Battery cell detection apparatus and battery cell detection method

Abstract

The present disclosure provides a battery cell detection apparatus and a battery cell detection method. The battery cell detection apparatus comprises: a first light source, configured to provide first light for a battery cell to be detected, wherein the first light is visible light; a second light source, configured to provide second light for said battery cell, wherein the second light is infrared light; an acquisition device, configured to acquire first image data of said battery cell when the first light is provided and second image data of said battery cell when the second light is provided; and a detection device, configured to detect said battery cell on the basis of the first image data and the second image data.

Description

Battery cell detection device and battery cell detection method

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 21, 2023, with application number 202311557518.0 and invention name “Battery Cell Detection Device and Battery Cell Detection Method”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the technical field of battery cell detection, and in particular to a battery cell detection device and a battery cell detection method. Background Art

[0003] During the lithium battery production process, coated cells require visual inspection. For example, this can detect bubbles, wrinkles, pits, foreign matter within the film, and edge defects. As production capacity requirements increase, equipment cycle times are also becoming increasingly demanding. Failure to accurately detect defective coated cells can lead to assembly anomalies in subsequent processes, impacting quality. Therefore, defect detection technology can be used to detect cell defects. However, related technologies cannot distinguish between defects below the film and above the film.

[0004] The above statements are merely intended to provide background information related to the present disclosure and do not necessarily constitute prior art.

[0005] Application Contents

[0006] A technical problem solved by the present disclosure is that, in related technologies, battery cell defect detection technology cannot distinguish between sub-membrane defects and surface-membrane defects of the battery cell.

[0007] According to one aspect of the present disclosure, a battery cell detection device is provided, including: a first light source, configured to provide a first light to the battery cell to be detected, wherein the first light is visible light; a second light source, configured to provide a second light to the battery cell to be detected, wherein the second light is infrared light; an acquisition device, configured to obtain first image data of the battery cell to be detected when the first light is provided and second image data of the battery cell to be detected when the second light is provided; and a detection device, configured to detect the battery cell to be detected based on the first image data and the second image data.

[0008] In the technical solution of the embodiment of the present application, a first light source capable of providing visible light and a second light source capable of providing infrared light are provided in the battery cell detection device. In this way, the acquisition equipment can obtain first image data of the battery cell to be detected under visible light irradiation and second image data of the battery cell to be detected under infrared light irradiation. Since visible light is irradiated on the surface of the battery cell to be detected and infrared light can penetrate into the interior of the battery cell to be detected, the detection equipment can distinguish whether the defect of the battery cell is a sub-membrane defect or an on-membrane defect when detecting the battery cell based on the first image data and the second image data, thereby improving the accuracy of battery cell defect detection.

[0009] In some embodiments, the battery cell detection device further includes a controller configured to control the activation or deactivation of the first light source, the second light source, and the acquisition device. By providing a controller in the battery cell detection device to control the activation or deactivation of the first light source, the second light source, and the acquisition device, the device can be more automated.

[0010] In some embodiments, the controller is configured to, upon determining that the battery cell to be inspected has reached the inspection position, send a stroboscopic control signal to the first light source and the second light source to control the first light source and the second light source to continuously start and shut down, and send an acquisition signal to the acquisition device to control the acquisition device to acquire an image of the battery cell to be inspected, and obtain the first image data and the second image data based on the image of the battery cell to be inspected. The controller uses the stroboscopic control signal to control the first light source and the second light source to continuously start and shut down, and uses the acquisition signal to control the acquisition device to acquire the image of the battery cell to be inspected, thereby achieving image acquisition of the battery cell to be inspected, thereby facilitating defect detection of the battery cell.

[0011] In some embodiments, the first light source, the second light source, and the acquisition device are located on the same side of the inspection position of the battery cell to be inspected. This facilitates the light source's illumination of the inspected surface of the battery cell to be inspected and the acquisition device's acquisition of an image of the inspected surface, thereby facilitating the acquisition of image data of the battery cell to be inspected and improving the accuracy of image data acquisition.

[0012] In some embodiments, the first light source includes a first sub-light source and a second sub-light source, each configured to provide the first light to the battery cell to be inspected. By providing two light sources capable of providing visible light, image data under two visible light conditions can be obtained. In this way, in subsequent processing, the image data of the two visible light fields can be combined to make defects with concave and convex deformation changes on the surface of the coated battery cell appear as defect features, reducing the problem of pits and foreign objects being missed.

[0013] In some embodiments, the incident angle of the first light provided by the first sub-light source on the surface of the battery cell to be inspected is equal to the incident angle of the first light provided by the second sub-light source on the surface of the battery cell to be inspected. Thus, when the first and second sub-light sources are irradiated, after obtaining corresponding image data, the image data of the two visible light fields are combined to enable defects with concave and convex deformation changes on the surface of the coated battery cell to be characterized, thereby reducing the problem of pits and foreign objects being missed.

[0014] In some embodiments, the first sub-light source and the second sub-light source are located on either side of a virtual plane perpendicular to the surface of the battery cell to be inspected and passing through the acquisition device. This helps minimize mutual interference between the first sub-light source and the second sub-light source when illuminating the surface of the battery cell to be inspected, thereby improving the accuracy of defect detection.

[0015] In some embodiments, the first sub-light source and the second sub-light source are symmetrically arranged relative to the virtual plane. This facilitates obtaining image data of two symmetrical visible light fields. By combining the image data of the two symmetrical visible light fields, defects with concave and convex deformations on the surface of the coated cell can be characterized, reducing the risk of pits and foreign objects being missed during inspection.

[0016] In some embodiments, the first light provided by the first light source has an incident angle α on the surface of the battery cell to be inspected in a range of 0° < α < 90°; and the second light provided by the second light source has an incident angle β on the surface of the battery cell to be inspected in a range of 0° < β < 90°. These incident angles facilitate the first and second lights to be incident on the surface of the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0017] In some embodiments, the inspection device is configured to determine a first defect set for the battery cell to be inspected based on the first image data, determine a second defect set for the battery cell to be inspected based on the second image data, and determine the types of various defects in the battery cell to be inspected based on the first defect set and the second defect set, wherein the first defect set includes one or more first defects and the second defect set includes one or more second defects. This achieves the purpose of determining the types of various defects in the battery cell to be inspected based on the first image data and the second image data, thereby improving the accuracy of battery cell defect detection.

[0018] In some embodiments, the inspection device is configured to determine the defect location of each second defect in the second defect set in the second image data, and determine the defect type of each second defect based on the defect location and the first defect set. This allows for determining the defect type of the battery cell defect.

