Solar cell electrode anomaly detection method, device and equipment and storage medium

Abstract

The invention provides a solar cell electrode anomaly detection method and device, equipment and a storage medium. The detection method comprises the following steps: acquiring a plurality of battery piece images without electrode abnormal defects, extracting electrode area images in the battery piece images, and training to generate a standard electrode template; in the online production stage, an image of a to-be-detected battery piece is obtained, and an electrode area image in the to-be-detected battery piece is extracted; reading a standard electrode template, and carrying out difference on an electrode area image extracted from the to-be-detected battery piece image and the standard electrode template to obtain an image difference part; screening the image difference part according to a preset screening parameter and a screening mode to obtain an electrode abnormal defect area; and marking the screened electrode abnormal defect area and calculating defect details. The method can effectively detect the abnormal electrode defect of the battery piece, and can adapt to the change of a battery piece model.

Description

Technical Field

[0001] The present invention relates to the technical field of solar cell panels, and in particular to a method, device, equipment and storage medium for detecting abnormality of electrodes of solar cell panels. Background Art

[0002] Nowadays, battery cell appearance defect detection based on machine vision has become the mainstream method of battery cell defect detection and has become a huge driving force for the construction of smart workshops. However, the existing electrode defect detection methods have some shortcomings, especially in terms of version switching and detection efficiency.

[0003] Abnormal defects of battery cell electrodes mainly include abnormal electrode overflow and abnormal electrode missing. During the screen printing process, printed electrodes may be abnormal due to deformation, blockage or damage of the screen, as well as abnormal slurry concentration. Figure 1 and Figure 2 The scene shows the abnormal missing electrode. Figure 1 The upper side of the middle electrode a is abnormally missing. Figure 2 The right side of middle electrode a is abnormally missing. Figure 3 The scene of abnormal electrode overflow is shown. Figure 3 The upper right corner of the middle electrode a has an abnormal overflow.

[0004] Chinese patent CN111833309A proposes a photovoltaic cell detection method. The method first pre-processes the cell to obtain a pre-processed image; uses a threshold segmentation function to segment the pre-processed image to obtain a roughly positioned initial electrode image; then performs a closing operation on the initial click image, and intersects the closed image with the initial electrode image to obtain a precisely positioned electrode image; the area of ​​the electrode is determined in turn from the precisely positioned image, and the electrode with a smaller area threshold is an abnormal electrode defect.

[0005] The above method is a common method for defect detection of photovoltaic solar cells. Although it can achieve the purpose of defect detection, it has two fatal shortcomings. First, the threshold of the defect is very difficult to determine. Since the electrode area is very large (usually more than 10,000 pixels), especially when the defect area is small (about 10 pixels), it is very easy to cause misjudgment. Second, in the production environment, due to imaging and screen printing, the area of ​​the electrode itself fluctuates and is not a fixed value. Under this premise, this method will lead to a lot of over-judgment and missed judgment, and cannot effectively achieve detection. Summary of the invention

[0006] In order to solve at least one technical problem in the prior art, the embodiments of the present invention provide a method, device, equipment and storage medium for detecting abnormality of electrodes of solar cells, which can effectively detect abnormal defects of electrodes of solar cells and can adapt to changes in the format of solar cells. In order to achieve the above technical objectives, the technical solution adopted by the embodiments of the present invention is: In a first aspect, an embodiment of the present invention provides a method for detecting abnormality of electrodes of a solar cell, comprising the following steps: In the offline training stage, multiple images of battery cells without electrode abnormal defects are obtained and the electrode area images are extracted, and then trained to generate standard electrode templates; In the online production stage, the image of the battery cell to be inspected is obtained and the electrode area image is extracted; Read the standard electrode template, and perform a difference between the electrode area image extracted from the battery cell image to be tested and the standard electrode template to obtain the image difference part; For the image difference portion, the electrode abnormal defect area is obtained by screening according to the preset screening parameters and screening methods; The screened electrode abnormal defect areas are marked and the defect details are calculated.

