abnormal points, the rest abnormal points are marked as concave point abnormal points;
and marking the pit abnormal points on the third image information, and determining second defect data based on a pit defect model.
2. The vision-inspection-based photovoltaic panel gumming control method as set forth in claim 1, wherein acquiring the height data of the bump abnormal point to determine the first defect data includes:
acquiring first height data of abnormal points of the salient points and surrounding areas on a first transverse cross-sectional image;
acquiring second height data of the abnormal points of the salient points and the surrounding areas on a second transverse cross-sectional image;
and drawing abnormal points of the salient points and surrounding area images to serve as first defect data by combining the first height data and the second height data and based on isothermal lines of the glass panel to be glued, which are defined by the thermal imaging images.
3. The visual inspection-based photovoltaic panel gumming process control method as set forth in claim 1, wherein labeling the pit anomaly points on the third image information and determining second defect data based on a pit defect model includes:
determining the relation between the reflection bending rate of the glass panel to be glued on the third image information and the pit depth value based on machine learning, and forming a depth lookup table;
acquiring the reflection bending rate of the pit abnormal point on the third image, and determining depth values corresponding to coordinates of the pit abnormal point and surrounding areas based on a depth lookup table;
and outlining the pit abnormal point and surrounding area image as second defect data based on the obtained depth values corresponding to the coordinates of the pit abnormal point and surrounding area.
4. The vision-inspection-based photovoltaic panel gumming control method as set forth in claim 2, further comprising:
acquiring the height value of the abnormal point of the convex point;
comparing the height value of the abnormal point of the convex point with a preset gluing thickness threshold value;
and when the height value of the abnormal points of the convex points is larger than a preset gluing thickness threshold value, judging that the glass panel to be glued is unqualified.
5. The visual inspection-based photovoltaic panel glue process control method of any of claims 1 to 4, wherein determining a glue coating scheme based on the thermal imaging data, first defect data, and second defect data comprises:
adjusting the coating glue outlet temperature based on the thermal imaging data;
and determining the glue spreading amount based on the first defect data and the second defect data.
6. The photovoltaic panel gluing control system based on visual detection is applied to the photovoltaic panel gluing control method based on visual detection as claimed in claim 1, and is characterized by comprising the following steps:
the first data acquisition module is used for acquiring first image information of the glass panel to be glued and determining thermal imaging data of the glass panel to be glued according to the first image information;
the second data acquisition module is used for acquiring second image information of the glass panel to be glued and determining first defect data of the glass panel to be glued according to the second image information;
the third data acquisition module is used for acquiring third image information of the glass panel to be glued and determining second defect data of the glass panel to be glued according to the third image information;
and the glue coating determining module is used for determining a glue coating scheme based on the thermal imaging data, the first defect data and the second defect data.
7. The device is applied to a gluing device, wherein a gluing head is arranged on the gluing device, and the device is characterized by further comprising a gluing controller, program codes of a photovoltaic panel gluing control method based on visual detection are embedded in the gluing controller, and the gluing controller is used for calling the program codes to execute the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022967.3A CN117525192B (en) | 2024-01-08 | 2024-01-08 | Photovoltaic panel gluing control method, system and device based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022967.3A CN117525192B (en) | 2024-01-08 | 2024-01-08 | Photovoltaic panel gluing control method, system and device based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117525192A CN117525192A (en) | 2024-02-06 |
| CN117525192B true CN117525192B (en) | 2024-03-15 |
Family
ID=89757097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410022967.3A Active CN117525192B (en) | 2024-01-08 | 2024-01-08 | Photovoltaic panel gluing control method, system and device based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117525192B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000206050A (en) * | 1999-01-13 | 2000-07-28 | Nikon Corp | Surface inspection method and device |
