Current collector weld bead depth measurement method and apparatus, device, and storage medium

Abstract

The present application discloses a current collector weld bead depth measurement method and apparatus, a device, and a storage medium. The current collector weld bead depth measurement method comprises: acquiring an original image of a welded current collector, wherein the original image is a three-dimensional image; removing image information of a weld bead position from the original image to obtain a topographic map of the current collector; filling a removed portion on the topographic map of the current collector to obtain a restored topographic map of the current collector; and on the basis of depth data of the same positions on the original image and the restored topographic map of the current collector, obtaining a weld bead depth map. According to the embodiments of the present application, the weld bead depth of the current collector can be accurately measured, so that defective products caused by insufficient welding can be determined.

Description

Collector plate weld depth measurement method, device, equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311753414.7, filed on December 19, 2023, entitled “Method, device, equipment and storage medium for measuring the depth of a collecting plate weld,” and the entire contents of that application are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of battery technology, and in particular to a method, device, equipment and storage medium for measuring the depth of a current collecting plate weld. Background Art

[0004] In the production scenarios of power batteries, due to the influence of process equipment factors, it is impossible to ensure that the size specifications of the batteries during the production process are completely consistent and meet the requirements, and the relevant technical dimensions affect the ultimate reliability and safety of the batteries.

[0005] During production, the welding quality of battery collector plates has a direct impact on battery performance. One way to quantify the quality of collector plate tab welding is to measure the weld depth, which allows for qualitative analysis of defective products such as cold welds. The accuracy of these measurements directly impacts the quality of batteries shipped.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a method, device, equipment and storage medium for measuring the depth of the collector plate weld, which is conducive to accurately measuring the depth of the collector plate weld, thereby facilitating the qualitative analysis of defective products such as cold welds.

[0008] In a first aspect, an embodiment of the present application provides a method for measuring the depth of a current collecting plate weld bead, comprising:

[0009] Obtaining an original image of the current collecting plate after welding, where the original image is a three-dimensional image;

[0010] The image information of the weld bead position in the original image is removed to obtain the collector plate topography image;

[0011] Filling the removed part of the collecting plate topography image to obtain a restored image of the collecting plate topography;

[0012] The weld depth map is obtained based on the depth data of the same position in the original image and the restored image of the collecting plate.

[0013] In an embodiment of the present application, the image information of the weld position on the original image after the collecting disk is welded is removed to obtain a collecting disk topography image, and the removed part of the collecting disk topography image is filled to obtain a collecting disk topography restoration image. In this way, the collecting disk surface with an uneven surface can be leveled without damaging the weld depth information, and the influence of the weld can be removed, thereby restoring the curved surface topography of the collecting disk. In this way, a relatively real weld depth map can be obtained based on the depth data at the same position in the original image and the collecting disk topography restoration image, which can be beneficial for accurately measuring the collecting disk weld depth based on the relatively real weld depth map, thereby facilitating the qualitative analysis of the production of defective products such as cold welding.

[0014] In some embodiments of the first aspect, removing image information of weld bead positions in an original image to obtain a current collecting plate topography image includes:

[0015] The weld bead position of the original image is corrected using the template image to obtain a position-corrected image, wherein the weld bead position in the position-corrected image is the same as the weld bead position in the template image;

[0016] The image information of the weld bead position in the position correction image is removed to obtain the collector plate topography image;

[0017] Based on the depth data of the same position in the original image and the restored image of the collecting plate, the weld depth map is obtained, including:

[0018] The weld depth map is obtained based on the depth data of the same position in the position correction image and the collector plate topography restoration image.

[0019] In some embodiments of the first aspect, correcting the weld bead position of the original image using the template image to obtain the position-corrected image includes:

[0020] Calculate the depth gradient map of the original image to obtain the weld bead position map corresponding to the original image;

[0021] The weld bead position map is registered with the template image to obtain the rotation angle and offset corresponding to the original image;

[0022] The original image is rotated and shifted according to the rotation angle and the offset to obtain a position-corrected image.

[0023] In some embodiments of the first aspect, calculating a depth gradient map of an original image to obtain a weld bead position map corresponding to the original image includes:

[0024] Calculating a first depth gradient in the horizontal direction and a second depth gradient in the vertical direction for each position point in the original image according to the depth of each position point in the original image;

[0025] Calculate the root mean square of the first depth gradient and the second depth gradient at each position point in the original image to obtain a depth gradient map corresponding to the original image;

[0026] The position points in the depth gradient map where the depth gradient is greater than a preset threshold are taken as weld bead positions, and a weld bead position map corresponding to the original image is obtained.

