Graphite boat image processing method, battery cell defect detection method and coating system

Abstract

The present application discloses a graphite boat image processing method, a cell defect detection method and a coating system, the method comprising: obtaining a first image of a graphite boat, wherein cells are loaded in a plurality of boat slots of the graphite boat, the first image comprising an imaging area of ​​a marking light projected on the boat leaf and the cell of the graphite boat, the angle between the projection plane of the marking light and the visual axis of an image acquisition device for acquiring the first image being a preset angle; cropping the first image to obtain a plurality of partial images, each of which corresponds to a boat slot; for the first partial image, performing a first region segmentation on the first partial image according to the color value of the marking light, determining a marking region in the first partial image; determining first detection information of the boat slot corresponding to the first partial image according to the position distribution information of pixels in the marking region, the first detection information comprising the loading state information and / or loading position information of the boat slot. The cost of cell defect detection can be reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of graphite boat image processing, and in particular, relates to a graphite boat image processing method, a battery cell defect detection method and a coating system. Background Art

[0002] In recent years, Plasma Enhanced Chemical Vapor Deposition (PECVD) technology has been widely used in the fields of solar cells, biomedicine, nanodevices, semiconductor devices, etc. Taking the use of an automated PECVD system to coat cells as an example, the graphite boat is the carrier for cell coating. Its internal structure is designed with multiple boats with a certain interval, and the cells are attached to both sides of the boat. During the coating process, the two adjacent boats will form positive and negative poles due to the applied voltage, so that glow discharge occurs, ionizing the silane and ammonia gases in the chamber to form a silicon nitride film deposited on the surface of the silicon wafer to achieve the purpose of coating. Affected by various factors, before or after coating, there may be abnormalities such as cell warping and cell missing in the graphite boat, which may have an adverse effect on the coating or subsequent cell processing flow.

[0003] Abnormal defects of cells in a graphite boat can be automatically detected by visual inspection. However, due to the thinness of the cells, the small spacing between the cells and the graphite boat pages, and the close color of the cells and the graphite boat, the identification of cells in a graphite boat in the prior art usually relies on harsh light source conditions, extremely high shooting accuracy, and complex image processing methods, resulting in high cost and low detection accuracy for cell defect detection in a graphite boat. Summary of the invention

[0004] The embodiments of the present application provide a graphite boat image processing method, a battery cell defect detection method, an apparatus, a terminal device, a battery cell coating system, a computer-readable storage medium, and a computer program product, which can simplify the battery cell defect detection process in the graphite boat, help reduce the detection cost of battery cell defects in the graphite boat, and improve the detection accuracy.

[0005] A first aspect of an embodiment of the present application provides a graphite boat image processing method, comprising:

[0006] Acquire a first image of a graphite boat, wherein multiple boat slots of the graphite boat are loaded with battery cells, the first image includes an imaging area of ​​a marking light projected onto a boat leaf and the battery cells of the graphite boat, and an angle between a projection plane of the marking light and a visual axis of an image acquisition device for acquiring the first image is a preset angle, and the preset angle is greater than 0 and less than an angle threshold;

[0007] cropping the first image to obtain a plurality of partial images, wherein each partial image corresponds to a boat tank;

[0008] For a first partial image among the multiple partial images, performing a first region segmentation on the first partial image according to the color value of the marking light, and determining a marking region in the first partial image, wherein the marking region is an imaging region of the marking light;

[0009] According to the position distribution information of the pixels in the marked area, first detection information of the boat corresponding to the first partial image is determined, wherein the first detection information includes film loading state information and / or film loading position information of the boat.

[0010] In one implementation, determining first detection information of the boat tank corresponding to the first partial image according to position distribution information of pixels in the marked area includes:

[0011] Determine an upper boat page marking area and a lower boat page marking area in the marking area according to coordinate components of each pixel in the marking area in a first direction, wherein the first direction is an image width direction of the partial image;

[0012] Determine a first search area and a second search area in the first partial image according to coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, wherein the second direction is an image height direction of the partial image;

[0013] The first detection information of the boat slot corresponding to the first partial image is determined according to the relative position relationship between the first search area and the second search area and other marking areas, wherein the other marking areas are areas other than the upper boat page marking area and the lower boat page marking area in the marking area.

[0014] In one embodiment, the first detection information includes film loading status information of the boat, and determining the first detection information of the boat corresponding to the first partial image according to the relative position relationship between the first search area and the second search area and other marking areas respectively includes:

[0015] In the case where there is an intersection area between the first search area and the other marking area, determining that the film loading state information of the boat slot is the first state information indicating that there is an upper film loading;

[0016] In the case where there is no intersection area between the first search area and the other marking area, determining that the film loading state information of the boat slot is the second state information indicating that there is no upper film loading;

[0017] In the case where there is an intersection area between the second search area and the other marking area, determining that the film loading state information of the boat slot is the third state information indicating that there is a lower loaded film;

[0018] In the case that there is no intersection area between the second search area and the other marking areas, the film loading state information of the boat slot is determined to be fourth state information indicating that there is no lower loaded film.

[0019] In one embodiment, the first detection information includes the film loading position information of the boat, and the first detection information of the boat corresponding to the first partial image is determined according to the relative position relationship between the first search area and the second search area and other marking areas, and further includes:

[0020] When it is determined that the film loading state information of the boat is the first state information, determining the position information of the upper film loading in the boat according to the coordinate components of the pixels in the intersection area between the first search area and the other marking area in the second direction;

[0021] When the film loading state information of the boat is determined to be the third state information, the position information of the lower loaded film in the boat is determined according to the coordinate components of the pixels in the intersection area between the second search area and other marking areas in the second direction.

[0022] In one embodiment, determining the first search area and the second search area in the first partial image according to the coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction includes:

[0023] Determine the minimum value of the coordinate component of each pixel in the mark area of ​​the upper boat page in the second direction;

[0024] Determine the maximum value of the coordinate component of each pixel in the mark area of ​​the lower boat page in the second direction;

[0025] Based on the minimum value and the maximum value, a first search area and a second search area are determined, wherein the coordinate component of the pixels in the first search area in the second direction is greater than or equal to the average of the maximum value and the minimum value and is less than the minimum value, and the coordinate component of the pixels in the second search area in the second direction is greater than the maximum value and is less than or equal to the average value.

[0026] In one embodiment, before determining the first search area and the second search area in the first partial image, the method further includes:

[0027] Determine the offset distance between the first projection portion and the second projection portion of the marking light according to the preset angle and the first distance, wherein the first distance is the distance between the first surface of the boat page in each boat slot and the second surface of the battery sheet, the first projection portion is located on the first surface, the second projection portion is located on the second surface, and the first surface and the second surface are perpendicular to the visual axis;

[0028] Determining a first search area and a second search area in a first partial image according to coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, including:

[0029] A first search area and a second search area are determined according to the offset distance, the coordinate components of each pixel in the upper boat page mark area in the first direction, and the coordinate components of each pixel in the lower boat page mark area in the first direction.

[0030] A second aspect of an embodiment of the present application provides a method for detecting defects in a battery cell, comprising:

[0031] Before pushing the graphite boat loaded with the battery cells into the coating furnace and / or after moving the graphite boat out of the coating furnace, using the graphite boat image processing method to determine the first detection information of each boat slot of the graphite boat;

[0032] Defect detection information of the battery cells in each boat slot of the graphite boat is determined according to the first detection information.

[0033] In one embodiment, the first detection information includes the cell loading status information of the boat slot, and the defect detection information of the cell in each boat slot of the graphite boat is determined according to the first detection information, including:

[0034] For each boat, when the cell loading state information of the boat is the first state information or the second state information, determining that the defect detection information of the cells in the boat is cell missing defect information indicating that the cells are missing;

[0035] and / or

[0036] The first detection information includes the cell loading position information of the boat slot. According to the first detection information, the defect detection information of the cell in each boat slot of the graphite boat is determined, including:

[0037] For each boat slot, determine the relative distance between the battery cell and the corresponding boat page according to the position of the battery cell loaded in the boat slot;

[0038] When the relative distance is greater than the relative distance threshold, it is determined that the defect detection information of the battery cell in the boat is warping defect information indicating that the battery cell is warped.

[0039] In one embodiment, before determining the marked area in the first partial image, the method further includes:

[0040] For each of the multiple partial images,

[0041] Performing a second region segmentation on the local image according to the color value of the boat page and the color value of the battery cell, and determining the boat page region and the battery cell region in the local image;

[0042] Determine initial defect detection information of the battery cell in the boat slot corresponding to the local image according to the number of battery cell regions and the relative position relationship between each battery cell region and the corresponding boat page region;

[0043] When the initial defect detection information indicates that a battery cell is missing, the partial image is used as the first partial image.

[0044] A third aspect of an embodiment of the present application provides a graphite boat image processing device, comprising:

[0045] An acquisition module is used to acquire a first image of a graphite boat, wherein multiple boat slots of the graphite boat are loaded with battery cells, the first image includes an imaging area of ​​a marking light projected onto a boat leaf and the battery cells of the graphite boat, and an angle between a projection plane of the marking light and a visual axis of an image acquisition device for acquiring the first image is a preset angle, and the preset angle is greater than 0 and less than an angle threshold;

[0046] A cropping module, used for cropping the first image to obtain a plurality of partial images, wherein each partial image corresponds to a boat tank;

[0047] a segmentation module, configured to perform a first region segmentation on a first partial image among the plurality of partial images according to a color value of the marking light, and determine a marking region in the first partial image, wherein the marking region is an imaging region of the marking light;

[0048] The first detection module is used to determine first detection information of the boat corresponding to the first partial image according to position distribution information of pixels in the marked area, wherein the first detection information includes film loading state information and / or film loading position information of the boat.

[0049] A fourth aspect of an embodiment of the present application provides a battery cell defect detection device, comprising:

[0050] An image processing module, used for determining first detection information of each boat slot of the graphite boat using the above-mentioned graphite boat image processing method before pushing the graphite boat loaded with battery cells into the coating furnace and / or after moving the graphite boat out of the coating furnace;

[0051] The second detection module is used to determine defect detection information of the battery cells in each boat slot of the graphite boat according to the first detection information.

[0052] The fifth aspect of an embodiment of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of a graphite boat image processing method and / or the steps of a battery cell defect detection method when executing the computer program.

[0053] A sixth aspect of the embodiments of the present application provides a cell coating system, comprising: a graphite boat, a coating furnace, a marking light projector, an image acquisition device, and a control device, wherein the control device is connected to the marking light projector and the image acquisition device, respectively, and the control device is used to:

[0054] Before the graphite boat is pushed into the coating furnace and / or after the graphite boat is moved out of the coating furnace, and when the graphite boat is located at the center of the field of view of the image acquisition device and the marking light projector, control the marking light projector to project the marking light onto the graphite boat;

[0055] Controlling the image acquisition device to acquire an image of the graphite boat to obtain a first image;

[0056] Execute the steps of the above-mentioned graphite boat image processing method and / or the steps of the above-mentioned battery cell defect detection method.

[0057] A seventh aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned graphite boat image processing method and / or the steps of the battery cell defect detection method are implemented.

[0058] An eighth aspect of an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to implement the steps of the above-mentioned graphite boat image processing method and / or the steps of the battery cell defect detection method.

[0059] The first aspect of the embodiment of the present application provides a graphite boat image processing method. First, a first image of the graphite boat is acquired. Since the image is collected when a marking light is projected onto the boat page and the battery cell of the graphite boat, the first image includes an imaging area of ​​the marking light. Then, the first partial image among the multiple partial images obtained by cropping is subjected to regional segmentation, and the marking area in the first partial image can be quickly and accurately determined. Since the angle between the projection plane of the marking light projected onto the graphite boat and the visual axis of the image acquisition device is greater than 0, the position of the projection area of ​​the marking light in the marking area on the battery cell is different from the position of the projection area on the boat page. Therefore, the loading state information and / or loading position information of the boat slot corresponding to the first partial image can be quickly and accurately determined based on the position distribution information of the pixels in the marking area. The processing efficiency and processing accuracy of this scheme are significantly improved, and the device cost of this scheme is lower and the amount of calculation consumed is also smaller.

[0060] It can be understood that the beneficial effects of the second to eighth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0062] Figure 1 It is a partial schematic diagram of a graphite boat image collected in the prior art;

[0063] Figure 2 is a schematic flow chart of a graphite boat image processing method provided by an embodiment of the present application;

[0064] Figure 3 This is a schematic diagram of a working scenario of a PECVD system provided by an embodiment of the present application;

[0065] Figure 4 is a schematic diagram of a first image acquisition scene provided by an embodiment of the present application;

[0066] Figure 5a is another schematic diagram of a first image acquisition scene provided by an embodiment of the present application;

[0067] Figure 5b yes Figure 5a An enlarged schematic diagram of the schematic area in FIG.

[0068] Figure 5c is a schematic diagram of a first search area and a second search area provided by an embodiment of the present application;

[0069] Figure 6 is a schematic flow chart of a cell defect detection method provided by an embodiment of the present application;

[0070] Figure 7 is a structural schematic diagram of a graphite boat image processing device provided by an embodiment of the present application;

[0071] Figure 8 is a schematic diagram of the structure of a battery cell defect detection device provided by an embodiment of the present application;

[0072] Fig. 9 is a schematic diagram of the structure of a terminal device provided by an embodiment of the present application;

[0073] Fig.10 It is a schematic diagram of the structure of a cell coating system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0074] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0075] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0076] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0077] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0078] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0079] As mentioned above, since the battery cells are thin, the spacing between the battery cells and the pages of the graphite boat is small, and the color of the battery cells and the graphite boat are darker and closer, the identification of battery cells in the graphite boat in the prior art usually relies on harsh light source conditions, extremely high shooting accuracy and complex image processing methods, resulting in high cost and low detection accuracy for battery cell defect detection in the graphite boat.

[0080] like Figure 1As shown, in the graphite boat image captured in the prior art, many cells are integrated with the background, making it difficult to detect all cells effectively. Some solutions use multiple high-precision cameras to capture images of the graphite boat from different angles, in the hope of combining the graphite boat images captured by different cameras to detect cells. However, the device cost and image processing calculation amount of this solution are both large.

[0081] In order to at least partially solve the above technical problems, the first aspect of the embodiments of the present application provides a graphite boat image processing method. The graphite boat image processing method can be applied to various suitable automated silicon wafer coating systems, such as automated PECVD systems, and can be specifically used to detect cells in a graphite boat before and after coating. Figure 2 As shown, the graphite boat image processing method provided in the embodiment of the present application includes the following steps:

[0082] Step S210, obtaining a first image of the graphite boat, wherein multiple boat slots of the graphite boat are loaded with battery cells, the first image includes an imaging area of ​​the marking light projected on the boat pages and battery cells of the graphite boat, and the angle between the projection plane of the marking light and the visual axis of the image acquisition device for acquiring the first image is a preset angle, which is greater than 0 and less than an angle threshold.

