Photovoltaic module EL detection method, device and storage medium

Abstract

The present invention discloses a method, device and storage medium for EL detection of a photovoltaic module. The detection method includes providing an EL image of the photovoltaic module to be measured, determining the gray scale value of each pixel cell in the image; obtaining the average gray scale value of multiple pixel cells corresponding to the EL sub-image; taking the maximum gray scale value among the average gray scale values corresponding to the EL sub-image to obtain a first difference between the maximum gray scale value and the remaining average gray scale values, or taking the minimum gray scale value among the average gray scale values corresponding to the EL sub-image to obtain a second difference between the remaining average gray scale values and the minimum gray scale value; if the proportion of the first difference is greater than a first preset threshold, the EL image of the photovoltaic module to be measured is abnormal; or if the proportion of the second difference is greater than a second preset threshold, the EL image of the photovoltaic module to be measured is abnormal. The present invention uses gray scale difference calculation to determine EL defects, and is less affected by external factors.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic technology, and more particularly, to a method, device and storage medium for EL detection of photovoltaic modules. Background Art

[0002] With the aggravation of environmental pollution and energy crisis, photovoltaic modules that generate electricity using solar energy have become the focus of attention. Renewable energy represented by solar energy has received strong support from the state, injecting new vitality into the solar energy industry, and the solar energy industry has developed vigorously. Currently, the main solar energy conversion tool, namely the photovoltaic cell, has the characteristics of high conversion efficiency, low cost, long life, etc. As a key component in photovoltaic modules, crystalline silicon solar cells undertake the important responsibility of converting solar energy into electrical energy.

[0003] Based on the principle of electroluminescence (EL for short), by using the method of near-infrared detection, latent defects in crystalline silicon solar cells and modules can be detected, including silicon material defects, diffusion defects, printing defects, sintering defects, and cracks during the module encapsulation process, etc. The EL testing technology is widely used in the inspection of crystalline silicon solar cells and modules. The electroluminescence of a solar cell means that when a forward bias is applied across the two ends of the solar cell, minority carriers are injected into the PN junction barrier region and the diffusion region. These non-equilibrium minority carriers continuously recombine with majority carriers and emit light. By using a CCD device to receive the electroluminescence or using a CCD camera to take pictures, the composite radiation distribution image of the solar cell is displayed. The EL testing process is carried out in a dark room. The measured EL luminescence intensity is proportional to the minority carrier lifetime (or minority carrier diffusion length) and the current density of the cell. The brightness and darkness of the luminescence image can clearly reflect the defect areas with a lower minority carrier diffusion length in the solar cell, and latent defects existing in the solar cell and module can be found.

[0004] However, the production process of photovoltaic cells is complex. Due to other processes such as cell coating, the produced cell wafers show different gray levels in the electroluminescence at the module end, which is called cell wafer mixing in the industry. These cell wafers with different gray levels on one module will affect the overall sales of the module. At present, in China, the determination of cell wafer mixing of photovoltaic cells mainly relies on manual visual inspection, which not only has low accuracy and long time consumption, but also has low manual sorting efficiency and high cost. Due to the strong subjective consciousness of the human eye, and the long-term manual sorting by the human eye is bound to cause eye fatigue, which will in turn lead to a decrease in work efficiency or an increase in the misdetection rate.

[0005] Therefore, how to replace manual labor, perform intelligent gray level determination, reduce the misjudgment rate of photovoltaic cells, improve the consistency of the quality of photovoltaic cell products, establish an objective evaluation standard for gray level detection and determination, and realize the intelligent upgrading and transformation of the photovoltaic industry has become a major issue facing people. Summary of the Invention

[0006] In view of this, the present invention provides a method, device and storage medium for EL detection of photovoltaic modules, which are used to replace manual work, perform intelligent gray-scale determination, reduce the misjudgment rate of photovoltaic cells, improve the consistency of the quality of photovoltaic cell products, and establish an objective evaluation standard for gray-scale detection and determination.

