Battery sealing nail welding inspection system and method

Abstract

The present application relates to the technical field of visual inspection, and discloses a battery sealing nail welding inspection system and method. The battery sealing nail welding inspection system comprises: a first camera and a first light source which are used for cooperatively collecting a 2D image of a battery cell; a second camera and a second light source which are used for collecting a 3D image of the battery cell; and a processing device electrically connected to the first camera, the first light source, the second camera, and the second light source and used for completing battery sealing nail welding inspection requirements on the basis of the 2D image and the 3D image corresponding to the same battery cell. According to the present application, some inspection requirements among inspection requirements related to the 2D image are completed by means of the first camera, and the remaining inspection requirements among inspection requirements related to the 3D image are completed in combination with the second camera, such that full coverage of battery sealing nail welding inspection requirements is achieved by means of the first camera and the second camera, widening the inspection range.

Description

Battery sealing nail welding detection system and method

[0001] Priority information

[0002] This application claims priority to Chinese patent application No. 202311208111.7 filed on September 19, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of visual inspection technology, and in particular to a battery sealing nail welding inspection system and method. Background Art

[0004] Currently, during the sealing process, welding is performed after the sealing pins seal the injection hole. After full welding, the sealing pins are visually inspected, and the battery cell is finally sealed. However, during the visual inspection of the battery cell, the inspection accuracy does not meet the inspection requirements.

[0005] Application Contents

[0006] In view of the above problems, the present application provides a battery sealing nail welding detection system and method, which aims to solve the problem that the inspection items in the existing battery cell visual inspection process cannot meet the inspection requirements.

[0007] The first camera and the first light source are used to cooperate in acquiring a 2D image of the battery cell;

[0008] A second camera and a second light source are used to cooperate in acquiring a 3D image of the battery cell; and

[0009] A processing device is electrically connected to the first camera, the first light source, the second camera, and the second light source, and is used to complete the battery sealing nail welding detection requirements based on the 2D image and 3D image corresponding to the same battery cell.

[0010] In the technical solution of the embodiment of the present application, the first camera is used to complete part of the battery sealing nail welding detection requirements related to the 2D image, and the second camera is combined to complete the remaining detection requirements of the battery sealing nail welding detection requirements related to the 3D image, so that the first camera is combined with the second camera to achieve full coverage of the battery sealing nail welding detection requirements, thereby improving the detection range.

[0011] In some embodiments, the first camera comprises a 2D camera; and / or the second camera comprises a light field camera.

[0012] In the technical solution of the embodiments of this application, a 2D camera uses continuous, planar scanning light to achieve detection, allowing it to acquire a complete target image in one go and perform 2D image acquisition in a timely manner. An area array camera can acquire a complete 2D image of a battery cell in one go, while a light field camera uses a single exposure, a single shot, and multiple angles to obtain the three-dimensional shape of a battery cell. A light field camera can capture the details of a battery cell, allowing for quick and accurate acquisition of a 3D image of the battery cell.

[0013] In some embodiments, the first camera and the second camera are movably installed along a first direction; the first camera and the second camera are spaced a first preset distance apart along the first direction to capture 2D images and 3D images corresponding to two battery cells spaced a first preset number apart.

[0014] In the technical solution of the embodiment of the present application, the first camera and the second camera are movably installed along the first direction, so that the first camera and the second camera can move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera and the second camera and improving the accuracy of detection.

[0015] In some embodiments, the first camera, the first light source, the second camera, and the second light source are correspondingly configured as acquisition groups. There are at least two acquisition groups, which are spaced apart along the second direction and are used to capture images of multiple columns of battery cells spaced apart along the second direction.

[0016] In the technical solution of the embodiment of the present application, when the incoming battery cells are in multiple rows, multiple groups can be used for simultaneous testing, making the combination method flexible and changeable, compatible with more incoming material methods, and helping to improve CT. The acquisition groups can be used in combination according to the number and arrangement of battery cells to improve the flexibility of detection.

[0017] In some embodiments, two adjacent acquisition groups are spaced apart by a second preset distance along the second direction, so as to acquire images corresponding to two columns of battery cells spaced apart by a second preset number.

[0018] In the technical solution of the embodiment of the present application, the collection groups can be used in combination according to the number and arrangement of battery cells to improve the flexibility of detection.

[0019] In some embodiments, in the same acquisition group, the first camera, the first light source, the second camera and the second light source move in the same direction; and / or,

[0020] The two first cameras and the two first light sources in at least two of the acquisition groups move in the same direction; and / or,

[0021] The two second cameras and the two second light sources in at least two of the acquisition groups move in the same direction.

[0022] In the technical solution of the embodiment of the present application, by moving the two first cameras and the two first light sources in the same direction and the two second cameras and the two second light sources in the same direction, the first camera and the second camera can move in the same direction, thereby improving the synchronization of the images taken by the first camera and the second camera and improving the accuracy of detection.

[0023] In some embodiments, the first camera, the first light source, the second camera, and the second light source move in the same direction.

[0024] In the technical solution of the embodiment of the present application, the first camera and the second camera can move synchronously in the same direction, thereby improving the synchronization of images captured by the first camera and the second camera and improving the accuracy of detection.

[0025] In some embodiments, the battery sealing nail welding detection system further includes:

[0026] A mounting bracket, wherein the first camera, the first light source, the second camera, and the first light source are all mounted on the mounting bracket; and

[0027] A driving device is connected to the mounting bracket to drive the mounting bracket to move, and the driving device is electrically connected to the processing device.

[0028] In the technical solution of the embodiment of the present application, the first camera and the second camera are connected by a mounting bracket, and the mounting bracket is driven by a driving device, so that the first camera and the second camera move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera and the second camera and improving the accuracy of detection.

[0029] In some embodiments, the first camera, the first light source, the second camera, and the second light source are correspondingly configured as acquisition groups, and at least two acquisition groups are configured;

[0030] At least two of the collection groups are arranged on the mounting bracket.

[0031] In the technical solution of the embodiment of the present application, when the incoming battery cells are in multiple rows, multiple groups can be used for simultaneous testing, making the combination method flexible and changeable, compatible with more incoming material methods, and helping to improve CT. The acquisition groups can be used in combination according to the number and arrangement of battery cells to improve the flexibility of detection.

[0032] In some embodiments, the first light source comprises:

[0033] a planar coaxial light source, provided on the collecting light path of the first camera; and

[0034] The annular light source is provided on the collection light path of the first camera and is located on a side of the planar coaxial light source facing away from the first camera.

[0035] In the technical solution of the embodiment of the present application, the first camera is supplemented with light by a planar coaxial light source and an annular light source, so that the image taken by the first camera is clearer and the accuracy of detection is improved.

[0036] In some embodiments, the second light source comprises:

[0037] The planar coaxial light source is arranged on the collecting light path of the second camera.

[0038] In the technical solution of the embodiment of the present application, the second camera is supplemented with light by a planar coaxial light source, so that the image captured by the second camera is clearer, thereby improving the accuracy of detection.

[0039] In some embodiments, the first camera and the second camera are movably mounted along a first direction;

[0040] Along the first direction, the first camera is located in front of the second camera and is configured to first capture a 2D image of the same battery cell and then capture a 3D image of the same battery cell.

[0041] In the technical solution of the embodiment of the present application, the first camera is placed in front and the second camera is placed in the back. The first camera is used to shoot first, and then the second camera is used to shoot. The shooting range of the first camera is larger than that of the second camera. After the first camera shoots a preliminary detection, the second camera is used for further detection, which improves the efficiency of detection.

