Battery electrode tab inspection apparatus and method

Abstract

An electrode tab inspection apparatus according to an embodiment of the present invention may comprise: at least one processor; and a memory to store at least one instruction executed by the at least one processor. Here, the at least one instruction may include: an instruction for obtaining computed tomography (CT) data of the battery from a CT device; deriving, from the CT data, a command of a predetermined upper portion of the electrode tab on the basis of an electrode tab region in which the height direction of the battery is located; instructions to extract a vertical cross-sectional image of the electrode tab from the CT data using the horizontal cross-sectional image within the electrode tab region; and instructions to determine whether the electrode tab is defective using the vertical cross-sectional image of the electrode tab.

Description

Technical Field

[0001] This application claims priority and benefit to Korean Patent Application No. 10-2024-0111015, filed on August 20, 2024, with the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference.

[0002] The present invention relates to an apparatus and method for inspecting electrode contacts of a battery, and more specifically, to an apparatus and method for inspecting electrode contacts of a battery by using computed tomography (CT) data of the battery to determine whether the electrode contacts are defective. Background Technology

[0003] Rechargeable and reusable secondary batteries can be used as energy for small devices such as mobile phones, tablets, and vacuum cleaners, as well as for medium and large devices such as automobiles and energy storage systems (ESS) for smart grids.

[0004] Secondary batteries can be divided into can batteries, in which the electrode assembly is housed in a cylindrical metal can, and pouch batteries, in which the electrode assembly is housed in a pouch-shaped box. Cylindrical can batteries are generally known for their relatively high capacity and structural stability.

[0005] Cylindrical batteries are manufactured through a series of processes, including electrode fabrication, electrode assembly fabrication, electrode assembly insertion, and can assembly assembly. Quality checks can be performed during and after the manufacturing process for cylindrical batteries.

[0006] The electrode assembly of a cylindrical battery is formed by stacking positive and negative electrode plates with spacers inserted between them and winding them into a coiled shape. Positive and negative electrode contacts protrude from the positive and negative electrode plates, respectively, and are attached to the positive and negative electrodes.

[0007] Typically, electrode patch defect inspection is performed by visually inspecting vertical cross-sectional images obtained from computed tomography (CT) scans of the batteries, and then screening out batteries with defective electrode patches. The accuracy of this electrode patch inspection method depends on the operator's skill, which can lead to low inspection reliability and time delays. Furthermore, this method cannot inspect all produced batteries and therefore can only inspect a select few.

[0008] To address these issues, a suitable inspection technique is needed that can more accurately and quickly determine whether a battery has defective electrode contacts.

[0009] KR 10-2024-0100647A is relevant to this invention in the prior art documents. Summary of the Invention

[0010] Technical issues

[0011] To eliminate one or more problems in the related art, embodiments of this disclosure provide an electrode patch inspection apparatus for determining whether electrode patches of a battery are defective using computed tomography (CT) data.

[0012] To eliminate one or more problems of the prior art, embodiments of this disclosure also provide an electrode patch inspection method performed by an electrode patch inspection device.

[0013] To eliminate one or more problems of the prior art, embodiments of this disclosure also provide an electrode patch inspection system including an electrode patch inspection device.

[0014] Technical solution

[0015] To achieve the purposes of this disclosure, the electrode patch inspection apparatus may include: at least one processor; and a memory configured to store at least one instruction executed by the at least one processor.

[0016] Here, at least one instruction may include: an instruction for obtaining CT data of the battery from a computed tomography (CT) device; an instruction for obtaining the electrode patch region where a predetermined upper portion of the electrode patch is located from the CT data based on the height direction of the battery; an instruction for extracting a vertical cross-sectional image of the electrode patch from the CT data using a horizontal cross-sectional image within the electrode patch region; and an instruction for determining whether the electrode patch is defective using the vertical cross-sectional image of the electrode patch.

[0017] Instructions for obtaining the electrode patch area may include instructions for determining the start and end heights of the upper portion of the electrode patch based on the gray levels of each of a plurality of horizontal cross-sectional images.

[0018] Instructions for obtaining the electrode patch region may include: instructions for determining a first height corresponding to a bent portion of the electrode patch and a second height corresponding to an end portion of the electrode patch; and instructions for determining the region from the first height to the second height as the electrode patch region.

[0019] Instructions for extracting a vertical cross-sectional image of an electrode patch may include instructions for extracting a vertical cross-sectional image passing through the vertical central plane of the electrode patch using a first horizontal cross-sectional image at a first height and a second horizontal cross-sectional image at a second height.