[0019] In some embodiments, the detection device is configured to determine that a second defect is a sub-film defect if the first defect is detected at the same location as a second defect in the first image data and the first defect does not meet detection requirements. This ensures the sub-film defect is accurately identified, improving the accuracy of cell defect detection.

[0020] In some embodiments, the detection device is configured to determine the defect type of the second defect based on the grayscale of each pixel in the image region of the second defect in the second image data. This achieves the purpose of determining the defect type based on the grayscale of the pixel, thereby improving the accuracy of battery cell defect detection.

[0021] In some embodiments, the detection device is configured to determine that the second defect is a bubble-type defect if the grayscale of each pixel in the image area of ​​the second defect is greater than or equal to a grayscale threshold; and to determine that the second defect is a foreign matter-type defect if the grayscale of the pixels in the middle portion of the image area of ​​the second defect is less than the grayscale threshold and the grayscale of the pixels in the remaining portion of the image area of ​​the second defect is greater than or equal to the grayscale threshold. This achieves the purpose of determining whether a defect is a bubble-type defect or a foreign matter-type defect based on the grayscale of the pixels, thereby improving the accuracy of battery cell defect detection.

[0022] In some embodiments, the first image data includes at least two first images captured under conditions of irradiating the first light from different directions; the inspection device is configured to fuse the at least two first images to generate a fused image, and identify the fused image to determine the first defect set of the battery cell to be inspected. By fusing the at least two first images, the characteristics of deformable defects such as bumps and depressions can be enhanced, thereby enabling defect detection.

[0023] In some embodiments, the detection device is configured to determine characteristic data of each defect of the defect type detected, and to determine the test result of the battery cell to be tested based on the characteristic data of each defect of the defect type. This achieves the purpose of determining the test result of the battery cell to be tested based on the characteristic data of the defect, thereby realizing defect detection.

[0024] According to another aspect of the present disclosure, a battery cell detection method is provided, including: obtaining first image data of the battery cell to be detected when a first light is provided to the battery cell to be detected, the first light being visible light; obtaining second image data of the battery cell to be detected when a second light is provided to the battery cell to be detected, the second light being infrared light; and detecting the battery cell to be detected based on the first image data and the second image data.

[0025] In the technical solution of the embodiment of the present application, first image data of the battery cell to be inspected under visible light irradiation and second image data of the battery cell to be inspected under infrared light irradiation are obtained. Since visible light is irradiated on the surface of the battery cell to be inspected and infrared light can penetrate into the interior of the battery cell to be inspected, the detection equipment can distinguish whether the defect of the battery cell is a sub-membrane defect or an on-membrane defect when inspecting the battery cell to be inspected based on the first image data and the second image data, thereby improving the accuracy of battery cell defect detection.

[0026] In some embodiments, the battery cell inspection method further includes: determining characteristic data of each defect of the defect type according to the defect type of the detected defect; and determining the inspection result of the battery cell to be inspected according to the characteristic data of each defect of the defect type. This achieves the purpose of determining the inspection result of the battery cell to be inspected based on the defect characteristic data, thereby realizing defect detection.

[0027] In some embodiments, the defect type is a foreign body defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of that defect type includes: obtaining the size of one or more defects in the foreign body defect; based on the characteristic data of each defect of that defect type, determining the inspection result of the battery cell to be inspected includes: if at least one defect among the one or more defect sizes is greater than or equal to a first size threshold, determining that the battery cell to be inspected has failed the inspection; if the sizes of the one or more defects are all less than the first size threshold, determining that the battery cell to be inspected has passed the inspection. In this way, if the defect type is a foreign body defect, whether the battery cell to be inspected can pass the inspection is determined by the size of the foreign body defect, thereby achieving the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0028] In some embodiments, the defect type is a bubble defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of that defect type includes: obtaining the number of the bubble defects; based on the characteristic data of each defect of that defect type, determining the test result of the battery cell to be tested includes: if the number of the bubble defects is greater than or equal to a quantity threshold, determining that the battery cell to be tested has failed the test; if the number of the bubble defects is less than the quantity threshold, determining that the battery cell to be tested has passed the test. In this way, if the defect type is a bubble defect, whether the battery cell to be tested can pass the test is determined by the number of bubble defects, thereby achieving the detection of the battery cell and improving the accuracy of the battery cell detection.

[0029] In some embodiments, the defect type is a bubble defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of the defect type includes: obtaining the size of one or more defects in the bubble defect; based on the characteristic data of each defect of the defect type, determining the inspection result of the battery cell to be inspected includes: if at least one defect among the one or more defect sizes is greater than or equal to a second size threshold, or if the sum of the sizes of the one or more defects is greater than or equal to a third size threshold, determining that the battery cell to be inspected has failed the inspection; if each defect among the one or more defect sizes is less than the second size threshold, and the sum of the sizes of the one or more defects is less than the third size threshold, determining that the battery cell to be inspected has passed the inspection. In this way, in the case where the defect type is a bubble defect, whether the battery cell to be inspected can pass the inspection is determined by the size of the bubble defect, thereby achieving the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0030] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0032] The present disclosure can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0033] FIG1 is a schematic structural diagram illustrating a battery cell detection device according to some embodiments of the present disclosure;

[0034] FIG2 is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure;

[0035] FIG3A is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure;

[0036] FIG3B is a schematic structural diagram showing a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle;

[0037] FIG4A is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure;

[0038] FIG4B is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle;

[0039] FIG5A is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure;

[0040] FIG5B is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle;

[0041] FIG6A is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure;

[0042] FIG6B is a schematic structural diagram illustrating a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle;

[0043] FIG7 is a schematic diagram illustrating the working principle of a battery cell detection device according to some embodiments of the present disclosure;

[0044] FIG8 is a schematic diagram illustrating a flow chart of an appearance detection method according to some embodiments of the present disclosure;

[0045] FIG9 is a flow chart illustrating a battery cell detection method according to some embodiments of the present disclosure.

[0046] It should be understood that the size of each part shown in the drawings is not drawn according to the actual proportional relationship.In addition, the same or similar reference numerals represent the same or similar components. DETAILED DESCRIPTION

[0047] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and in no way limits the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of parts and steps, the composition of materials, numerical expressions and numerical values ​​set forth in these embodiments should be interpreted as merely exemplary and not as limiting.

[0048] The terms "first", "second" and similar terms used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The terms "include" or "comprises" and similar terms mean that the elements before the term include the elements listed after the term, and do not exclude the possibility of also including other elements. The terms "upper", "lower", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0049] In the present disclosure, when a specific device is described as being located between a first device and a second device, an intervening device may or may not be present between the specific device and the first device or the second device. When a specific device is described as being connected to another device, the specific device may be directly connected to the other device without an intervening device, or may be not directly connected to the other device but with an intervening device.