[0083] In the embodiment of the present application, a variety of suitable image acquisition devices can be used to acquire images of the graphite boat, including but not limited to various types of area array cameras and line array cameras. For example, the graphite boat can be photographed by an area array camera to obtain a first image, and the area array camera can include a telecentric lens, so that the first image captured by the area array camera is more realistic, making subsequent detection more accurate.

[0084] In the embodiment of the present application, the first image is a color image, such as an RGB image, a CMYK image, etc. The first image may be an original image acquired by an image acquisition device, or may be a processed image obtained by performing processing such as filtering, cropping, or image stitching on the original image.

[0085] In the embodiment of the present application, the first image may be an image including the complete imaging area of ​​the graphite boat, or may be an image including only a partial imaging area of ​​the graphite boat. For example, a camera is used to photograph different parts of the graphite boat to obtain multiple small images. Then, the multiple small images are stitched together using an image stitching method to obtain the first image. For another example, the image of the partial area of ​​the graphite boat captured by the camera each time may be directly used as the first image. For example, the shooting area of ​​the camera may correspond to Figure 1The portion of the graphite boat shown in FIG. This portion can accommodate a row of battery cells, which is referred to as a boat page row for simplicity. For example, the graphite boat includes 6 boat page rows. Optionally, the camera can be fixedly mounted above the graphite boat, and each boat page row of the graphite boat can be photographed at different times during the movement of the graphite boat, so that 6 first images can be captured for each graphite boat. Alternatively, when the graphite boat is stationary, the camera can be controlled to slide along the sliding track above the graphite boat, and each time the camera moves above a boat page row, the camera is controlled to shoot, and a first image corresponding to each boat page row is obtained.

[0086] The following uses the PECVD automation system as an example to explain the capture scenario of the first image. In the embodiment of the present application, the image of the graphite boat can be captured by a camera before the graphite boat enters the coating furnace to obtain the first image; the image of the graphite boat can also be captured after the graphite boat is removed from the coating furnace to obtain the first image. For example, on a cell production line, the cell to be coated can be located in a cell basket, and the cell can be taken out of the cell basket in advance by a robotic arm and automatically loaded into the cell basket. Figure 3 In the graphite boat shown in FIG. Figure 3 As shown, the graphite boat can be placed horizontally, the plane where the boat pages of the graphite boat are located can be parallel to the xoz plane in the figure, and the camera can take a bird's-eye view of the graphite boat from the top, that is, the camera's visual axis can be parallel to the z-axis, that is, the camera takes a picture of the graphite boat in the opposite direction of the z-axis in the figure.

[0087] It can be understood that since the battery cells are loaded into the boat groove formed by two adjacent boat pages, under ideal shooting conditions, the camera can capture the upper surface of each boat page (the surface in the thickness direction of the boat page, hereinafter referred to as the first surface) and the surface in the thickness direction of the battery cell (parallel to the first surface of the boat page). Figure 3 The xoy plane in the graphite boat is referred to as the second surface hereinafter). Since the thickness of the boat sheet is about 2.5 mm and the thickness of the cell is about 200 μm, the imaging area of ​​the boat sheet in the first image is larger than the imaging area of ​​the cell. When the lighting conditions are limited and the distance between the individual cell and the boat sheet is close, it may be difficult to effectively identify the imaging area of ​​the cell from the graphite boat image taken by the camera.

[0088] In order to solve this problem, in the embodiment of the present application, the operation of the camera collecting the graphite boat image (such as the first image) is performed under the condition that a marking light is projected onto the surface of the graphite boat. Figure 3 Before the camera captures the image of the graphite boat, the marking light projector located above the graphite boat can be controlled to project a marking light. The marking light can be a straight line with a preset color. The difference between the preset color and the color of the graphite boat is greater than or equal to a difference threshold. The graphite boat is usually black, and the preset color can be, for example, a color with higher brightness, such as red or green. For example, Figure 3 The marking light projector in the image may be a laser projector. The laser projector and the camera may be set at the same height (i.e., the z coordinates of the two may be equal) to reduce the risk of mutual interference. For example, the distance between the projection of the center of the laser projector and the camera on the horizontal plane and the projection of the center of the battery cell in the boat column to be photographed on the horizontal plane is less than or equal to the distance threshold, so that the battery cell in the boat column to be photographed can be in the visual center area of ​​the camera, and the marking light emitted by the laser projector can be projected near the center position of the second surface of the battery cell, which is convenient for subsequent detection of the position of the battery cell.

[0089] Combination Figure 3 and Figure 4 , the laser projector can be along the plane l Projection red laser line, flat surface l Can be perpendicular to Figure 3 The xoz plane in the l It can be at a preset angle θ with the camera visual axis. The preset angle is greater than 0 and less than the angle threshold. The angle threshold can be set according to the width of the battery cell and the distance between the second surface of the battery cell and the first surface of the boat page (corresponding to the absolute value of the z-coordinate difference between the two planes). Exemplarily, the distance threshold can be less than 1 / 2 of the width of the battery cell. For example, if the height difference between the second surface of the battery cell and the first surface of the boat page is equal to 1 cm, and the width of the battery cell is 3 cm, the angle threshold can be greater than 10° and less than 45°.

[0090] In the embodiment of the present application, when it is determined that the area to be photographed of the graphite boat (for example, the boat page column to be photographed) is located at the center of the field of view of the marking light projector and the image acquisition device, the marking light projector can be controlled to project the marking light to the graphite boat, and then the image acquisition device can be controlled to acquire the image of the graphite boat to obtain the first image. For example, at the moment when each boat page column of the graphite boat is located at the center of the field of view of the laser projector and the camera, the laser projector is first controlled to project a red laser line to the surface of the graphite boat, and then at the next moment, the camera with a telecentric lens is controlled to capture the image of the boat page column below, and the first image corresponding to each boat page column is obtained.

[0091] It is easy to understand that since the first surface of the boat page and the second surface of the battery cell are not blocked by other objects, the marking light projector can project the marking light on the first surface of each boat page and the second surface of the battery cell of the current boat page column. Specifically, it can be the intersection area of ​​the first surface and the second surface with the marking light projection plane. The width of the marking light can be greater than 0 and less than the width threshold. The width threshold can be set according to actual needs, for example, 3mm. The width of the marking light can be 1mm, for example. Taking the thickness of the boat page as 2.5mm and the thickness of the battery cell as 200μm as an example, without considering the influence of other interference factors, the projection part of the marking light on the first surface of the boat page is approximately a rectangular area of ​​2.5mm*1mm, and the projection part of the marking light on the second surface of the battery cell is approximately a rectangular area of ​​0.2mm*1mm. Since the brightness of the marking light is higher than the brightness of the graphite boat and the battery cell, these projection parts of the marking light projected on the boat page and the battery cell can be clearly imaged in the first image. That is, the first image can include the marking area corresponding to these projection parts.

[0092] Step S220, cropping the first image to obtain a plurality of partial images, wherein each partial image corresponds to a boat tank.

[0093] In an embodiment of the present application, a boat groove may be a groove-shaped space between two boat leaves located adjacently in the same boat leaf row. Each boat leaf row may include a preset number of boat grooves. The preset number is, for example, 29. The entire graphite boat may include 174 boat grooves. For a case where the first image corresponds to a boat leaf row of a graphite boat, the first image may be cropped into 29 partial images. For a case where the first image corresponds to a complete graphite boat, the first image may be cropped into 174 partial images. In an embodiment of the present application, each partial image may include an imaging area (for example, referred to as an upper boat leaf and a lower boat leaf) of two boat leaves (for example, referred to as an upper boat leaf area and a lower boat leaf area) and an imaging area (for example, referred to as a boat groove area) of the groove between the boat leaves. For a case where a battery cell is loaded in the boat groove, the boat groove area may also include an imaging area (for example, referred to as a battery cell area) of the battery cell. Of course, the partial image also includes the imaging area of ​​the projection part of the marking light on the corresponding upper boat page, lower boat page and battery sheet. In some cases, the partial image may also include the imaging area of ​​the projection part of the marking light on the bottom of the boat tank. These imaging areas obtained by projecting the marking light may be referred to as projection areas. The colors of these projection areas are different from the colors of the non-projection areas outside the projection areas.

[0094] In an embodiment of the present application, a variety of suitable methods can be used to crop the first image. The following is an example of a boat page column corresponding to a graphite boat in the first image. In a specific example, the first image can be cropped by a template matching method. For example, a template image corresponding to each boat page column of the graphite boat can be pre-collected and marked (the template image may not include a marked area). Specifically, the position frame of each cropping area in the template image and the code of each cropping area can be marked. Each cropping area corresponds to a boat groove. The position frame of each cropping area can be a rectangular outer envelope of the image area including the upper boat page area, the boat groove area and the lower boat page area. The code of each cropping area is represented by "m_n", for example. m can represent the digital number corresponding to the current boat page column, and n can represent the digital number corresponding to the row where the boat groove is located. For example: "6_15" represents the boat groove located in the 15th row of the 6th column. After a first image is collected, the corresponding template image can be feature matched, and the first image can be affine transformed according to the matching result so that the size of the imaging area of ​​the boat page column in the first image is equal to the size and position of the imaging area of ​​the boat page column in the template image. Furthermore, the first image may be cropped according to the position boxes of the cropping areas marked in the template image to obtain a plurality of partial images, and the code corresponding to each partial image may be stored.

[0095] Step S230 , for a first partial image among the multiple partial images, performing a first region segmentation on the first partial image according to the color value of the marking light, and determining a marking region in the first partial image, wherein the marking region is an imaging region of the marking light.

[0096] In the embodiment of the present application, the first partial image may be each partial image or each of the partial partial images. In the latter case, the first partial image may be a partial image that satisfies the marking area segmentation condition selected from the multiple partial images obtained in step S220 by various suitable methods. For example, before controlling the laser projector to emit a red laser line to the graphite boat, the second image of the graphite boat may be collected first. And the method of the above step S220 may be used to segment the partial images corresponding to each boat groove. Then, the conventional cell defect detection method may be used to determine whether the cell in each boat groove has defects and determine the defect type (such as missing cell, warped cell, broken cell, etc.). As mentioned above, the identification of cells in the graphite boat in the prior art usually relies on harsh light source conditions, extremely high shooting accuracy and complex image processing methods. Therefore, when these conditions are limited, there may be an over-inspection phenomenon, such as the failure to identify the cells in some boat grooves, thus erroneously determining the boat groove containing normal cells as a boat groove with missing cells. In one example, if a conventional cell defect detection method is used to preliminarily determine that a certain boat has a cell missing defect, it can be determined that the local image corresponding to the boat satisfies the marked area segmentation condition. For example, if it is preliminarily determined that a boat corresponding to a local image coded as "6_15" has a cell missing defect, the local image coded as "6_15" is used as the first local image to perform this step S230.

[0097] As mentioned above, in the embodiment of the present application, the difference between the color value of the marking light and the color value of the graphite boat is greater than the difference threshold. Therefore, in this step, a suitable segmentation threshold can be set according to the difference between the color value of the marking light and the color value of the graphite boat, and the local image can be segmented according to the segmentation threshold, so that the marked area in the local image can be obtained quickly and accurately. For example, R value = 200, G value = 80, B value = 80, that is, the pixels whose R value is greater than or equal to 200 and whose G value and B value are both less than 80 can be used as marked pixels, and the other pixels in the local image except the marked pixels can be used as non-marked pixels. Each area composed of marked pixels can be used as a marked area, and each area composed of non-marked pixels can be used as a non-marked area.

[0098] In one example, the marking area may include: the imaging area of ​​the projection part of the marking light on the corresponding upper boat page, lower boat page and battery sheet, and the imaging area of ​​the projection part of the marking light on the bottom of the boat tank. That is, the marking area may include various projection areas of the marking light.

[0099] In another example, the marking area may only include the imaging area of ​​the projection part of the marking light on the corresponding upper boat page, lower boat page and battery cell. In this example, the imaging area of ​​the projection part of the marking light at the bottom of the boat tank can be filtered out in advance by setting a suitable segmentation threshold. It can be understood that, under normal circumstances, the height of the boat page of the graphite boat (z-axis direction) exceeds 20cm, so some marking lights that are sensitive to the propagation distance decrease in intensity when they reach the bottom of the boat tank. Therefore, the brightness of the imaging area of ​​the projection part of the marking light at the bottom of the boat tank is less than the brightness of the imaging area of ​​the projection part of the marking light on the corresponding upper boat page, lower boat page and battery cell. The appropriate segmentation threshold can be set by testing, so that this part of the projection area can be segmented into a non-marking area.

[0100] Step S240: determining first detection information of the boat corresponding to the first partial image according to the position distribution information of the pixels in the marked area, wherein the first detection information includes film loading state information and / or film loading position information of the boat.

[0101] In the embodiment of the present application, the loading state information of the boat groove may be state information indicating whether the loading position in the boat groove is loaded with a battery cell. For example, the loading state information of the boat groove includes: first state information indicating the presence of an upper loading film, second state information indicating the absence of an upper loading film, third state information indicating the presence of a lower loading film, and fourth state information indicating the absence of a lower loading film. It can be understood that each boat groove is usually loaded with a battery cell adjacent to an upper boat page (referred to as an upper loading film) and a battery cell adjacent to a lower boat page (referred to as a lower loading film). The upper boat page and the lower boat page are relative, and the same boat page is an upper boat page for one boat groove, and may be a lower boat page for another boat groove. The definition of upper and lower can be set according to the imaging position of the boat page in the image. For example, the boat page close to the top of the image in the partial image can be called the upper boat page, and the boat page close to the bottom of the image can be called the lower boat page.

[0102] In the embodiment of the present application, the cell loading position information of the boat slot may be any information that can indicate the position of the cell loaded in the boat slot, for example, the absolute coordinates of the cell, or the relative distance between the cell and the upper boat page.

[0103] In the embodiment of the present application, a variety of suitable methods can be used to determine the first detection information of the boat corresponding to the first partial image according to the position distribution information of the pixels in the marking area. In the embodiment of the present application, it can be determined whether the marking area contains the imaging area (for example, called the second projection area) of the projection position (for example, called the second projection part) of the marking light on the second surface of the battery cell according to the position distribution information of the pixels in the marking area. If not, it is determined that the loading state information of the boat corresponding to the first partial image is the second state information and the fourth state information (that is, it indicates that there is no battery cell in the boat). If yes, it is further determined that the loading state information of the boat corresponding to the first partial image is the first state information and / or the fourth state information according to the position and number of the second projection area. It can be understood that according to the loading state information of the boat, it can be further determined whether there is a defect of missing battery cells in the boat. In the case of determining that the marking area includes the second projection area, it is also possible to accurately obtain the loading position information of the boat, such as the relative distance between the battery cell and the upper boat page, according to the position of the second projection area. It can be understood that the loading position information of the boat can be further used to determine whether there is a warping defect in the battery cell. Therefore, this image processing solution can be used to realize automatic cell defect detection before or after cell coating.

[0104] It should be noted that, combined with Figure 3 , Figure 4 , Figure 5a and Figure 5b It can be seen that since the height difference between the first surface of each boat page and the second surface of the battery cell loaded on the boat page is greater than 0, the projection plane of the marking light l When the angle with the camera visual axis is greater than 0, the lateral distance (the absolute value of the x-coordinate difference, corresponding to the absolute value of the x-coordinate difference) between the projection position of the marking light on the first surface of the boat page (the first projection part) and the projection position of the solar cell loaded on the boat page (the second projection part) is Figure 5b △x in the mark area is greater than 0. Therefore, the second projection area can be quickly and accurately identified according to the difference in the x coordinates of each pixel in the marked area, that is, whether there are cells in the boat slot and the approximate position of the cells can be quickly obtained. Compared with the prior art solution of using multiple cameras to shoot the graphite boat from different angles, requiring harsh light source conditions and complex image processing methods, the graphite boat image processing solution of the embodiment of the present application can quickly and accurately detect the position of the cells through a simple image processing method under basic light source conditions.

[0105] The graphite boat image processing method provided in the embodiment of the present application first obtains the first image of the graphite boat. Since the image is collected when the marking light is projected onto the boat page and the battery cell of the graphite boat, the first image includes the imaging area of ​​the marking light. Then, after the first image is cropped, a local image corresponding to each boat slot is obtained; then, according to the color value of the marking light, the first local image among the multiple local images obtained by cropping is region-segmented, and the marking area in the first local image can be quickly and accurately determined. Since the angle between the projection plane of the marking light projected onto the graphite boat and the visual axis of the image acquisition device is greater than 0, the position of the projection area of ​​the marking light on the battery cell in the marking area is different from the position of the projection area on the boat page. Therefore, the loading state information and / or loading position information of the boat slot corresponding to the first local image can be quickly and accurately determined based on the position distribution information of the pixels in the marking area. The processing efficiency and processing accuracy of the scheme are significantly improved, and the device cost of the scheme is lower and the amount of calculation consumed is also smaller.

[0106] In one embodiment, step S240 determines the first detection information of the boat tank corresponding to the first partial image according to the position distribution information of the pixels in the marked area, including the following steps:

[0107] Step S241, determining an upper boat page marking area and a lower boat page marking area in the marking area according to coordinate components of each pixel in the marking area in a first direction, wherein the first direction is an image width direction of the partial image;

[0108] Step S242, determining a first search area and a second search area in the first partial image according to coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, wherein the second direction is an image height direction of the partial image;

[0109] Step S243, determining first detection information of the boat slot corresponding to the first partial image according to the relative position relationship between the first search area and the second search area and other marking areas, wherein the other marking areas are areas in the marking area excluding the upper boat page marking area and the lower boat page marking area.

[0110] In the embodiment of the present application, the upper boat page marking area may be an imaging area of ​​the projection portion of the marking light on the first surface of the upper boat page, and the lower boat page marking area may be an imaging area of ​​the projection portion of the marking light on the first surface of the lower boat page. Figure 5cIn the case where the marking area only includes the imaging area of ​​the projection part of the marking light on the corresponding upper boat page, lower boat page and battery cell, the upper boat page marking area and the lower boat page marking area in the marking area can be determined according to the x coordinate of each pixel in the marking area. Specifically, according to the situation that the thickness of the boat page is much greater than the thickness of the battery cell, two areas with a large number of pixels with the same x coordinate can be used as boat page marking areas. And one of the areas with a larger pixel y coordinate can be used as the upper boat page marking area, and the area with a smaller pixel y coordinate can be used as the lower boat page marking area.

[0111] In the embodiment of the present application, the first search area may be an area where the projection area of ​​the marking light on the upper sheet may be located, and the second search area may be an area where the projection area of ​​the marking light on the lower sheet may be located. The coordinate components of each pixel in the upper and lower sheet marking areas in the first and second directions may be analyzed to determine the first search area and the second search area in the first partial image. For example, referring to Figure 5c The y-coordinate ranges of the first search area and the second search area can be determined according to the lower limit value of the y-coordinate of the pixels in the upper boat page mark area and the upper limit value of the y-coordinate of the pixels in the lower boat page mark area. The x-coordinate ranges of the first search area and the second search area can be determined according to the average value of the x-coordinate of the pixels in the upper boat page mark area and the x-coordinate of the pixels in the lower boat page mark area, the angle between the projection plane of the marking light and the visual axis of the camera, and the distance between the second surface of the battery cell and the first surface of the boat page.

[0112] In the embodiment of the present application, the other marking area is the area other than the upper boat page marking area and the lower boat page marking area in the marking area. A variety of suitable methods can be used to determine the relative position relationship between the first search area and the second search area and the other marking areas, and then determine the first detection information of the boat tank corresponding to the first partial image based on the relative position relationship.

[0113] In one embodiment, the first detection information includes film loading status information of the boat. Step S243 determines the first detection information of the boat corresponding to the first partial image according to the relative positional relationship between the first search area and the second search area and other marking areas, including: when there is an intersection area between the first search area and other marking areas, determining the film loading status information of the boat as first status information indicating that there is an upper film; when there is no intersection area between the first search area and other marking areas, determining the film loading status information of the boat as second status information indicating that there is no upper film; when there is an intersection area between the second search area and other marking areas, determining the film loading status information of the boat as third status information indicating that there is a lower film; when there is no intersection area between the second search area and other marking areas, determining the film loading status information of the boat as fourth status information indicating that there is no lower film.

[0114] Reference again Figure 5c It can be understood that if there is an intersection between the first search area in the figure and other marking areas, it can be explained that the marking area includes the projection area of ​​the marking light on the second surface of the upper sheet, thereby determining that there is an upper sheet in the boat tank; otherwise, it can be explained that the marking area does not include the projection area of ​​the marking light on the second surface of the upper sheet, thereby determining that there is no upper sheet in the boat tank. Similarly, if there is an intersection between the second search area in the figure and other marking areas, it can be explained that the marking area includes the projection area of ​​the marking light on the second surface of the lower sheet, thereby determining that there is a lower sheet in the boat tank; otherwise, it can be explained that the marking area does not include the projection area of ​​the marking light on the second surface of the lower sheet, thereby determining that there is no lower sheet in the boat tank.

[0115] In the application embodiment, the loading state information can also be outputted by an output device. For example, when the loading state information of the boat tank is determined to be the second state information or the fourth state information, a state information interface can be displayed on a display device in the PECVD system. The state information interface can include information related to Figure 5a In the example, a similar graphite boat simulation image is displayed. Specifically, the display mode of the corresponding boat slot area can be different from the display mode of other boat slot areas. For example, if the loading state information of the boat slot is determined to be the second state information and the third state information, the upper half of the corresponding boat slot area in the graphite boat simulation image is filled with a red block; if the loading state information of the boat slot is determined to be the first state information and the fourth state information, the lower half of the corresponding boat slot area in the graphite boat simulation image is filled with a red block; if the loading state information of the boat slot is determined to be the second state information and the fourth state information, the entire corresponding boat slot area in the graphite boat simulation image is filled with a red block. In this way, the user can intuitively know the missing information of the battery cells in each boat slot, which is convenient for timely processing.

[0116] In one embodiment, the first detection information includes the film loading position information of the boat. Step S243 determines the first detection information of the boat corresponding to the first partial image according to the relative position relationship between the first search area and the second search area and other marking areas, and also includes the following steps: when the film loading state information of the boat is determined to be the first state information, the position information of the upper film in the boat is determined according to the coordinate components of the pixels in the intersection area between the first search area and other marking areas in the second direction; when the film loading state information of the boat is determined to be the third state information, the position information of the lower film in the boat is determined according to the coordinate components of the pixels in the intersection area between the second search area and other marking areas in the second direction.