[0020] Instructions for extracting vertical cross-sectional images may include: instructions defining the bend line of the electrode patch in a first horizontal cross-sectional image and the end line of the electrode patch in a second horizontal cross-sectional image; instructions for defining the center line of the electrode patch passing through the midpoint of the bend line and the midpoint of the end line; and instructions for extracting a vertical cross-sectional image corresponding to the center line of the electrode patch from CT data.

[0021] Instructions for determining whether an electrode contact is defective may include instructions to use a vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode contact and the electrode assembly; whether there is contact between the electrode contact and the inner wall of the battery; and whether the electrode contact has shape defects.

[0022] Instructions for determining whether an electrode patch is defective may include instructions for inputting a vertical cross-sectional image into a diagnostic model pre-trained using the vertical cross-sectional image as learning data and obtaining diagnostic result data from the diagnostic model.

[0023] According to another embodiment of this disclosure, the electrode patch inspection method uses an electrode patch inspection device connected to a computed tomography (CT) device. The electrode patch inspection method may include: acquiring CT data of a battery from the CT device; obtaining an electrode patch region in the height direction of the battery based on the CT data, representing a predetermined upper portion of the electrode patch; extracting a vertical cross-sectional image of the electrode patch from the CT data using a horizontal cross-sectional image within the electrode patch region; and determining whether the electrode patch has defects using the vertical cross-sectional image of the electrode patch.

[0024] The steps of obtaining the electrode patch area may include determining the start and end heights of the upper portion of the electrode patch based on the gray levels of each of the multiple horizontal cross-sectional images.

[0025] The steps of obtaining the electrode patch region may include determining a first height corresponding to the bent portion of the electrode patch and a second height corresponding to the end portion of the electrode patch; and determining the region from the first height to the second height as the electrode patch region.

[0026] The step of extracting a vertical cross-sectional image of an electrode patch may include the step of extracting a vertical cross-sectional image through a vertical central plane of the electrode patch using a first horizontal cross-sectional image at a first height and a second horizontal cross-sectional image at a second height.

[0027] The steps of extracting a vertical cross-sectional image may include: defining a bend line of the electrode patch in a first horizontal cross-sectional image and defining an end line of the electrode patch in a second horizontal cross-sectional image; defining a center line of the electrode patch that passes through the midpoint of the bend line and the midpoint of the end line; and extracting a vertical cross-sectional image corresponding to the center line of the electrode patch from the CT data.

[0028] The steps to determine whether an electrode tab is defective may include using a vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode tab and the electrode assembly; whether there is contact between the electrode tab and the inner wall of the battery; and whether the electrode tab has shape defects.

[0029] The steps for determining whether an electrode patch is defective may include inputting a vertical cross-sectional image into a diagnostic model that is pre-trained using the vertical cross-sectional image as learning data and obtaining diagnostic result data from the diagnostic model.

[0030] According to another embodiment of this disclosure, an electrode patch inspection system may include: a computed tomography (CT) device configured to generate CT data of a battery; and an electrode patch inspection apparatus configured to obtain the CT data from the CT device and use the CT data to determine whether there are defects in the electrode patches located inside the battery.

[0031] Here, the electrode patch inspection device extracts vertical cross-sectional images of the electrode patches from CT data and uses the extracted vertical cross-sectional images to determine whether the electrode patches have defects.

[0032] Beneficial effects

[0033] According to embodiments of this disclosure, a vertical cross-sectional image passing through the vertical central plane of the electrode patch can be used to perform defect inspection of the electrode patch, thereby further improving the accuracy and time efficiency of electrode patch inspection. Attached Figure Description

[0034] Figure 1 The diagram illustrates normal electrode contacts and defective electrode contacts.

[0035] Figure 2 This is a block diagram of an electrode patch inspection system according to an embodiment of the present invention.

[0036] Figure 3 This is a side view of a CT device according to an embodiment of the present invention.

[0037] Figure 4 This is a flowchart illustrating the operation of an electrode patch inspection method according to an embodiment of the present invention.

[0038] Figure 5 This is a flowchart illustrating a method for obtaining an electrode patch region according to an embodiment of the present invention.

[0039] Figure 6 and Figure 7 This is a reference diagram illustrating a method for obtaining an electrode patch region according to an embodiment of the present invention.

[0040] Figure 8 This is an operation flowchart of a method for obtaining a vertical cross-sectional image of an electrode patch according to an embodiment of the present invention.