[0007] On the one hand, the present invention provides a method for EL detection of photovoltaic modules, including the steps of:

[0008] Providing a photovoltaic module to be tested, where the photovoltaic module includes N cell pieces, and N is a positive integer greater than 1;

[0009] Collecting an EL image of the photovoltaic module to be tested, where the EL image of the photovoltaic module is composed of pixel cells, and determining the gray-scale value of each pixel cell;

[0010] Dividing the EL image corresponding to each cell piece into M EL sub-images, where the EL sub-images contain multiple pixel cells, and obtaining the gray-scale average values of the multiple pixel cells corresponding to the M×N EL sub-images, and M is a positive integer greater than or equal to 2;

[0011] Taking the maximum gray-scale value among the gray-scale average values corresponding to the M×N EL sub-images to obtain a first difference between the M×N - 1 maximum gray-scale values and the remaining gray-scale average values, or taking the minimum gray-scale value among the gray-scale average values corresponding to the M×N EL sub-images to obtain a second difference between the remaining gray-scale average values and the minimum gray-scale value;

[0012] Constructing a difference ratio distribution diagram, obtaining the difference ratio distribution diagram through the first difference, determining the distribution of the ratio of the first difference, and comparing the ratio of the first difference with a first preset threshold: if the ratio of the first difference is greater than the first preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the first difference is less than or equal to the first preset threshold, the EL image of the photovoltaic module to be tested is qualified;

[0013] Alternatively, obtaining the difference ratio distribution diagram through the second difference, determining the distribution of the ratio of the second difference, and comparing the ratio of the second difference with a second preset threshold: if the ratio of the second difference is greater than the second preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the second difference is less than or equal to the second preset threshold, the EL image of the photovoltaic module to be tested is qualified.

[0014] Optionally, it further includes the step of presetting a gray-scale card, where different gray-scale values in the gray-scale card correspond to black with different saturations, comparing each pixel cell with the gray-scale card, and determining the gray-scale value of each pixel cell.

[0015] Optionally, comparing each of the pixel cells with the gray scale card to determine the gray scale value of each pixel cell includes: the gray scale value of the pixel cell is the gray scale value with the highest similarity in saturation to that in the gray scale card.

[0016] Optionally, the gray scale values in the gray scale card are greater than or equal to 0% and less than or equal to 100%.

[0017] Optionally, M is an even number.

[0018] Optionally, the areas of the M EL sub-images are all equal.

[0019] Optionally, M ≤ 10.

[0020] On the other hand, the present invention also provides an electronic device, including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the photovoltaic module EL detection method described in any one of the above is implemented.

[0021] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the photovoltaic module EL detection method described in any one of the above is implemented.

[0022] Compared with the prior art, the photovoltaic module EL detection method, device and storage medium provided by the present invention at least achieve the following beneficial effects:

[0023] The detection method of the present invention first collects the EL image of the photovoltaic module to be tested, determines the gray-scale value of each pixel cell in the EL image, and then divides the EL image corresponding to each cell into M EL sub-images, obtaining the average gray-scale values of multiple pixel cells corresponding to M×N EL sub-images. Take the maximum gray-scale value among the average gray-scale values corresponding to M×N EL sub-images to obtain the first difference between M×N - 1 maximum gray-scale values and the remaining average gray-scale values. Alternatively, take the minimum gray-scale value among the average gray-scale values corresponding to M×N EL sub-images to obtain the second difference between the remaining average gray-scale values and the minimum gray-scale value; then construct a difference ratio distribution map, obtain the difference ratio distribution map through the first difference, determine the distribution of the ratio of the first difference, and compare the ratio of the first difference with the first preset threshold: if the ratio of the first difference is greater than the first preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the first difference is less than or equal to the first preset threshold, the EL image of the photovoltaic module to be tested is qualified; or, obtain the difference ratio distribution map through the second difference, determine the distribution of the ratio of the second difference, and compare the ratio of the second difference with the second preset threshold: if the ratio of the second difference is greater than the second preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the second difference is less than or equal to the second preset threshold, the EL image of the photovoltaic module to be tested is qualified. The present invention uses gray-scale difference to automatically determine the uneven gray-scale of the image after the photovoltaic cell is electroluminescent. Since the current passed during the EL test will affect the overall EL performance at the same time, that is, the same brightness or the same darkness, it will not affect the gray-scale difference. Therefore, the overall EL performance is calculated by the difference to determine the EL defect, which is more fair, less affected by external factors, and does not require manual sorting. Through intelligent gray-scale determination, it can reduce the misjudgment rate of photovoltaic cells, improve the consistency of the quality of photovoltaic cell products, and establish an objective evaluation standard for gray-scale detection and determination; in addition, the detection method of the present invention can be applied to various poor performances after the EL imaging of photovoltaic modules, such as poor soldering, hidden cracks, scratches, contamination, etc.