| CN1705094A (en) * | 2004-06-01 | 2005-12-07 | 松下电器产业株式会社 | Lug detection device and method of IC parts, and lug forming method |
| CN104359915A (en) * | 2014-12-08 | 2015-02-18 | 合肥京东方光电科技有限公司 | Coated glue detection method and device |
| CN113284124A (en) * | 2021-06-07 | 2021-08-20 | 南京航空航天大学 | Photovoltaic panel defect detection method based on unmanned aerial vehicle vision |
| CN115294031A (en) * | 2022-07-18 | 2022-11-04 | 青海黄河上游水电开发有限责任公司光伏产业技术分公司 | Photovoltaic module fault image identification method based on infrared thermal imaging analysis |
| CN117152165A (en) * | 2023-11-01 | 2023-12-01 | 深圳中科精工科技有限公司 | Photosensitive chip defect detection method and device, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109926341A (en) * | 2019-03-26 | 2019-06-25 | 武汉大学 | Silicon photrouics scanning vortex thermal imaging detection platform and defect classification method |
-
2024
- 2024-01-08 CN CN202410022967.3A patent/CN117525192B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000206050A (en) * | 1999-01-13 | 2000-07-28 | Nikon Corp | Surface inspection method and device |
| CN1705094A (en) * | 2004-06-01 | 2005-12-07 | 松下电器产业株式会社 | Lug detection device and method of IC parts, and lug forming method |
| CN104359915A (en) * | 2014-12-08 | 2015-02-18 | 合肥京东方光电科技有限公司 | Coated glue detection method and device |
| CN113284124A (en) * | 2021-06-07 | 2021-08-20 | 南京航空航天大学 | Photovoltaic panel defect detection method based on unmanned aerial vehicle vision |
| CN115294031A (en) * | 2022-07-18 | 2022-11-04 | 青海黄河上游水电开发有限责任公司光伏产业技术分公司 | Photovoltaic module fault image identification method based on infrared thermal imaging analysis |
| CN117152165A (en) * | 2023-11-01 | 2023-12-01 | 深圳中科精工科技有限公司 | Photosensitive chip defect detection method and device, storage medium and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| Automatic defect detection based on segmentation of pulsed thermographic images;Kaiyi Zheng 等;Chemometrics and Intelligent Laboratory Systems;20170315;第162卷;全文 * |
| 基于视觉的汽车装配件缺陷检测研究进展;张瀚丹 等;仪器仪表学报;20230815;第44卷(第8期);全文 * |
| 复合材料缺陷的红外热成像检测研究;林隆荣;伏喜斌;黄学斌;陈伟强;张秋坤;钟舜聪;;机电工程;20190620(06);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117525192A (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2021003698A (en) | Technique for aligning-printing permanent layer with improved speed and accuracy | |
| CN111982921B (en) | Method and device for detecting hole defects, conveying platform and storage medium | |
| CN110503638B (en) | Spiral adhesive quality online detection method | |
| US11092432B2 (en) | Reference plate and method for calibrating and/or checking a deflectometry sensor system | |
| KR102406558B1 (en) | Surface inspection method using mold surface inspection device | |
| CN105424721A (en) | Metal strain gauge defect automatic detection system | |
| CN114413799B (en) | Chip substrate warpage detection method, system and device and electronic equipment | |
| CN116500086B (en) | Deep learning-based copper complex aluminum heat dissipation bottom plate production evaluation method and system | |
| CN117525192B (en) | Photovoltaic panel gluing control method, system and device based on visual detection | |
| JP2010256053A (en) | Shape defect inspection device, shape modeling device, and shape defect inspection program | |
| CN113068326B (en) | Welding quality processing method and device and circuit board | |
| CN116985525B (en) | Intelligent management method and system for full-automatic vision printer | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN114972825B (en) | Method for realizing automatic detection of MMI key icon matrix | |
| CN112270724A (en) | Photovoltaic cell panel welding strip deviation detection method and device based on artificial intelligence | |
| JP2002066771A (en) | Laser system | |
| CN112150458A (en) | Photovoltaic cell panel welding strip deviation detection method and system based on artificial intelligence | |
| CN104394292A (en) | Scanning correction method and image scanning module with correction function | |
| CN115239002A (en) | New energy distributed photovoltaic power station monitoring and early warning system and method | |
| CN117291909B (en) | Intelligent control method and system for light-emitting diode production equipment | |
| JP2017016169A (en) | Inspection method, inspection apparatus, image processing apparatus, program, and recording medium | |
| CN117078743B (en) | Method and system for calculating area of silver paste line of circuit board based on image | |
| CN112822473B (en) | Calibration test method and system for projection product | |
| CN117790086B (en) | Method for cutting metering identification of double-meter-mark electric wires and cables | |
| CN112256905B (en) | Method and device for displaying defect hot spot distribution of image data set |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |