Battery sealing nail welding detection system and method

By combining 2D and 3D image acquisition in the battery sealing nail welding detection system, the problem of insufficient detection accuracy in the prior art is solved, and a more comprehensive battery sealing nail welding detection is achieved.

CN119595651APending Publication Date: 2025-03-11CONTEMPORARY AMPEREX TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311166743.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-09-11
Publication Date
2025-03-11

AI Technical Summary

Technical Problem

During the existing visual inspection of battery cells, the detection accuracy cannot meet the detection requirements.

Method used

A battery sealing nail welding detection system is provided, combining the first camera and the second camera to collect 2D images and 3D images of the battery cell respectively, and the battery sealing nail welding detection requirements are completed through the processing device.

Benefits of technology

Through the combination of the first camera and the second camera, full coverage of battery sealing nail welding detection requirements is achieved, and the detection range and accuracy are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119595651A_ABST
    Figure CN119595651A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of visual inspection, and discloses a battery sealing nail welding detection system and method.The battery sealing nail welding detection system comprises a first camera and a light source which are used for cooperatively collecting a 2D image of a single battery; the second camera is used for collecting 3D images of the battery monomers; and the processing device is electrically connected with the first camera, the light source and the second camera, and is used for completing the welding detection requirement of the battery sealing nail according to the 2D image and the 3D image corresponding to the same battery monomer. According to the battery sealing nail welding detection method and device, part of detection requirements in detection requirements related to the 2D image are completed through the first camera, the remaining detection requirements in detection requirements related to the 3D image are completed in combination with the second camera, and therefore full coverage of the battery sealing nail welding detection requirements is achieved through combination of the first camera and the second camera, and the detection range is widened.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] 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

[0002] At present, in the sealing nail process, welding is performed after the sealing nail seals the injection hole, and the sealing nail is visually inspected after full welding, and the battery cell completes the final sealing. However, during the visual inspection of the battery cell, the inspection accuracy cannot meet the inspection requirements of the inspection items. Summary of the invention

[0003] In view of the above problems, the present application provides a battery sealing pin welding detection system and method, aiming to solve the problem that the detection items in the existing battery cell visual inspection process cannot meet the detection requirements.

[0004] In a first aspect, the present application provides a battery sealing nail welding detection system, comprising:

[0005] A first camera and a light source are used to cooperate in acquiring a 2D image of a battery cell;

[0006] A second camera is used to collect a 3D image of the battery cell; and

[0007] A processing device electrically connected to the first camera, the light source and the second camera, for completing the battery sealing nail welding detection requirements according to the 2D image and 3D image corresponding to the same battery cell

[0008] In the technical solution of the embodiment of the present application, part of the battery sealing nail welding detection requirements related to the 2D image are completed by the first camera, 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, so that the full coverage of the battery sealing nail welding detection requirements is achieved by the first camera combined with the 3D line scan camera and the second camera, thereby improving the detection range.

[0009] In some embodiments, the first camera includes an area array camera; and / or the second camera includes a line scan camera.

[0010] In the technical solution of the embodiment of the present application, the area array camera uses continuous, planar scanning light to achieve detection, which can obtain a complete target image at one time, and can timely perform 2D image acquisition. The area array camera can obtain a complete 2D image of a battery cell at one time, and the line scan camera scans the battery cell through a laser line and converts the signal reflected by the laser line into a digital signal to obtain the three-dimensional shape of the battery cell. The line scan camera can capture the details of the battery cell, thereby quickly and accurately obtaining a 3D image of the battery cell.

[0011] 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.

[0012] 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.

[0013] In some embodiments, the first camera, the light source and the second camera are correspondingly arranged as a collection group, at least two of the collection groups are arranged at intervals along the second direction, and are used to collect images of multiple columns of battery cells arranged at intervals along the second direction.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] In some embodiments, in the same acquisition group, the first camera, the light source and the second camera move in the same direction; and / or,

[0018] At least two of the first cameras in the two acquisition groups and the two light sources move in the same direction; and / or,

[0019] The two second cameras in at least two of the acquisition groups move in the same direction.

[0020] In the technical solution of the embodiment of the present application, by moving the first camera, the two light sources and the second camera 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.

[0021] In some embodiments, the first camera, the light source, and the second camera move in the same direction.

[0022] 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 taken by the first camera and the second camera and improving the accuracy of detection.

[0023] In some embodiments, the battery sealing nail welding detection system further includes:

[0024] A mounting bracket, wherein the first camera, the light source, and the second camera are all mounted on the mounting bracket; and

[0025] 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.

[0026] 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.

[0027] In some embodiments, the first camera, the light source and the second camera are correspondingly arranged as a collection group, and at least two of the collection groups are arranged;

[0028] At least two of the collection groups are arranged on the mounting bracket.

[0029] 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.

[0030] In some embodiments, the light source comprises:

[0031] A planar coaxial light source, arranged on the light collecting path of the first camera; and

[0032] 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.

[0033] In the technical solution of the embodiment of the present application, the first camera 10 is supplemented with light by a planar coaxial light source and an annular light source, so that the image taken by the first camera 10 is clearer, thereby improving the accuracy of detection.

[0034] In some embodiments, the first camera and the second camera are movably mounted along a first direction;

[0035] 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.

[0036] In the technical solution of the embodiment of the present application, the first camera is used in front and the second camera is used in the back. The first camera is used to shoot first, and then the second camera is used to perform a flying scan. The shooting range of the first camera is larger than that of the second camera. After the preliminary detection taken by the first camera, the second camera is used for further detection, which improves the efficiency of detection.

[0037] In a second aspect, the present application provides a battery sealing nail welding detection method, the battery sealing nail welding detection method comprising:

[0038] Control the first camera and the light source to cooperate in collecting a 2D image of the battery cell;

[0039] Controlling the second camera to collect a 3D image of the battery cell;

[0040] Complete battery sealing pin welding inspection requirements based on the 2D and 3D images corresponding to the same battery cell.

[0041] In the technical solution of the embodiment of the present application, part of the battery sealing nail welding detection requirements related to the 2D image are completed by the first camera, 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, so that the full coverage of the battery sealing nail welding detection requirements is achieved by combining the first camera with the second camera, thereby improving the detection range.

[0042] In some embodiments, the battery sealing nail welding detection method further includes: in the case of detecting that the battery cell moves to a preset area, controlling the first camera and the second camera to move along a first direction;

[0043] When it is detected that the first camera, the light source, and the battery cell are concentric in a third direction, the first camera and the light source cooperate to collect a 2D image of the battery cell;

[0044] The second camera is controlled to sweep the battery cell along the first direction at a uniform speed to collect a 3D image of the battery cell.

[0045] 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 image detection.

[0046] In some embodiments, the step of acquiring the 3D image of the battery cell by the second camera includes:

[0047] The second camera is controlled to sweep the battery cell along the first direction at a uniform speed to collect a 3D image of the battery cell.

[0048] In the technical solution of the embodiment of the present application, the second camera is a line scan camera, which generates a 3D image by uniform horizontal scanning without the aid of an external light source, thereby improving the efficiency of detection.

[0049] In some embodiments, the battery sealing nail welding detection method further includes:

[0050] 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.

[0051] 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 working processes of the first camera and the second camera.

[0052] In some embodiments, the battery sealing nail welding detection method further includes:

[0053] Statistically collect 2D and 3D images;

[0054] When the number of the collected 2D images and 3D images reaches a preset number, the first camera, the light source and the second camera are controlled to return to preset positions.

[0055] In the technical solution of the embodiment of the present application, the 2D camera, 3D line scan camera and 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.

[0056] In some embodiments, the trigger conditions for controlling the first camera and the light source to cooperate in capturing a 2D image of a battery cell include at least one of the following: the battery cell reaches a preset detection position; a first trigger signal is received; and it is detected that the first camera, the light source, and the center of the battery cell coincide with each other, wherein the light source provides light for the first camera and is coaxial with the first camera.

[0057] In the technical solution of the embodiment of the present application, the first camera is triggered to take photos in a variety of ways, thereby improving the flexibility of controlling the first camera.

[0058] In some embodiments, detecting that the first camera, the light source, and the battery cell centers coincide with each other includes:

[0059] If the current battery cell image captured by the first camera matches a pre-stored image that coincides with the center of the battery cell, it is determined that the first camera, the light source, and the center of the battery cell coincide.

[0060] In the technical solution of the embodiment of the present application, the coincidence of the centers of the first camera, the light source and the battery cell is determined by image matching of the coincidence of the centers of the battery cells, thereby improving the accuracy of the control of the first camera.

[0061] In some embodiments, the trigger condition for controlling the second camera to capture the 3D image of the battery cell includes at least one of the following: receiving a second trigger signal; the second camera detecting the battery cell; the first camera moving to the detection position corresponding to the battery cell with a preset number.

[0062] In the technical solution of the embodiment of the present application, the second camera is triggered to take photos in a variety of ways, thereby improving the flexibility of controlling the second camera.

[0063] In some embodiments, it also includes:

[0064] Extracting features from the first image of the battery cell to obtain extracted features;

[0065] Comparing the extracted features with preset defect features to determine the defect location;

[0066] Extracting a defect image corresponding to the defect position in the second image of the battery cell;

[0067] Image recognition is performed on the defect image to obtain a sealing pin welding detection result of the battery cell.

[0068] In the technical solution of the embodiment of the present application, the defect location is first determined by the first image, and a preliminary screening is performed, and then the second image is used for verification to obtain the sealing pin welding detection result of the battery cell, thereby improving the accuracy of the detection.

[0069] In some embodiments, performing image recognition on the defect image to obtain a sealing pin welding detection result of the battery cell includes:

[0070] Performing image recognition on the defect image to obtain defect information;

[0071] Classifying the defect information to obtain a defect type;

[0072] The sealing pin welding detection result of the battery cell is obtained according to the defect type.

[0073] In the technical solution of the embodiment of the present application, the defect type is further located according to the defect information, and automated sealing pin welding detection is realized to improve the efficiency of detection.

[0074] 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

[0075] Figure 1 This is a schematic diagram of the structure of a battery sealing pin welding detection system according to some embodiments of the present application;

[0076] Figure 2 A schematic diagram of the numbering method of battery cells in some embodiments of the present application;

[0077] Figure 3 This is a schematic diagram of the overall structure of a battery sealing nail welding detection system according to some embodiments of the present application;

[0078] Figure 4 A schematic diagram of the structure of a battery sealing nail welding detection system in multiple groups according to some embodiments of the present application;

[0079] Figure 5 A schematic diagram of a flow chart of a battery sealing pin welding detection method proposed in some embodiments of the present application;

[0080] Figure 6a-6i A schematic diagram of the overall detection process of the battery sealing pin welding detection method proposed in some embodiments of the present application.

[0081] The reference numerals in the specific implementation manner are as follows:

[0082] Battery sealing nail welding detection system 100

[0083] A first camera 10 , a second camera 20 , a light source 30 , a mounting bracket 40 , a telecentric lens 50 , and a processing device 60 . DETAILED DESCRIPTION

[0084] The following embodiments of the technical solution of the present application are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0085] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field 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" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0086] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0087] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0088] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0089] 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).

[0090] 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. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, which 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 referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the embodiments of the present application.

[0091] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection 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 the specific circumstances. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0092] At present, in the sealing nail process, welding is performed after the sealing nail seals the injection hole, and the sealing nail is visually inspected after full welding, and the battery cell completes the final sealing. However, during the process of visual inspection of the sealing nail, the inspection accuracy cannot meet the inspection requirements of the inspection items.

[0093] 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 first camera combined with the second camera, thereby improving the inspection range.

[0094] The battery cell 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 be, but are not limited to, mobile phones, tablets, laptops, electric toys, electric tools, battery cars, electric cars, ships, spacecraft, etc. Among them, electric toys can include fixed or mobile electric toys, such as game consoles, electric car toys, electric ship toys, and electric airplane toys, etc., and spacecraft can include airplanes, rockets, space shuttles, and spacecraft, etc.

[0095] At present, in the sealing process, welding is performed after the sealant seals the injection hole, and visual inspection of the sealant 40 is performed after full welding is completed, and the battery cell completes the final sealing. However, during the visual inspection of the sealant 40, the inspection accuracy cannot meet the inspection requirements of the inspection items.

[0096] In view of the problem that the inspection items in the existing sealing nail visual inspection process cannot meet the inspection requirements, this application proposes a battery sealing nail welding inspection system 100, please refer to Figure 1 In this example, the battery sealing nail welding detection system 100 includes: a first camera 10 and a light source 30, which are used to cooperate in collecting a 2D image of a battery cell;

[0097] A second camera 20 is used to collect a 3D image of a battery cell; and

[0098] The processing device 60 is electrically connected to the first camera, the light source and the second camera, and is used to complete the battery sealing nail welding detection requirements according to the 2D image and the 3D image corresponding to the same battery cell.

[0099] The first camera 10 is a camera that 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 10 can obtain a complete 2D image of a battery cell at one time.

[0100] The second camera 20 scans the battery cell through a laser line and converts the signal reflected by the laser line into a digital signal to obtain the three-dimensional shape of the battery cell. The second camera 20 can capture the details of the battery cell, thereby quickly and accurately obtaining a 3D image of the battery cell.

[0101] The processing device 60 is used to complete the first detection requirement of the battery sealing nail welding detection requirements according to the first image, and complete the second detection requirement of the battery sealing nail welding detection requirements according to the second image.

[0102] The first detection requirement may be a test item related to the first image 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 the second image 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 by the first detection requirement and the second detection requirement.

[0103] The processing device 60 may be a server, or a microprocessor or an industrial control center. Each collecting component transmits the collected information to the processing device, which performs calculation and control.

[0104] The battery cells can be one-time double-row 2*6=12pcs battery cells, or other forms of battery cells. This embodiment does not limit this. In this embodiment, 2*6=12pcs of battery cells are used as an example for explanation. The center spacing of the battery cells can be determined according to the actual situation of the battery cells. This embodiment does not limit this. In this embodiment, the center spacing of the battery cells is 70mm*240mm as an example for explanation.

[0105] In some embodiments, the battery cells are sequentially provided with identification marks for each row and column of the battery cells according to the arrangement mode. The identification marks are unique and correspond to the battery cells one by one. 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 identification method of numbers is taken as an example for explanation. For example, Figure 2 The battery cells shown are numbered in other ways, where 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.

[0106] The first camera 10 and the second camera 20 move synchronously to detect the battery cell. The image captured when the first camera 10 is triggered to take a photo facing the battery cell is the first image, and the image captured when the 3D area array camera 10 is triggered to take a photo facing the battery cell is the second image. At the same time, the first image of the battery cell captured by the first camera 10 and the second image of the battery cell captured by the 3D area array camera 10 are not images of the same battery cell, because the first camera 10 may capture the image of battery cell No. 3, but the first camera 10 has just started to capture the image of battery cell No. 1. Within a period of time, the first image of the battery cell captured by the first camera 10 and the second image of the battery cell captured by the 3D area array camera 10 may be the image of the same battery cell. For example, the first camera 10 captures images of the first row of 6 battery cells, and the 3D area array camera 10 also captures images of the first row of 6 battery cells. The first image and the second image can accommodate more detection requirements.

[0107] Under normal circumstances, by using 3D line scanning laser, a single-station dual-channel total of two 3D line scanning lasers, dual-channel simultaneous detection to complete the battery sealing nail welding detection requirements, but some battery sealing nail welding detection requirements need to be detected by the first camera 10, resulting in the inability to complete the battery sealing nail welding detection requirements. Therefore, this embodiment uses the first camera 10 in combination with the second camera 20 to complete the battery sealing nail welding detection requirements.

[0108] In this embodiment, part of the battery sealing nail welding detection requirements related to the 2D image are completed by the first camera 10 and the remaining battery sealing nail welding detection requirements related to the 3D image are completed in combination with the second camera 20. Thus, the full coverage of the battery sealing nail welding detection requirements is achieved by the first camera 10 combined with the second camera 20, thereby improving the detection range.

[0109] According to the detection accuracy requirement of the current detection item, the device is selected: the first camera 10 includes an area array camera; and / or the second camera 20 includes a line scan camera.

[0110] The XY direction accuracy of the first camera 10 is 0.003mm, and the height direction accuracy of the second camera 20 is less than 0.001mm. At the same time, in order to meet the production line CT: 75PPM, a combination of area array camera + 3D line scanning laser is adopted. When 2*6=12pcs of battery monomers are incoming, a single-station dual-channel has two area array cameras and two 3D line scanning lasers. The dual channels are tested simultaneously, and the detection accuracy meets the height ≥ 0.1mm and the area ≥ 0.25mm 2 The combination has XY accuracy of 0.003mm and Z accuracy of 0.001mm. For the post-weld inspection of sealing pins, the production line CT requirement is 75ppm. The combination has a CT of 86ppm, thus achieving a wide range of accuracy compatibility, a wide range of field of view compatibility, a wide range of combination compatibility, and higher CT compatibility requirements.

[0111] Area array cameras use continuous, planar scanning light to achieve detection. They can obtain a complete target image at one time and can collect 2D images in a timely manner. Area array cameras can obtain a complete 2D image of a battery cell at one time. Line scan cameras use a laser line to scan the battery cell and convert the signal reflected by the laser line into a digital signal to obtain the three-dimensional shape of the battery cell. Line scan cameras can capture the details of the battery cell, thereby quickly and accurately obtaining a 3D image of the battery cell.

[0112] According to some embodiments of the present application, optionally, please refer to Figure 3 The first camera 10 and the second camera 20 are spaced apart by a preset distance, wherein the preset distance is determined according to the center distance between the battery cells.

[0113] The first camera 10 and the second camera 20 are movably installed along a first direction; the first camera 10 and the second camera 20 are spaced a first preset distance apart along the first direction to simultaneously capture 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, and 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 images taken by the first camera and the second camera and improving the accuracy of detection.

[0115] The first preset distance is the distance d between the centers of the first camera 10 and the second camera 20. Since the working principles of the first camera 10 and the second camera 20 are different, in order to ensure the accuracy of the images taken by the first camera 10 and the second camera 20, the first camera 10 and the second camera 20 are spaced apart by the first preset distance.

[0116] The first preset distance is not an arbitrary distance, but is determined according to 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 10 and the second camera 20 is 175mm, that is, when the first camera 10 is located directly above the third battery cell, the scanning line of the second camera 20 can be located at the edge of the first battery cell and start scanning, so as to obtain a complete image of the first battery cell, avoid incomplete scanning, and accurately trigger the second camera 20 to start shooting, thereby improving the integrity of the shooting of the second camera 20.

[0117] In some embodiments, in the same acquisition group, the first camera 10 , the light source 30 , and the second camera 20 move in the same direction.

[0118] Optionally, in the same acquisition group, the first camera 10, the light source 30 and the second camera 20 move synchronously in the same direction, and continue as follows. Figure 4 As shown, there are two acquisition groups, each of which includes a 2D camera, a light source used with the 2D camera, and a 3D camera. For each acquisition group, the first camera 10, the light source 30, and the second camera 20 are controlled to move synchronously, thereby improving the accuracy of detection.

[0119] The two first cameras 10 and the two light sources 30 in at least two acquisition groups move in the same direction.

[0120] Optionally, the two first cameras 10 and the two light sources 30 in at least two acquisition groups move synchronously in the same direction.

[0121] In this embodiment, the first camera 10 in the first acquisition group is controlled, and the two light sources move synchronously, so that the two acquisition groups run synchronously, which improves the efficiency of detection. The corresponding acquisition groups can also be set according to the arrangement of the battery cells.

[0122] The two second cameras in at least two acquisition groups move in the same direction.

[0123] In this embodiment, the second cameras in the two acquisition groups are controlled to move synchronously to achieve multi-channel detection, thereby improving the detection efficiency.

[0124] In the technical solution of the embodiment of the present application, by synchronously moving the first camera 10, the two light sources and the second camera, the first camera 10 and the second camera can move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera 10 and the second camera and improving the accuracy of detection.

[0125] In some embodiments, the first camera 10 , the light source 30 , and the second camera 20 move in the same direction.

[0126] In the technical solution of the embodiment of the present application, the first camera 10, the light source 30 and the second camera 20 can move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera 10 and the second camera 20 and improving the accuracy of detection.

[0127] In some embodiments, the first camera 10, the light source 30 and the second camera 20 can also move relative to each other. For example, the first camera 10 and the light source 30 move from left to back to capture a 2D image. After the first camera completes the capture of the same battery cell, the second camera moves from right to left to capture a 3D image of the same battery cell.

[0128] In some embodiments, the first camera 10, the light source 30 and the second camera 20 can also move relatively simultaneously. For example, the first camera 10 and the light source 30 move from left to back to collect a 2D image, and the second camera 20 moves from right to left to collect a 3D image of the same battery cell. In the event of interference between the first camera 10 and the second camera 20, the first camera 10 or the second camera 20 is adjusted by an avoidance device.

[0129] According to some embodiments of the present application, optionally, please refer to Figure 3 , the battery sealing nail welding detection system also includes: a mounting bracket 40 and a driving device (not shown in the figure);

[0130] A mounting bracket 40, on which the first camera 10, the light source 30 and the second camera 20 are all mounted; and,

[0131] The driving device is connected to the mounting bracket 40 to drive the mounting bracket to move. The driving device is electrically connected to the processing device 60.

[0132] In the technical solution of the embodiment of the present application, the first camera 10 and the second camera 20 are connected by a mounting bracket, and the mounting bracket 40 is driven by a driving device, so that the first camera 10 and the second camera 20 move synchronously in the same direction, thereby improving the synchronization of the images taken by the first camera 10 and the second camera 20 and improving the accuracy of detection.

[0133] The mounting bracket 40 is used to fix the first camera 10 and the second camera 20 , and the driving device is used to drive the mounting bracket 40 to make the first camera 10 and the second camera 20 move synchronously in the same direction.

[0134] The first camera 10 and the second camera 20 are fixed on the same bracket and installed parallel to each other. On the same bracket, they can move forward synchronously to detect 1 / 2 / 3 / 4 / 5 / 6 battery cells. When the first camera 10 and the second camera 20 are two groups, they detect 1 / 2 / 3 / 4 / 5 / 6 battery cells and 7 / 8 / 9 / 10 / 11 / 12 battery cells respectively.

[0135] The driving device may 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, and the motor drives the mounting bracket 40 to drive the first camera 10 and the second camera 20 to move synchronously in the same direction, thereby improving the synchronization of the images captured by the first camera 10 and the second camera 20 and improving the accuracy of detection.

[0136] According to some embodiments of the present application, optionally, a driving device is used to drive the first camera 10 and the second camera 20 respectively, so that the first camera and the second camera move synchronously in the same direction.

[0137] In this embodiment, there is no need to drive the mounting bracket 40 through a driving device to drive the first camera 10 and the second camera 20 to move synchronously in the same direction. Instead, the first camera 10 and the second camera 20 are directly driven simultaneously with the first camera 10 and the second camera 20. This embodiment is explained by taking a motor as an example. When a double row of 2*6=12pcs of battery cells are incoming, one inspection station, two area array 2D cameras and two second cameras 20, two sets of image detection combinations are driven by a motor and move synchronously. The 2D area array is fixed and the second camera 20 is flying. The movement speed of the linear motor can be set to 300mm / s, thereby improving the photographing effect. In addition, the first camera 10 and the second camera 20 are made to move synchronously in the same direction through the driving device, thereby improving the detection efficiency.

[0138] According to some embodiments of the present application, optionally, please refer to Figure 3 , the battery sealing nail welding detection system also includes: a light source 30;

[0139] The light source 30 is fixed to the mounting bracket 40 and is located between the first camera 10 and the battery cell, and coincides with the center of the first camera 10 and is coaxial;

[0140] The light source 30 is used to provide light source 30 for the first camera 10. Since generating a 2D image requires the aid of an external light source 30 - a planar coaxial light source and an annular light source, the second camera 20 generates a 3D image by scanning horizontally at a uniform speed without the aid of an external light source 30. The light source 30 is used to supplement the light for the first camera 10, so that the image taken by the first camera 10 is clearer, thereby improving the accuracy of detection.

[0141] According to some embodiments of the present application, optionally, please refer to Figure 3 The light source 30 includes a planar coaxial light source, which is arranged on the light collection path of the first camera 10, and an annular light source, which is arranged on the light collection path of the first camera 10 and is located behind 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 10, and the planar coaxial light source is close to the first camera 10. The planar coaxial light source and the annular light source are used to fill in the light for the first camera 10, so that the image captured by the first camera 10 is clearer, and the accuracy of detection is improved.

[0142] According to some embodiments of the present application, optionally, please refer to Figure 3 When the first camera 10 and the second camera 20 are moved to be arranged opposite to the battery cell, the first camera and the second camera respectively take pictures of the battery cell, and when the second camera 20 is moved to be arranged opposite to the battery cell, the second camera takes pictures of the battery cell.

[0143] The first camera 10 and the second camera 20 can be movably arranged, and the first camera 10 and the second camera 20 can move in a preset direction. When the first camera 10 is facing the battery cell, it starts to take pictures of the battery cell, and when the scanning line of the second camera 20 encounters the boundary of the battery cell, it starts to take pictures. By setting shooting stations, at each shooting station, the first camera 10 and the second camera 20 are used to take pictures of each battery cell that is set facing each other.

[0144] For one-time double-row 2*6=12pcs battery cells, the center spacing of the battery cells is 70mm*240mm. For smaller battery cells, the single-station battery cell incoming method has limited space reserved for visual device inspection, so that the first camera 10 and the second camera 20 both adopt a vertical downward shooting method. The area array camera 10 and the line scan camera are small in size, which meets the space requirements and improves the convenience of image acquisition.

[0145] According to some embodiments of the present application, optionally, please refer to Figure 3 , the first camera 10 and the second camera 20 are movably installed along a first direction;

[0146] Along the first direction, the first camera 10 is located in front of the second camera 20 and is used to first capture the 2D image of the same battery cell and then capture the 3D image of the same battery cell.

[0147] In one embodiment, the first camera 10 and the second camera 20 move synchronously in the same direction. In the moving detection direction of the first camera 10 and the second camera 20 , the first camera 10 is located at the front side, and the second camera 20 is located at the rear side.

[0148] In this embodiment, after the battery cell reaches the inspection station, it stops moving, and the first camera 10 and the second camera 20 move synchronously in the same direction according to the instruction to inspect the battery cell located below. The first camera 10 and the second camera 20 can also move synchronously in the same direction, and the battery cell continues to move with the conveying line, and the battery cell is inspected after reaching the inspection area of ​​the first camera 10 and the second camera 20. The battery cell can also continue to move with the conveying line, and the first camera 10 and the second camera 20 are fixed, and the battery cell is inspected after it moves to the inspection area of ​​the first camera 10 and the second camera 20. The first camera 10 and the second camera 20 can be directly above the battery cell for inspection, or the first camera 10 and the second camera 20 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 10 and the second camera 20.

[0149] Taking the example of the battery cell stopping after arriving at the inspection station, and the first camera 10 and the second camera 20 moving synchronously in the same direction according to the instruction to inspect the battery cell located below, the first camera 10 is in front and the second camera 20 is in the back, the first camera 10 is used to shoot first, and then the second camera 20 is used to scan. The shooting range of the first camera 10 is larger than that of the second camera 20. After the preliminary inspection taken by the first camera 10, the second camera 20 is used for further inspection, which improves the efficiency of the inspection.

[0150] According to some embodiments of the present application, optionally, please refer to Figure 3 The first camera 10 includes a telecentric lens 50. Since the telecentric lens 50 has high measurement accuracy, the accuracy of image acquisition is improved.

[0151] According to some embodiments of the present application, optionally, please refer to Figure 4 The first camera 10 , the light source 30 and the second camera 20 are correspondingly arranged as a collection group, and at least two collection groups are arranged; at least two of the collection groups are arranged on the mounting bracket 40 .

[0152] When a double row of 2*6=12pcs of battery cells are incoming at one time, two groups of image detection groups can be used to simultaneously detect the first row 1 / 2 / 3 / 4 / 5 / 6 battery cells and the second row 7 / 8 / 9 / 10 / 11 / 12 battery cells. When the incoming battery cells are in multiple rows, multiple groups can be used for simultaneous detection, making the combination flexible and compatible with more incoming material methods, which helps to improve CT. The image detection groups can be used in combination according to the number and arrangement of battery cells to improve the flexibility of detection.

[0153] According to some embodiments of the present application, optionally, please refer to Figure 4The battery cells include at least two rows, and the multiple battery cells in each row are arranged in sequence; an image detection group is correspondingly arranged in the arrangement direction of the battery cells in each row, and the image detection group can be arranged according to the arrangement of the battery cells to avoid missed detection and improve the accuracy of detection.

[0154] According to some embodiments of the present application, referring to Figure 5 , Figure 5 It is a flow chart of a battery sealing pin welding detection method proposed according to some embodiments of the present application.

[0155] In this embodiment, the battery sealing nail welding detection method includes:

[0156] Step S10: Control the first camera and the light source to cooperate to collect a 2D image of the battery cell.

[0157] Step S20: controlling the second camera to collect a 3D image of the battery cell.

[0158] Step S30: completing the battery sealing pin welding inspection requirements according to the 2D image and 3D image corresponding to the same battery cell.

[0159] The battery sealing nail welding detection system includes a first camera and a second camera, and the first camera and the second camera are connected through the same bracket. Figure 4 As shown, the first camera and the second camera move synchronously above the battery monomer to take pictures of the battery monomer below for detection. The battery monomers are numbered according to the arrangement of the battery monomers. For example, 2*6=12pcs of battery monomers are incoming. The battery monomers in the first row are numbered 1 / 2 / 3 / 4 / 5 / 6, and the battery monomers in the second row are numbered 7 / 8 / 9 / 10 / 11 / 12. The first camera is in front and the second camera is in the back. This combination is used as a set of image detection combinations. The two sets of image detection combinations are installed in parallel with each other, and can move forward synchronously to detect 1 / 2 / 3 / 4 / 5 / 6 battery monomers and 7 / 8 / 9 / 10 / 11 / 12 batteries respectively.

[0160] The first camera is used to complete some of the battery sealing nail welding detection requirements related to the 2D image, and the second camera is used to complete the remaining detection requirements of the battery sealing nail welding detection requirements related to the 3D image. For example, when the 2D image of battery No. 1 is taken, the battery 2D algorithm processes some detection items, and when the 3D image of battery No. 1 is taken, the battery 3D algorithm processes the remaining detection items, and the detection result of battery No. 1 is output after the algorithm detection is completed, so that the first camera and the second camera are combined to achieve full coverage of the battery sealing nail welding detection requirements and improve the detection range.

[0161] According to some embodiments of the present application, optionally, the battery sealing nail welding detection method further includes: when it is detected that the battery cell moves to a preset area, controlling the first camera and the second camera to move synchronously along a first direction.

[0162] When it is detected that the first camera, the light source, and the battery cell are concentric in the third direction, the 2D image of the battery cell is collected by the cooperation of the first camera and the light source.

[0163] The second camera is controlled to sweep the battery cell along the first direction at a uniform speed to collect a 3D image of the battery cell.

[0164] 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 moves to the detection position, the first camera and the second camera are controlled to move synchronously in the horizontal direction, and 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.

[0165] The third direction may be a coaxial vertical direction of the first camera, the light source and the battery cell, and a complete imaging effect may be achieved by using a fixed-shot method with a 2D camera and a flying-shot method with a 3D camera.

[0166] 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 image detection.

[0167] In some embodiments, the step of acquiring the 3D image of the battery cell by the second camera includes:

[0168] The second camera is controlled to sweep the battery cell along the first direction at a uniform speed to collect a 3D image of the battery cell.

[0169] In the technical solution of the embodiment of the present application, the second camera is a line scan camera, which generates a 3D image by uniform horizontal scanning without the aid of an external light source, thereby improving the efficiency of detection.

[0170] In some embodiments, the battery sealing nail welding detection method further includes:

[0171] 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.

[0172] In the technical solution of the embodiment of the present application, when there are multiple rows of battery cells, such as Figure 4 As shown, the entire process of battery sealing nail welding detection is controlled, and the effective control of the detection process is improved by controlling the working processes of the first camera and the second camera.

[0173] In some embodiments, the battery sealing nail welding detection method further includes:

[0174] Counting the collected 2D images and 3D images; when the number of the collected 2D images and 3D images reaches a preset number, controlling the first camera, the light source and the second camera to return to a preset position.

[0175] The preset number is the number of battery cells. In the case of multiple rows of battery cells, after collecting 2D and 3D images of all battery cells, the 2D camera, 3D line scan camera and light source are controlled to return to the initial detection position.

[0176] In the technical solution of the embodiment of the present application, the 2D camera, 3D line scan camera and 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.

[0177] The battery sealing nail welding detection method further includes: controlling the shooting order of the first camera and the second camera respectively according to the control timing. The control timing is a control signal in the shooting process of the first camera and the second camera, which is used to control the entire process of the battery sealing nail welding detection. By controlling the working process of the first camera and the second camera through the control timing, the effective control of the detection process is improved.

[0178] 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.

[0179] like Figure 6a-6i , Figure 6a It means taking a photo of the No. 1 battery 2D. Figure 6b It means taking a photo of the AA battery 2D. Figure 6c It means taking a photo of the AA battery 2D. Figure 6d It means taking 2D photos with AA batteries and 3D photos with D batteries. Figure 6e It means taking 2D photos with AA batteries and 3D photos with AA batteries. Figure 6f It means taking 2D photos with AA batteries and 3D photos with AA batteries. Figure 6g It means taking 3D photos of AA batteries. Figure 6h It means taking 3D photos of AA batteries. Figure 6i It means taking 3D photos of AA batteries. The overall steps of the detection process are as follows:

[0180] 1. When the battery cell moves to the inspection station, the first camera, light source, and the center of the No. 1 battery cell coincide with each other in the Z-axis direction, a 2D photo of the battery is taken.

[0181] 2. When the centers of the first camera, light source, and No. 2 battery cell coincide in the Z-axis direction, take a 2D photo with 2 batteries.

[0182] 3. 3-battery 2D photography when the centers of the first camera, light source, and No. 3 battery cell coincide in the Z-axis direction

[0183] 4. When the centers of the first camera, light source, and No. 4 battery cell coincide in the Z-axis direction, 2D photos of 4 batteries are taken. Before 2D photos of 4 batteries are taken, the second camera moves horizontally at a uniform speed to scan 1 battery, and 3D images of 1 battery are collected.

[0184] 5. When the centers of the first camera, light source and No. 5 battery cell coincide in the Z-axis direction, 2D photos of 5 batteries are taken. Before 2D photos of 5 batteries are taken, the 3D camera moves horizontally at a uniform speed to scan 2 batteries, and 3D images of 2 batteries are collected.

[0185] 6. When the centers of the first camera, light source, and No. 6 battery cell coincide in the Z-axis direction, 2D photos of 6 batteries are taken. Before 2D photos of 6 batteries are taken, the 3D camera moves horizontally at a uniform speed to scan the 3 batteries, and 3D images of the 3 batteries are collected.

[0186] 7. The 3D camera moves horizontally at a uniform speed to scan the 4 batteries and collect 3D images of the 4 batteries.

[0187] 8. The 3D camera moves horizontally at a uniform speed to scan 5 batteries, and 3D images of the 5 batteries are collected.

[0188] 9. The 3D camera moves horizontally at a uniform speed to scan 6 batteries and collect 3D images of the 6 batteries.

[0189] After the above steps are completed, the 2D camera, the second camera and the 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.

[0190] According to some embodiments of the present application, optionally, the battery sealing nail welding detection system also includes a light source, and the situations in 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 light source and the battery cell coincide, wherein the light source provides light for the first camera and is coaxial with the first camera.

[0191] The battery cell reaches the preset detection position, and when it is detected that the battery cell reaches the preset detection position, the first camera is triggered to take a photo. A sensor is provided at the preset detection position to detect whether the battery cell reaches the preset detection position.

[0192] 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.

[0193] The coincidence of the first camera, the light source and the center of the battery cell is detected by matching the current battery cell image taken by the first camera with the pre-stored image that coincides with the center of the battery cell. Then, it is determined that the first camera, the 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.

[0194] According to some embodiments of the present application, optionally, detecting that the first camera, the light source, and the center of the battery cell coincide with each other may be that a current battery cell image taken by the first camera matches a pre-stored image that coincides with the center of the battery cell, thereby determining that the first camera, the light source, and the center of the battery cell coincide with each other.

[0195] Before determining whether the centers of the first camera, the light source, and the battery cell coincide, the first camera may be firstly coincided with the centers of the battery cell, and then an image of the battery cell when the centers of the first camera and the battery cell coincide is captured, and the image of the battery cell is stored in a preset position. 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 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 first camera, the light source, and the battery cell do not coincide. Thus, the coincidence of the centers of the first camera, the 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.

[0196] According to some embodiments of the present application, optionally, the situation in which the second camera triggers taking pictures at least includes: receiving a second trigger signal; the second camera detects a battery cell; and the first camera moves to a detection position corresponding to a battery cell with a preset number.

[0197] The received second 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 when a set time is reached, or may generate a PLC-CCD trigger signal when a preset number of battery cells is reached.

[0198] The second camera detects the battery cell when the second camera is scanning. When the scanning line initially scans the battery cell, the second camera may be triggered to start taking pictures.

[0199] 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 can be 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.

[0200] 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 175mm, that is, when the first camera is located directly above the third battery cell, the scanning line of the second camera can be located at the edge of the first battery cell and start scanning, so as to obtain a complete image of the first battery cell, avoid incomplete scanning, and accurately trigger the second camera to start shooting, thereby improving the integrity of the shooting of the second camera.