[0042] In a second aspect, the present application provides a battery sealing nail welding detection method, the battery sealing nail welding detection method comprising:

[0043] Controlling the first camera and the first light source to cooperate in acquiring a 2D image of the battery cell;

[0044] Control the second camera and the second light source to cooperate in acquiring a 3D image of the battery cell;

[0045] Complete battery sealing pin welding inspection requirements based on the 2D and 3D images corresponding to the same battery cell.

[0046] In the technical solution of the embodiment of the present application, the first camera is used to complete part of the battery sealing nail welding detection requirements related to the 2D image, and the second camera is combined to complete the remaining detection requirements of the battery sealing nail welding detection requirements related to the 3D image, so that the first camera is combined with the second camera to achieve full coverage of the battery sealing nail welding detection requirements, thereby improving the detection range.

[0047] In some embodiments, the battery sealing nail welding detection method further includes: controlling the first camera and the second camera to move along a first direction when detecting that the battery cell moves to a preset area;

[0048] When it is detected that the first camera, the first light source, and the battery cell are concentric in a third direction, the first camera and the first light source cooperate to capture a 2D image of the battery cell;

[0049] When it is detected that the second camera, the second light source, and the battery cell are concentric in the third direction, a 3D image of the battery cell is collected by the second camera and the second light source in cooperation.

[0050] In the technical solution of the embodiment of the present application, the precise control of the detection is improved by controlling the first camera and the second camera to move to a preset photographing position, receiving a trigger signal, triggering photographing, completing photographing, and detecting the image.

[0051] In some embodiments, the battery sealing nail welding detection method further includes:

[0052] In the case where there are multiple battery cells arranged along a first direction, the first camera is controlled to move along the first direction to sequentially capture 2D images of the battery cells arranged in the first direction, and the second camera is controlled to move along the first direction to sequentially capture 3D images of the battery cells arranged in the first direction.

[0053] In the technical solution of the embodiment of the present application, when there are multiple rows of battery cells, the entire process of battery sealing nail welding detection is controlled, and the effective control of the detection process is improved by controlling the work flow of the first camera and the second camera.

[0054] In some embodiments, the battery sealing nail welding detection method further includes:

[0055] Statistically collect 2D and 3D images;

[0056] When the number of the collected 2D images and 3D images reaches a preset number, the first camera, the first light source, the second camera, and the second light source are controlled to return to preset positions.

[0057] In the technical solution of the embodiment of the present application, the 2D camera, light field camera, first light source and second light source are simultaneously moved to the position of the first step to form a closed loop to wait for the next group of battery cells to arrive for cyclic detection, thereby improving the precise control of the detection.

[0058] In some embodiments, completing the battery sealing nail welding inspection requirement based on the 2D image and 3D image corresponding to the same battery cell includes:

[0059] performing feature extraction on the 2D image of the battery cell to obtain extracted features;

[0060] Comparing the extracted features with preset defect features to determine the defect location;

[0061] Extracting a defect image corresponding to the defect position in the 3D image of the battery cell;

[0062] Perform image recognition on the defect image to complete the battery sealing nail welding detection requirements.

[0063] In the technical solution of the embodiment of the present application, the defect location is first determined through 2D images for preliminary screening, and then verified through 3D images to obtain the sealing pin welding detection results of the battery cell, thereby improving the accuracy of the detection.

[0064] In some embodiments, performing image recognition on the defect image to obtain a sealing pin welding inspection result of the battery cell includes:

[0065] performing image recognition on the defect image to obtain defect information;

[0066] Classifying the defect information to obtain a defect type;

[0067] The sealing pin welding inspection result of the battery cell is obtained based on the defect type.

[0068] In the technical solution of the embodiment of the present application, the defect type is further located based on the defect information, and automated sealing pin welding detection is realized to improve the efficiency of detection.

[0069] 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

[0070] FIG1 is a schematic structural diagram of a battery sealing nail welding detection system according to some embodiments of the present application;

[0071] FIG2 is a schematic diagram of the numbering method of battery cells in some embodiments of the present application;

[0072] FIG3 is a schematic diagram of the overall structure of a battery sealing nail welding detection system according to some embodiments of the present application;

[0073] FIG4 is a schematic structural diagram of a battery sealing nail welding detection system in a multi-group situation according to some embodiments of the present application;

[0074] FIG5 is a schematic flow chart of a battery sealing pin welding detection method proposed in some embodiments of the present application;

[0075] FIG6 is a schematic diagram of the overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0076] FIG7 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0077] FIG8 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0078] FIG9 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0079] FIG10 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0080] FIG11 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0081] FIG12 is a schematic diagram of another overall detection process of a battery sealing nail welding detection method proposed in some embodiments of the present application;

[0082] FIG13 is another schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application.

[0083] The accompanying drawings in the specific implementation manner are as follows:

[0084] Battery sealing nail welding detection system 100

[0085] A first camera 101 , a second camera 102 , a first light source 103 , a second light source 104 , a mounting bracket 105 , and a processing device 106 . DETAILED DESCRIPTION

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0093] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", and "fixed" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

[0094] Currently, during the sealing process, welding is performed after the sealing pins seal the injection hole. After full welding, the sealing pins are visually inspected, completing the final sealing of the battery cell. However, during the visual inspection of the sealing pins, the inspection accuracy does not meet the inspection requirements.

[0095] In order to solve the problem that the inspection items in the existing sealing nail visual inspection process cannot meet the inspection requirements, the embodiment of the present application uses the first camera to complete part of the inspection requirements of the battery sealing nail welding inspection related to the 2D image and combines the second camera to complete the remaining inspection requirements of the battery sealing nail welding inspection related to the 3D image, thereby achieving full coverage of the battery sealing nail welding inspection requirements through the combination of the first camera and the second camera, thereby improving the inspection range.

[0096] The battery cells disclosed in the embodiments of the present application can be used in electrical devices that use batteries as power sources or various energy storage systems that use batteries as energy storage elements. Electrical devices can include, but are not limited to, mobile phones, tablets, laptops, electric toys, power tools, battery-powered vehicles, electric vehicles, ships, spacecraft, and the like. Electric toys can include fixed or mobile electric toys, such as game consoles, electric car toys, electric ship toys, and electric airplane toys, and spacecraft can include airplanes, rockets, space shuttles, and spacecraft, among others.

[0097] Currently, during the sealing process, welding is performed after the sealant seals the injection hole. After full welding, the sealant is visually inspected, completing the final sealing of the battery cell. However, during the visual inspection of the sealant, the inspection accuracy does not meet the inspection requirements of the inspection items.

[0098] This application addresses the problem that the inspection items in the existing visual inspection process for sealing nails cannot meet the inspection requirements. A battery sealing nail welding inspection system 100 is proposed. Referring to FIG1 , in this example, the battery sealing nail welding inspection system 100 includes: a first camera 101 and a first light source 103 for cooperating to capture a 2D image of a battery cell;

[0099] The second camera 102 and the second light source 104 are used to cooperate in collecting 3D images of the battery cell; and the processing device 106 is electrically connected to the first camera 101, the first light source 103, the second camera 102 and the second light source 104, and is used to complete the battery sealing nail welding detection requirements based on the 2D images and 3D images corresponding to the same battery cell.

[0100] The first camera 101 uses continuous, planar scanning light to achieve detection, can obtain a complete target image at one time, and can perform 2D image acquisition in a timely manner. The first camera 101 and the first light source 103 can obtain a complete 2D image of the battery cell at one time.

[0101] The second camera 102 uses a light field camera to capture the battery cells through single exposure, constructing a light field that contains information about the direction and intensity of light propagation, thereby obtaining the three-dimensional shape of the battery cells. The second camera 102 and the second light source 104 can capture the details of the battery cells, thereby quickly and accurately obtaining a 3D image of the battery cells.