[0007] Furthermore, the method of acquiring a plurality of battery cell images without electrode abnormal defects and extracting electrode area images therein, and then training and generating a standard electrode template specifically includes: Acquire multiple images of battery cells without electrode abnormal defects, perform image correction on each image of battery cells without electrode abnormal defects, transform the position and angle of the image of battery cells without electrode abnormal defects into standard position and standard angle respectively, and obtain standardized images of battery cells without electrode abnormal defects; For the standardized battery cell image without electrode abnormality defect, the electrode area image is extracted through the electrode fixed position; For all extracted electrode area images, standard electrode templates are generated by training and saved.

[0008] Furthermore, the step of acquiring the image of the battery cell to be inspected and extracting the electrode area image therein specifically includes: Acquire the image of the battery cell to be inspected, perform image deflection correction on the image of the battery cell to be inspected, transform the position and angle of the image of the battery cell to be inspected into a standard position and a standard angle respectively, and obtain a standardized image of the battery cell to be inspected; For the standardized image of the battery cell to be inspected, the electrode area image is extracted through the electrode fixed position.

[0009] More preferably, when extracting the electrode area image, it is necessary to first expand the extraction position corresponding to the electrode fixed position so that the extracted electrode area image is larger than the actual electrode area; the extracted electrode area image is 1.2 to 1.5 times the actual electrode area.

[0010] Furthermore, the reading of the standard electrode template and the difference between the electrode area image extracted from the battery cell image to be detected and the standard electrode template to obtain the image difference part specifically include: For the standard electrode template, any pixel The pixel value is recorded as , the variance is recorded as ; Set the upper pixel value and lower pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected, as shown in formulas (1) and (2) respectively; (1) (2) in, is the upper pixel value, is the lower pixel value, is an absolute parameter, is a relative parameter; The pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected Respectively with the upper pixel value and lower pixel value For comparison, if or The pixel point is recorded as the image difference point and is included in the image difference part.

[0011] Furthermore, the absolute parameter The value range of is [5, 50]; the relative parameter The value range of is [1, 10]; The method also includes adjusting the absolute parameter and the relative parameters , and again calculate the pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected Respectively with the upper pixel value and lower pixel value Make a comparison.

[0012] Further, the screening parameters include the area of ​​the difference portion, the length of the difference portion, the width of the difference portion and the aspect ratio of the difference portion; The screening methods include: When the area of ​​the difference part, the length of the difference part, the width of the difference part and the aspect ratio of the difference part are all greater than their respective corresponding thresholds, the image difference part is determined to be an abnormal defect area of ​​the electrode; Alternatively, when one of the difference portion area, the difference portion length, the difference portion width and the difference portion aspect ratio is greater than a corresponding threshold value, the image difference portion is determined to be an electrode abnormal defect region.

[0013] In a second aspect, an embodiment of the present invention provides a solar cell electrode abnormality detection device, comprising: The template training module is used to obtain multiple battery cell images without electrode abnormal defects and extract electrode area images therein during the offline training stage, and then train and generate a standard electrode template; An online extraction module is used to obtain the image of the battery cell to be inspected and extract the electrode area image therein during the online production stage; An image difference module is used to read the standard electrode template, and to perform a difference between the electrode area image extracted from the battery cell image to be detected and the standard electrode template to obtain the image difference part; A screening module, used for screening the image difference part to obtain the electrode abnormal defect area according to preset screening parameters and screening methods; The marking and calculation module is used to mark the screened electrode abnormal defect areas and calculate the defect details.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory storing a computer program; The processor is used to run the computer program, and when the computer program is run, the steps of the method for detecting abnormality of solar cell electrodes as described above are executed.

[0015] In a fourth aspect, an embodiment of the present invention provides a storage medium, wherein a computer program is stored in the storage medium, and the computer program is configured to execute the steps of the solar cell electrode abnormality detection method as described above when running.

[0016] The beneficial effects of the technical solution provided by the embodiment of the present invention are as follows: through the detection method proposed in the embodiment of the present invention, abnormal electrode defects of battery cells can be detected quickly and effectively; this detection method not only ensures the accuracy of abnormal electrode defect detection, but also takes into account the detection speed, and guarantees the high-efficiency operation of the production line to the greatest extent, and can significantly reduce the detection rhythm, providing strong support for improving production capacity. At the same time, the detection method also opens some adjustment parameters to users to obtain better detection results. Faced with the changing production environment of battery cell templates (different electrode shapes), it can quickly adapt to changes in the template and reduce the cost of template replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of a scenario of abnormal electrode loss in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of a second abnormal electrode missing scenario in an embodiment of the present invention.

[0019] Figure 3 Schematic diagram of an abnormal electrode overflow scenario in an embodiment of the present invention.

[0020] Figure 4 4 is a flow chart of the detection method in an embodiment of the present invention.

[0021] Figure 5 Schematic diagram of a detection device in an embodiment of the present invention.

[0022] Figure 6 Schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] In the description of the embodiments of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0025] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] like Figure 4 As shown, an embodiment of the present invention provides a method for detecting abnormality of electrodes of a solar cell, comprising the following steps: Step S10, in the offline training stage, obtains a plurality of battery cell images without electrode abnormal defects and extracts electrode area images therein, and then trains to generate a standard electrode template; specifically includes: Step S101, obtaining a plurality of images of battery cells without electrode abnormality defects, performing image correction on each image of battery cells without electrode abnormality defects, transforming the position and angle of the image of battery cells without electrode abnormality defects into a standard position and a standard angle, respectively, to obtain a standardized image of battery cells without electrode abnormality defects; In the embodiment of the present invention, the image processing process is performed by Halcon machine vision software; Specifically, the image can be rectified by using diagonal affine transformation or four-corner transmission transformation; During the offline training phase, it is usually necessary to obtain more than 20 images of battery cells without electrode abnormal defects and perform training; Step S102, for the standardized battery cell image without electrode abnormality defect, extracting the electrode area image therein by fixing the electrode position; In this step, since the electrode position in each standardized battery cell image without electrode abnormality defect is fixed, which is referred to as the electrode fixed position in this embodiment, the electrode area image can be extracted through the electrode fixed position; Preferably, when extracting the electrode area image, it is necessary to first expand the extraction position corresponding to the electrode fixed position so that the extracted electrode area image is larger than the actual electrode area; for example, the extraction position coordinates corresponding to the electrode fixed position are scaled by 1.2 to 1.5 times; thus, the extracted electrode area image is 1.2 to 1.5 times the actual electrode area; Step S103, for all extracted electrode region images, training and generating a standard electrode template and saving it; In this embodiment, the train_variation_model operator in Halcon can be used to train all extracted electrode area images and generate a standard electrode template; Step S20, in the online production stage, obtains the image of the battery cell to be inspected and extracts the electrode area image therein; specifically includes: Step S201, obtaining an image of a battery cell to be inspected, performing image deflection correction on the image of the battery cell to be inspected, transforming the position and angle of the image of the battery cell to be inspected into a standard position and a standard angle respectively, and obtaining a standardized image of the battery cell to be inspected; The processing process of this step is the same as step S101; Step S202, for the standardized battery cell image to be inspected, extracting the electrode area image therein by using the electrode fixed position; The processing process of this step is the same as step S102; Preferably, when extracting the electrode area image, it is necessary to first expand the extraction position corresponding to the electrode fixed position so that the extracted electrode area image is larger than the actual electrode area; for example, the extraction position coordinates corresponding to the electrode fixed position are scaled by 1.2 to 1.5 times; thus, the extracted electrode area image is 1.2 to 1.5 times the actual electrode area; Step S30, reading the standard electrode template, performing a difference between the electrode area image extracted from the cell image to be detected and the standard electrode template, and obtaining the image difference part; specifically comprising: Step S301: for a standard electrode template, any pixel point The pixel value is recorded as , the variance is recorded as ; Set the upper pixel value and lower pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected, as shown in formulas (1) and (2) respectively; (1) (2) in, is the upper pixel value, is the lower pixel value, is an absolute parameter, is a relative parameter; Preferably, the absolute parameter The value range of is [5, 50]; the relative parameter The value range of is [1, 10]; when the detection effect is not good, the absolute parameter can be adjusted and the relative parameters ; In a preferred embodiment, the absolute parameter The value is 20, the relative parameter The value of is 3; Step S302: The pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected is Respectively with the upper pixel value and lower pixel value For comparison, if or Then the pixel point is recorded as the image difference point and is included in the image difference part; Optional step S303, adjusting the absolute parameter and the relative parameters , and again calculate the pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected Respectively with the upper pixel value and lower pixel value Make comparisons; Step S40, for the image difference portion, screening to obtain the electrode abnormal defect area according to the preset screening parameters and screening method; In one embodiment, the screening parameters include differential portion area, differential portion length, differential portion width, and differential portion aspect ratio; In one embodiment, the screening method includes: when the area of ​​the difference part, the length of the difference part, the width of the difference part and the aspect ratio of the difference part are all greater than their respective corresponding thresholds, the image difference part is determined as an abnormal defect area of ​​the electrode; In another embodiment, the screening method includes: when one of the difference portion area, the difference portion length, the difference portion width and the difference portion aspect ratio is greater than a corresponding threshold value, the image difference portion is determined as an electrode abnormal defect region; Step S50, marking the screened electrode abnormal defect area and calculating the defect details; In this step, the screened electrode abnormal defect region is first marked, and then the defect details are calculated, including: calculating the electrode abnormal defect region area, the electrode abnormal defect region length, the electrode abnormal defect region width and the electrode abnormal defect region center coordinates for the screened electrode abnormal defect region; After marking the electrode abnormal defect area, the marking information can be returned to the host computer for display; after calculating the area of ​​the electrode abnormal defect area, the length of the electrode abnormal defect area, the width of the electrode abnormal defect area and the center coordinates of the electrode abnormal defect area, the area of ​​the electrode abnormal defect area, the length of the electrode abnormal defect area, the width of the electrode abnormal defect area and the center coordinates of the electrode abnormal defect area can also be returned to the host computer for business judgment.