[0024] Of course, any product implementing the present invention does not necessarily need to achieve all the above-mentioned technical effects simultaneously.

[0025] Other features and advantages of the present invention will become clear from the following detailed description of the exemplary embodiments of the present invention with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments of the present invention and, together with the description, are used to explain the principles of the present invention.

[0027] Figure 1 is a flowchart of a method for detecting EL of a photovoltaic module provided by the present invention;

[0028] Figure 2A partial view of an EL image provided by the present invention;

[0029] Figure 3 It is an enlarged view of a pixel cell in an EL image of the present invention;

[0030] Figure 4 A schematic diagram of the division of a battery cell provided by the present invention;

[0031] Figure 5 It is an image of a qualified product in an embodiment provided by the present invention;

[0032] Figure 6 It is Figure 5 The corresponding difference ratio distribution diagram;

[0033] Figure 7 It is an image of a qualified product in an embodiment provided by the present invention;

[0034] Figure 8 It is Figure 7 The corresponding difference ratio distribution diagram;

[0035] Figure 9 A gray scale card provided by the present invention;

[0036] Figure 10 A structural block diagram of an electronic device provided by the present invention. Detailed implementation manners

[0037] Now, various exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention.

[0038] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way serves as a limitation to the present invention or its application or use.

[0039] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be regarded as part of the specification.

[0040] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0041] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof in subsequent drawings is not required.

[0042] In combination with Figure 1, Figure 1 is a flowchart of a method for EL detection of a photovoltaic module provided by the present invention. As Figure 1 shown, the method for EL detection of a photovoltaic module provided in this embodiment includes the following steps:

[0043] S1: Provide a photovoltaic module to be tested. The photovoltaic module includes N solar cells, and N is a positive integer greater than 1;

[0044] S2: Collect the EL image of the photovoltaic module to be tested. The EL image of the photovoltaic module is composed of pixel cells, and determine the gray-scale value of each pixel cell;

[0045] S3: Divide the EL image corresponding to each solar cell into M EL sub-images. Each EL sub-image contains multiple pixel cells, and obtain the gray-scale average values of the multiple pixel cells corresponding to M×N EL sub-images. M is a positive integer greater than or equal to 2;

[0046] S4: Take the maximum gray-scale value among the gray-scale average values corresponding to M×N EL sub-images to obtain the first difference between M×N - 1 maximum gray-scale values and the remaining gray-scale average values. Alternatively, take the minimum gray-scale value among the gray-scale average values corresponding to M×N EL sub-images to obtain the second difference between the remaining gray-scale average values and the minimum gray-scale value;

[0047] S5: Construct a difference ratio distribution diagram. Obtain the difference ratio distribution diagram through the first difference, determine the distribution of the ratio of the first difference, and compare the ratio of the first difference with a first preset threshold: If the ratio of the first difference is greater than the first preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the first difference is less than or equal to the first preset threshold, the EL image of the photovoltaic module to be tested is qualified.

[0048] Alternatively, obtain the difference ratio distribution diagram through the second difference, determine the distribution of the ratio of the second difference, and compare the ratio of the second difference with a second preset threshold: If the ratio of the second difference is greater than the second preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the second difference is less than or equal to the second preset threshold, the EL image of the photovoltaic module to be tested is qualified.

[0049] The object of the present invention is to achieve automatic judgment, directly supplement the defects that need to be judged manually with intelligence and standards, and judge whether it is qualified.

[0050] Specifically, when testing, it is necessary to assemble the photovoltaic cell to be tested into a photovoltaic module. The structure of the photovoltaic module (not shown in the figure) generally includes a photovoltaic cell, an upper encapsulation layer and a lower encapsulation layer on both sides of the photovoltaic cell, a cover plate on the upper encapsulation layer, and a backplane on the lower encapsulation layer.