[0041] Figure 9 This is a reference diagram illustrating a method for obtaining a vertical cross-sectional image of an electrode patch according to an embodiment of the present invention.

[0042] Figure 10 This is a reference diagram illustrating a method for determining whether an electrode contact has defects according to an embodiment of the present invention.

[0043] Figure 11 This is a block diagram of an electrode patch inspection system according to another embodiment of the present invention.

[0044] Figure 12 This is a block diagram of an electrode patch inspection device according to an embodiment of the present invention.

[0045] 100: Battery

[0046] 200: CT scanner

[0047] 300: Electrode contact inspection equipment

[0048] 400: Diagnostic model generation equipment

[0049] 1200: Electrode contact inspection equipment Detailed Implementation

[0050] This invention can be modified in various forms and has various embodiments, and specific embodiments thereof are shown by way of example in the accompanying drawings, and will be described in detail below. However, it should be understood that this is not intended to limit the invention to the specific embodiments; rather, the invention is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Throughout the description of the drawings, the same reference numerals refer to the same elements.

[0051] It will be understood that while terms such as first, second, A, B, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, a first element may be referred to as a second element without departing from the scope of the invention, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes a combination of a plurality of associated listed items or any one of a plurality of associated listed items.

[0052] What will be understood is that when a component is referred to as "connected to" or "connected to" another component, the component can be directly connected to or connected to the other component, or there may be intermediate components. In contrast, when a component is referred to as "directly connected to" or "directly connected to" another component, there are no intermediate components.

[0053] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are also intended to include the plural forms. It will also be understood that the terms “comprising,” “including,” “containing,” and / or “having,” when used herein, specify the presence of said features, integers, steps, operations, constituent elements, components, and / or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, constituent elements, components, and / or combinations thereof.

[0054] Unless otherwise defined, all terms used herein, including technical and scientific terms, shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It will be further understood that terms, such as those defined in commonly used dictionaries, shall be interpreted as having the meaning consistent with their meaning in the context of the relevant field and shall not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0055] The present invention and its exemplary embodiments will be described in detail below with reference to the accompanying drawings.

[0056] Figure 1 The diagram illustrates normal electrode contacts and defective electrode contacts.

[0057] The cylindrical battery cell may include an electrode assembly 10 housed in a cylindrical metal can 20, a positive electrode contact 30 electrically connected to the positive electrode of the electrode assembly and protruding from the electrode assembly, and a negative electrode contact electrically connected to the negative electrode of the electrode assembly and protruding from the electrode assembly.

[0058] like Figure 1As shown, the positive electrode contact 30 protrudes upward from the electrode assembly 10, and the upper end of the positive electrode contact 30 is coupled to the positive terminal. Figure 1 As shown in (A), the normal positive electrode contact is bent at two locations and is not in contact with the electrode assembly 10 and the metal can 20.

[0059] On the other hand, such as Figure 1 As in the case of the positive electrode contact in (B), if the positive electrode contact 30 is aligned opposite to the intended alignment position relative to the vertical central axis (reverse alignment), and therefore does not form the intended shape during the top cover assembly process, then at least a portion of the positive electrode contact 30 may contact the electrode assembly 10 and / or the metal can 20.

[0060] General electrode patch inspection, which determines whether electrode patches have defective shapes or poor contacts, is usually performed by the operator, who visually examines vertical cross-sectional images obtained from the battery's CT data to screen for defective batteries.

[0061] This type of electrode patch inspection method makes it difficult for operators to identify the vertical cross-section passing through the vertical central plane of the electrode patch, thus limiting the inspection accuracy.

[0062] Figure 2 This is a block diagram of an electrode patch inspection system according to an embodiment of the present invention.

[0063] The battery electrode contact inspection system according to an embodiment of the present invention can be used in the process of inspecting defects in the electrode contacts of the battery 100.

[0064] The electrode patch inspection system may include: a CT device 200, which is positioned at a specific location to generate CT data by performing a CT scan on the battery 100; and an electrode patch inspection device 300, which is configured to acquire the CT data from the CT device 200 and use the CT data to determine whether there are defects in the electrode patches located inside the battery 100.

[0065] The battery 100 according to an embodiment of the present invention may correspond to a cylindrical battery cell, but the scope of the present invention is not limited thereto.

[0066] The CT device 200 can generate CT data for the battery 100. Here, CT data can refer to three-dimensional image data synthesized from slice images of the interior of the battery 100.

[0067] For example, the CT device 200 can acquire a cross-sectional image by irradiating the side of the battery 100 with X-rays and detecting the X-rays that have passed through the interior of the battery 100. Here, the CT device 200 can acquire multiple (e.g., 360) slice images as the battery 100 is rotated sequentially by a unit angle (e.g., 1 degree), and use a predefined reconstruction algorithm to synthesize the slice images to generate CT data representing the internal shape of the battery.

[0068] The CT device 200 can be positioned on the battery delivery line and generate CT data for each of the multiple batteries. Here, the CT device 200 can sequentially generate CT data for each battery by using a gripper to grasp the battery cell and reconstructing slice images acquired during the rotation of the gripper.

[0069] The electrode patch inspection device 300 can acquire CT data of the battery 100 from the CT device 200 and use the CT data to determine whether there are defects in the electrode patches.

[0070] The electrode contact inspection device 300 can determine whether one or more of the positive and negative electrode contacts of a battery are defective. Meanwhile, as an example, a method for inspecting defects in the positive electrode contact is described below. However, the scope of the invention is not limited to the type of electrode contact.

[0071] Electrode contact inspection equipment 300 can use CT data to determine one or more of the following: whether there is contact between the electrode contact and the electrode assembly, whether there is contact between the electrode contact and the inner wall of the battery, whether there is misalignment of the electrode contact, and whether there are shape defects in the electrode contact. For example, electrode contact inspection equipment 300 can output one or more of the following: whether there are defects (OK or NG) in the electrode contact and the type of defect (poor contact with the electrode assembly, poor contact with the can, misalignment defect, or shape defect).

[0072] Figure 3 This is a side view of a CT device according to an embodiment of the present invention.

[0073] A CT device according to an embodiment of the present invention may include an X-ray irradiation unit 210, a battery holder 220, a lifting unit 230, a detector 240, and a data processor 250.

[0074] The battery holder 220 can hold the upper part of the battery 100 and rotate it sequentially by a predetermined unit angle. For example, the battery holder 220 can rotate it counterclockwise by 1 degree while holding the battery 100.

[0075] The X-ray irradiation unit 210 can irradiate X-rays toward the side of the battery 100. Here, the X-ray irradiation unit 210 can irradiate X-rays toward the side of the battery 100 while the battery 100 is rotated by a unit angle in sequence.

[0076] The detector 240 can detect X-rays that have passed through the interior of the battery 100 and send the X-ray detection data corresponding to the detected X-rays to the data processor 250.

[0077] The data processor 250 can use X-ray detection data received from the detector 240 to generate CT data. Specifically, the data processor 250 can use X-ray detection data acquired during the process of the battery 100 rotating unit angles in sequence to generate multiple (e.g., 360) slice images, and use a predefined restoration algorithm to synthesize the slice images to generate CT data representing the internal shape of the battery.

[0078] In one embodiment, the battery holder 220 can be fixedly connected to the lifting unit 230 and lifted vertically by the lifting unit 230.

[0079] like Figure 3 As shown, the X-ray irradiation unit 210 can irradiate X-rays toward the side of the upper portion of the battery 100, enabling the acquisition of multiple slice images (e.g., 360 images) of the upper region of the battery. Subsequently, the lifting unit 230 can rise to a predetermined position, and the X-ray irradiation unit 210 can irradiate X-rays toward the side of the lower region of the battery 100, enabling the acquisition of multiple slice images (e.g., 360 images) of the lower region of the battery. Here, the data processor 250 can use the slice images of the upper and lower regions of the battery to generate CT data.

[0080] The data processor 250 can send the generated CT data to the electrode mounting examination device.

[0081] Figure 4 This diagram illustrates an operation flowchart of an electrode patch inspection method according to an embodiment of the present invention. The electrode patch inspection method according to an embodiment of the present invention can be performed by an electrode patch inspection device that is connected to and interacts with a CT scanner.

[0082] The electrode patch inspection equipment can obtain CT data of the battery from the CT device (S410).

[0083] The electrode patch inspection device can obtain the electrode patch area from CT data (S420), in which the upper portion of a predefined electrode patch is positioned relative to the height of the battery within the electrode patch area. Here, the upper portion of the electrode patch can be defined as the area from the height of the bent portion of the electrode patch to the height of the end portion of the electrode patch.

[0084] In other words, the electrode patch inspection device can determine a first height corresponding to the bent portion of the electrode patch and a second height corresponding to the end portion of the electrode patch based on CT data, and define the area from the first height to the second height as the electrode patch area.

[0085] The electrode patch inspection device can extract a vertical cross-sectional image of the electrode patch from CT data using one or more horizontal cross-sectional images within the electrode patch area defined in S420 (S430). Here, the extracted vertical cross-sectional image can be a vertical cross-sectional image passing through the vertical central plane of the electrode patch.

[0086] In one implementation, the electrode patch inspection device can extract a vertical cross-sectional image passing through the vertical central plane of the electrode patch using a first horizontal cross-sectional image at a first height and a second horizontal cross-sectional image at a second height. For example, the electrode patch inspection device can identify a first region corresponding to a bent portion of the electrode patch in the first horizontal cross-sectional image, identify a second region corresponding to an end portion of the electrode patch in the second horizontal cross-sectional image, and then obtain the centerline of the electrode patch based on the first and second regions. The electrode patch inspection device can then obtain a vertical cross-sectional image passing through the vertical central plane of the electrode patch by extracting the vertical cross-sectional image passing through the centerline of the electrode patch from CT data.

[0087] The electrode patch inspection device can use the vertical cross-sectional image extracted in step S430 to determine whether the electrode patch has defects. Here, the electrode patch inspection device can use the vertical cross-sectional image to determine whether there is contact between the electrode patch and the electrode assembly, whether there is contact between the electrode patch and the inner wall of the battery, whether the electrode patch is misaligned, and whether the electrode patch has shape defects, or one or more of these.

[0088] Figure 5 The illustration shows a method for obtaining an electrode patch region according to an embodiment of the present invention. Figure 4 The flowchart of the implementation of S420, and Figure 6 and Figure 7 It is used for illustration. Figure 5 The method is illustrated in the reference diagram.

[0089] The electrode patch inspection device can extract multiple horizontal cross-sectional images from CT data (S510). Here, the electrode patch inspection device can extract horizontal cross-sectional images within a predetermined search area based on the height direction of the battery.

[0090] For example, refer to Figure 6 (A) The search area can be predefined as the region from height s1 to height s2. Here, the search area can be the region where the upper part of the electrode tab (from the bent part to the end part) may be located, and s1 and s2 can be predefined by the administrator.

[0091] Subsequently, the electrode patch inspection device can determine the starting height (S520) and the ending height (S530) of the upper portion of the electrode patch based on the gray level of each of the multiple horizontal cross-sectional images extracted in S510.

[0092] For example, refer to Figure 6 In (B), the electrode patch inspection device can determine the starting height h1 (corresponding to the first height of the bent portion) and the ending height h2 (corresponding to the second height of the end portion) of the upper part of the electrode patch.

[0093] Reference Figure 7 A more detailed example of the methods used to determine h1 and h2 is provided.

[0094] The electrode patch inspection device can calculate the gray level of each of the multiple horizontal cross-sectional images extracted in S510, and inspect the gray levels sequentially from the lowest image to the highest image. Here, the electrode patch inspection device can determine the first horizontal cross-sectional image at an initial height where the gray level becomes equal to or greater than a predetermined value. Figure 7 A) and the second horizontal cross-sectional image with the highest gray level ( Figure 7 B).

[0095] The first horizontal cross-sectional image determined based on the gray levels described above ( Figure 7 A) can show a portion of the bent portion T1 of the electrode tab, and a second horizontal cross-sectional image ( Figure 7 B) A portion of the end portion T2 of the electrode tab can be displayed.

[0096] The electrode patch inspection device can determine the height coordinates of the first horizontal cross-sectional image as h1 (first height), which is the starting height of the upper part of the electrode patch, and determine the height coordinates of the second horizontal cross-sectional image as h2 (second height), which is the ending height of the upper part of the electrode patch.

[0097] Subsequently, the electrode patch inspection device can define the area from the first height (h1) determined in step S520 to the second height (h2) determined in step S530 as the electrode patch area (S540).

[0098] Figure 8 This is a method for obtaining a vertical cross-sectional image of an electrode patch according to an embodiment of the present invention. Figure 4 The operation flowchart of the implementation of S430, and Figure 9 It is used to explain the basis Figure 8 The method is illustrated in the reference diagram.

[0099] The electrode patch inspection device can define the bend line of the electrode patch in a first horizontal cross-sectional image at a first height (h1) (S810).

[0100] For example, refer to Figure 9 (A) The electrode patch inspection device can identify a first region corresponding to the bent portion of the electrode patch, and define the contour closest to the battery canister in the contour of the first region as the bend line L1 of the electrode patch. Here, the electrode patch inspection device can identify the first region and obtain the contour of the first region using a predefined edge detection algorithm.

[0101] Furthermore, the electrode patch inspection device can define the end line of the electrode patch in the second horizontal cross-sectional image at the second height (h2) (S820).