[0117] Reference again Figure 5c If it is determined that there is a battery cell in the boat tank, the position of the battery cell can be further determined. Specifically, the mean value of the y coordinate of each pixel in the intersection area between the first search area and other marking areas in the figure can be calculated, for example, denoted as y c Then, the minimum value y of the y coordinates of the pixels in the mark area of ​​the previous page can be calculated. a ', and can calculate y a 'with y c Similarly, the mean of the y coordinates of each pixel in the intersection area between the second search area and other marking areas in the figure can be calculated, for example, denoted as y d Then, the maximum value y of the y coordinate of the pixels in the mark area of ​​the next boat page can be calculated b ', and can calculate y d With y b ' is used as the position of the next piece.

[0118] In one implementation, step S242 determines the first search area and the second search area in the first partial image according to the coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, including the following steps:

[0119] Step S242.1, determining the minimum value of the coordinate component of each pixel in the mark area of ​​the upper boat page in the second direction;

[0120] Step S242.2, determining the maximum value of the coordinate component of each pixel in the mark area of ​​the next boat page in the second direction;

[0121] Step S242.3, determine a first search area and a second search area based on the minimum value and the maximum value, wherein the coordinate component of the pixels in the first search area in the second direction is greater than or equal to the average of the maximum value and the minimum value and is less than the minimum value, and the coordinate component of the pixels in the second search area in the second direction is greater than the maximum value and is less than or equal to the average value.

[0122] Reference again Figure 5c , the minimum value y of the y coordinate of each pixel in the mark area of ​​the upper page can be calculated respectively a ' and the maximum value y of the y coordinates of each pixel in the mark area of ​​the previous page b '. Then, y can be calculated a ' and y b The mean value y of e The first search area and the second search area may be rectangular areas. The y coordinate of the upper edge of the first search area may be equal to y a ', the y coordinate of the lower edge can be equal to y e The y coordinate of the upper edge of the second search area can be equal to y e , the y coordinate of the lower edge can be equal to y b '.

[0123] In one embodiment, before determining the first search area and the second search area in the first local image in step S242, the graphite boat image processing method of the embodiment of the present application also includes: determining the offset distance between the first projection portion and the second projection portion of the marking light according to a preset angle and a first distance, wherein the first distance is the distance between the first surface of the boat page in each boat slot and the second surface of the battery cell, the first projection portion is located on the first surface, the second projection portion is located on the second surface, and the first surface and the second surface are perpendicular to the visual axis.

[0124] It can be understood that the first distance is the reference distance between the first surface of the boat sheet in each boat slot and the second surface of the battery cell, that is, the height difference between the placement height of the battery cell and the boat sheet surface under normal circumstances. The first distance can be determined according to the structural design parameters of the graphite boat. Taking the preset angle θ and the first distance d as an example, according to the trigonometric function relationship, the offset distance between the first projection part and the second projection part of the marking light is equal to .

[0125] Step S242 determines the first search area and the second search area in the first partial image according to the coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, including:

[0126] Step S242.4, determining a first search area and a second search area according to the offset distance, the coordinate components of each pixel in the upper boat page mark area in the first direction, and the coordinate components of each pixel in the lower boat page mark area in the first direction.

[0127] For example, the conversion relationship between the pixel size in the local image and the physical size in the physical space can be determined in advance through camera calibration, and the offset distance calculated in the above steps can be converted into a pixel distance in the local image in pixels based on the conversion relationship. Then, based on the pixel distance, a preset pixel distance threshold, the coordinate components of each pixel in the upper boat page mark area in the first direction, and the coordinate components of each pixel in the lower boat page mark area in the first direction, the value range of the coordinate components of the pixels in the first search area and the second search area in the first direction can be determined, so as to determine the positions of the two edges of the first search area and the second search area in the first direction. Specifically, the pixel distance is, for example, D, and the pixel distance threshold is, for example, D0. Figure 5c As shown, the minimum x coordinate of each pixel in the mark area of ​​the upper page can be calculated. a , the minimum x coordinate of each pixel in the next page mark area b After that, the x coordinate x of the left edge of the first search area can be determined c =x a -D-D0, and the x coordinate x of the right edge of the first search area can be determined c’ =x a -D+D0. Similarly, the x coordinate x of the left edge of the second search area can be determined d =x b -D-D0, and the x coordinate x of the right edge of the second search area can be determined d’ =x b -D+D0. Thus, the first search area and the second search area can be obtained quickly and accurately.

[0128] A second aspect of the present application provides a method for detecting defects in a battery cell. Figure 6 As shown, the battery cell defect detection method includes the following steps:

[0129] Step S610, before pushing the graphite boat loaded with the battery cells into the coating furnace and / or after moving the graphite boat out of the coating furnace, using the above-mentioned graphite boat image processing method to determine the first detection information of each boat slot of the graphite boat;

[0130] Step S620: Determine defect detection information of the battery cells in each boat slot of the graphite boat according to the first detection information.

[0131] In the embodiment of the present application, the defect detection information of the battery cells in the boat groove may include information on whether the battery cells in the boat groove have defects and information on the defect categories of the battery cells in the boat groove. In the embodiment of the present application, a variety of suitable determination logics may be used to determine the defect detection information of the battery cells in each boat groove of the graphite boat according to the first detection information.

[0132] The cell defect detection method provided in the embodiment of the present application, based on the rapid and accurate determination of the cell loading status information and / or cell loading position information of the boat slot corresponding to the local image, further realizes the rapid defect detection of the cell in each boat slot according to the cell loading status information and / or cell loading position information. The detection efficiency and detection accuracy of this scheme are significantly improved, the device cost is also lower, and the amount of calculation consumed is also smaller. Therefore, the production quality and production efficiency of the cell can be significantly improved.

[0133] In one embodiment, the first detection information includes the cell loading status information of the boat slot. Step S620 determines the defect detection information of the cell in each boat slot of the graphite boat according to the first detection information, including:

[0134] Step S621, for each boat slot, when the cell loading state information of the boat slot is the first state information or the second state information, determining that the defect detection information of the cells in the boat slot is cell missing defect information indicating that the cells are missing;

[0135] For example, when it is determined in the aforementioned step S243 that a boat slot in the graphite boat does not have an upper loading sheet or a lower loading sheet, it is determined that the boat slot has a missing sheet defect, and corresponding defect prompt information can be output to remind the user to pay attention and handle it in time.

[0136] In one embodiment, the first detection information includes the loading position information of the boat slot. Step S620 determines the defect detection information of the battery cells in each boat slot of the graphite boat according to the first detection information, including the following steps: Step S622, for each boat slot, according to the position of the battery cells loaded in the boat slot, determine the relative distance between the battery cell and the corresponding boat page; Step S623, when the relative distance is greater than the relative distance threshold, determine that the defect detection information of the battery cell in the boat slot is the warping defect information indicating the warping of the battery cell.

[0137] For example, refer to Figure 5c , when it is determined that there is an upper piece in the current boat tank, the average of the y coordinates of each pixel in the intersection area between the first search area and other marked areas in the figure can be calculated as the position of the upper piece. For example, y c Then, the minimum value y of the y coordinates of the pixels in the mark area of ​​the previous page can be calculated. a ', and can calculate y a 'with yc The difference between the two is taken as the relative distance between the upper loading sheet and the upper boat page. Similarly, the average of the y coordinates of each pixel in the intersection area between the second search area and other marking areas in the figure can be calculated as the position of the lower loading sheet. For example, y d Then, the maximum value y of the y coordinate of the pixels in the mark area of ​​the next boat page can be calculated b ', and can calculate y d With y b The difference between ' is used as the relative distance between the lower mounting sheet and the lower boat page.