[0051] In the above step S1, the provided photovoltaic module includes N cell pieces to form a plurality of cell strings for generating photocurrent, where N is a positive integer greater than 1.

[0052] In the above step S2, after the cell pieces are connected in series and in parallel and then powered on and photographed by a power-on device, an electroluminescence image of the photovoltaic module (also known as the EL image of the photovoltaic module) is obtained. Figure 2 This is a partial view of an EL image provided by the present invention. It can be understood that the EL image is composed of pixel cells, and each pixel cell corresponds to a gray scale value. Of course, the process of determining the gray scale value of each pixel cell is automatically completed by a computer program.

[0053] In the above step S3, in the present invention, the EL image corresponding to each cell piece is divided into M EL sub-images. The purpose of doing this is to reduce calculations. On the one hand, it is to prevent misjudgment caused by abnormal single values, and on the other hand, it is to simplify the calculation. It can be understood that the EL sub-image contains multiple pixel cells. Refer to Figure 3 , Figure 3 This is an enlarged view of a pixel cell in an EL image provided by the present invention. In this step, the gray scale average values of the pixel cells corresponding to M×N EL sub-images can be obtained. In the present invention, M is a positive integer greater than or equal to 2.

[0054] It can be understood that in order to reduce calculations, it is necessary to set the unit area size, that is, calculate the average gray scale size of each set unit area. For example, the size of a half cell piece is 163.75mm×81.875mm, which can be evenly divided into two parts, the two parts can be evenly divided into four parts, the four parts can be evenly divided into eight parts, and so on. There is no specific limitation here.

[0055] Refer to Figure 4 , Figure 4 This is a schematic diagram of cell piece division provided by the present invention. In it, the half cell piece is divided into eight parts, and each part is a unit area. By setting a program to separately calculate the average value of the gray scale values of each pixel cell included in each unit area, eight groups of average values can be calculated for the eight evenly divided parts of the photovoltaic half cell piece; that is, eight unit area gray scale average values can be obtained for each photovoltaic cell half piece; assuming that a photovoltaic module includes 120 photovoltaic cell halves, 8×120 = 960 unit area gray scale average values can be obtained through program verification and calculation.

[0056] In the above step S4, by comparing and arranging the average grayscale values of 960 unit areas, the minimum value can be calibrated. Taking the minimum value as the reference line, the computer program subtracts the remaining 959 values from the minimum grayscale value, thus obtaining 959 grayscale differences of unit areas, that is, 959 first differences. Of course, the maximum value can also be calibrated. Taking the maximum value as the reference line, the computer program subtracts the remaining 959 values from the maximum grayscale value, thus obtaining 959 grayscale differences of unit areas, that is, 959 second differences.

[0057] In the above step S5, first, a difference proportion distribution graph is constructed. In the difference proportion distribution graph, the abscissa is the difference distribution interval, and the ordinate is the difference proportion. The above 959 first differences or 959 second differences are input into the difference proportion distribution graph. The steps for constructing the difference proportion distribution graph are as follows: the abscissa is the difference interval, and the ordinate is the difference proportion. The difference intervals are grayscale difference = 0, grayscale difference ≤ 5, grayscale difference ≤ 10, grayscale difference ≤ 15, grayscale difference ≤ 20... grayscale difference ≤ 100, and the ordinate is the difference proportion. For example, Figure 6 the proportion of cases where the grayscale difference = 0 is 14.9%, and the proportion of cases where the grayscale difference ≤ 5 is 50.9%. Of course, here, when the grayscale difference ≤ 5, it does not include the cases where the grayscale difference = 0, but represents the part where the grayscale difference is in the range of (0, 5]. And so on. Then, the first differences or the second differences are summarized to obtain the proportion distribution graph.