[0102] For example, refer to Figure 9 (B) The electrode patch inspection device can identify a second region corresponding to the end portion of the electrode patch, and define the contour closest to the battery canister in the contour of the second region as the end line L2 of the electrode patch. Here, the electrode patch inspection device can identify the second region and obtain the contour of the second region using a predefined edge detection algorithm.

[0103] Subsequently, the electrode patch inspection device can define the center line of the electrode patch using the bend line L1 defined in S810 and the end line L2 defined in S820 (S830). Here, the center line of the electrode patch can be defined as a line passing through the midpoint of the bend line L1 and the midpoint of the end line L2.

[0104] For example, refer to Figure 9 (C) The electrode patch inspection device can determine the midpoint of each of the bend line L1 and the end line L2, and define the line passing through these midpoints as the electrode patch center line Lc.

[0105] Subsequently, the electrode patch inspection device can extract a vertical cross-sectional image corresponding to the center line Lc of the electrode patch from the CT data (S840). In other words, the electrode patch inspection device can obtain a vertical cross-sectional image passing through the vertical central plane of the electrode patch by extracting a vertical cross-sectional image passing through the center line Lc of the electrode patch from the CT data.

[0106] Figure 10 This is a reference diagram illustrating a method for determining whether an electrode contact has defects according to an embodiment of the present invention.

[0107] The electrode patch inspection device can use the vertical cross-sectional image extracted in step S840 to determine whether the electrode patch is defective. Here, the electrode patch inspection device can use the vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode patch and the electrode assembly, whether there is contact between the electrode patch and the inner wall of the battery, whether there is misalignment of the electrode patch, and whether there are shape defects in the electrode patch.

[0108] Figure 10 (A) is an example of a vertical cross-sectional image. Electrode contact inspection equipment can use a vertical cross-sectional image that passes through the vertical central plane of the electrode contact to determine whether the positive electrode contact Tp is defective.

[0109] Electrode patch inspection equipment can use predefined region segmentation algorithms to identify electrode patch areas, tank areas, and electrode assembly areas in vertical cross-sectional images.

[0110] like Figure 10 As shown in (B), the electrode contact inspection device can calculate the shortest distance between the electrode contact area and the can area, and the shortest distance between the electrode contact area and the electrode assembly area. Using the calculated shortest distance, the electrode contact inspection device can determine whether there is contact between the electrode contact and the electrode assembly, whether there is contact between the electrode contact and the inner wall of the battery, and whether there are shape defects in the electrode contact. For example, if the shortest distance between the electrode contact and the electrode assembly is 0, the electrode contact inspection device can determine that the electrode contact and the electrode assembly are in contact. As another example, if the shortest distance between the electrode contact and the can exceeds a first preset range, and the shortest distance between the electrode contact and the electrode assembly exceeds a second preset range, the electrode contact inspection device can determine that the electrode contact has a shape defect.

[0111] Furthermore, if the electrode patch area is separated from the predetermined alignment position by a threshold distance, the electrode patch inspection device can determine that the electrode patch is reverse aligned.

[0112] Figure 11 This is a block diagram of an electrode patch inspection system according to another embodiment of the present invention.

[0113] A battery electrode patch inspection system according to another embodiment of the present invention may include a CT device 200, an electrode patch inspection device 300, and a diagnostic model generation device 400.

[0114] The electrode patch inspection device 300 may include a diagnostic model 310, which has been pre-trained, and the electrode patch inspection device 300 may use CT data and the diagnostic model 310 to determine whether the electrode patch is defective.

[0115] The diagnostic model generation device 400 can generate a machine learning-based diagnostic model 310 for electrode patch inspection.

[0116] The diagnostic model generation device 400 can train the diagnostic model 310 and, upon completion of training, provide the diagnostic model 310 to the electrode patch inspection device 300.

[0117] The diagnostic model 310 can be a machine learning-based model pre-trained using vertical cross-sectional images labeled with defect types as training data. Here, the diagnostic model 310 can be defined as: when a vertical cross-sectional image is input, outputting whether the electrode patch is defective and one or more of the following defect types. For example, when the vertical cross-sectional image is input as input data, the diagnostic model 310 can output the following as output data: whether the electrode patch is defective (OK or NG); and one or more of the following defect types (electrode assembly contact failure, can contact failure, misalignment failure, shape failure).

[0118] The electrode patch inspection device 300 can input the vertical cross-sectional image extracted in step S430 or step S840 into the diagnostic model 310 received from the diagnostic model generation device 400, and output the output data of the diagnostic model 310 as the diagnostic result.