[0138] In an embodiment of the present application, a relative distance threshold can be set according to the distance between two adjacent boat pages. For example, the relative distance threshold can be less than or equal to 1 / 2 of the distance between two adjacent boat pages. Take the relative distance threshold equal to 1 / 3 of the distance between two adjacent boat pages as an example. If the determined relative distance between the upper loading sheet and the upper boat page and / or the relative distance between the lower loading sheet and the lower boat page is greater than the relative distance threshold, it can be determined that there is a battery cell warping defect in the boat slot. Specifically, if the determined relative distance between the upper loading sheet and the upper boat page is greater than the relative distance threshold, it can be determined that there is a warping defect in the upper loading sheet in the boat slot; if the determined relative distance between the lower loading sheet and the lower boat page is greater than the relative distance threshold, it can be determined that there is a warping defect in the lower loading sheet in the boat slot. And the corresponding defect prompt information can be output to remind the user to pay attention and handle it in time.

[0139] In one embodiment, before determining the marked area in the first partial image in step S130, the battery cell defect detection method further includes the following steps:

[0140] Step S101, for each of the plurality of partial images, performing a second region segmentation on the partial image according to the color value of the boat page and the color value of the battery cell, and determining the boat page region and the battery cell region in the partial image;

[0141] Step S102, determining initial defect detection information of the battery cell in the boat slot corresponding to the partial image according to the number of battery cell regions and the relative position relationship between each battery cell region and the corresponding boat page region;

[0142] Step S103: when the initial defect detection information indicates that the battery cell is missing, the partial image is used as the first partial image.

[0143] For example, before executing step S101, each local image may be converted into a grayscale image. And in step S101, according to the color value of the boat page and the color value of the battery cell, a second region segmentation may be performed on each grayscale image to determine the boat page region and the battery cell region in the local image. Specifically, a suitable grayscale threshold may be set according to the difference between the grayscale value of the first surface of the boat page and the grayscale value of the first surface of the battery cell and the grayscale value of other regions of the graphite boat. Further, according to the grayscale threshold, each grayscale image is segmented to segment the battery cell region and the boat page region in the grayscale image. Then, in step S102, according to the number of battery cell regions and the relative positional relationship between each battery cell region and the corresponding boat page region, the initial defect detection information of the battery cell in the boat slot corresponding to the local image is preliminarily determined. Specifically, the existing battery cell defect detection method may be used to preliminarily determine the initial defect detection information of the battery cell in the boat slot corresponding to each grayscale image. For example, when the number of battery cell regions is 2 and the difference in the coordinate component of each battery cell region and the corresponding boat page region in the second direction is less than the difference threshold, it is determined that the battery cells in the boat slot are all normal. If the number of cell regions is 2 and the difference in the coordinate component of any cell region and the corresponding boat page region in the second direction is greater than the difference threshold, it can be determined that the cell in the boat has a warping defect. If the number of cell regions is less than 2, it can be determined that there is a cell missing defect in the boat. In step S103, if it is determined that there is a cell missing defect in the boat, the local image corresponding to the grayscale image can be used as the first local image. Then, the aforementioned steps S230, S240 and S620 are performed on these first local images to achieve secondary detection of the cells in these boats. Thereby, the accuracy of cell defect detection can be further improved.

[0144] A third aspect of the embodiments of the present application provides a graphite boat image processing device. Figure 7 As shown, the graphite boat image processing device 700 includes:

[0145] An acquisition module 710 is used to acquire a first image of a graphite boat, wherein multiple boat slots of the graphite boat are loaded with battery cells, and the first image includes an imaging area of ​​a marking light projected onto the boat pages and battery cells of the graphite boat, and an angle between a projection plane of the marking light and a visual axis of an image acquisition device for acquiring the first image is a preset angle, and the preset angle is greater than 0 and less than an angle threshold;

[0146] A cropping module 720, configured to crop the first image to obtain a plurality of partial images, wherein each partial image corresponds to a boat tank;

[0147] The segmentation module 730 is used to perform a first region segmentation on a first partial image among the plurality of partial images according to the color value of the marking light, and determine a marking region in the first partial image;

[0148] The first detection module 740 is used to determine first detection information of the boat corresponding to the first partial image according to the position distribution information of the pixels in the marked area, wherein the first detection information includes the film loading state information and / or the film loading position information of the boat.

[0149] A fourth aspect of the present application provides a battery cell defect detection device. Figure 8 As shown, the battery cell defect detection device 800 includes:

[0150] The image processing module 810 is used to determine the first detection information of each boat slot of the graphite boat by using the above-mentioned graphite boat image processing method before pushing the graphite boat loaded with the battery cells into the coating furnace and / or after moving the graphite boat out of the coating furnace;

[0151] The second detection module 820 is used to determine defect detection information of the battery cells in each boat slot of the graphite boat according to the first detection information.

[0152] like Fig. 9 As shown, the embodiment of the present application further provides a terminal device 900, including: at least one processor 910 ( Fig. 9 Only one processor is shown in the figure), a memory 920, and a computer program 930 stored in the memory 920 and executable on at least one processor 910. When the processor 910 executes the computer program 930, the steps of the above-mentioned graphite boat image processing method and / or the steps of the battery cell defect detection method are implemented.

[0153] The terminal device may include but is not limited to a processor and a memory. Fig. 9It is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. The processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0154] The present application also provides a cell coating system. Fig.10 As shown, the cell coating system 1000 includes: a graphite boat 1010, a coating furnace 1020, a marking light projector 1030, an image acquisition device 1040 and a control device 1050. The graphite boat 1010 is used to load the cells. The coating furnace 1020 is used to coat the cells in the graphite boat 1010 when the graphite boat 1010 enters the coating furnace 1020. For example, the cells are coated by a thin film deposition method. Among them, the control device 1050 is connected to the marking light projector 1030 and the image acquisition device 1040 respectively.

[0155] The control device 1050 in the embodiment of the present application is used to: before pushing the graphite boat 1010 into the coating furnace 1020 and / or after moving the graphite boat 1010 out of the coating furnace 1020, and when the graphite boat 1010 is located at the center of the field of view of the image acquisition device 1040 and the marking light projector 1030, control the marking light projector 1030 to project the marking light to the graphite boat 1010; control the image acquisition device 1040 to acquire the image of the graphite boat 1010 to obtain the first image; and perform the steps of the above-mentioned graphite boat image processing method and / or the steps of the above-mentioned cell defect detection method. In some embodiments, the cell coating system 1000 also includes a driving device. The driving device is used to drive the graphite boat 1010 to move. The control device 1050 is also used to control the driving device to drive the graphite boat 1010 to move. The above-mentioned image acquisition device 1040 can be a camera with a telecentric lens.

[0156] In a specific example, after loading the battery cells in the graphite boat 1010, the control device 1050 drives the graphite boat 1010 to move toward the entrance of the coating machine furnace 1020 by controlling the driving device. In this process, the control device 1050 can automatically determine the timing of the marking light projector 1030 projecting the marking light and the timing of the image acquisition device 1040 acquiring the image of the graphite boat according to the moving speed of the graphite boat 1010, the width of each boat groove, and the position of the width center of the battery cells in the width direction of each boat groove. For example, the control device 1050 can determine the time period Ti from the start of the graphite boat moving to the time when the width center of the battery cells in the i-th (i≥1) boat groove of the graphite boat falls in the center of the field of view of the marking light projector 1030 according to the moving speed of the graphite boat 1010, the width of each boat groove, and the position of the width center of the battery cells in the width direction of each boat groove, and then determine the timing of each projection of the marking light by the marking light projector 1030 according to Ti. The timing of the image acquisition device 1040 acquiring the image of the graphite boat may be the same as the timing of the marking light projector 1030 projecting the marking light. In another example, in the example of mass production of cells of the same specification, since the cell specifications and the graphite boat specifications are the same, a setting window for the shooting time and the marking light projecting time may be provided in advance and set by the user. In other words, the user may also pre-set the marking light projecting time and the image acquisition time through test calibration.