[0058] It should be noted that when comparing the proportion of the first difference with the first preset threshold, a one-to-one comparison is required. After the proportions of all gray-level differences meet the conditions, it can be determined whether the EL image of the photovoltaic module to be tested is abnormal. For example, it is necessary to compare one by one the proportions of gray-level differences ≤5, gray-level differences ≤10, gray-level differences ≤15, gray-level differences ≤20... gray-level differences ≤100. Among them, the first preset threshold also corresponds to the gray-level difference. For example, the first preset threshold for the proportion of gray-level differences ≤5 can be any value less than 100%, because when the gray-level difference ≤5, it indicates that the difference between the images is small, so the first preset threshold can be set larger; the first preset threshold for the proportion of gray-level differences ≤30% can be 0, because when the gray-level difference ≤30%, it indicates that the difference between the images is large, and no matter what the proportion is, it is unqualified. Similarly, when comparing the proportion of the second difference with the second preset threshold, a one-to-one comparison is required. After the proportions of all gray-level differences meet the conditions, it can be determined whether the EL image of the photovoltaic module to be tested is abnormal. For example, it is necessary to compare one by one the proportions of gray-level differences ≤5, gray-level differences ≤10, gray-level differences ≤15, gray-level differences ≤20... gray-level differences ≤100. Among them, the first preset threshold also corresponds to the gray-level difference. For example, the second preset threshold for the proportion of gray-level differences ≤10 can be any value less than 100%, because when the gray-level difference ≤10, it indicates that the difference between the images is small, so the second preset threshold can be set larger; the second preset threshold for the proportion of gray-level differences ≤35% can be 0, because when the gray-level difference ≤35%, it indicates that the difference between the images is large, and no matter what the proportion is, it is unqualified. In this way, the final gray-level span data of the entire EL image can be obtained; according to the established gray-level span level, the computer automatically performs data comparison and determines whether there is an unqualified area; finally, it determines whether the entire module is qualified; of course, the computer AI learns, improves the database, and increases the possibility.

[0059] In the present invention, the computer automatically identifies the target image to be determined and analyzes the average gray-level value of each region; the computer automatically performs data algorithms, successively selects all the maximum and minimum value regions for comparison, performs subtraction operations, or once selects all the maximum value regions for comparison and performs subtraction operations.

[0060] Refer to Figures 5 to 8 , Figure 5 is the image of a qualified product in an embodiment provided by the present invention, Figure 6 is the same as Figure 5 the corresponding difference proportion distribution diagram, Figure 7 is the image of a qualified product in an embodiment provided by the present invention, Figure 8 is the same as Figure 7 the corresponding difference proportion distribution diagram. Figure 6 and Figure 8Classify the 959 gray - scale differences per unit area according to the existing gray - scale standard of photovoltaic module EL images; Figure 6 and Figure 8 is a distribution graph of the difference proportion. The abscissa is the difference interval, and the ordinate is the difference proportion. Of course, the gray - scale difference here can be the first difference or the second difference, and no specific limitation is made here. The difference intervals are gray - scale difference = 0, gray - scale difference ≤ 5, gray - scale difference ≤ 10, gray - scale difference ≤ 15, gray - scale difference ≤ 20... gray - scale difference ≤ 100, and the ordinate is the difference proportion. For example, Figure 6 in it, the proportion of gray - scale difference = 0 is 14.9%, and the proportion of gray - scale difference ≤ 5 is 50.9%. Of course, here when gray - scale difference ≤ 5, it does not include the case of gray - scale difference = 0, but represents the part where the gray - scale difference is in the range of (0, 5], and so on.

[0061] Then, by comparing with the existing standard, it can be obtained whether the gray - scale distribution span of the EL image of this photovoltaic module is within the range allowed by the existing standard; at the same time, the computer program has an AI recognition function. After comparing with the existing standard, if it is qualified, it will display that the gray - scale span of the EL image of this photovoltaic module is within the existing standard. If it is unqualified, it will automatically circle the unqualified unit area and display the unqualified gray - scale value. For example, Figure 5 and Figure 6 as shown, Figure 5 in it, the unqualified unit area is automatically circled, Figure 6 in it, the unqualified gray - scale value is displayed; for example, Figure 7 and Figure 8 as shown, it shows that the gray - scale span of the EL image of this photovoltaic module is within the existing standard.