[0050] All terms (including technical or scientific terms) used in this disclosure have the same meaning as those understood by one of ordinary skill in the art to which this disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in, for example, general dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined herein.

[0051] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0052] In related technologies, battery cell defect detection technology cannot distinguish between sub-membrane defects and surface-membrane defects of battery cells, resulting in poor detection accuracy.

[0053] In view of this, the present disclosure provides a battery cell detection device, so as to distinguish whether the defect of the battery cell is a sub-membrane defect or an upper-membrane defect when detecting the battery cell, thereby improving the accuracy of battery cell defect detection.

[0054] FIG1 is a schematic diagram showing the structure of a battery cell detection device according to some embodiments of the present disclosure. As shown in FIG1 , the battery cell detection device includes: a first light source 11 , a second light source 12 , a collection device 13 , and a detection device 14 .

[0055] The first light source 11 is configured to provide a first light 21 to the battery cell 15 to be inspected. The first light 21 is visible light. For example, the first light source includes a visible light source. For example, the first light source is a line scan light source.

[0056] The second light source 12 is configured to provide a second light 22 to the battery cell 15 to be inspected. The second light 22 is infrared light. For example, the second light source includes an infrared light source. For example, the second light source is a line scan light source.

[0057] The acquisition device 13 is configured to obtain first image data of the battery cell to be inspected when providing a first light and second image data of the battery cell to be inspected when providing a second light. For example, the acquisition device includes a camera (e.g., a CCD (Charge Coupled Device) camera, a 3D (Three Dimensional) camera, etc.). For example, the camera is a line scan camera. For example, the camera's scan line 23 and the light line of the light source overlap on the inspected surface 151 of the battery cell to be inspected 15, thereby facilitating the acquisition of the first image data and the second image data.

[0058] The inspection device 14 is configured to inspect the battery cell to be inspected based on the first image data and the second image data. For example, the inspection device includes a visual industrial computer.

[0059] Thus, a battery cell inspection device according to some embodiments of the present disclosure is provided. The battery cell inspection device includes: a first light source configured to provide a first light source, which is visible light, to the battery cell to be inspected; a second light source configured to provide a second light source, which is infrared light, to the battery cell to be inspected; a collection device configured to obtain first image data of the battery cell to be inspected when the first light is provided and second image data of the battery cell to be inspected when the second light is provided; and a detection device configured to inspect the battery cell to be inspected based on the first and second image data. In this embodiment, the battery cell inspection device is provided with a first light source capable of providing visible light and a second light source capable of providing infrared light. Thus, the collection device can obtain first image data of the battery cell to be inspected under visible light illumination and second image data of the battery cell to be inspected under infrared light illumination. Because visible light illuminates the surface of the battery cell to be inspected, while infrared light can penetrate into the interior of the battery cell to be inspected, the detection device can distinguish whether the battery cell defect is a sub-film defect or an on-film defect when inspecting the battery cell based on the first and second image data, thereby improving the accuracy of battery cell defect detection.

[0060] In addition, infrared light field images and visible light images can be used to eliminate as much as possible the pseudo bubbles generated by the loose fit between the blue film and the shell.

[0061] In some embodiments, as shown in FIG1 , the first light source 11, the second light source 12, and the acquisition device 13 are located on the same side of the detection position (e.g., the current position of the battery cell 15) where the battery cell 15 is to be detected. This facilitates the illumination of the detection surface of the battery cell by the light source and the acquisition device to capture an image of the detection surface, thereby facilitating the acquisition of image data of the battery cell to be detected and improving the accuracy of image data acquisition.

[0062] In some embodiments, as shown in FIG1 , the first light source 11 provides a first light 21 having an incident angle α on the surface of the battery cell 15 to be inspected (referred to as a first incident angle) in the range of 0° < α < 90°; the second light source 12 provides a second light 21 having an incident angle β on the surface of the battery cell 15 to be inspected (referred to as a second incident angle) in the range of 0° < β < 90°. These incident angles facilitate the first and second lights to be incident on the surface of the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0063] FIG2 is a schematic diagram showing the structure of a battery cell detection device according to some other embodiments of the present disclosure. As shown in FIG2 , the battery cell detection device includes: a first light source 11 , a second light source 12 , a collection device 13 and a detection device 14 .

[0064] In some embodiments, as shown in FIG2 , the battery cell detection device further includes a controller 16. Controller 16 (which may be referred to as a first controller) is configured to control the activation or deactivation of the first light source 11, the second light source 12, and the data acquisition device 13. By providing a controller in the battery cell detection device to control the activation or deactivation of the first light source, the second light source, and the data acquisition device, the device can be more automated.

[0065] For example, the controller 16 is a time-sharing strobe controller. The controller 16 can receive a trigger signal 18 sent by another controller (which can be called a second controller, not shown in the figure) and a coding signal sent by an encoder 17. For example, the second controller includes a PLC (Programmable Logic Controller). The second controller can be electrically connected to a position detection sensor (not shown in the figure). The position detection sensor is installed at a predetermined position, and when the battery cell to be detected is detected, a position signal is sent to the second controller. After receiving the position signal, the second controller determines that the battery cell to be detected has run to the detection position, and then sends a trigger signal to the controller 16. After receiving the trigger signal, the controller 16 determines that the battery cell to be detected has run to the detection position. The controller 16 receives a coding signal (for example, a pulse signal) from the encoder, and the coding signal is used as a continuous acquisition signal to control the acquisition device to acquire the image of the battery cell to be detected.

[0066] Optionally, the battery cell detection device may further include the encoder 17 , a second controller, and a position detection sensor as described above.

[0067] In some embodiments, the controller 16 is configured to send a stroboscopic control signal to the first light source 11 and the second light source 12 to control the first light source and the second light source to start and shut down continuously when it is determined that the battery cell to be inspected has run to the inspection position, and send an acquisition signal to the acquisition device 13 to control the acquisition device to acquire an image of the battery cell to be inspected, and obtain first image data and second image data based on the image of the battery cell to be inspected.

[0068] In this embodiment, the controller controls the first light source and the second light source to start and shut down continuously through a stroboscopic control signal, and controls the acquisition device to acquire images of the battery cells to be inspected through an acquisition signal, thereby realizing image acquisition of the battery cells to be inspected, thereby facilitating defect detection of the battery cells.

[0069] Figure 3A is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure. Figure 3B is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle.

[0070] It should be noted that although the detection device and controller are not shown in Figures 3A and 3B, the battery cell detection device shown in Figures 3A and 3B includes, in addition to the first light source 11, the second light source 12, and the acquisition device 13, a detection device 14. Optionally, the battery cell detection device may also include a controller 16.

[0071] In some embodiments, as shown in Figures 3A and 3B, the first light source 11 includes a first sub-light source 111 and a second sub-light source 112, each of which is configured to provide a first light 21 to the battery cell 15 to be inspected. By providing two light sources capable of providing visible light, image data under two visible light conditions can be obtained. In subsequent processing, the image data from the two visible light fields can be combined to reveal the defect characteristics of defects in the coated battery cell with concave-convex deformation changes on the surface, thereby reducing the problem of pits and foreign objects being missed.

[0072] In some embodiments, as shown in FIG3A , the incident angle α1 of the first light 21 provided by the first sub-light source 111 on the surface of the battery cell to be inspected (which may be referred to as the first sub-incident angle) is equal to the incident angle α2 of the first light 21 provided by the second sub-light source 112 on the surface of the battery cell to be inspected (which may be referred to as the second sub-incident angle). Thus, when the first and second sub-light sources are irradiated, after obtaining corresponding image data, the image data of the two visible light fields are combined to enable defects with concave and convex deformation changes on the surface of the coated battery cell to be characterized, thereby reducing the problem of pits and foreign objects being missed.

[0073] In the battery cell inspection device shown in Figures 3A and 3B, the second incident angle β of the second light provided by the second light source 12 on the surface of the battery cell to be inspected is greater than the first incident angle α (for example, the first sub-incident angle α1 or the second sub-incident angle α2) of the first light provided by the first light source 11 on the surface of the battery cell to be inspected. This makes it easier for the light emitted by the first and second light sources to be incident on the inspection area of ​​the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0074] Of course, those skilled in the art will appreciate that the second incident angle β may also be smaller than the first incident angle α, which will be described later with reference to other figures. Therefore, the scope of the present disclosure is not limited thereto.

[0075] In some embodiments, as shown in Figures 3A and 3B, the first sub-light source 111 and the second sub-light source 112 are respectively located on either side of a virtual plane 310, which is perpendicular to the surface of the battery cell 15 to be inspected and passes through the acquisition device 13. In fact, the virtual plane is the plane where the scanning line 23 of the acquisition device is located during the scanning and photographing process of the acquisition device, that is, the plane where the normal of the inspected surface of the battery cell to be inspected is located. In this embodiment, by locating the first sub-light source and the second sub-light source on either side of the virtual plane, the first sub-light source and the second sub-light source minimize mutual interference when illuminating the surface of the battery cell to be inspected, thereby improving the accuracy of defect detection.

[0076] In some embodiments, as shown in Figures 3A and 3B, the first sub-light source 111 and the second sub-light source 112 are symmetrically arranged relative to the virtual plane 310. This facilitates obtaining image data of two symmetrical visible light fields. By combining the image data of the two symmetrical visible light fields, defects with concave and convex deformation changes on the surface of the coated battery cell can be characterized, reducing the problem of pits and foreign objects being missed during inspection.

[0077] In the battery cell inspection device shown in Figures 3A and 3B , the second light source 12 and the second sub-light source 112 are located on the same side of the virtual plane 310. Of course, those skilled in the art will appreciate that the second light source 12 and the first sub-light source 111 may also be located on the same side of the virtual plane 310, as will be explained later with reference to other figures. Therefore, the scope of the present disclosure is not limited thereto.

[0078] Other configurations of the first light source (the first sub-light source and the second sub-light source) and the second light source will be described below in conjunction with FIG. 4A-FIG . 4B , FIG. 5A-FIG . 5B and FIG. 6A-FIG . 6B .

[0079] Figure 4A is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure. Figure 4B is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle.

[0080] In the battery cell inspection device shown in Figures 4A and 4B, the second incident angle β of the second light provided by the second light source 12 on the surface of the battery cell to be inspected is greater than the first incident angle α (for example, the first sub-incident angle α1 or the second sub-incident angle α2) of the first light provided by the first light source 11 on the surface of the battery cell to be inspected, and the second light source 12 and the first sub-light source 111 are on the same side of the virtual plane 310. This makes it easier for the light emitted by the first and second light sources to be incident on the inspection area of ​​the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0081] Figure 5A is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure. Figure 5B is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle.

[0082] In the battery cell inspection device shown in Figures 5A and 5B, the second incident angle β of the second light provided by the second light source 12 on the surface of the battery cell to be inspected is smaller than the first incident angle α (for example, the first sub-incident angle α1 or the second sub-incident angle α2) of the first light provided by the first light source 11 on the surface of the battery cell to be inspected, and the second light source 12 and the first sub-light source 111 are located on the same side of the virtual plane 310. This facilitates the light emitted by the first and second light sources to be incident on the inspection area of ​​the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0083] Figure 6A is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure. Figure 6B is a schematic diagram illustrating the structure of a battery cell detection device according to other embodiments of the present disclosure at a certain viewing angle.

[0084] In the battery cell inspection device shown in Figures 6A and 6B, the second incident angle β of the second light provided by the second light source 12 on the surface of the battery cell to be inspected is smaller than the first incident angle α (for example, the first sub-incident angle α1 or the second sub-incident angle α2) of the first light provided by the first light source 11 on the surface of the battery cell to be inspected, and the second light source 12 and the second sub-light source 112 are located on the same side of the virtual plane 310. This facilitates the light emitted by the first and second light sources to be incident on the inspection area of ​​the battery cell to be inspected, thereby facilitating the detection of battery cell defects.

[0085] So far, different configurations of the first light source (including the first sub-light source and the second sub-light source) and the second light source have been described. Of course, the scope of the present disclosure is not limited to the configurations of the first light source and the second light source described herein.

[0086] In some embodiments, the inspection device 14 is configured to determine a first defect set for the battery cell to be inspected based on the first image data, determine a second defect set for the battery cell to be inspected based on the second image data, and determine the types of various defects in the battery cell to be inspected based on the first defect set and the second defect set, where the first defect set includes one or more first defects and the second defect set includes one or more second defects. This achieves the purpose of determining the types of various defects in the battery cell to be inspected based on the first image data and the second image data, thereby improving the accuracy of battery cell defect detection.

[0087] Exemplarily, the detection device can determine the first defect contained in the battery cell to be detected by identifying the first image data to obtain a first defect set including the first defect, and can determine the second defect contained in the battery cell to be detected by identifying the second image data to obtain a second defect set including the second defect.

[0088] The criteria for determining first and second defects can be set based on actual needs. For example, if the color of a certain location in the first image (i.e., first image data) is different from the color of the surrounding area, it can be determined as a first defect; if the color of a certain location in the second image (i.e., second image data) is different from the color of the surrounding area, it can be determined as a second defect.

[0089] The inspection device can determine the types of various defects in the battery cell to be inspected based on the first defect set and the second defect set. In other words, the types of various defects in the battery cell to be inspected can be determined based on the difference between the image under visible light and the image under infrared light.

[0090] For example, the types of defects may include: bubbles, wrinkles, pits, foreign matter, damage, scratches, and edge defects, etc. Among them, foreign matter can also be divided into foreign matter under the film, foreign matter on the film, etc.

[0091] For example, under the penetration of infrared light, foreign matter under the membrane of the battery cell appears to be dark in the middle and white at the edges, while bubbles are white as a whole. This feature can be used to distinguish between defects under the membrane and defects on the membrane in combination with a visible light source. Therefore, the types of various defects in the battery cell to be inspected can be determined based on the first defect set and the second defect set.

[0092] In the above embodiment, not only can defects on the surface of the battery cell be identified, but also defects under the blue film can be identified with the cooperation of the second image data and the first image data, so that the identification of defects in the battery cell can be more comprehensive and the detection results of the battery cell can be more reliable.

[0093] In some embodiments, the inspection device 14 is configured to determine the defect location of each second defect in the second defect set in the second image data, and determine the defect type of each second defect based on the defect location and the first defect set. This allows for determination of the defect type of the battery cell defect.

[0094] In some embodiments, the detection device 14 is configured to determine that a second defect is a sub-film defect if the first defect is detected at the same location as a second defect in the first image data and the first defect does not meet the detection requirements. This ensures the sub-film defect is accurately detected, improving the accuracy of cell defect detection.

[0095] For example, for a relatively small defect under the blue film of a battery cell, the defect under the film cannot be presented in a visible light image, but can only be presented in an infrared light image; for a relatively large defect under the film of a battery cell, the defect under the film may be presented in a visible light image, but the presented defect image is not obvious (i.e., the difference between the grayscale of the defect image and the grayscale of the surrounding background image is relatively small), and the defect under the film can be presented in an infrared light image. On the other hand, the defect on the blue film of a battery cell can be presented in both a visible light image (i.e., the difference between the grayscale of the defect image and the grayscale of the surrounding background image is relatively large) and an infrared light image. Therefore, it can be determined by the positions of the first defect set and the second defect set whether the defects at various positions in the battery cell to be tested are under-film defects or on-film defects.

[0096] For example, the detection device 14 determines the defect position of a second defect in the second defect set in the second image data, and determines the same position of the first image data based on the defect position. If the difference between the grayscale of the pixel at the position and the grayscale of the surrounding background image is less than the grayscale threshold (this situation includes: the first defect is not detected at the same position as the defect position of the second defect in the first image data (that is, the difference between the grayscale of the pixel at the position and the grayscale of the surrounding background image is 0, that is, less than the grayscale threshold) or the first defect is detected but the first defect does not meet the detection requirements (that is, the difference between the grayscale of the pixel at the position and the grayscale of the surrounding background image is less than the grayscale threshold)), then it indicates that the defect is a sub-membrane defect; if the difference between the grayscale of the pixel at the position and the grayscale of the surrounding background image is greater than or equal to the grayscale threshold (that is, the first defect is detected at the same position as the defect position of the second defect in the first image data and the first defect meets the detection requirements), then it indicates that the defect is an on-membrane defect. In this way, the defect type of the battery cell defect is detected, making the battery cell detection result more reliable.

[0097] It should be noted that the grayscale threshold can be referred to as the second grayscale threshold. For example, the range of the second grayscale threshold is greater than or equal to 10. Of course, the second grayscale threshold can be determined according to actual conditions, and the scope of the present disclosure is not limited to the range of the second grayscale threshold.

[0098] In some embodiments, the inspection device 14 is configured to determine the defect type based on the grayscale of pixels in the first and second images and the defect morphology. For example, a foreign matter defect may appear black in the center with a whitish periphery, while a bubble defect may only appear whitish. Combining grayscale and morphology allows for more accurate determination of the defect type.

[0099] In some embodiments, the detection device 14 is configured to determine the defect type of the second defect based on the grayscale of each pixel in the image region of the second defect in the second image data. This achieves the purpose of determining the defect type based on the grayscale of the pixel, and improves the accuracy of battery cell defect detection.

[0100] For example, the detection device 14 is configured to determine that the second defect is a bubble-type defect if the grayscale of each pixel in the image area of ​​the second defect is greater than or equal to a grayscale threshold (which may be referred to as a first grayscale threshold), and to determine that the second defect is a foreign matter-type defect if the grayscale of the pixels in the middle portion of the image area of ​​the second defect is less than the grayscale threshold and the grayscale of the pixels in the remaining portion of the image area of ​​the second defect is greater than or equal to the grayscale threshold. This achieves the purpose of determining whether a defect is a bubble-type defect or a foreign matter-type defect based on the grayscale of the pixels, thereby improving the accuracy of battery cell defect detection.

[0101] It should be noted that, the whiter the color of the defect in the image is, the larger the grayscale value is.

[0102] For example, as mentioned above, under the penetration of infrared light, the foreign matter under the membrane of the battery cell presents the characteristics of dark middle and white edge (that is, the grayscale of the pixels in the middle part of the image area of ​​the second defect is less than the grayscale threshold and the grayscale of the pixels in the remaining part of the image area of ​​the second defect is greater than or equal to the grayscale threshold), while the bubbles are overall white (that is, the grayscale of each pixel in the image area of ​​the second defect is greater than or equal to the grayscale threshold). This feature is used to distinguish whether the defect is a foreign matter defect or a bubble defect.

[0103] In some embodiments, the range of the first grayscale threshold is greater than or equal to 10. Of course, the first grayscale threshold can be determined according to actual conditions, and the scope of the present disclosure is not limited to the range of the first grayscale threshold.

[0104] In some embodiments, the first image data includes at least two first images captured when the first light is irradiated from different directions. For example, as described above, the first light source includes a first sub-light source and a second sub-light source, and the first sub-light source and the second sub-light source respectively provide the first light to the battery cell to be inspected. In this way, two first images can be obtained during the process of obtaining the first image data.

[0105] In some embodiments, the inspection device 14 is configured to fuse the at least two first images to obtain a fused image, and identify the fused image to determine the first defect set of the battery cell to be inspected. In this embodiment, by fusing the at least two first images, the characteristics of deformable defects such as concavities and convexities can be enhanced (i.e., the defects are highly reproducible), thereby enabling defect detection.