[0102] The processing device 106 is used to complete the first detection requirement of the battery sealing nail welding detection requirement based on the 2D image of the same battery cell, and complete the second detection requirement of the battery sealing nail welding detection requirement based on the 3D image of the same battery cell.

[0103] The first detection requirement may be a test item related to 2D images in the test items of the battery cell, that is, a partial test in the test item. The second detection requirement may be a test item related to 3D images in the test items of the battery cell, that is, a test of the remaining items in the test item. The test requirements of the entire test item can be met through the first detection requirement and the second detection requirement.

[0104] The processing device 106 may be a server, or a microprocessor or an industrial control center. Each collecting component transmits the collected information to the processing device 106 , which performs calculation and control.

[0105] The battery cells can be supplied in a disposable double row of 2*6 = 12 battery cells, or in other forms, depending on specific testing requirements. For example, the battery cells can be supplied in a disposable single row of 1*12 = 12 battery cells, or in a disposable single row of 3*6 = 18 battery cells. This embodiment does not limit this. In this embodiment, 2*6 = 12 battery cells are used as an example for illustration. The center-to-center spacing of the battery cells can be determined based on the actual situation of the battery cell supply and is not limited in this embodiment.

[0106] In some embodiments, identification marks are set for the battery cells in each row and column in sequence according to the arrangement of the battery cells. The identification marks are unique and correspond one-to-one to the battery cells. The battery cells can be effectively located by the identification marks. The identification marks can be in the form of numbers or other forms. This embodiment does not limit this. In this embodiment, the numbering method is used as an example for explanation. For example, the numbering method of the battery cells shown in Figure 2 can also be other numbering methods. The battery cells in the first row are numbered 1 / 2 / 3 / 4 / 5 / 6, and the battery cells in the second row are numbered 7 / 8 / 9 / 10 / 11 / 12. In Figure 2, the direction of arrangement of the battery cells along the x-axis is the horizontal direction, and the direction of arrangement along the y-axis is the vertical direction.

[0107] The first camera 101 and the second camera 102 move synchronously to inspect the battery cells. When the first camera 101 is triggered to take a photo facing the battery cell, the image captured is a 2D image. When the second camera 102 is triggered to take a photo facing the battery cell, the image captured is a 3D image. At the same moment, the 2D image of the battery cell captured by the first camera 101 and the 3D image of the battery cell captured by the second camera 102 are not images of the same battery cell, because the first camera 101 may be capturing the image of battery cell No. 3, but the second camera 102 has just started capturing the image of battery cell No. 1. Over a period of time, the 2D image of the battery cell captured by the first camera 101 and the 3D image of the battery cell captured by the second camera 102 may be images of the same battery cell. For example, the first camera 101 captures images of the first row of 6 battery cells, and the second camera 102 also captures images of the first row of 6 battery cells. The use of 2D and 3D images can accommodate more inspection requirements.

[0108] Under normal circumstances, by using a 3D light field camera, a single-station dual-channel total of two 3D light field cameras, the dual-channel simultaneous detection completes the battery sealing nail welding detection requirements, but some battery sealing nail welding detection requirements need to be detected by the first camera 101, resulting in the inability to complete the battery sealing nail welding detection requirements. Therefore, this embodiment uses the first camera 101 in combination with the second camera 102 to complete the battery sealing nail welding detection requirements.

[0109] In this embodiment, part of the battery sealing nail welding detection requirements related to the 2D image is completed by the first camera 101, and the remaining detection requirements of the battery sealing nail welding detection requirements related to the 3D image are completed in combination with the second camera 102. Thus, the full coverage of the battery sealing nail welding detection requirements is achieved by the first camera 101 combined with the second camera 102, thereby improving the detection range.

[0110] According to the detection accuracy requirement of the current detection item, the devices are selected: the first camera 101 includes an area array camera; and / or the second camera 102 includes a light field camera.

[0111] Area array cameras use continuous, planar scanning light to achieve detection, capturing a complete target image in a single pass and enabling timely 2D image acquisition. Area array cameras can capture a complete 2D image of a battery cell in a single pass. Light field cameras capture multiple layers of images to construct a light field containing information about the direction and intensity of light propagation. This light field can be viewed as a function in three-dimensional space, describing the information about light entering the camera from different directions and positions. Light field cameras can capture the details of battery cells, allowing for quick and accurate 3D image acquisition.

[0112] According to some embodiments of the present application, optionally, referring to FIG. 3 , the first camera 101 and the second camera 102 are spaced apart by a preset distance d, wherein the preset distance d is determined according to the center distance between battery cells.

[0113] The first camera 101 and the second camera 102 are movably installed along a first direction; the first camera 101 and the second camera 102 are spaced a first preset distance apart along the first direction, for simultaneously capturing 2D images and 3D images corresponding to two battery cells spaced a first preset number apart.

[0114] In this embodiment, the first direction may be a horizontal direction. Continuing with FIG. 2 and FIG. 3 , the horizontal direction is the direction in which the battery cells are arranged along the x-axis. The first camera 101 and the second camera 102 are movably installed along the first direction, so that the first camera 101 and the second camera 102 can move synchronously in the same direction, thereby improving the synchronization of the images captured by the first camera 101 and the second camera 102 and improving the accuracy of detection.

[0115] The first preset distance is the distance d between the centers of the first camera 101 and the second camera 102. Since the first camera 101 and the second camera 102 operate differently, the first preset distance is set between the first camera 101 and the second camera 102 to ensure the accuracy of the images captured by the first camera 101 and the second camera 102.

[0116] The first preset distance is not an arbitrary distance; it is determined based on the center-to-center distance between battery cells and is N times that distance. For example, if the center-to-center distance between the batteries is 70mm*240mm, the center-to-center distance between first camera 101 and second camera 102 is 140mm. This means that when first camera 101 is directly above battery cell No. 3, second camera 102 is directly above battery cell No. 1. This allows for precise triggering of second camera 102 to begin capturing, improving the integrity of the capture captured by second camera 102. When the first preset distance is 140mm, the first preset number is 1, meaning the first preset distance is twice the center-to-center distance between adjacent battery cells in the first direction.

[0117] In some embodiments, in the same acquisition group, the first camera 101 , the first light source 103 , the second camera 102 , and the second light source 104 move synchronously.

[0118] Continuing as shown in FIG4 , there are two acquisition groups, each acquisition group includes a 2D camera, a first light source 103 used in conjunction with the 2D camera, and a 3D camera and a second light source 104 used in conjunction with the 3D camera. For each acquisition group, the first camera 101, the first light source 103, the second camera 102, and the second light source 104 are controlled to move synchronously, thereby improving the accuracy of detection.

[0119] Two adjacent acquisition groups are spaced apart by a second preset distance along the second direction, so as to acquire images corresponding to two columns of battery cells spaced apart by a second preset number.

[0120] The second direction is perpendicular to the first direction. When the first direction is horizontal, the second direction is vertical. Continuing with Figures 2 and 3, the vertical direction is the direction in which the battery cells are arranged along the y-axis. The second preset distance is determined based on the center-to-center distance between battery cells, specifically the center-to-center distance between two rows of battery cells. Specifically, it can be N times the center-to-center distance between adjacent battery cells in the vertical direction. For example, if the center-to-center distance between battery cells is 70 mm by 240 mm, and the center-to-center distance between adjacent battery cells in the vertical direction is 240 mm, then the second preset distance can be set to 240 mm, meaning that the distance between two adjacent collection groups is 240 mm. The second preset distance is 0, meaning that there is no battery cell between the two collection groups. For example, if the second preset distance between two collection groups is set to 480 mm, then there is one battery cell between the two collection groups. By providing multiple collection groups in the second direction, multiple rows of battery cells can be collected simultaneously, improving collection efficiency.