[0027] In some embodiments of the first aspect, registering the weld bead position map with the template image to obtain a rotation angle and an offset corresponding to the original image includes:

[0028] Based on the preset step size, the position where the weld position map and the template image reach the expected similarity coefficient is searched, and the corresponding rotation angle and offset of the original image are obtained.

[0029] In some embodiments of the first aspect, the preset step size includes a first preset step size and a second preset step size, and the first preset step size is larger than the second preset step size;

[0030] Based on the preset step size, the weld position map and the template image are searched for the position where the expected similarity coefficient is reached, and the corresponding rotation angle and offset of the original image are obtained, including:

[0031] Searching for a first position where the weld bead position map and the template image reach a first expected similarity coefficient based on a first preset step size;

[0032] Starting from the first position, a second position where the weld position map and the template image reach a second expected similarity coefficient is searched based on a second preset step size to obtain a rotation angle and an offset corresponding to the original image.

[0033] In some embodiments of the first aspect, filling the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image includes:

[0034] The collecting disk topography image is interpolated and smoothed to fill the removed portion of the collecting disk topography image and obtain a restored collecting disk topography image.

[0035] Based on the same inventive concept, in a second aspect, an embodiment of the present application provides a device for measuring the depth of a current collecting plate weld bead, comprising:

[0036] The original image acquisition module is used to obtain the original image of the collecting plate after welding, and the original image is a three-dimensional image;

[0037] The first processing module is used to remove the image information of the weld bead position in the original image to obtain the collector plate topography image;

[0038] The second processing module is used to fill the removed portion of the collecting plate topography image to obtain a restored image of the collecting plate topography;

[0039] The third processing module is used to obtain a weld depth map based on the depth data of the same position in the original image and the restored image of the collecting plate topography.

[0040] Based on the same inventive concept, in a third aspect, an embodiment of the present application provides an electronic device, including:

[0041] A processor and a memory storing computer program instructions, wherein when the processor executes the computer program instructions, the method for measuring the depth of the current collecting plate weld bead as described in any one of the embodiments of the first aspect is implemented.

[0042] Based on the same inventive concept, in a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for measuring the depth of a current collecting plate weld bead as described in any one of the embodiments in the first aspect is implemented.

[0043] Based on the same inventive concept, in the fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the current collecting plate weld depth measurement method shown in any one of the embodiments of the first aspect.

[0044] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, in which the same or similar reference numerals represent the same or similar features and the accompanying drawings are not drawn to scale.

[0046] FIG1 is a schematic flow chart of a method for measuring the depth of a current collecting plate weld provided by an embodiment of the present application;

[0047] FIG2 is a schematic diagram showing a rotation angle and an offset in a method for measuring the depth of a current collecting plate weld provided by an embodiment of the present application;

[0048] FIG3 is a schematic diagram showing a scenario of a method for measuring the depth of a current collecting plate weld provided by an embodiment of the present application;

[0049] FIG4 shows a schematic structural diagram of a device for measuring the depth of a current collecting plate weld provided in an embodiment of the present application;

[0050] FIG5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0053] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0054] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0055] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0056] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0057] The collector plate itself is relatively thin, such as when made of sheet metal. After repeated stresses during processing, the surface of the collector plate becomes uneven. The depth variation caused by deformation of the collector plate itself is often much greater than the weld depth created by welding. Therefore, the uneven surface of the collector plate makes it difficult to measure the weld depth.

[0058] To solve the above technical problems, embodiments of the present application provide a method, device, equipment, and storage medium for measuring the depth of a current collecting plate weld, which will be described below with reference to the accompanying drawings.

[0059] The following first introduces the collector plate weld depth measurement method provided in the embodiment of the present application.

[0060] As shown in FIG. 1 , the method for measuring the depth of a current collecting plate weld provided in an embodiment of the present application may include steps 10 to 40 .

[0061] Step 10, obtaining an original image of the current collecting plate after welding, the original image being a three-dimensional image;

[0062] Step 20, removing the image information of the weld bead position in the original image to obtain a collector plate topography image;

[0063] Step 30, filling the removed portion of the current collecting plate topography image to obtain a restored image of the current collecting plate topography;

[0064] Step 40: Obtain a weld depth map based on the depth data of the same position in the original image and the restored image of the collecting plate topography.

[0065] The specific implementation of each of the above steps will be described in detail below.