[0106] Here, an image fusion algorithm known to those skilled in the art may be used for fusion, and the scope of the present disclosure is not limited to the specific image fusion algorithm.

[0107] In some embodiments, the inspection device 14 is configured to determine characteristic data of each defect of the defect type detected based on the defect type, and determine the inspection result of the battery cell to be inspected based on the characteristic data of each defect of the defect type. This achieves the purpose of determining the inspection result of the battery cell to be inspected based on the characteristic data of the defect, thereby realizing defect detection.

[0108] In some embodiments, the defect type is a foreign object defect. The inspection device 14 is configured to obtain the size of one or more defects in the foreign object defect; if at least one of the one or more defect sizes is greater than or equal to a first size threshold, the inspected cell is determined to have failed the inspection; if the one or more defect sizes are all less than the first size threshold, the inspected cell is determined to have passed the inspection.

[0109] That is to say, for one or more defects among the foreign body defects, if there is at least one defect with a relatively large size (i.e., the size of at least one defect is greater than or equal to the first size threshold), it is determined that the battery cell to be inspected has failed the inspection; if the sizes of all defects are relatively small (i.e., the sizes of all defects are smaller than the first size threshold), such foreign body defects can be ignored, and it is determined that the battery cell to be inspected has passed the inspection.

[0110] Therefore, in the above embodiment, when the defect type is a foreign body defect, whether the battery cell to be inspected can pass the inspection is determined by the size of the foreign body defect, thereby realizing the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0111] In some embodiments, the range of the first size threshold is that the first size threshold is greater than or equal to 0.1 mm (millimeter). Of course, it should be noted that the above-mentioned first size threshold can be set according to actual needs, and the scope of this disclosure is not limited to the specific value of the first size threshold.

[0112] In some embodiments, the defect type is a bubble defect. The inspection device 14 is configured to obtain a number of bubble defects; if the number of bubble defects is greater than or equal to a threshold number, the inspected battery cell is determined to have failed the inspection; if the number of bubble defects is less than the threshold number, the inspected battery cell is determined to have passed the inspection.

[0113] That is, in the above embodiment, for bubble defects, whether the battery cell to be tested has passed the test can be determined based on the number of bubble defects. If the number of bubble defects is large (i.e., the number of bubble defects is greater than or equal to the number threshold), the battery cell to be tested is determined to have failed the test; if the number of bubble defects is small (i.e., the number of bubble defects is less than the number threshold), the battery cell to be tested is determined to have passed the test.

[0114] Therefore, in the above embodiment, when the defect type is a bubble defect, whether the battery cell to be inspected can pass the inspection is determined by the number of bubble defects, thereby realizing the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0115] In some embodiments, the range of the quantity threshold is that the quantity threshold is greater than or equal to 3. Of course, the above quantity threshold can be set according to actual needs, and the scope of the present disclosure is not limited to the specific value of the quantity threshold.

[0116] In some embodiments, the defect type is a bubble defect. The inspection device 14 is configured to obtain the size of one or more bubble defects; if at least one of the one or more defect sizes is greater than or equal to a second size threshold, or if the sum of the one or more defect sizes is greater than or equal to a third size threshold, the inspected cell is determined to have failed the inspection; if each of the one or more defect sizes is less than the second size threshold, and the sum of the one or more defect sizes is less than the third size threshold, the inspected cell is determined to have passed the inspection.

[0117] That is to say, in the above embodiment, for bubble-type defects, whether the battery cell to be tested has passed the test can be determined based on the size of the bubble-type defects. Here, the size of the bubble-type defects can be considered in two dimensions, namely, the size of a single defect in the bubble-type defects and the sum of the sizes of all bubble-type defects. When there is at least one defect in the bubble-type defects that is larger in size (that is, the size of at least one defect is greater than or equal to the second size threshold), or when the sum of the sizes of all bubble-type defects is larger (that is, the sum of the sizes of all bubble-type defects is greater than or equal to the third size threshold), it is determined that the battery cell to be tested has not passed the test. When the size of each defect in the bubble-type defects is smaller (that is, the size of each defect in the bubble-type defects is smaller than the second size threshold), and the sum of the sizes of all bubble-type defects is smaller (that is, the sum of the sizes of all bubble-type defects is smaller than the third size threshold), it is determined that the battery cell to be tested has passed the test.

[0118] Therefore, in the above embodiment, when the defect type is a bubble defect, whether the battery cell to be inspected can pass the inspection is determined by the size of the bubble defect, thereby realizing the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0119] In some embodiments, the second size threshold is in a range of greater than or equal to 0.5 mm2 (square millimeters). In some embodiments, the third size threshold is in a range of greater than or equal to 1.0 mm2. Of course, the second and third size thresholds can be set according to actual needs, and the scope of this disclosure is not limited to the specific values ​​of the second and third size thresholds.

[0120] FIG7 is a schematic diagram illustrating the working principle of a battery cell detection device according to some embodiments of the present disclosure.

[0121] As shown in Figure 7, when the battery cell moves to the time-sharing stroboscopic photography position, the PLC (not shown in Figure 7) will send a trigger signal to the controller (e.g., a time-sharing stroboscopic controller), notifying the controller that the battery cell has reached the detection position. The controller receives a pulse signal (i.e., an encoded signal) from the encoder, then sends a continuous stroboscopic signal to the light source (i.e., the first light source and the second light source), and sends a continuous acquisition signal to the camera through the acquisition card, thereby controlling the line scan light source and the acquisition card in parallel. For example, the camera can flash three times in a single shot. There is no requirement for the order in which the light sources light up during each flash. Flashing three times completes a single shot, but the order in which the light sources light up can be consistent for each flash. Multiple shots are taken until the entire moving battery cell is fully imaged. The camera transmits the image (e.g., the first image data and the second image data) back to the acquisition card. The acquisition card transmits the image to the detection equipment (e.g., a visual industrial computer). The detection equipment detects the battery cell to be detected based on the first image data and the second image data. The detection equipment can send the detection results to the host computer for subsequent processing.