[0028] The solar cell electrode anomaly detection method proposed in the embodiment of the present invention can quickly adapt to the changes in the layout of the solar cell (different electrode shapes) in the production environment, thereby reducing the cost of layout replacement; it can also adapt to the electrode anomaly detection in two scenarios: abnormal electrode overflow and abnormal electrode missing.

[0029] like Figure 5 As shown, the embodiment of the present invention also provides a solar cell electrode abnormality detection device, comprising: The template training module is used to obtain multiple battery cell images without electrode abnormal defects and extract electrode area images therein during the offline training stage, and then train and generate a standard electrode template; An online extraction module is used to obtain the image of the battery cell to be inspected and extract the electrode area image therein during the online production stage; An image difference module is used to read the standard electrode template, and to perform a difference between the electrode area image extracted from the battery cell image to be detected and the standard electrode template to obtain the image difference part; A screening module, used for screening the image difference part to obtain the electrode abnormal defect area according to preset screening parameters and screening methods; The marking and calculation module is used to mark the screened electrode abnormal defect areas and calculate the defect details.

[0030] like Figure 6 As shown, an embodiment of the present invention further proposes an electronic device, comprising: a processor and a memory; the processor and the memory communicate with each other, for example, are connected and communicate with each other through a bus; a computer program is stored in the memory; the processor is used to run the computer program, and when the computer program is running, the steps of the solar cell electrode abnormality detection method as described above are executed; the processor can be a CPU, or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components and other devices; the memory can include volatile memory, such as random access memory; the memory can also include non-volatile memory, such as flash memory, hard disk or solid state drive; the memory can also include a combination of the above-mentioned types of memory.

[0031] An embodiment of the present invention further proposes a storage medium, in which a computer program is stored, and the computer program is configured to execute the steps of the solar cell electrode abnormality detection method as described above when running; the storage medium includes a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated: HDD) or a solid-state drive (SSD), etc. and any combination thereof.

[0032] Finally, it should be noted that the above specific implementation methods are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A method for detecting abnormality of electrodes of solar cells, characterized in that: The following steps are involved: In the offline training stage, multiple battery cell images without electrode abnormality defects are obtained and the electrode area images are extracted, and then trained to generate a standard electrode template; In the online production stage, the image of the battery cell to be inspected is obtained and the electrode area image is extracted; Read the standard electrode template, and perform a difference between the electrode area image extracted from the battery cell image to be tested and the standard electrode template to obtain the image difference part; For the image difference portion, the electrode abnormal defect area is obtained by screening according to the preset screening parameters and screening methods; The screened electrode abnormal defect areas are marked and the defect details are calculated.