[0066] According to the collecting plate weld depth measurement method provided in the embodiment of the present application, the image information of the weld position on the original image after the collecting plate is welded is removed to obtain a collecting plate topography map, and the removed part of the collecting plate topography map is filled to obtain a collecting plate topography restoration map. In this way, the collecting plate surface with an uneven surface can be leveled without damaging the weld depth information, and the influence of the weld can be removed, thereby restoring the curved surface topography of the collecting plate. In this way, a relatively real weld depth map can be obtained based on the depth data at the same position in the original image and the collecting plate topography restoration map, which can be beneficial for accurately measuring the collecting plate weld depth based on the relatively real weld depth map, thereby facilitating the qualitative analysis of the production of defective products such as cold welding.

[0067] To facilitate understanding, the implementation process of each step is described below with examples.

[0068] In step 10, a 3D structured light camera or a 3D line scan camera can be used to photograph the welded collector plate to obtain a raw image of the welded collector plate. The raw image includes two-dimensional dimensional information and depth information of the welded collector plate. The raw image can be understood as the three-dimensional appearance of the welded collector plate.

[0069] For example, the welding of the collector plate and the image capture after welding can be performed at different stations. After the battery collector plate is welded, it can be moved a distance on the production line to the measurement station, where a 3D camera can be used to capture the original image of the collector plate after welding.

[0070] In some application scenarios, the current collecting disk may include a current collecting disk of a cylindrical battery. It is understandable that the current collecting disk of a cylindrical battery is a circular current collecting disk.

[0071] As mentioned above, after welding, the current collecting plate of the battery has to move a certain distance on the production line before it can reach the measurement station. Due to the axially symmetrical shape of the cylindrical battery, the cylindrical battery will rotate during this movement, and the current collecting plate of the cylindrical battery will also rotate accordingly, resulting in a random angle when it reaches the 3D imaging station, which makes it inconvenient to measure the depth of the weld.

[0072] In some embodiments, removing image information of weld bead positions in the original image to obtain a current collecting plate topography image includes:

[0073] The weld bead position of the original image is corrected using the template image to obtain a position-corrected image, wherein the weld bead position in the position-corrected image is the same as the weld bead position in the template image;

[0074] The image information of the weld bead position in the position correction image is removed to obtain the collector plate topography image;

[0075] Based on the depth data of the same position in the original image and the restored image of the collecting plate, the weld depth map is obtained, including:

[0076] The weld depth map is obtained based on the depth data of the same position in the position correction image and the collector plate topography restoration image.

[0077] In an embodiment of the present application, the weld position is corrected, and the weld position in the position correction image is the same as the weld position in the template image. In this way, when measuring the weld depth of the collecting plate, the weld position is unified, making it easy to measure the weld position of different collecting plates.

[0078] Exemplarily, obtaining a weld depth map based on depth data at the same position in the position-corrected image and the current collecting plate topography restoration image may include:

[0079] The depth data of the same position in the position correction image and the collector plate topography restoration image are subtracted to obtain the weld depth map.

[0080] In some embodiments, the template image includes complete weld bead information, so that the weld bead information in the image to be corrected and the weld bead information in the target image can be accurately registered, thereby improving the accuracy of weld bead position correction.

[0081] For example, an image with a complete weld bead may be selected from a plurality of images of the current collecting plate after welding, and then the image may be subjected to surface leveling processing to obtain a template image.

[0082] In some embodiments, correcting the weld bead position of the original image using the template image to obtain a position-corrected image includes:

[0083] Calculate the depth gradient map of the original image to obtain the weld bead position map corresponding to the original image;

[0084] The weld bead position map is registered with the template image to obtain the rotation angle and offset corresponding to the original image;

[0085] The original image is rotated and shifted according to the rotation angle and the offset to obtain a position-corrected image.

[0086] To correct the weld bead position, it's necessary to obtain the weld bead's position information from the original image. On a collector plate, the weld surface is more uneven than the surface elsewhere. In this embodiment, a weld bead position map is calculated from the original image to match the curved surface topography of the collector plate after welding, enabling accurate determination of the weld bead's position information.

[0087] In some embodiments, calculating the depth gradient map of the original image to obtain the weld bead position map corresponding to the original image includes:

[0088] Calculating a first depth gradient in the horizontal direction and a second depth gradient in the vertical direction for each position point in the original image according to the depth of each position point in the original image;

[0089] Calculate the root mean square of the first depth gradient and the second depth gradient at each position point in the original image to obtain a depth gradient map corresponding to the original image;

[0090] The position points in the depth gradient image where the root mean square is greater than a preset threshold are taken as weld bead positions, and a weld bead position map corresponding to the original image is obtained.

[0091] For ease of understanding, the calculation process of the first depth gradient, the second depth gradient, and the root mean square of the first depth gradient and the second depth gradient is exemplarily described below.

[0092] For example, the matrix M represents the depth values ​​of some points in the original image:

[0093] In the matrix M, 6 represents the depth of the position point (1, 1), 9 represents the depth of the position point (1, 2), 3 represents the depth of the position point (1, 3), and so on, which will not be repeated here.

[0094] The matrix Fx represents the first depth gradient in the horizontal direction of some points in the original image:

[0095] The first value in the first row of matrix Fx is equal to the difference between the second and first values ​​in the first row of matrix M, that is, 3 = 9-6; the second value in the first row of matrix Fx is equal to half the difference between the third and first values ​​in the first row of matrix M, that is, -1.5 = (3-6) / 2; the third value in the first row of matrix Fx is equal to half the difference between the fourth and second values ​​in the first row of matrix M, that is, -2.5 = (4-9) / 2; the fourth value in the first row of matrix Fx is equal to half the difference between the fifth and third values ​​in the first row of matrix M, that is, -1.5 = (0-3) / 2; the fifth value in the first row of matrix Fx is equal to the difference between the fifth and fourth values ​​in the first row of matrix M, that is, -4 = 0-4. The calculation method for the values ​​in the other rows of matrix Fx is similar to that of the first row, and will not be repeated here.

[0096] The matrix Fy represents the second depth gradient of some points in the original image in the vertical direction:

[0097] The first value in the first column of matrix Fy is equal to the difference between the second and first values ​​in the first column of matrix M, that is, -1 = 5-6; the second value in the first column of matrix Fy is equal to half the difference between the third and first values ​​in the first column of matrix M, that is, 0 = (6-6) / 2; the third value in the first column of matrix Fy is equal to half the difference between the fourth and second values ​​in the first column of matrix M, that is, 1 = (7-5) / 2; the fourth value in the first column of matrix Fy is equal to the difference between the fourth and third values ​​in the first column of matrix M, that is, 1 = 7-6. The calculation method for the values ​​of the other columns of matrix Fy is similar to that of the first column and will not be repeated here.

[0098] For example, the root mean square Fxy of the first depth gradient and the second depth gradient at each position point may be calculated using the following formula:

[0099] For example, the first depth gradient of the position point (1, 1) is 3, the second depth gradient of the position point (1, 1) is -1, and the root mean square F of the position point (1, 1) is (1,1) for:

[0100] On the collecting plate, the surface of the weld bead is more uneven than the surface at other positions, and the surface at other positions outside the weld bead is relatively smooth. Therefore, the root mean square of the weld bead position is larger, and the root mean square of other positions outside the weld bead is smaller.

[0101] The threshold value can be preset based on experience. For example, the threshold value can be determined by counting more three-dimensional images of the collecting plate after welding. This ensures that the threshold value is applicable to more situations after the collecting plate is welded, so that the weld position can be accurately found.

[0102] Exemplarily, the positions in the weld bead position map that are greater than the threshold value may be set to 1, and the positions that are less than or equal to the threshold value may be set to 0.

[0103] In an embodiment of the present application, by calculating the first depth gradient and the second depth gradient of each position point in the original image, and calculating the root mean square of the first depth gradient and the second depth gradient of each position point, and taking the root mean square greater than the threshold as the weld position, the weld position can be accurately determined by utilizing the fact that the weld surface on the collecting plate is more uneven than the surfaces at other positions, and the surfaces at other positions outside the weld are relatively smooth.

[0104] In some embodiments, registering the weld bead position map with the template image to obtain the rotation angle and offset corresponding to the original image includes:

[0105] Based on the preset step size, the position where the weld position map and the template image reach the expected similarity coefficient is searched, and the corresponding rotation angle and offset of the original image are obtained.

[0106] For example, the rotation angle and offset may correspond to different preset step sizes. For example, the preset step size corresponding to the rotation angle is rotating the weld bead position diagram 10 degrees to the right, and the preset step size corresponding to the offset is moving the collector plate in the weld bead position diagram to the lower right by one tenth of the image size.

[0107] The position where the expected similarity coefficient is achieved may be the position where the similarity coefficient between the weld position map and the template image is the highest. Of course, the expected similarity coefficient may be, for example, a similarity coefficient of 80% or above, or other values.

[0108] In the embodiment of the present application, the positions where the weld position map has a high similarity coefficient with the template image are searched according to a preset step size, so that the rotation angle and offset corresponding to the original image can be quickly determined.

[0109] In some embodiments, the preset step length includes a first preset step length and a second preset step length, the first preset step length is larger than the second preset step length, and searching for a position where the weld bead position map and the template image reach an expected similarity coefficient based on the preset step length to obtain the rotation angle and offset corresponding to the original image includes:

[0110] Searching for a first position where the weld bead position map and the template image reach a first expected similarity coefficient based on a first preset step size;

[0111] Starting from the first position, a second position where the weld position map and the template image reach a second expected similarity coefficient is searched based on a second preset step size to obtain a rotation angle and an offset corresponding to the original image.

[0112] For example, the rotation angle and offset may correspond to different first and second preset step sizes, respectively. For example, the first preset step size corresponding to the rotation angle is a 10-degree rightward rotation of the weld bead position diagram, while the second preset step size corresponding to the rotation angle is a 5-degree rightward rotation of the weld bead position diagram. The first preset step size corresponding to the offset is a 10-tenth of the image size of the current collecting plate in the weld bead position diagram moving to the lower right, while the second preset step size corresponding to the offset is a 20-th of the image size of the current collecting plate in the weld bead position diagram moving to the lower right.

[0113] The first position reaching the first expected similarity coefficient may be the first position where the similarity coefficient between the weld position map obtained based on the first preset step length search and the template image is the highest. Of course, the first expected similarity coefficient may be, for example, a similarity coefficient of at least 80%.

[0114] The second position reaching the second expected similarity coefficient may be the second position where the similarity coefficient between the weld position map obtained based on the second preset step length search and the template image is the highest. Of course, the second expected similarity coefficient may be, for example, a similarity coefficient of at least 90%.

[0115] In the embodiment of the present application, it is equivalent to using a pyramid search method, first searching with a large step size to find the position where the weld bead position map has the highest similarity coefficient with the template image, and then searching with a small step size to find the position where the weld bead position map has the highest similarity coefficient with the template image, so that the rotation angle and offset corresponding to the original image can be quickly determined.

[0116] In order to understand the rotation angle and offset more intuitively, FIG2 is used as an example to illustrate.

[0117] As shown in Figure 2, it includes a template image and an image to be corrected. After determining the rotation angle and offset corresponding to the image to be corrected, both the rotation angle and the offset include directional information. For example, the rotation angle may include the rotation direction and rotation angle, and the offset may include the offset direction and offset distance. The image to be corrected can first be rotated according to the determined rotation direction and rotation angle, and then the rotated image can be offset according to the offset direction and offset distance. For example, the image to be corrected in Figure 2 can first be rotated 45 degrees to the left, and then the smiling face in the rotated image can be moved to the lower right to the center of the image.

[0118] In some embodiments, the above steps of: removing the image information of the weld bead position in the original image, or removing the image information of the weld bead position in the position-corrected image; can be understood as subtracting the image information of the weld bead position in the original image, or subtracting the image information of the weld bead position in the position-corrected image; that is, subtracting the weld bead in the image.

[0119] In some embodiments, filling the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image includes:

[0120] The collecting disk topography image is interpolated and smoothed to fill the removed portion of the collecting disk topography image and obtain a restored collecting disk topography image.

[0121] In the embodiment of the present application, the removed portion is filled by interpolation and smoothing, which can more realistically restore the shape of the collecting plate, thereby facilitating a more accurate determination of the weld depth.

[0122] In order to more intuitively understand the method for measuring the depth of the current collecting plate weld provided in the embodiment of the present application, FIG3 is used as an example for illustration.

[0123] In FIG3 , an original image 1 of the current collecting disk after welding can be obtained first. The current collecting disk is a current collecting disk of a cylindrical battery. In the original image 1 , the current collecting disk is circular.

[0124] In order to correct the weld bead position, a weld bead position map needs to be obtained. On the collector plate, the weld bead surface is more uneven than other locations, so the weld bead position image 2 can be obtained by calculating the depth gradient map of the original image 1.

[0125] By registering and analyzing weld bead position image 2 with the standard weld bead template image 0, the rotation angle and offset of the weld bead position map can be obtained. The obtained rotation angle and offset are then used to process the original image 1 to obtain a position-corrected image 3 in which all weld bead positions are identical to those in the template image.

[0126] The collector plate itself is made of thin sheet metal, and after repeated stresses during processing, its surface becomes uneven. The depth variation caused by deformation of the collector plate itself is often much greater than the weld depth created by welding. Therefore, to obtain a weld depth map, it is necessary to perform surface correction on the position-corrected image 3 of the collector plate to determine the actual weld depth.

[0127] In order to perform surface correction on the collector plate image, it is first necessary to find the surface where the collector plate is located. In the position correction image 3, except for the weld position, the remaining positions should all be the collector plate surface outside the weld. Therefore, the image information of the weld position in the position correction image 3 can be deducted to remove the influence of the weld depth on the collector plate morphology, forming the collector plate morphology image 4. The removed portion of the collector plate morphology image 4 can then be filled through interpolation, smoothing and other operations to restore the true collector plate surface morphology, obtaining the collector plate morphology restoration image 5. Subtracting the collector plate morphology restoration image 5 from the position correction image 3 can obtain the true weld depth image 6. Based on the true weld depth image 6, the weld depth can be determined more accurately.

[0128] It should be noted that the application scenarios described in the above-mentioned embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Ordinary technicians in this field can know that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0129] Based on the same inventive concept, the present application also provides a device for measuring the depth of a current collecting plate weld bead, which will be described in detail with reference to FIG4 .

[0130] FIG4 shows a schematic diagram of a structure of a device for measuring the depth of a current collecting plate weld bead provided in an embodiment of the present application. As shown in FIG4 , the device 400 for measuring the depth of a current collecting plate weld bead may include an original image acquisition module 401 , a first processing module 402 , a second processing module 403 , and a third processing module 404 .

[0131] The original image acquisition module 401 is used to acquire the original image of the collector plate after welding, and the original image is a three-dimensional image;

[0132] The first processing module 402 is used to remove the image information of the weld bead position in the original image to obtain a collector plate topography image;

[0133] The second processing module 403 is used to fill the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image;

[0134] The third processing module 404 is configured to obtain a weld depth map based on the depth data of the same position in the original image and the restored image of the collecting plate topography.

[0135] In an embodiment of the present application, the weld position is corrected, and the weld position in the position correction image is the same as the weld position in the template image. In this way, when measuring the weld depth of the collecting plate, the weld position is unified, making it easy to measure the weld position of different collecting plates.

[0136] In some embodiments, the first processing module 402 is configured to:

[0137] The weld bead position of the original image is corrected using the template image to obtain a position-corrected image, wherein the weld bead position in the position-corrected image is the same as the weld bead position in the template image;

[0138] The image information of the weld bead position in the position correction image is removed to obtain the collector plate topography image;

[0139] The third processing module 404 is configured to:

[0140] The weld depth map is obtained based on the depth data of the same position in the position correction image and the collector plate topography restoration image.

[0141] In an embodiment of the present application, the weld position is corrected, and the weld position in the position correction image is the same as the weld position in the template image. In this way, when measuring the weld depth of the collecting plate, the weld position is unified, making it easy to measure the weld position of different collecting plates.

[0142] In some embodiments, the first processing module 402 is configured to:

[0143] Calculate the depth gradient map of the original image to obtain the weld bead position map corresponding to the original image;

[0144] The weld bead position map is registered with the template image to obtain the rotation angle and offset corresponding to the original image;

[0145] The original image is rotated and shifted according to the rotation angle and the offset to obtain a position-corrected image.

[0146] To correct the weld bead position, it's necessary to obtain the weld bead's position information from the original image. On a collector plate, the weld surface is more uneven than the surface elsewhere. In this embodiment, a weld bead position map is calculated from the original image to match the curved surface topography of the collector plate after welding, enabling accurate determination of the weld bead's position information.

[0147] In some embodiments, the first processing module 402 is configured to:

[0148] Calculating a first depth gradient in the horizontal direction and a second depth gradient in the vertical direction for each position point in the original image according to the depth of each position point in the original image;

[0149] Calculate the root mean square of the first depth gradient and the second depth gradient at each position point in the original image to obtain a depth gradient map corresponding to the original image;

[0150] The position points in the depth gradient map where the depth gradient is greater than a preset threshold are taken as weld bead positions, and a weld bead position map corresponding to the original image is obtained.

[0151] In an embodiment of the present application, by calculating the first depth gradient and the second depth gradient of each position point in the original image, and calculating the root mean square of the first depth gradient and the second depth gradient of each position point, and taking the root mean square greater than the threshold as the weld position, the weld position can be accurately determined by utilizing the fact that the weld surface on the collecting plate is more uneven than the surfaces at other positions, and the surfaces at other positions outside the weld are relatively smooth.

[0152] In some embodiments, the first processing module 402 is configured to:

[0153] Based on the preset step size, the position where the weld position map and the template image reach the expected similarity coefficient is searched, and the corresponding rotation angle and offset of the original image are obtained.

[0154] In the embodiment of the present application, the positions where the weld position map has a high similarity coefficient with the template image are searched according to a preset step size, so that the rotation angle and offset corresponding to the original image can be quickly determined.

[0155] In some embodiments, the preset step length includes a first preset step length and a second preset step length, and the first preset step length is larger than the second preset step length;

[0156] The first processing module 402 is configured to:

[0157] Searching for a first position where the weld bead position map and the template image reach a first expected similarity coefficient based on a first preset step size;

[0158] Starting from the first position, a second position where the weld position map and the template image reach a second expected similarity coefficient is searched based on a second preset step size to obtain a rotation angle and an offset corresponding to the original image.