[0121] The two first cameras 101 and the two first light sources 103 in at least two acquisition groups move in the same direction.

[0122] In this embodiment, the first camera 101 and the first light source 103 in the first acquisition group are controlled to move synchronously, so that the two acquisition groups run synchronously, which improves the efficiency of detection. The corresponding acquisition group can also be set according to the arrangement of the battery cells.

[0123] The two second cameras 102 in at least two acquisition groups move synchronously.

[0124] In this embodiment, the second cameras 102 and the second light sources 104 in the two acquisition groups are controlled to move synchronously to achieve multi-channel detection, thereby improving detection efficiency.

[0125] In the technical solution of the embodiment of the present application, by moving the first camera 101 and the first light source 103 in the same direction and the second camera 102 and the second light source 104 in the same direction, the first camera 101 and the second camera 102 can move synchronously in the same direction, thereby improving the synchronization of the images captured by the first camera 101 and the second camera 102 and improving the accuracy of detection.

[0126] In some embodiments, the first camera 101 , the first light source 103 , and the second camera 102 and the second light source 104 move synchronously.

[0127] In the technical solution of the embodiment of the present application, the first camera 101, the first light source 103, the second camera 102 and the second light source 104 can move synchronously in the same direction, thereby improving the synchronization of the images captured by the first camera 101 and the second camera 102 and improving the accuracy of detection.

[0128] According to some embodiments of the present application, optionally, referring to FIG3 , the battery sealing nail welding detection system further includes: a mounting bracket 105 and a driving device (not shown);

[0129] The mounting bracket 105, the first camera 101, the first light source 103, the second camera 102 and the second light source 104 are all arranged on the mounting bracket 105; and the driving device is driven and connected to the mounting bracket 105 to drive the mounting bracket 105 to move, and the driving device is electrically connected to the processing device 106.

[0130] In the technical solution of the embodiment of the present application, the first camera 101 and the second camera 102 are connected by a mounting bracket 105, and the mounting bracket 105 is driven by a driving device, so that the first camera 101 and the second camera 102 move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera 101 and the second camera 102 and improving the accuracy of detection.

[0131] The mounting bracket 105 is used to fix the first camera 101 and the second camera 102 , and the driving device is used to drive the mounting bracket 105 to make the first camera 101 and the second camera 102 move synchronously in the same direction.

[0132] The first camera 101 and the second camera 102 are fixed on the same bracket and installed parallel to each other. On the same bracket, they can move forward synchronously to detect battery cells 1 / 2 / 3 / 4 / 5 / 6. When the first camera 101 and the second camera 102 are two groups, they detect battery cells 1 / 2 / 3 / 4 / 5 / 6 and battery cells 7 / 8 / 9 / 10 / 11 / 12 respectively.

[0133] The driving device can be a motor or other forms of driving devices, and this embodiment is not limited thereto. This embodiment is described using a motor as an example. The motor drives the mounting bracket 105 to drive the first camera 101 and the second camera 102 to move synchronously in the same direction, thereby improving the synchronization of the images captured by the first camera 101 and the second camera 102 and improving the accuracy of detection.

[0134] According to some embodiments of the present application, optionally, a driving device is used to drive the first camera 101 and the second camera 102 respectively, so that the first camera 101 and the second camera 102 move synchronously in the same direction.

[0135] In this embodiment, there is no need to drive the mounting bracket 105 through a driving device to drive the first camera 101 and the second camera 102 to move in the same direction synchronously. Instead, it is directly connected to the first camera 101 and the second camera 102 to drive the first camera 101 and the second camera 102 simultaneously. This embodiment is explained using a motor as an example. When a double row of 2*6=12 pcs of battery cells are supplied, one inspection station, two area array 2D cameras and two light field cameras, and two sets of image detection combinations are driven by a motor and move synchronously. The 2D area array is fixed and the light field camera is exposed and photographed. The movement speed of the linear motor can be set to 300 mm / s, thereby improving the photographic effect. In addition, the first camera 101 and the second camera 102 are made to move in the same direction synchronously through the driving device, thereby improving the detection efficiency. The battery cell is controlled by the control device to reach the detection position, and the movement takes 0.1s. At this time, the first camera 101 is triggered by the trigger signal, which takes 0.1s, and the two 2D area array cameras are controlled to simultaneously capture battery cell No. 1 and battery cell No. 7 respectively, which takes 0.2s. After the imaging is completed, an imaging completion signal is generated, which takes 0.1s. The total time for collecting the 2D images of battery cell No. 1 and battery cell No. 7 is 0.5s. Next, 2D images of battery cells No. 2 and No. 8 are captured, and the two 2D area array cameras are controlled to move to the next battery cell. The movement takes 0.4 seconds, and the two 2D area array cameras are triggered by the trigger signal to capture 2D images of battery cells No. 2 and No. 8 respectively. The total time is 0.4 seconds. Then, 2D images of battery cells No. 3 and No. 9 are captured. At the same time, two light field cameras are used to capture 3D images of battery cells No. 1 and No. 7 at the same time. The 2D area array camera and the light field camera move simultaneously to battery cells No. 3 and No. 9 respectively. As well as battery cell No. 1 and battery cell No. 7, it takes 0.4s to move, and the two 2D area array cameras and two light field cameras are triggered by the trigger signal to collect images of the corresponding battery cells. The trigger signal takes 0.1s, the two 2D area array cameras take images in 0.2s, the two light field cameras take images in 0.2s, and it takes 0.1s to generate the imaging completion signal. The total time for 2D imaging of battery cell No. 3 and battery cell No. 9 and 3D imaging of battery cell No. 1 and battery cell No. 7 is 0.6s, and the detection results of battery cell No. 1 and battery cell No. 7 are obtained, which takes 0.1s. The 2D area array camera then moves to battery cells No. 4 and No. 10, and the light field camera moves to battery cells No. 2 and No. 8. The movement takes 0.4 seconds. Similarly, 2D imaging of battery cells No. 4 and No. 10 and 3D imaging of battery cells No. 2 and No. 8 take a total of 0.6 seconds, and the detection results of battery cells No. 2 and No. 8 are obtained in 0.1 seconds.The 2D area array camera then moves to battery cells #5 and #11, and the light field camera moves to battery cells #3 and #9. This movement takes 0.4 seconds. 2D images of battery cells #5 and #11, and 3D images of battery cells #3 and #9, take a total of 0.6 seconds. Inspection results for battery cells #3 and #9 are obtained in 0.1 seconds. The 2D area array camera moves to battery cells #6 and #12, and the light field camera moves to battery cells #4 and #10. This movement takes 0.4 seconds. 2D images of battery cells #6 and #12, and 3D images of battery cells #4 and #10, take a total of 0.6 seconds. Inspection results for battery cells #4 and #10 are obtained in 0.1 seconds. Then the 2D area array camera moves to the outside of the battery cell, and the light field camera moves to battery cell No. 5 and battery cell No. 11. The movement takes 0.4 seconds, and the total time for 3D imaging of battery cell No. 5 and battery cell No. 11 is 0.4 seconds, and the inspection results of battery cell No. 5 and battery cell No. 10 are obtained, which takes 0.1 seconds. Then the light field camera moves to battery cell No. 6 and battery cell No. 12. The movement takes 0.4 seconds, and the total time for 3D imaging of battery cell No. 6 and battery cell No. 12 is 0.4 seconds, and the inspection results of battery cell No. 6 and battery cell No. 12 are obtained, which takes 0.1 seconds. Through the above acquisition process, the inspection of double-row 2*6=12pcs battery cells is completed in a total of 7.5 seconds, thereby achieving the inspection requirement of 75PPM for the entire workstation.

[0136] According to some embodiments of the present application, optionally, referring to FIG3 , the battery sealing nail welding detection system further includes: a first light source 103 and a second light source 104 ;

[0137] The first light source 103 is fixed to the mounting bracket 105 and is located between the first camera 101 and the battery cell, and coincides with the center of the first camera 101.

[0138] The first light source 103 is used to provide light for the first camera 101. Since generating a 2D image requires the use of an external light source - a planar coaxial light source and a ring light source, the second light source 104 provides light for the second camera. Since generating a 3D image requires the use of an external light source - a planar coaxial light source, the first light source 103 is used to provide fill light for the first camera 101, and the second light source 104 is used to provide fill light for the second camera 102, making the images captured by the first camera 101 and the second camera 102 clearer, thereby improving the accuracy of detection.

[0139] According to some embodiments of the present application, optionally, and continuing with reference to FIG3 , the first light source 103 includes a planar coaxial light source, which is disposed on the light collection path of the first camera 101, and an annular light source, which is disposed on the light collection path of the first camera 101 and is located opposite the planar coaxial light source. The planar coaxial light source and the annular light source are sequentially arranged along the axis of the first camera 101, with the planar coaxial light source being close to the first camera 101. The planar coaxial light source and the annular light source provide fill light for the first camera 101, making the image captured by the first camera 101 clearer and improving the accuracy of detection.

[0140] According to some embodiments of the present application, optionally, referring to FIG3 , the second light source 104 includes a planar coaxial light source disposed in the light collection path of the second camera 102. The planar coaxial light source provides fill light for the second camera 40, making the image captured by the second camera 102 clearer and improving the accuracy of detection.

[0141] According to some embodiments of the present application, optionally, referring to Figure 3, when the first camera 101 and the second camera 102 are moved to be positioned opposite the battery cell, the first camera 101 and the second camera 102 respectively take pictures of the battery cell, and when the second camera 102 is moved to be positioned opposite the battery cell, the second camera 102 takes pictures of the battery cell.

[0142] The first camera 101 and the second camera 102 can be movably arranged and can move in a preset direction. When the first camera 101 is facing the battery cell, it starts to take a picture of the battery cell. When the second camera 102 is facing the battery cell, it starts to take a picture of the battery cell. By setting shooting stations, at each shooting station, the first camera 101 and the second camera 102 are used to take pictures of each battery cell that is facing each other.

[0143] For a one-time double-row 2*6=12 pcs battery cell material, the center spacing of the battery cells is 70mm*240mm. For smaller battery cells, the single-station battery cell material feeding method reserves limited space for visual device inspection, so the first camera 101 and the second camera 102 both adopt a vertical downward shooting method. The area array camera 10 and the light field camera are small in size, which meets the space requirements and improves the convenience of image acquisition.

[0144] According to some embodiments of the present application, optionally, referring to FIG. 3 , the first camera 101 and the second camera 102 are movably installed along a first direction;

[0145] Along the first direction, the first camera 101 is located in front of the second camera 102 and is configured to first capture a 2D image of the same battery cell and then capture a 3D image of the same battery cell.

[0146] In one embodiment, the first camera 101 and the second camera 102 move synchronously in the same direction. In the moving detection direction of the first camera 101 and the second camera 102 , the first camera 101 is located at the front side, and the second camera 102 is located at the rear side.

[0147] In this embodiment, after the battery cell reaches the inspection station, it stops moving, and the first camera 101 and the second camera 102 move synchronously in the same direction according to the instruction to inspect the battery cell located below. The first camera 101 and the second camera 102 can also move synchronously in the same direction, and the battery cell continues to move along the conveyor line, and the battery cell is inspected after reaching the inspection area of ​​the first camera 101 and the second camera 102. The battery cell can also continue to move along the conveyor line, and the first camera 101 and the second camera 102 are fixed, and the battery cell is inspected after moving to the inspection area of ​​the first camera 101 and the second camera 102. The first camera 101 and the second camera 102 can be directly above the battery cell for inspection, or the first camera 101 and the second camera 102 can be located on one side in the vertical direction, and the battery cell is located on the other side in the vertical direction, and the battery cell is inspected after moving to the inspection area of ​​the first camera 101 and the second camera 102.

[0148] The first camera 101 and the second camera 102 move synchronously in the same direction according to the instruction, and the detection of the battery cell located below is described as an example. The first camera 101 is in front and the second camera 102 is in the back. The first camera 101 takes the picture first, and then the second camera 102 takes the picture. The shooting range of the first camera 101 is larger than that of the second camera 102. After the preliminary detection by the first camera 101, the second camera 102 is further used for detection, which improves the efficiency of detection.

[0149] According to some embodiments of the present application, optionally, referring to Figure 4, the first camera 101, the first light source 103 and the second camera 102, the second light source 104 are correspondingly set as acquisition groups, and at least two acquisition groups are set; at least two acquisition groups are set on the mounting bracket 105.

[0150] When a double row of 2*6=12 pcs of battery cells is received at one time, two acquisition groups can be used to simultaneously detect battery cells 1 / 2 / 3 / 4 / 5 / 6 in the first row and battery cells 7 / 8 / 9 / 10 / 11 / 12 in the second row. When the incoming battery cells are in multiple rows, multiple groups can be used for simultaneous detection, making the combination flexible and changeable, compatible with more incoming material methods, and helping to improve CT. The image detection group can be used in combination according to the number and arrangement of battery cells to improve detection flexibility.

[0151] According to some embodiments of the present application, optionally, referring to Figure 4, the battery cells include at least two rows, and multiple battery cells in each row are arranged in sequence; a collection group is set corresponding to the arrangement direction of the battery cells in each row, and the collection group can be arranged according to the arrangement method of the battery cells to avoid missed detection and improve the accuracy of detection.

[0152] According to some embodiments of the present application, referring to FIG. 5 , FIG. 5 is a flow chart of a battery sealing nail welding detection method proposed according to some embodiments of the present application.

[0153] In this embodiment, the battery sealing nail welding detection method includes:

[0154] Step S10: controlling the first camera and the first light source to cooperate to capture a 2D image of the battery cell.

[0155] Step S20: controlling the second camera and the second light source to cooperate in capturing a 3D image of the battery cell.

[0156] Step S30: completing the battery sealing pin welding inspection requirements based on the 2D image and 3D image corresponding to the same battery cell.

[0157] The battery sealing nail welding detection system includes a first camera and a second camera, which are connected by the same bracket. As shown in Figure 4, the first camera and the second camera move synchronously above the battery cell to take pictures of the battery cell below for detection. The battery cells are numbered according to the arrangement of the battery cells. For example, 2*6=12pcs of battery cells are numbered as 1 / 2 / 3 / 4 / 5 / 6 in the first row and 7 / 8 / 9 / 10 / 11 / 12 in the second row. The first camera is in front and the second camera is in the back. This combination is used as an image detection combination. The two sets of image detection combinations are installed in parallel with each other and can move forward synchronously to detect battery cells 1 / 2 / 3 / 4 / 5 / 6 and batteries 7 / 8 / 9 / 10 / 11 / 12 respectively.

[0158] The first camera is used to complete some of the battery sealing nail welding detection requirements related to 2D images, and the second camera is used to complete the remaining detection requirements of the battery sealing nail welding detection requirements related to 3D images. For example, when the 2D image of battery No. 1 is completed, the battery 2D algorithm processes some detection items, and when the 3D image of battery No. 1 is completed, the battery 3D algorithm processes the remaining detection items. After the algorithm detection is completed, the detection result of battery No. 1 is output, thereby achieving full coverage of the battery sealing nail welding detection requirements through the combination of the first camera and the second camera, thereby improving the detection range.

[0159] According to some embodiments of the present application, optionally, the battery sealing nail welding detection method further includes: controlling the first camera and the second camera to move synchronously along the first direction when it is detected that the battery cell moves to a preset area.

[0160] When it is detected that the first camera, the first light source, and the battery cell are concentric in the third direction, a 2D image of the battery cell is collected by the first camera and the first light source in cooperation.

[0161] The second camera and the second light source are controlled to photograph the battery cell to collect a 3D image of the battery cell.

[0162] In this embodiment, the preset area may be a detection area, the detection area may be a fixed detection position where the movement of the battery cell is terminated, the first direction may be a horizontal direction, and when it is detected that the battery cell has moved to the detection position, the first camera and the second camera are controlled to move synchronously in the horizontal direction. When the first camera and the second camera are located directly above the battery cell, the corresponding 2D image and 3D image of the battery cell are used.

[0163] The third direction may be a vertical downward direction coaxial with the first camera, the light source, and the battery cell. A complete imaging effect may be achieved by using a fixed-shot method with a 2D camera and a fixed-shot method with a 3D camera.

[0164] In the technical solution of the embodiment of the present application, the precise control of the detection is improved by controlling the first camera and the second camera to move to a preset photographing position, receiving a trigger signal, triggering photographing, completing photographing, and detecting the image.

[0165] In some embodiments, the battery sealing nail welding detection method further includes:

[0166] When there are multiple battery cells arranged along a first direction, the first camera is controlled to move along the first direction to sequentially capture 2D images of the battery cells arranged in the first direction, and the second camera is controlled to move along the first direction to sequentially capture 3D images of the battery cells arranged in the first direction.

[0167] In the technical solution of the embodiment of the present application, when there are multiple rows of battery cells, as shown in Figure 4, the entire process of battery sealing nail welding detection is controlled, and the effective control of the detection process is improved by controlling the work flow of the first camera and the second camera.

[0168] In some embodiments, the battery sealing nail welding detection method further includes:

[0169] Counting the collected 2D images and 3D images; when the number of collected 2D images and 3D images reaches a preset number, controlling the first camera, the first light source, the second camera and the second light source to return to a preset position.

[0170] The preset number is the number of battery cells. When there are multiple rows of battery cells, after collecting 2D and 3D images of all battery cells, the 2D camera, light field camera, first light source and second light source are controlled to return to the initial detection position.

[0171] In the technical solution of the embodiment of the present application, the 2D camera, the first light source, the light field camera and the second light source are simultaneously moved to the position of the first step to form a closed loop to wait for the next group of battery cells to arrive for cyclic detection, thereby improving the precise control of the detection.

[0172] The battery sealing pin welding inspection method further includes: controlling the order in which the first camera and the second camera take photos, respectively, according to a control sequence. The control sequence is a control signal during the first and second camera shooting processes, which is used to control the entire battery sealing pin welding inspection process. By controlling the workflow of the first and second cameras through the control sequence, effective control of the inspection process is improved.

[0173] According to some embodiments of the present application, optionally, the workflow includes at least moving the first camera and the second camera to a preset photographing position, receiving a trigger signal, triggering photographing, completing photographing, and image detection.

[0174] As shown in Figure 6, Figure 6 is a schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application, and Figure 6 shows that a photo of battery No. 1 2D is taken. As shown in Figure 7, Figure 7 is another schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application, and Figure 7 shows that a photo of battery No. 2 2D is taken. As shown in Figure 8, Figure 8 is another schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application, and Figure 8 shows that a photo of battery No. 3 2D and a photo of battery No. 1 3D are taken. As shown in Figure 9, Figure 9 is another schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application, and Figure 9 shows that a photo of battery No. 4 2D and a photo of battery No. 2 3D are taken. As shown in Figure 10, Figure 10 is another schematic diagram of the overall detection process of the battery sealing nail welding detection method proposed in some embodiments of the present application, and Figure 10 shows that a photo of battery No. 5 2D and a photo of battery No. 3 3D are taken. As shown in Figure 11, Figure 11 is another overall detection process diagram of the battery sealing nail welding detection method proposed in some embodiments of the present application. Figure 11 shows taking a 2D photo of a No. 6 battery and a 3D photo of a No. 4 battery. As shown in Figure 12, Figure 12 is another overall detection process diagram of the battery sealing nail welding detection method proposed in some embodiments of the present application. Figure 12 shows taking a 3D photo of a No. 5 battery. As shown in Figure 13, Figure 13 is another overall detection process diagram of the battery sealing nail welding detection method proposed in some embodiments of the present application. Figure 13 shows taking a 3D photo of a No. 6 battery. The overall steps of the detection process are as follows:

[0175] 1. When the battery cell moves to the inspection station, the first camera, the first light source, and the center of the No. 1 battery cell coincide in the Z-axis direction and a 2D photo of the No. 1 battery is taken.

[0176] 2. When the centers of the first camera, the first light source, and the No. 2 battery cell coincide in the Z-axis direction, take a 2D photo with the No. 2 battery.

[0177] 3. When the centers of the first camera, the first light source, and the No. 3 battery cell coincide in the Z-axis direction, a 2D image of the No. 3 battery is taken. Before the 2D image of the No. 3 battery is taken, when the centers of the second camera, the second light source, and the No. 1 battery cell coincide in the Z-axis direction, a 3D image of the No. 1 battery is taken.

[0178] 4. When the centers of the first camera, the first light source, and the No. 4 battery cell coincide in the Z-axis direction, a 2D image of the No. 4 battery is taken. Before taking the 2D image of the No. 4 battery, when the centers of the second camera, the second light source, and the No. 2 battery cell coincide in the Z-axis direction, a 3D image of the No. 2 battery is taken.

[0179] 5. When the centers of the first camera, the first light source, and the No. 5 battery cell coincide in the Z-axis direction, a 2D image of the No. 5 battery is taken. Before taking the 2D image of the No. 5 battery, when the centers of the second camera, the second light source, and the No. 3 battery cell coincide in the Z-axis direction, a 3D image of the No. 3 battery is taken.

[0180] 6. When the centers of the first camera, the first light source, and the No. 6 battery cell coincide in the Z-axis direction, a 2D image of the No. 6 battery is taken. Before taking the 2D image of the No. 6 battery, when the centers of the second camera, the second light source, and the No. 4 battery cell coincide in the Z-axis direction, a 3D image of the No. 4 battery is taken.

[0181] 7. When the 3D light field camera, the second light source, and the center of the No. 5 battery cell coincide in the Z-axis direction, a 3D image of the No. 5 battery is taken.

[0182] 8. When the 3D light field camera, the second light source, and the center of the No. 6 battery cell coincide in the Z-axis direction, a 3D image of the No. 6 battery is taken.

[0183] After the above steps are completed, the 2D camera, the first light source, the second camera and the second light source move to the position of the first step at the same time to form a closed loop and wait for the next group of battery cells to arrive for cyclic detection, thereby controlling the first camera and the second camera to move to the preset photo position, receive the trigger signal, trigger the photo, complete the photo taking and image detection, thereby improving the precise control of the detection.

[0184] According to some embodiments of the present application, optionally, the battery sealing nail welding detection system also includes a first light source, and the conditions under which the first camera is triggered to take pictures include at least: the battery cell reaches a preset detection position; a first trigger signal is received; the centers of the first camera, the first light source and the battery cell coincide, wherein the first light source provides the first light source for the first camera and is coaxial with the first camera.

[0185] The battery cell reaches the preset detection position, which triggers the first camera to take a photo when the battery cell is detected to have reached the preset detection position. A sensor may be provided at the preset detection position to detect whether the battery cell has reached the preset detection position.

[0186] The received first trigger signal may be a PLC-CCD trigger signal or other forms of trigger signals, which are not limited in this embodiment. The PLC-CCD trigger signal may generate a PLC-CCD trigger signal to trigger the first camera to take a photo when the battery cell reaches a preset detection position, or may generate a PLC-CCD trigger signal when a set time is reached.

[0187] The detection of the coincidence of the first camera, the first light source and the center of the battery cell can be that the current battery cell image taken by the first camera is matched with a pre-stored image that coincides with the center of the battery cell, then it is determined that the first camera, the first light source and the center of the battery cell coincide, and the first camera is triggered to take pictures in a variety of ways, thereby improving the flexibility of controlling the first camera.

[0188] According to some embodiments of the present application, optionally, the detection of the coincidence of the first camera, the first light source and the center of the battery cell can be that the current battery cell image taken by the first camera is matched with a pre-stored image that coincides with the center of the battery cell, then it is determined that the first camera, the first light source and the center of the battery cell coincide.

[0189] Before determining whether the centers of the first camera, the first light source and the battery cell coincide, the first camera and the battery cell center may be first coincided, and then an image of the battery cell when the centers of the first camera and the battery cell coincide is captured, and the battery cell image is stored in a preset location. When determining whether the first camera is triggered to take a photo, the preset stored battery cell image is compared with the currently captured battery cell image. If the preset stored battery cell image is consistent with the currently captured battery cell image, it is determined that the centers of the first camera, the first light source and the battery cell coincide. If the preset stored battery cell image is inconsistent with the currently captured battery cell image, it is determined that the centers of the first camera, the first light source and the battery cell do not coincide. Thus, the coincidence of the centers of the first camera, the first light source and the battery cell is determined by image matching of the coincidence of the centers of the battery cell, thereby improving the accuracy of the control of the first camera.

[0190] According to some embodiments of the present application, optionally, the battery sealing nail welding detection system also includes a second light source, and the situation in which the second camera is triggered to take pictures includes at least: receiving a second trigger signal; the second camera, the second light source and the center of the battery cell coincide with each other, wherein the second light source provides a second light source for the second camera and is coaxial with the second camera.

[0191] The received second trigger signal may be a PLC-CCD trigger signal or a trigger signal in other forms. This embodiment does not limit this. The PLC-CCD trigger signal may generate a PLC-CCD trigger signal when the set time is reached, or may generate a PLC-CCD trigger signal when a preset number of battery cells is reached.

[0192] The detection of the coincidence of the second camera, the second light source and the center of the battery cell can be that the current battery cell image taken by the second camera is matched with the pre-stored image that coincides with the center of the battery cell, then it is determined that the second camera, the second light source and the center of the battery cell coincide, and the second camera is triggered to take pictures in a variety of ways, thereby improving the flexibility of the control of the second camera.

[0193] Since the battery cells are numbered, when the first camera reaches a battery cell with a preset number, the second camera can be triggered to start taking pictures. For example, when the first camera takes a picture of battery cell No. 3, the second camera is triggered to start taking pictures. In this way, the second camera can be triggered to take pictures in multiple ways, thereby improving the flexibility of controlling the second camera.

[0194] According to some embodiments of the present application, optionally, the center distance between adjacent battery cells is not an arbitrary distance, but is determined based on the center distance between the battery cells. For example, if the center distance of the battery is 70mm*240mm, the center distance between the first camera and the second camera is 140mm. That is, when the first camera is located directly above battery cell No. 3, the second camera is located directly above battery cell No. 1, so that a complete image of battery cell No. 1 can be obtained, avoiding incomplete shooting, and the second camera can be accurately triggered to start shooting, thereby improving the integrity of the shooting of the second camera.

[0195] The second camera is triggered to take photos based on the center distance between adjacent battery cells. When the second camera takes photos, a complete battery cell image can be captured, thereby improving the accuracy of the second camera's photos. When capturing images of the same battery cell, both the first camera and the second camera are taken concentrically with the battery cell, eliminating the need for coordinate system alignment and improving detection accuracy.

[0196] According to some embodiments of the present application, optionally, completing battery sealing nail welding inspection requirements based on 2D images and 3D images corresponding to the same battery cell includes:

[0197] Perform feature extraction on the 2D image of the battery cell to obtain extracted features; compare the extracted features with preset defect features to determine the defect location; extract the defect image corresponding to the defect location in the 3D image of the battery cell; perform image recognition on the defect image to obtain the sealing nail welding detection result of the battery cell.

[0198] Feature extraction can be performed through image recognition extraction or gradient extraction.

[0199] In the technical solution of the embodiment of the present application, the defect location is first determined through 2D images for preliminary screening, and then verified through 3D images to obtain the sealing pin welding detection results of the battery cell, thereby improving the accuracy of the detection.

[0200] According to some embodiments of the present application, optionally, performing image recognition on the defect image to obtain a sealing pin welding inspection result of the battery cell includes:

[0201] Perform image recognition on the defect image to obtain defect information; classify the defect information to obtain the defect type; and obtain the sealing nail welding detection result of the battery cell based on the defect type.

[0202] In the technical solution of the embodiment of the present application, the defect type is further located based on the defect information, and automated sealing pin welding detection is realized to improve the efficiency of detection.

[0203] The battery sealing nail welding detection system and method of the present application can be used to perform battery sealing nail welding detection in the field of visual inspection technology. This battery sealing nail welding detection system is applied to a specific production line, such as in a welding production line where the sealing nail seals the liquid injection hole after the battery cell production is completed. After full welding is completed, welding detection is performed to determine whether the battery cell has defects, and corresponding processing is performed based on the detection results to complete the final sealing of the battery cell. By using the battery sealing nail welding detection system and method of the present application, full coverage of battery sealing nail welding detection requirements can be achieved, thereby improving the detection range and detection accuracy.

[0204] Finally, it should be noted that the above embodiments 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, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A battery sealing nail welding detection system, wherein: include: The first camera and the first light source are used to cooperate in collecting a 2D image of the battery cell; The second camera and the second light source are used to cooperate in collecting a 3D image of the battery cell; as well as, A processing device, electrically connected to the first camera, the first light source, the second camera and the second light source, for completing the battery sealing nail welding detection requirements according to the 2D image and the 3D image corresponding to the same battery cell; The first camera comprises a 2D camera; and / or, The second camera comprises a light field camera.

2. The battery sealing nail welding detection system according to claim 1, wherein: The first camera and the second camera are movably installed along a first direction; The first camera and the second camera are spaced apart by a first preset distance along a first direction, so as to collect 2D images and 3D images corresponding to two battery cells spaced apart by a first preset number.

3. The battery sealing nail welding detection system as claimed in claim 2, wherein: The first preset distance is determined according to the center distance between the battery cells, and the first preset distance is N times the center distance between adjacent battery cells in the first direction.

4. The battery sealing nail welding detection system according to claim 1, wherein: The arrangement position of the battery cells is determined according to the incoming material mode of the battery cells, and identification marks are set for the battery cells in each row and column in turn according to the arrangement position. The identification marks are unique and correspond one-to-one with the battery cells. The acquisition process of the battery cells by the first camera and the second camera is determined by the identification marks, and image acquisition is performed through the acquisition process.