[0062] The standard in an embodiment of the present invention is as follows: When the gray - scale difference is less than 30, it is an allowed situation and can be not controlled; when the cumulative proportion of the gray - scale values of gray - scale difference ≤ 30 and gray - scale difference ≤ 35 does not exceed 5%, it is qualified; when the cumulative proportion of the gray - scale values of gray - scale difference ≤ 30 and gray - scale difference ≤ 35 is greater than 5%, it is unqualified; when the gray - scale difference is greater than 30, it is unqualified. It can be understood that the cumulative proportion of the gray - scale values of gray - scale difference ≤ 30 and gray - scale difference ≤ 35 not exceeding 5% is only the first preset threshold, and the gray - scale difference being greater than 30 being unqualified is also the first preset threshold. Of course, the specific values of the first preset threshold and the second preset threshold are not limited here either.

[0063] For example, Figure 6 as shown, when the gray - scale difference is less than 30, it is an allowed situation. The proportion of gray - scale difference ≤ 30 is 1.57%, the proportion of gray - scale difference ≤ 35 is 1.18%, and the cumulative proportion of the gray - scale values of gray - scale difference ≤ 30 and gray - scale difference ≤ 35 is 2.75%, which also meets the requirements. However, the proportion of gray - scale difference ≤ 40 is 0.39%, which is not allowed and is determined to be unqualified. At the same time, Figure 5The unqualified areas are automatically circled in it.

[0064] As Figure 8 shown, when the grayscale difference is less than 30, it is an allowed situation. The proportion of differences with grayscale difference ≤ 30 is 0.73%, the proportion of differences with grayscale difference ≤ 35 is 0.21%, and the cumulative proportion of grayscale values with grayscale difference ≤ 30 and grayscale difference ≤ 35 is 0.95%, which also meets the requirements. The proportion of differences with grayscale difference ≤ 40 is 0%, and it is determined to be qualified. Figure 7 There is no need to circle the unqualified areas in it.

[0065] The present invention uses the grayscale difference to automatically determine the uneven grayscale of the image after the electroluminescence of the photovoltaic cell in the photovoltaic module. Since the current applied during the EL test will affect the overall EL performance at the same time, that is, all bright or all dark, it will not affect the grayscale difference. Therefore, the overall EL performance is calculated by the difference to determine the EL defect, which is more fair, less affected by external factors, and does not require manual sorting. Through intelligent grayscale determination, the misjudgment rate of the photovoltaic cell can be reduced, the consistency of the quality of the photovoltaic cell product can be improved, and an objective evaluation standard for grayscale detection and determination can be established. In addition, the detection method of the present invention can be applied to various poor performances after the EL imaging of the photovoltaic module, such as poor soldering, hidden crack, scratch, pollution, etc.

[0066] In some optional embodiments, before the test, it is necessary to collect the existing EL images of the photovoltaic module and establish a database; analyze the average grayscale value of each area of the target image in the database by a computer; perform modeling and analysis on the existing data to establish a grayscale span level for subsequent detection. The first preset threshold and the second preset threshold can be adjusted through the database. If the preset threshold is adjusted according to the database, a large amount of product performance data of the photovoltaic module needs to be collected, and the preset threshold is adjusted according to the change of the long-term performance. In some optional embodiments, referring to Figure 9 , Figure 9 is a grayscale card provided by the present invention. The detection method of this embodiment further includes the step of presetting the grayscale card. Different grayscale values in the grayscale card correspond to black with different saturations. Each pixel cell is compared with the grayscale card to determine the grayscale value of each pixel cell.

[0067] Optionally, the grayscale card here is pre-stored in the computer program, and the computer program automatically retrieves the grayscale card during the EL detection.

[0068] It can be understood that different grayscale values correspond to different saturations. Each pixel cell has a grayscale value corresponding to the grayscale scale. The computer program can obtain the grayscale level value corresponding to each pixel cell by comparing each pixel cell with the grayscale scale.

[0069] In some optional embodiments, continue to refer to Figure 9, compare each pixel cell with a gray scale card to determine the gray value of each pixel cell, including: the gray value of the pixel cell is the gray value with the highest saturation similarity in the gray scale card.

[0070] It can be understood that each pixel cell has a gray value corresponding to the gray scale. The computer program compares each pixel cell with the gray scale, and the gray value of the pixel cell is the gray value with the highest saturation similarity in the gray scale card, so as to obtain the gray level value corresponding to each pixel cell.

[0071] In some alternative embodiments, continue to refer to Figure 9 , the gray value in the gray scale card is greater than or equal to 0% and less than or equal to 100%.