[0159] In the embodiment of the present application, it is equivalent to using a pyramid search method, first searching with a large step size to find the position where the weld bead position map has the highest similarity coefficient with the template image, and then searching with a small step size to find the position where the weld bead position map has the highest similarity coefficient with the template image, so that the rotation angle and offset corresponding to the original image can be quickly determined.

[0160] In some embodiments, the second processing module 403 is configured to:

[0161] The collecting disk topography image is interpolated and smoothed to fill the removed portion of the collecting disk topography image and obtain a restored collecting disk topography image.

[0162] In the embodiment of the present application, the removed portion is filled by interpolation and smoothing, which can more realistically restore the shape of the collecting plate, thereby facilitating a more accurate determination of the weld depth.

[0163] The collector plate weld depth measuring device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0164] The device for measuring the depth of a current collecting plate weld provided in the embodiment of the present application can implement each process in the embodiment of the method for measuring the depth of a current collecting plate weld shown in FIG1 , and will not be described again here to avoid repetition.

[0165] Based on the same inventive concept, an embodiment of the present application further provides an electronic device. FIG5 shows a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application.

[0166] The electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0167] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0168] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 502 may include removable or non-removable (or fixed) media. Where appropriate, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0169] In certain embodiments, the memory 502 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these. For example, the memory may include non-volatile transient memory.

[0170] The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the current collecting plate weld bead depth measurement methods in the above embodiments.

[0171] In one example, the electronic device may further include a communication interface 503 and a bus 55. As shown in FIG5 , the processor 501, the memory 502, and the communication interface 503 are connected via the bus 55 and communicate with each other.

[0172] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiment of the present invention.

[0173] Bus 55 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus can include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI- Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 55 can include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.

[0174] Illustratively, the electronic device 500 may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0175] The electronic device can execute the current collecting plate weld bead depth measurement method in the embodiment of the present application, thereby realizing the current collecting plate weld bead depth measurement method and current collecting plate weld bead depth measurement device described in combination with FIG. 1 and FIG. 4 .

[0176] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program can implement the collector plate weld depth measurement method described in the above embodiment and achieve the same technical effect. To avoid repetition, the above computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., and is not limited here.

[0177] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0178] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link via a data signal carried in a carrier wave. "Computer-readable medium" can include any medium capable of storing or transmitting information. Examples of computer-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0179] According to an embodiment of the present application, the computer-readable storage medium may be a non-transitory computer-readable storage medium.

[0180] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0181] Aspects of the present application have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed via the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. This processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or the flowchart and the combination of the boxes in the block diagram and / or the flowchart can also be implemented by the dedicated hardware that performs the specified function or action, or can be implemented by the combination of dedicated hardware and computer instructions.

[0182] While the embodiments described above are not exhaustive, they do not limit the present application to the specific embodiments described. Clearly, numerous modifications and variations are possible based on the above description. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present application, thereby enabling those skilled in the art to better utilize the present application and its modifications. The present application is limited only by the claims and their full scope and equivalents.

Claims

1. A method for measuring the depth of a collector plate weld, comprising: Acquire an original image of the current collecting plate after welding, wherein the original image is a three-dimensional image; Removing the image information of the weld bead position in the original image to obtain a collector plate topography image; Filling the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image; A weld depth map is obtained based on the depth data of the same position in the original image and the restored image of the current collecting plate.

2. The method according to claim 1, wherein: The step of removing the image information of the weld bead position in the original image to obtain the collector plate topography image comprises: Correcting the weld bead position of the original image using the template image to obtain a position-corrected image, wherein the weld bead position in the position-corrected image is the same as the weld bead position in the template image; Removing the image information of the weld bead position in the position correction image to obtain a collector plate topography image; The step of obtaining a weld depth map according to the depth data of the same position of the original image and the restored image of the current collecting plate morphology comprises: A weld bead depth map is obtained based on the depth data of the same position of the position correction image and the current collecting plate topography restoration image.

3. The method according to claim 2, wherein: The method of correcting the weld bead position of the original image by using the template image to obtain a position-corrected image includes: Calculating a depth gradient map of the original image to obtain a weld bead position map corresponding to the original image; Registering the weld bead position map with the template image to obtain the rotation angle and offset corresponding to the original image; The original image is rotated and offset according to the rotation angle and offset to obtain a position-corrected image.