[0201] The triggering of the second camera to take photos is determined according to the center distance between adjacent battery cells. When the second camera is taking photos, a complete image of the battery cell can be taken, thereby improving the accuracy of the second camera taking photos.

[0202] According to some embodiments of the present application, optionally, the battery sealing nail welding detection method further includes:

[0203] The battery cells are numbered in sequence; when the first camera moves to a battery cell with a preset number, the second camera is triggered to take a photo, thereby numbering the battery cells in sequence and realizing precise control of the detection process according to the number of the battery cell currently photographed.

[0204] According to some embodiments of the present application, optionally, the method further includes:

[0205] Perform feature extraction on the first 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 second image of the battery cell; perform image recognition on the defect image to obtain the sealing nail welding detection result of the battery cell.

[0206] Feature extraction can be performed through image recognition extraction or gradient extraction.

[0207] In the technical solution of the embodiment of the present application, the defect location is first determined by the first image, and a preliminary screening is performed, and then the second image is used for verification to obtain the sealing pin welding detection result of the battery cell, thereby improving the accuracy of the detection.

[0208] According to some embodiments of the present application, optionally, performing image recognition on the defect image to obtain the sealing pin welding detection result of the battery cell includes:

[0209] Perform image recognition on the defect image to obtain defect information; classify the defect information to obtain the defect type; and obtain the sealing pin welding detection result of the battery cell according to the defect type.

[0210] In the technical solution of the embodiment of the present application, the defect type is further located according to the defect information, and automated sealing pin welding detection is realized to improve the efficiency of detection.

[0211] 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 replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate 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, characterized in that: include: A first camera and a light source are used to cooperate in acquiring a 2D image of a battery cell; A second camera is used to collect 3D images of the battery cells; as well as, A processing device is electrically connected to the first camera, the light source and the second camera, and is used to complete the battery sealing nail welding detection requirements according to the 2D image and the 3D image corresponding to the same battery cell.

2. The battery sealing nail welding detection system according to claim 1, characterized in that: The first camera comprises an area array camera; and / or, The second camera includes a line scan camera.

3. The battery sealing nail welding detection system according to claim 1, characterized in that: 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.

4. The battery sealing nail welding detection system according to claim 1, characterized in that: The first camera, the light source and the second camera 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.

5. The battery sealing nail welding detection system according to claim 4, characterized in that: Two adjacent acquisition groups are spaced apart by a second preset distance along a second direction, so as to acquire images corresponding to two columns of battery cells spaced apart by a second preset number.

6. The battery sealing nail welding detection system according to claim 4, characterized in that: In the same acquisition group, the first camera, the light source and the second camera move in the same direction; and / or, At least two of the first cameras in two of the acquisition groups and the two light sources move in the same direction; and / or, The two second cameras in at least two of the acquisition groups move in the same direction.

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

8. The battery sealing nail welding detection system according to claim 7, characterized in that: The battery sealing nail welding detection system also includes: A mounting bracket, wherein the first camera, the light source, and the second camera 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.

9. The battery sealing nail welding detection system according to claim 8, characterized in that: The first camera, the light source and the second camera 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.

10. The battery sealing nail welding detection system according to any one of claims 1 to 9, characterized in that: The light source comprises: A planar coaxial light source is 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.

11. The battery sealing nail welding detection system according to any one of claims 1 to 10, characterized in that: 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.

12. A battery sealing nail welding detection method, characterized in that: The battery sealing nail welding detection method comprises: Control the first camera and the light source to cooperate in collecting a 2D image of the battery cell; Controlling the second camera to collect 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.

13. The battery sealing nail welding detection method according to claim 12, characterized in that: 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 light source, and the battery cell are concentric in a third direction, the first camera and the light source cooperate to collect a 2D image of the battery cell; The second camera is controlled to sweep the battery cell along the first direction at a uniform speed to collect a 3D image of the battery cell.

14. The battery sealing nail welding detection method according to claim 12, characterized in that: 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.

15. The battery sealing nail welding detection method according to claim 12, characterized in that: 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 light source and the second camera are controlled to return to preset positions.

16. The battery sealing nail welding detection method according to claim 12, characterized in that: The triggering condition for controlling the first camera and the light source to cooperate in collecting the 2D image of the battery cell includes at least one of the following: The battery cell reaches the preset detection position; receiving a first trigger signal; It is detected that the centers of the first camera, the light source, and the battery cell coincide with each other, wherein the light source provides light for the first camera and is coaxial with the first camera.

17. The battery sealing nail welding detection method according to claim 16, characterized in that: The detecting that the centers of the first camera, the light source, and the battery cell coincide with each other includes: If the current battery cell image captured by the first camera matches a pre-stored image that coincides with the center of the battery cell, it is determined that the first camera, the light source, and the center of the battery cell coincide.

18. The battery sealing nail welding detection method according to any one of claims 12 to 17, characterized in that: The triggering condition for controlling the second camera to collect the 3D image of the battery cell includes at least one of the following: receiving a second trigger signal; The second camera detects a battery cell; The first camera moves to a detection position corresponding to a battery cell with a preset number.

19. The battery sealing nail welding detection method according to any one of claims 12 to 18, characterized in that: Also includes: Extracting features from the first 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 second image of the battery cell; Image recognition is performed on the defect image to obtain a sealing pin welding detection result of the battery cell.

20. The battery sealing nail welding detection method according to claim 19, characterized in that: The performing image recognition on the defect image to obtain the sealing pin welding detection result of the battery cell includes: Performing image recognition on the defect image to obtain defect information; Classifying the defect information to obtain a defect type; The sealing pin welding detection result of the battery cell is obtained according to the defect type.