5. The battery sealing nail welding detection system according to claim 1, wherein: The first camera, the first light source, the second camera and the second light source are correspondingly arranged as a collection group. At least two of the collection groups are arranged at intervals along the second direction for collecting images of multiple columns of battery cells arranged at intervals along the second direction.

6. The battery sealing nail welding detection system as claimed in claim 5, wherein: Two adjacent acquisition groups are spaced apart by a second preset distance along the second direction to acquire images corresponding to two columns of battery cells spaced apart by a second preset number, and the second preset distance is N times the center distance between adjacent battery cells in the second direction.

7. The battery sealing nail welding detection system according to claim 5, wherein: In the same acquisition group, the first camera, the first light source, the second camera and the second light source move in the same direction; and / or, Two of the first cameras in at least two of the acquisition groups and two of the first light sources move in the same direction; and / or, The two second cameras and the two second light sources in at least two of the acquisition groups move in the same direction.

8. The battery sealing nail welding detection system according to claim 1, wherein: The first camera and the second camera move synchronously to detect the battery cell. When the first camera collects images facing the battery cell, a 2D image corresponding to the battery cell is obtained. When the second camera collects images facing the battery cell, a 3D image corresponding to the battery cell is obtained. At the same moment, the 2D image collected by the first camera and the 3D image collected by the second camera are images of different battery cells.

9. The battery sealing nail welding detection system according to claim 1, wherein: The first camera, the first light source, the second camera and the second light source move in the same direction.

10. The battery sealing nail welding detection system according to claim 9, wherein: The battery sealing nail welding detection system also includes: A mounting bracket, wherein the first camera, the first light source, the second camera and the second light source are all mounted on the mounting bracket; and A driving device is drivingly connected to the mounting bracket to drive the mounting bracket to move, and the driving device is electrically connected to the processing device.

11. The battery sealing nail welding detection system according to claim 9, wherein: The battery sealing nail welding detection system also includes: The driving device is used to drive the first camera and the second camera respectively, so that the first camera and the second camera move synchronously in the same direction.

12. The battery sealing nail welding detection system according to claim 10, wherein: The first camera, the first light source, the second camera and the second light source are correspondingly arranged as a collection group, and at least two of the collection groups are arranged; At least two of the collection groups are arranged on the mounting bracket.

13. The battery sealing nail welding detection system according to any one of claims 1 to 12, wherein: The first light source comprises: A planar coaxial light source, arranged on the light collecting path of the first camera; and The annular light source is arranged on the collecting light path of the first camera and is located on the side of the planar coaxial light source facing away from the first camera.

14. The battery sealing nail welding detection system according to any one of claims 1 to 12, wherein: The second light source comprises: The planar coaxial light source is arranged on the collecting light path of the second camera.

15. The battery sealing nail welding detection system according to any one of claims 1 to 12, wherein: The first camera and the second camera are movably installed along a first direction; Along the first direction, the first camera is located in front of the second camera, and is used to first collect the 2D image of the same battery cell and then collect the 3D image of the same battery cell.

16. The battery sealing nail welding detection system according to any one of claims 1 to 12, wherein: The first light source includes a planar coaxial light source and an annular light source, which are arranged on the light collection path of the first camera, and the annular light source is located in the opposite direction of the planar coaxial light source. The planar coaxial light source and the annular light source are arranged in sequence along the axial direction of the first camera, and the planar coaxial light source is close to the first camera, and the planar coaxial light source and the annular light source are used to fill in the light for the first camera; the second light source includes a planar coaxial light source, which is arranged on the light collection path of the second camera. The planar coaxial light source fills in the light for the second camera.

17. The battery sealing nail welding detection system according to any one of claims 1 to 12, wherein: The first camera and the second camera move synchronously in the same direction according to the instructions to detect the battery cells located below, with the first camera in front and the second camera in the back, first taking pictures with the first camera and then with the second camera. The shooting range of the first camera is larger than that of the second camera. After the preliminary inspection taken by the first camera, further inspection is performed with the second camera.

18. A battery sealing nail welding detection method, wherein: The battery sealing nail welding detection method comprises: Controlling the first camera and the first light source to cooperate in collecting a 2D image of the battery cell; Control the second camera and the second light source to cooperate in collecting a 3D image of the battery cell; Complete battery sealing pin welding inspection requirements based on the 2D and 3D images corresponding to the same battery cell.

19. The battery sealing nail welding detection method according to claim 18, wherein: The battery sealing nail welding detection method also includes: When it is detected that the battery cell moves to a preset area, controlling the first camera and the second camera to move along a first direction; When it is detected that the first camera, the first light source, and the battery cell are concentric in a third direction, the first camera and the first light source cooperate to collect a 2D image of the battery cell; When it is detected that the second camera, the second light source, and the battery cell are concentric in the third direction, a 3D image of the battery cell is collected by the cooperation of the second camera and the second light source.

20. The battery sealing nail welding detection method according to claim 19, wherein: The battery sealing nail welding detection method also includes: Acquire a current battery cell image taken by the first camera; Matching the current battery cell image with a pre-stored image of the battery cell center; When the match is consistent, it is determined that the first camera, the first light source, and the battery cell are concentric in the third direction.

21. The battery sealing nail welding detection method according to claim 18, wherein: The battery sealing nail welding detection method also includes: In the case where there are multiple battery cells arranged along a first direction, the first camera is controlled to move along the first direction to sequentially capture 2D images of the battery cells arranged in the first direction, and the second camera is controlled to move along the first direction to sequentially capture 3D images of the battery cells arranged in the first direction.

22. The battery sealing nail welding detection method according to claim 18, wherein: The battery sealing nail welding detection method also includes: Statistically collect 2D and 3D images; When the number of the collected 2D images and 3D images reaches a preset number, the first camera, the first light source, the second camera, and the second light source are controlled to return to preset positions.

23. The battery sealing nail welding detection method according to claim 18, wherein: The battery sealing nail welding detection requirement is completed according to the 2D image and the 3D image corresponding to the same battery cell, including: Extracting features from the 2D image of the battery cell to obtain extracted features; Comparing the extracted features with preset defect features to determine the defect location; Extracting a defect image corresponding to the defect position in the 3D image of the battery cell; Image recognition is performed on the defect image to meet the battery sealing pin welding detection requirements.

24. The battery sealing nail welding detection method according to claim 23, wherein: The image recognition of the defect image is performed to complete the battery sealing nail welding detection requirements, including: Performing image recognition on the defect image to obtain defect information; Classifying the defect information to obtain a defect type; The sealing nail welding detection result of the battery cell is obtained through the defect type, and the battery sealing nail welding detection requirements are met.

25. The battery sealing nail welding detection method according to claim 18, wherein: The battery sealing nail welding detection method also includes: Controlling the first camera and the first light source, the second camera and the second light source to move synchronously in the same direction; When the first camera, the first light source, the second camera, and the second light source move to a preset area, detecting whether the first camera and the first light source are concentric with the corresponding battery cell in a third direction, and detecting whether the second camera and the second light source are concentric with the corresponding battery cell in the third direction; When it is detected that the first camera and the first light source are concentric with the corresponding battery cell in the third direction and the second camera and the second light source are concentric with the corresponding battery cell in the third direction, the first camera and the first light source are controlled to cooperate to capture a 2D image of the battery cell, and the second camera and the second light source are controlled to cooperate to capture a 3D image of the battery cell; Counting the 2D images captured by the first camera and the 3D images captured by the second camera; When the number of the collected 2D images and 3D images reaches a preset number, the first camera, the first light source, the second camera, and the second light source are controlled to return to preset positions.

Images