4. The method according to claim 3, wherein: The step of calculating the depth gradient map of the original image to obtain a weld bead position map corresponding to the original image includes: Calculating a first depth gradient in a horizontal direction and a second depth gradient in a vertical direction for each position point in the original image according to the depth of each position point in the original image; Calculate the first depth gradient and the second depth gradient of each position point in the original image The root mean square of the gradient is obtained to obtain a depth gradient map corresponding to the original image; The position points in the depth gradient map where the root mean square is greater than a preset threshold are taken as weld bead positions to obtain a weld bead position map corresponding to the original image.

5. The method according to claim 3, wherein: The weld bead position map is registered with the template image to obtain the rotation angle and offset corresponding to the original image, including: The weld bead position map is searched based on a preset step length to reach a position where the expected similarity coefficient is reached between the weld bead position map and the template image, and the rotation angle and offset corresponding to the original image are obtained.

6. The method according to claim 5, wherein: The preset step length includes a first preset step length and a second preset step length, and the first preset step length is larger than the second preset step length; The step of searching the weld bead position map based on a preset step length and the position where the template image reaches an expected similarity coefficient to obtain the rotation angle and offset corresponding to the original image includes: Searching for a first position where the weld bead position map and the template image reach a first expected similarity coefficient based on the first preset step length; Taking the first position as a starting point, based on the second preset step length, searching for a second position where the weld bead position map and the template image reach a second expected similarity coefficient, the rotation angle and offset corresponding to the original image are obtained.

7. The method according to claim 1, wherein: The step of filling the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image comprises: The collecting disk topography image is interpolated and smoothed to fill in the removed portion of the collecting disk topography image to obtain a collecting disk topography restoration image.

8. The method according to claim 1, wherein: The obtaining of the original image of the current collecting plate after welding comprises: The welded collector plate is photographed using a 3D structured light camera or a 3D line scan camera to obtain an original image of the welded collector plate.

9. The method according to claim 1, wherein: The original image includes two-dimensional size information and depth information of the current collecting plate after welding.

10. The method according to claim 2, wherein: The step of obtaining the weld depth map according to the depth data of the same position of the position correction image and the current collecting plate topography restoration image may include: The depth data of the same position of the position correction image and the current collecting plate topography restoration image are compared. Subtract to get the weld depth map.

11. The method according to claim 2, wherein: Before correcting the weld bead position of the original image using the template image to obtain the position-corrected image, the method further includes: An image with a complete weld bead is selected from a plurality of images of current collecting plates after welding, and then the image is subjected to a surface leveling process to obtain a template image.

12. The method according to claim 1, wherein: The step of removing the image information of the weld bead position in the original image to obtain the collector plate topography image comprises: The image information of the weld bead position in the original image is deducted to obtain a collector plate topography image.

13. The method according to claim 2, wherein: The step of removing the image information of the weld bead position in the position correction image to obtain the collector plate topography image comprises: The image information of the weld bead position in the position correction image is subtracted to obtain a collector plate topography image.

14. The method according to claim 4, wherein: The step of calculating, according to the depth of each position point in the original image, a first depth gradient in the horizontal direction and a second depth gradient in the vertical direction for each position point in the original image comprises: The original image includes multiple rows and columns of position points. For a position point, the depth difference between two position points in the row where the position point is located is selected to determine the first depth gradient of the position point in the horizontal direction, and the depth difference between two position points in the column where the position point is located is selected to determine the second depth gradient of the position point in the vertical direction.

15. The method according to claim 4, wherein: The calculating the root mean square of the first depth gradient and the second depth gradient of each position point in the original image includes: The root mean square of the first depth gradient and the second depth gradient at each position point in the original image is calculated using the following formula: Among them, Fxy represents the root mean square, Fx represents the first depth gradient, and Fy represents the second depth gradient.

16. The method according to claim 3, wherein: The rotation angle may include a rotation direction and a rotation angle, and the offset may include an offset direction and an offset distance.

17. The method according to claim 1, wherein: The current collecting plate comprises a circular current collecting plate.

18. A device for measuring the depth of a current collecting plate weld, comprising: An original image acquisition module, used to acquire an original image of the collector plate after welding, wherein the original image is a three-dimensional image; A first processing module is used to remove the image information of the weld bead position in the original image to obtain a collector plate topography image; A second processing module is used to fill the removed portion of the current collecting disk topography image to obtain a restored current collecting disk topography image; The third processing module is used to obtain a weld depth map according to the depth data of the same position of the original image and the restored image of the current collecting plate.

19. An electronic device comprising: A processor and a memory storing computer program instructions, wherein when the processor executes the computer program instructions, the method for measuring the depth of the collector plate weld bead according to any one of claims 1 to 17 is implemented. 20 . A computer-readable storage medium storing a computer program, wherein the computer-readable storage medium implements the method for measuring the depth of a current collecting plate weld bead according to claim 1 when the computer program is executed by a processor.

Images