[0122] In some embodiments, the detection device may store a built-in model algorithm, and pass the two collected visible light images through the image enhancement algorithm to generate a dark field image, a bright field image and an enhanced image respectively. This makes the contrast effect between the defect and the background stronger, and uses image fusion to enhance the defect features so that all types of defects are detected. The fusion image is placed in the AI ​​(Artificial Intelligence) semantic segmentation model to detect defects in the appearance of the battery cell, and the defects are further classified using a classification model. If the defect is a raised feature in the visible light image, the infrared image is used to further distinguish whether it is a bubble or a foreign object. If it is determined to be a foreign object, the height can be re-judged by the symmetrical visible light image and the diffuse reflection principle (that is, whether the height of the defect is greater than or equal to the height threshold. If the height of the defect is greater than or equal to the height threshold, it is determined that the battery cell has not passed the test. If the height of the defect is less than the height threshold, it is determined that the battery cell has passed the test). If it is determined to be a bubble defect, the area size, number and other thresholds of the bubble defect are used to reduce the problem of bubble over-inspection.

[0123] For example, the range of the height threshold is that the height threshold is greater than or equal to 0.1 mm. Of course, the height threshold in the embodiment of the present disclosure can be set according to actual needs. The scope of the present disclosure is not limited to the specific value of the height threshold.

[0124] In some embodiments of the present disclosure, bubbles and foreign matter under the membrane can be distinguished by using images under the infrared light field, and defects under the membrane and on the membrane can be distinguished by combining visible light images, thereby filtering out defects that cannot be seen by the naked eye, such as dirt on the shell under the membrane and slight scratches. In addition, by using two symmetrical visible light field images, scratches, breakages, dirt, pits and other defects on the membrane can be effectively presented in different defect forms. By combining infrared light field images and visible light images, defects such as foreign matter, breakages, scratches and other defects at the edges of the coated battery cells can be effectively presented, thereby improving the defect detection rate.

[0125] After algorithmically fusing images generated by symmetrical visible light sources, the height of foreign objects and the depth of pits can be reproduced. For example, after algorithmically fusing images generated by symmetrical visible light sources, foreign objects with a height of less than 0.1mm and pits with a depth of less than 0.1mm can be filtered out.

[0126] Furthermore, after the images collected by time-sharing stroboscopic imaging are fused by algorithm, the characteristics of deformable defects such as concave and convex can be enhanced, and the height direction information of the defects can be obtained through the algorithm for height re-judgment.

[0127] FIG8 is a schematic flow chart illustrating an appearance detection method according to some embodiments of the present disclosure.

[0128] As shown in Figure 8, in the appearance inspection method, it is possible to determine whether the battery cell is good or defective through processes and mechanisms such as feeding code scanning, feeding pitch change, bottom and narrow surface detection mechanism, pitch change mechanism and loading, visual inspection mechanism, discharge assembly line, unloading and pitch change mechanism. In addition, a magnetic levitation ring conveyor line, a defective product assembly line, etc. can also be provided in the entire equipment. Here, the visual inspection mechanism can include the battery cell detection device of the embodiment of the present disclosure. Other processes and mechanisms can adopt processes and mechanisms known to those skilled in the art and will not be described in detail here.

[0129] FIG9 is a flow chart illustrating a method for detecting a battery cell according to some embodiments of the present disclosure. As shown in FIG9 , the method for detecting a battery cell includes steps S902 to S906 .

[0130] In step S902 , first image data of the battery cell to be inspected is obtained when a first light is provided to the battery cell to be inspected, where the first light is visible light.

[0131] In step S904 , second image data of the battery cell to be inspected is obtained when a second light is provided to the battery cell to be inspected, where the second light is infrared light.

[0132] In step S906 , the battery cell to be inspected is inspected according to the first image data and the second image data.

[0133] Thus, a battery cell inspection method according to some embodiments of the present disclosure is provided. In this battery cell inspection method, first image data of the battery cell to be inspected under visible light irradiation and second image data of the battery cell to be inspected under infrared light irradiation are obtained. Because visible light irradiates the surface of the battery cell to be inspected, while infrared light can penetrate into the interior of the battery cell to be inspected, the inspection device can distinguish whether the battery cell defect is a sub-membrane defect or an upper-membrane defect when inspecting the battery cell to be inspected based on the first and second image data, thereby improving the accuracy of battery cell defect detection.

[0134] In some embodiments, the battery cell inspection method further includes: determining characteristic data of each defect of the defect type according to the defect type of the detected defect; and determining an inspection result of the battery cell to be inspected based on the characteristic data of each defect of the defect type. This achieves the purpose of determining the inspection result of the battery cell to be inspected based on the defect characteristic data, thereby realizing defect detection.

[0135] In some embodiments, the defect type is a foreign body defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of that defect type includes: obtaining the size of one or more defects in the foreign body defect; based on the characteristic data of each defect of that defect type, determining the test result of the battery cell to be tested includes: if at least one of the one or more defect sizes is greater than or equal to a first size threshold, determining that the battery cell to be tested has failed the test; if the one or more defect sizes are all less than the first size threshold, determining that the battery cell to be tested has passed the test. In this way, if the defect type is a foreign body defect, whether the battery cell to be tested can pass the test is determined by the size of the foreign body defect, thereby achieving the detection of the battery cell and improving the accuracy of the battery cell detection.

[0136] In some embodiments, the defect type is a bubble defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of that defect type includes: obtaining the number of bubble defects; based on the characteristic data of each defect of that defect type, determining the test result of the battery cell to be tested includes: if the number of bubble defects is greater than or equal to a quantity threshold, determining that the battery cell to be tested has failed the test; if the number of bubble defects is less than the quantity threshold, determining that the battery cell to be tested has passed the test. In this way, if the defect type is a bubble defect, whether the battery cell to be tested can pass the test is determined by the number of bubble defects, thereby achieving the test of the battery cell and improving the accuracy of the battery cell test.

[0137] In some embodiments, the defect type is a bubble defect; based on the defect type to which the detected defect belongs, determining the characteristic data of each defect of the defect type includes: obtaining the size of one or more defects in the bubble defect; based on the characteristic data of each defect of the defect type, determining the inspection result of the battery cell to be inspected includes: if at least one defect among the one or more defect sizes is greater than or equal to the second size threshold, or if the sum of the sizes of the one or more defects is greater than or equal to the third size threshold, determining that the battery cell to be inspected has failed the inspection; if each defect among the one or more defect sizes is less than the second size threshold, and the sum of the sizes of the one or more defects is less than the third size threshold, determining that the battery cell to be inspected has passed the inspection. In this way, in the case where the defect type is a bubble defect, whether the battery cell to be inspected can pass the inspection is determined by the size of the bubble defect, thereby realizing the inspection of the battery cell and improving the accuracy of the battery cell inspection.