[0157] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0158] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The functional modules in the embodiment can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. In addition, the specific names of the functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0159] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned graphite boat image processing method and / or the steps in the above-mentioned battery cell defect detection method can be implemented.

[0160] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned graphite boat image processing method and / or the steps in the above-mentioned battery cell defect detection method.

[0161] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A graphite boat image processing method, characterized in that: include: Acquire a first image of a graphite boat, wherein a plurality of boat slots of the graphite boat are loaded with battery cells, the first image includes an imaging area of ​​a marking light projected onto a boat leaf of the graphite boat and the battery cells, and an angle between a projection plane of the marking light and a visual axis of an image acquisition device for acquiring the first image is a preset angle, and the preset angle is greater than 0 and less than an angle threshold; Cropping the first image to obtain a plurality of partial images, wherein each partial image corresponds to a boat tank; For a first partial image among the multiple partial images, performing a first region segmentation on the first partial image according to the color value of the marking light, and determining a marking region in the first partial image, wherein the marking region is an imaging region of the marking light; According to the position distribution information of the pixels in the marked area, first detection information of the boat corresponding to the first partial image is determined, wherein the first detection information includes film loading state information and / or film loading position information of the boat.

2. The graphite boat image processing method according to claim 1, characterized in that: The determining, according to the position distribution information of the pixels in the marked area, the first detection information of the boat tank corresponding to the first partial image comprises: determining an upper boat page marking area and a lower boat page marking area in the marking area according to coordinate components of each pixel in the marking area in a first direction, wherein the first direction is an image width direction of the partial image; Determine a first search area and a second search area in the first partial image according to coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction, wherein the second direction is an image height direction of the partial image; The first detection information of the boat slot corresponding to the first local image is determined according to the relative position relationship between the first search area and the second search area and other marking areas respectively, wherein the other marking areas are areas within the marking area excluding the upper boat page marking area and the lower boat page marking area.

3. The graphite boat image processing method according to claim 2, characterized in that: The first detection information includes the film loading state information of the boat, and the determining the first detection information of the boat corresponding to the first partial image according to the relative position relationship between the first search area and the second search area and other marking areas respectively includes: In the case where there is an intersection area between the first search area and the other marking area, determining that the film loading state information of the boat slot is first state information indicating that there is an upper film loading; In the case where there is no intersection area between the first search area and the other marking area, determining that the film loading state information of the boat slot is second state information indicating that there is no upper film loading; In the case where there is an intersection area between the second search area and the other marking area, determining that the film loading state information of the boat slot is third state information indicating that there is a lower loaded film; In the case that there is no intersection area between the second search area and the other marking areas, it is determined that the film loading state information of the boat slot is fourth state information indicating that there is no lower loaded film.

4. The graphite boat image processing method according to claim 3, characterized in that: The first detection information includes the film loading position information of the boat, and the determining the first detection information of the boat corresponding to the first partial image according to the relative position relationship between the first search area and the second search area and other marking areas respectively, further includes: When it is determined that the film loading state information of the boat is the first state information, determining the position information of the upper film loading in the boat according to the coordinate components of the pixels in the intersection area between the first search area and the other marking area in the second direction; When it is determined that the film loading state information of the boat slot is the third state information, the position information of the lower film loaded in the boat slot is determined according to the coordinate components of the pixels in the intersection area between the second search area and the other marking areas in the second direction.

5. The graphite boat image processing method according to claim 2, characterized in that: The determining the first search area and the second search area in the first partial image according to the coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction comprises: Determine the minimum value of the coordinate component of each pixel in the upper boat page mark area in the second direction; Determine the maximum value of the coordinate component of each pixel in the lower boat page mark area in the second direction; Based on the minimum value and the maximum value, the first search area and the second search area are determined, wherein the coordinate components of the pixels in the first search area in the second direction are greater than or equal to the average of the maximum value and the minimum value and are less than the minimum value, and the coordinate components of the pixels in the second search area in the second direction are greater than the maximum value and are less than or equal to the average value.

6. The graphite boat image processing method according to claim 2, characterized in that: Before determining the first search area and the second search area in the first partial image, the method further includes: Determine the offset distance between the first projection portion and the second projection portion of the marking light according to the preset angle and the first distance, wherein the first distance is the distance between the first surface of the boat page in each boat slot and the second surface of the battery sheet, the first projection portion is located on the first surface, the second projection portion is located on the second surface, and the first surface and the second surface are perpendicular to the visual axis; The determining the first search area and the second search area in the first partial image according to the coordinate components of each pixel in the upper boat page mark area and the lower boat page mark area in the first direction and the second direction comprises: The first search area and the second search area are determined according to the offset distance, the coordinate components of each pixel in the upper boat page mark area in the first direction, and the coordinate components of each pixel in the lower boat page mark area in the first direction.

7. A method for detecting defects in a battery cell, characterized in that: include: Before pushing the graphite boat loaded with battery cells into the coating furnace and / or after moving the graphite boat out of the coating furnace, using the graphite boat image processing method according to any one of claims 1 to 6 to determine first detection information of each boat slot of the graphite boat; Defect detection information of the battery cells in each boat slot of the graphite boat is determined according to the first detection information.

8. The method for detecting defects in a battery cell according to claim 7, wherein: The first detection information includes the cell loading status information of the boat slot, and the step of determining the defect detection information of the cell in each boat slot of the graphite boat according to the first detection information includes: For each boat, when the cell loading state information of the boat is the first state information or the second state information, determining that the defect detection information of the cells in the boat is cell missing defect information indicating that the cells are missing; and / or The first detection information includes the cell loading position information of the boat slot, and the step of determining the defect detection information of the cell in each boat slot of the graphite boat according to the first detection information includes: For each boat slot, according to the position of the battery sheet loaded in the boat slot, determine the relative distance between the battery sheet and the corresponding boat leaf; When the relative distance is greater than the relative distance threshold, it is determined that the defect detection information of the battery cell in the boat is warping defect information indicating that the battery cell is warped.

9. The method for detecting defects in a battery cell according to claim 8, wherein: Before determining the marked area in the first partial image, the method further includes: For each partial image in the plurality of partial images, Performing a second region segmentation on the local image according to the color value of the boat page and the color value of the battery cell to determine the boat page region and the battery cell region in the local image; Determine initial defect detection information of the battery cell in the boat slot corresponding to the partial image according to the number of battery cell regions and the relative position relationship between each battery cell region and the corresponding boat page region; When the initial defect detection information indicates that the battery cell is missing, the partial image is used as the first partial image.

10. A cell coating system, comprising: A graphite boat, a coating furnace, a marking light projector, an image acquisition device and a control device, wherein the control device is connected to the marking light projector and the image acquisition device respectively, and the control device is used to: Before pushing the graphite boat into the coating furnace and / or after moving the graphite boat out of the coating furnace, and when the graphite boat is located at the center of the field of view of the image acquisition device and the marking light projector, controlling the marking light projector to project a marking light onto the graphite boat; Controlling the image acquisition device to acquire the image of the graphite boat to obtain the first image; Execute the steps of the graphite boat image processing method as described in any one of claims 1-6 and / or the steps of the battery cell defect detection method as described in any one of claims 7-9.

Images