2. The method for detecting abnormality of a solar cell electrode according to claim 1, wherein: The method of acquiring multiple battery cell images without electrode abnormal defects and extracting electrode area images therein, and then training and generating a standard electrode template specifically includes: Acquire multiple images of battery cells without electrode abnormal defects, perform image correction on each image of battery cells without electrode abnormal defects, transform the position and angle of the image of battery cells without electrode abnormal defects into standard position and standard angle respectively, and obtain standardized images of battery cells without electrode abnormal defects; For the standardized battery cell image without electrode abnormality defect, the electrode area image is extracted through the electrode fixed position; For all extracted electrode area images, standard electrode templates are generated and saved.

3. The method for detecting abnormality of a solar cell electrode according to claim 1, wherein: The step of acquiring the image of the battery cell to be inspected and extracting the electrode area image therein specifically includes: Acquire the image of the battery cell to be inspected, perform image deflection correction on the image of the battery cell to be inspected, transform the position and angle of the image of the battery cell to be inspected into a standard position and a standard angle respectively, and obtain a standardized image of the battery cell to be inspected; For the standardized image of the battery cell to be inspected, the electrode area image is extracted through the electrode fixed position.

4. The method for detecting abnormality of a solar cell electrode according to claim 2 or 3, characterized in that: When extracting the electrode area image, it is necessary to first expand the extraction position corresponding to the electrode fixed position so that the extracted electrode area image is larger than the actual electrode area; the extracted electrode area image is 1.2 to 1.5 times the actual electrode area.

5. The method for detecting abnormality of a solar cell electrode according to claim 1, wherein: The step of reading the standard electrode template and performing a difference between the electrode region image extracted from the cell image to be detected and the standard electrode template to obtain the image difference portion specifically includes: For the standard electrode template, any pixel The pixel value is recorded as , the variance is recorded as ; Set the upper pixel value and lower pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected, as shown in formulas (1) and (2) respectively; (1) (2) in, is the upper pixel value, is the lower pixel value, is an absolute parameter, is a relative parameter; The pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected Respectively with the upper pixel value and lower pixel value For comparison, if or The pixel point is recorded as the image difference point and is included in the image difference part.

6. The method for detecting abnormality of a solar cell electrode according to claim 5, characterized in that: The absolute parameter The value range of is [5, 50]; the relative parameter The value range of is [1, 10]; The method also includes adjusting the absolute parameter and the relative parameters , and again calculate the pixel value of any pixel point in the electrode area image extracted from the battery cell image to be detected Respectively with the upper pixel value and lower pixel value Make a comparison.

7. The method for detecting abnormality of a solar cell electrode according to claim 1, wherein: The screening parameters include the area of ​​the difference portion, the length of the difference portion, the width of the difference portion and the aspect ratio of the difference portion; The screening methods include: When the area of ​​the difference part, the length of the difference part, the width of the difference part and the aspect ratio of the difference part are all greater than their respective corresponding thresholds, the image difference part is determined to be an abnormal defect area of ​​the electrode; Alternatively, when one of the difference portion area, the difference portion length, the difference portion width and the difference portion aspect ratio is greater than a corresponding threshold value, the image difference portion is determined to be an electrode abnormal defect region.

8. A solar cell electrode abnormality detection device, characterized in that: include: The template training module is used to obtain multiple battery cell images without electrode abnormal defects and extract electrode area images therein during the offline training stage, and then train and generate a standard electrode template; An online extraction module is used to obtain the image of the battery cell to be inspected and extract the electrode area image therein during the online production stage; An image difference module is used to read the standard electrode template, and to perform a difference between the electrode area image extracted from the battery cell image to be detected and the standard electrode template to obtain the image difference part; A screening module, used for screening the image difference part to obtain the electrode abnormal defect area according to preset screening parameters and screening methods; The marking and calculation module is used to mark the screened electrode abnormal defect areas and calculate the defect details.

9. An electronic device, characterized in that: include: a memory storing a computer program; The processor is used to run the computer program, and when the computer program is run, the steps of the solar cell electrode abnormality detection method according to any one of claims 1 to 7 are executed.

10. A storage medium, characterized in that: The storage medium stores a computer program, and the computer program is configured to execute the steps of the solar cell electrode abnormality detection method according to any one of claims 1 to 7 when running.

Images