[0138] Thus far, various embodiments of the present disclosure have been described in detail. To avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0139] Although some specific embodiments of the present disclosure have been described in detail through examples, those skilled in the art will understand that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that the above embodiments may be modified or some technical features may be replaced with equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A battery cell detection device, comprising: A first light source is configured to provide a first light to the battery cell to be detected, wherein the first light is visible light; A second light source is configured to provide a second light to the battery cell to be detected, wherein the second light is infrared light; A collection device configured to obtain first image data of the battery cell to be inspected when the first light is provided and second image data of the battery cell to be inspected when the second light is provided; and The detection device is configured to detect the battery cell to be detected according to the first image data and the second image data.

2. The battery cell detection device according to claim 1, further comprising: The controller is configured to control the first light source, the second light source and the collection device to start or shut down.

3. The battery cell detection device according to claim 2, wherein: The controller is configured to, when determining that the battery cell to be inspected has run to the inspection position, send a stroboscopic control signal to the first light source and the second light source to control the first light source and the second light source to start and shut down continuously, and send an acquisition signal to the acquisition device to control the acquisition device to acquire an image of the battery cell to be inspected, and obtain the first image data and the second image data based on the image of the battery cell to be inspected.

4. The battery cell detection device according to any one of claims 1 to 3, wherein: The first light source, the second light source and the acquisition device are located on the same side of the detection position where the battery cell to be detected is located.

5. The battery cell detection device according to any one of claims 1 to 4, wherein: The first light source includes a first sub-light source and a second sub-light source, and the first sub-light source and the second sub-light source are respectively configured to provide the first light to the battery cell to be inspected.

6. The battery cell detection device according to claim 5, wherein: The incident angle of the first light provided by the first sub-light source on the surface of the battery cell to be inspected is equal to the incident angle of the first light provided by the second sub-light source on the surface of the battery cell to be inspected.

7. The battery cell detection device according to claim 5 or 6, wherein: The first sub-light source and the second sub-light source are respectively located on two sides of a virtual plane, and the virtual plane is perpendicular to the surface of the battery cell to be detected and passes through the acquisition device.

8. The battery cell detection device according to claim 7, wherein: The first sub-light source and the second sub-light source are arranged symmetrically with respect to the virtual plane.

9. The battery cell detection device according to any one of claims 1 to 7, wherein: The range of the incident angle α of the first light provided by the first light source on the surface of the battery cell to be inspected is 0°<α<90°; The range of the incident angle β of the second light provided by the second light source on the surface of the battery cell to be inspected is 0°<β<90°.

10. The battery cell detection device according to any one of claims 1 to 9, wherein: The detection device is configured to determine a first defect set of the battery cell to be detected based on the first image data, determine a second defect set of the battery cell to be detected based on the second image data, and determine types of various defects in the battery cell to be detected based on the first defect set and the second defect set, wherein the first defect set includes one or more first defects, and the second defect set includes one or more second defects.

11. The battery cell detection device according to claim 10, wherein: The detection device is configured to determine a defect position of each second defect in the second defect set in the second image data, and determine a defect type of each second defect according to the defect position and the first defect set.

12. The battery cell detection device according to claim 11, wherein: The detection device is configured to determine that the one second defect is a sub-film defect when the first defect is detected at the same position as a defect position of the one second defect in the first image data and the first defect does not meet the detection requirement.

13. The battery cell detection device according to claim 12, wherein: The detection device is configured to determine a defect type of the second defect according to the grayscale of each pixel in the image area of ​​the second defect in the second image data.

14. The battery cell detection device according to claim 13, wherein: The detection device is configured to determine that the second defect is a bubble-type defect when the grayscale of each pixel in the image area of ​​the second defect is greater than or equal to the grayscale threshold, and to determine that the second defect is a foreign matter-type defect when the grayscale of the pixels in the middle part of the image area of ​​the second defect is less than the grayscale threshold and the grayscale of the pixels in the remaining part of the image area of ​​the second defect is greater than or equal to the grayscale threshold.

15. The battery cell detection device according to claim 10, wherein: The first image data includes at least two first images acquired when the first light is irradiated in different directions; The detection device is configured to fuse the at least two first images to obtain a fused image, and identify the fused image to determine a first defect set of the battery cell to be detected.

16. The battery cell detection device according to any one of claims 1 to 15, wherein: The detection device is configured to determine characteristic data of each defect of the defect type according to the defect type to which the detected defect belongs, and determine the detection result of the battery cell to be detected according to the characteristic data of each defect of the defect type.

17. A battery cell detection method, comprising: obtaining first image data of the battery cell to be inspected when providing first light to the battery cell to be inspected, wherein the first light is visible light; obtaining second image data of the battery cell to be inspected when a second light is provided to the battery cell to be inspected, wherein the second light is infrared light; and The battery cell to be inspected is inspected according to the first image data and the second image data.

18. The battery cell detection method according to claim 17, further comprising: Determine characteristic data of each defect of the defect type according to the defect type to which the detected defect belongs; and The detection result of the battery cell to be detected is determined according to the characteristic data of each defect of the defect type.

19. The battery cell detection method according to claim 18, wherein: The defect type is a foreign body defect; Determining characteristic data of each defect of the defect type according to the defect type to which the detected defect belongs includes: obtaining the size of one or more defects in the foreign body defect; Determining the inspection result of the battery cell to be inspected based on the characteristic data of each defect of this defect type includes: when the size of at least one defect among the one or more defects is greater than or equal to a first size threshold, determining that the battery cell to be inspected has failed the inspection; when the sizes of the one or more defects are all smaller than the first size threshold, determining that the battery cell to be inspected has passed the inspection.

20. The battery cell detection method according to claim 18, wherein: The defect type is a bubble defect; Determining characteristic data of each defect of the defect type according to the defect type to which the detected defect belongs includes: obtaining the number of the bubble-type defects; Determining the inspection result of the battery cell to be inspected based on the characteristic data of each defect of this defect type includes: when the number of the bubble-type defects is greater than or equal to the quantity threshold, determining that the battery cell to be inspected has failed the inspection; and when the number of the bubble-type defects is less than the quantity threshold, determining that the battery cell to be inspected has passed the inspection.

21. The battery cell detection method according to claim 18, wherein: The defect type is a bubble defect; According to the defect type to which the detected defect belongs, determining the characteristic data of each defect of the defect type includes: obtaining the size of one or more defects in the bubble type defects; Determining the inspection result of the battery cell to be inspected based on the characteristic data of each defect of this defect type includes: when at least one defect among the one or more defects has a size greater than or equal to a second size threshold, or when the sum of the sizes of the one or more defects is greater than or equal to a third size threshold, determining that the battery cell to be inspected has failed the inspection; when the size of each of the one or more defects is less than the second size threshold and the sum of the sizes of the one or more defects is less than the third size threshold, determining that the battery cell to be inspected has passed the inspection.

Images