[0119] Figure 12 This is a block diagram of an electrode patch inspection device according to an embodiment of the present invention.

[0120] The electrode patch inspection device 1200 according to an embodiment of the present invention can be linked to a CT device.

[0121] The electrode patch inspection device 1200 may include at least one processor 1210, a memory 1220 storing at least one instruction executed by the processor, and a transceiver 1230 connected to a network to perform communication.

[0122] The at least one instruction may include: an instruction for obtaining computed tomography (CT) data of the battery from a CT device; an instruction for obtaining an electrode patch region in the height direction of the battery based on the CT data, representing a predetermined upper portion of the electrode patch; an instruction for extracting a vertical cross-sectional image of the electrode patch from the CT data using a horizontal cross-sectional image within the electrode patch region; and an instruction for determining whether the electrode patch is defective using the vertical cross-sectional image of the electrode patch.

[0123] Instructions for obtaining the electrode patch area may include instructions for determining the start and end heights of the upper portion of the electrode patch based on the gray levels of each of a plurality of horizontal cross-sectional images.

[0124] Instructions for obtaining the electrode patch region may include: instructions for determining a first height corresponding to a bent portion of the electrode patch and a second height corresponding to an end portion of the electrode patch; and instructions for determining the region from the first height to the second height as the electrode patch region.

[0125] Instructions for extracting a vertical cross-sectional image of an electrode patch may include instructions for extracting a vertical cross-sectional image passing through the vertical central plane of the electrode patch using a first horizontal cross-sectional image at a first height and a second horizontal cross-sectional image at a second height.

[0126] Instructions for extracting vertical cross-sectional images may include: instructions for defining the bend line of the electrode patch in a first horizontal cross-sectional image and defining the end line of the electrode patch in a second horizontal cross-sectional image; instructions for defining the center line of the electrode patch passing through the midpoint of the bend line and the midpoint of the end line; and instructions for extracting the vertical cross-sectional image corresponding to the center line of the electrode patch from CT data.

[0127] Instructions for determining whether an electrode tab is defective may include instructions to use a vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode tab and the electrode assembly; whether there is contact between the electrode tab and the inner wall of the battery; and whether the electrode tab has shape defects.

[0128] Instructions for determining whether an electrode patch is defective may include inputting a vertical cross-sectional image into a diagnostic model that is pre-trained using the vertical cross-sectional image as learning data, and obtaining diagnostic result data from the diagnostic model.

[0129] Furthermore, the electrode patch inspection device 1200 according to an embodiment of the present invention may also include an input interface device 1240, an output interface device 1250, a storage device 1260, etc. The various components included in the electrode patch inspection device 1200 can be connected via a bus 1270 and can communicate with each other.

[0130] Here, processor 1210 may refer to a central processing unit (CPU), graphics processing unit (GPU), or dedicated processor on which the methods according to embodiments of the present invention are executed. Furthermore, the memory may include at least one of volatile / temporary storage media and non-volatile / non-temporary storage media. For example, the memory may include at least one of read-only memory (ROM) and random access memory (RAM), and may include electrically erasable programmable read-only memory (EEPROM).

[0131] The operation of the method according to embodiments of the present invention can be implemented as a computer-readable program or code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices for storing data readable by a computer system. Furthermore, the computer-readable recording medium can be distributed across a network-connected computer system, thereby storing and executing the computer-readable program or code in a distributed manner.

[0132] The operation of the method according to embodiments of the present invention can be implemented in various forms related to the program, such as the computer program or code itself or a computer program product.

[0133] In addition, computer-readable recording media may include one or more of volatile / temporary recording media and non-volatile / non-temporary recording media.

[0134] Additionally, computer-readable recording media can include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory, and can include, for example, various types of servers located on a network. Program instructions can include not only machine language code, such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter.

[0135] Although some aspects of the invention have been described in the context of apparatus, some aspects of the invention may also refer to the description of the corresponding method, wherein a block or apparatus corresponds to a method step or feature of a method step. Similarly, aspects described in the context of a method may also refer to features of a corresponding block or item or a corresponding apparatus. Some or all of the method steps may be performed by (or using) hardware devices such as microprocessors, programmable computers, or electronic circuits. In some embodiments, one or more of the most important method steps may be performed by such apparatus.

[0136] In the foregoing, the present invention has been described with reference to exemplary embodiments thereof. However, those skilled in the art will understand that various modifications and changes can be made to the invention within the scope of the invention as described in the appended claims without departing from the spirit and scope of the invention.