[0072] Figure 9 In

[0073] In some alternative embodiments, continue to refer to Figure 4 , M is an even number.

[0074] Figure 4 In

[0075] It can be understood that usually the battery cell is in a rectangular or square structure. Dividing the battery cell into an even number makes it easier to divide it into multiple EL sub-images, which is convenient for subsequent calculations.

[0076] In some alternative embodiments, continue to refer to Figure 4 , the areas of the M EL sub-images are all equal.

[0077] It can be understood that dividing the battery cell into an even number of equal-area parts can obtain an even number of unit-area gray level averages during calculation, which makes the calculation more accurate. If the areas of the divided parts are not equal, the gray level averages of different parts are inaccurate.

[0078] In some alternative embodiments, continue to refer to Figure 4 , M ≤ 10.

[0079] It can be understood that dividing the cell into multiple parts can facilitate calculation. However, if the number of divided parts is too large, it will also increase the calculation amount and reduce the work efficiency. In this embodiment, the EL image corresponding to each cell is divided into multiple EL sub-images, and the number of divided EL sub-images is less than or equal to 10, which can simplify the calculation and improve the work efficiency.

[0080] Based on the same inventive concept, the present invention further provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the photovoltaic module EL detection method of any of the above embodiments.

[0081] Combined with Figure 10 shown, Figure 10 FIG. is a structural block diagram of an electronic device provided by the present invention. The electronic device 200 provided in this embodiment includes a memory 240 storing computer-executable instructions and a processor 210. The memory 240 is used to store one or more programs. When the one or more programs are executed by the one or more processors 210, the one or more processors 210 implement the photovoltaic module EL detection method of any one of the above embodiments.

[0082] Continuing to combine with Figure 10 shown, the electronic device 200 may include a processor 210 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the system memory (ROM) 220 or the program loaded from the memory 240 into the random access memory (RAM) 230. In the RAM 230, various programs and data required for the operation of the electronic device 200 are also stored. The processor 210, the ROM 220, and the RAM 230 are connected to each other through a bus 260. The input / output (I / O) interface 250 is also connected to the bus 260.

[0083] The following components are connected to the I / O interface 250: an input part 280 including a keyboard, a mouse, etc.; an output part 290 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part including a hard disk, etc.; and a communication part 270 including a network interface card such as a LAN card, a modem, etc. The communication part 270 performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 250 as needed. A removable medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive as needed, so that the computer program read from it can be installed into the storage part as needed.

[0084] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 270, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above functions defined in the system of the present invention are executed.

[0085] The electronic device 200 provided in the above embodiments can execute the photovoltaic module EL detection method provided in any embodiment disclosed in the present invention, and has corresponding functional units and beneficial effects for executing the method. For technical details not described in detail in the above embodiments, reference can be made to the photovoltaic module EL detection method provided in any embodiment disclosed in the present invention.

[0086] The computer program code for performing the operations of the embodiments disclosed in the present invention can be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of designing a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer.

[0087] The units involved in this embodiment can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation to the unit itself in some cases.

[0088] Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the photovoltaic module EL detection method in any of the above embodiments is implemented.

[0089] As can be seen from the above embodiments, the photovoltaic module EL detection method, device and storage medium provided by the present invention at least achieve the following beneficial effects:

[0090] The detection method of the present invention first collects the EL image of the photovoltaic module to be tested, determines the gray scale value of each pixel cell in the EL image, and then divides the EL image corresponding to each cell into M EL sub-images, obtaining the average gray scale values of multiple pixel cells corresponding to M×N EL sub-images. Take the maximum gray scale value among the average gray scale values corresponding to M×N EL sub-images to obtain the first difference between the M×N - 1 maximum gray scale values and the remaining average gray scale values. Alternatively, take the minimum gray scale value among the average gray scale values corresponding to M×N EL sub-images to obtain the second difference between the remaining average gray scale values and the minimum gray scale value; then construct a difference ratio distribution map. Obtain the difference ratio distribution map through the first difference to determine the distribution of the ratio of the first difference, and compare the ratio of the first difference with the first preset threshold: if the ratio of the first difference is greater than the first preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the first difference is less than or equal to the first preset threshold, the EL image of the photovoltaic module to be tested is qualified. Or, obtain the difference ratio distribution map through the second difference to determine the distribution of the ratio of the second difference, and compare the ratio of the second difference with the second preset threshold: if the ratio of the second difference is greater than the second preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the second difference is less than or equal to the second preset threshold, the EL image of the photovoltaic module to be tested is qualified. The present invention uses gray scale differences to automatically determine the uneven gray scale of the image after the electroluminescence of photovoltaic cells in a photovoltaic module. Since the current applied during the EL test will simultaneously affect the overall EL performance, that is, all bright or all dark, it will not affect the gray scale difference. Therefore, by calculating the overall EL performance through the difference to determine EL defects, it is more fair, less affected by external factors, and does not require manual sorting. Through intelligent gray scale determination, it can reduce the misjudgment rate of photovoltaic cells, improve the consistency of the quality of photovoltaic cell products, and establish an objective evaluation standard for gray scale detection and determination; in addition, the detection method of the present invention can be applied to various abnormal performances after the EL imaging of photovoltaic modules, such as virtual soldering, hidden cracks, scratches, contamination, etc.

[0091] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the present invention. Those skilled in the art should understand that the above embodiments can be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for EL detection of a photovoltaic module, characterized in that, For detecting silicon material defects, diffusion defects, printing defects, sintering defects in a photovoltaic module, and cracks during the encapsulation process of the photovoltaic module, including the steps of: Providing a photovoltaic module to be tested, where the photovoltaic module includes N cell pieces, and N is a positive integer greater than 1; After the N cell pieces are connected in series and in parallel and then powered on, an electroluminescence (EL) image of the photovoltaic module to be tested is collected. The EL image of the photovoltaic module is composed of pixel cells, and the gray level value of each pixel cell is determined; Dividing the EL image corresponding to each cell piece into M EL sub-images. Each EL sub-image contains multiple pixel cells, and the gray level average values of the multiple pixel cells corresponding to the M×N EL sub-images are obtained. M is a positive integer greater than or equal to 2; Taking the maximum gray level value among the gray level average values corresponding to the M×N EL sub-images to obtain a first difference between the M×N - 1 maximum gray level values and the remaining gray level average values, or taking the minimum gray level value among the gray level average values corresponding to the M×N EL sub-images to obtain a second difference between the remaining gray level average values and the minimum gray level value; Constructing a difference ratio distribution map, obtaining the difference ratio distribution map through the first difference, determining the distribution of the ratio of the first difference, and comparing the ratio of the first difference with a first preset threshold: If the ratio of the first difference is greater than the first preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the first difference is less than or equal to the first preset threshold, the EL image of the photovoltaic module to be tested is qualified; Or, obtaining the difference ratio distribution map through the second difference, determining the distribution of the ratio of the second difference, and comparing the ratio of the second difference with a second preset threshold: If the ratio of the second difference is greater than the second preset threshold, the EL image of the photovoltaic module to be tested is abnormal; if the ratio of the second difference is less than or equal to the second preset threshold, the EL image of the photovoltaic module to be tested is qualified.

2. The EL detection method for a photovoltaic module according to claim 1, characterized in that It further includes the step of presetting a gray scale card. Different gray scale values in the gray scale card correspond to different saturations of black. Each pixel cell is compared with the gray scale card to determine the gray level value of each pixel cell.

3. The EL detection method for a photovoltaic module according to claim 2, wherein The step of comparing each pixel cell with the gray scale card to determine the gray level value of each pixel cell includes: The gray level value of the pixel cell is the gray scale value with the highest similarity in saturation to the gray scale card.

4. The EL detection method for a photovoltaic module according to claim 3, wherein The gray scale values in the gray scale card are greater than or equal to 0% and less than or equal to 100%.

5. The EL detection method for a photovoltaic module according to claim 1, wherein, M is an even number.

6. The EL detection method for a photovoltaic module according to claim 1, characterized in that, The areas of the M EL sub-images are all equal.

7. The EL detection method for a photovoltaic module according to claim 1, 5 or 6, characterized in that, M≤10。 8. An electronic device, characterized in that, It includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the photovoltaic module EL detection method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when the computer program is executed by a processor, it implements the photovoltaic module EL detection method according to any one of claims 1 to 7.

Images