Claims

1. An electrode contact inspection device, comprising: At least one processor; as well as A memory configured to store at least one instruction executed by the at least one processor. Wherein, the at least one instruction includes: Instructions for obtaining computed tomography (CT) data from a CT scanner; Instructions for determining the predetermined upper portion of the electrode patch based on the electrode patch region in the height direction of the battery are obtained from the CT data. Instructions for extracting a vertical cross-sectional image of the electrode patch from the CT data using a horizontal cross-sectional image within the electrode patch area; and Instructions to determine whether the electrode patch is defective using the vertical cross-sectional image of the electrode patch.

2. The electrode patch inspection device according to claim 1, wherein, The instructions for obtaining the electrode patch area include: Instructions for determining the start and end heights of the upper portion of the electrode patch based on the grayscale level of each of a plurality of horizontal cross-sectional images.

3. The electrode patch inspection device according to claim 1, wherein, The instructions for obtaining the electrode patch area include: Instructions for determining a first height corresponding to the bent portion of the electrode contact and a second height corresponding to the end portion of the electrode contact; and The instruction to define the region from the first height to the second height as the electrode patch region.

4. The electrode patch inspection device according to claim 3, wherein, The instructions for extracting the vertical cross-sectional image of the electrode patch include: Instructions to extract a vertical cross-sectional image through the vertical central plane of the electrode tab using a first horizontal cross-sectional image at the first height and a second horizontal cross-sectional image at the second height.

5. The electrode patch inspection device according to claim 4, wherein, The instructions for extracting the vertical cross-sectional image include: Instructions defining the bend lines of the electrode tabs in the first horizontal cross-sectional image and defining the end lines of the electrode tabs in the second horizontal cross-sectional image; Instructions for defining the center line of the electrode patch passing through the midpoint of the bend line and the midpoint of the end line; and Instructions to extract a vertical cross-sectional image corresponding to the center line of the electrode patch from the CT data.

6. The electrode patch inspection device according to claim 1, wherein, Instructions for determining whether the electrode contacts are defective include: Instructions for using the vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode tab and the electrode assembly; whether there is contact between the electrode tab and the inner wall of the battery; and whether the electrode tab has shape defects.

7. The electrode patch inspection device according to claim 1, wherein, Instructions for determining whether the electrode contacts are defective include: Instructions for inputting the vertical cross-sectional image into a diagnostic model pre-trained using the vertical cross-sectional image as learning data and obtaining diagnostic result data from the diagnostic model.

8. An electrode patch inspection method, the electrode patch inspection method using an electrode patch inspection device connected to a computed tomography (CT) device, the electrode patch inspection method comprising: The steps for acquiring CT data from the battery using the CT device; The step of obtaining the predetermined upper portion of the electrode patch based on the height direction of the battery from the CT data; The step of extracting a vertical cross-sectional image of the electrode patch from the CT data using a horizontal cross-sectional image within the electrode patch area; as well as The step of using the vertical cross-sectional image of the electrode patch to determine whether the electrode patch is defective.

9. The electrode contact inspection method according to claim 8, wherein, The steps for obtaining the electrode patch area include: The step of determining the starting height and ending height of the upper portion of the electrode patch based on the gray level of each of the multiple horizontal cross-sectional images.

10. The electrode contact inspection method according to claim 8, wherein, The steps for obtaining the electrode patch area include: The steps of determining a first height corresponding to the bent portion of the electrode contact and a second height corresponding to the end portion of the electrode contact; and The step of determining the region from the first height to the second height as the electrode patch region.

11. The electrode patch inspection method according to claim 10, wherein, The step of extracting the vertical cross-sectional image of the electrode patch includes: The step of using a first horizontal cross-sectional image at the first height and a second horizontal cross-sectional image at the second height to extract a vertical cross-sectional image through the vertical central plane of the electrode patch.

12. The electrode patch inspection method according to claim 11, wherein, The steps for extracting the vertical cross-sectional image include: The steps of defining the bend line of the electrode tab in the first horizontal cross-sectional image and defining the end line of the electrode tab in the second horizontal cross-sectional image; The step of defining the center line of the electrode patch passing through the midpoint of the bend line and the midpoint of the end line; and The step of extracting a vertical cross-sectional image corresponding to the center line of the electrode patch from the CT data.

13. The electrode patch inspection method according to claim 8, wherein, The steps for determining whether the electrode contacts are defective include: The steps of using the vertical cross-sectional image to determine one or more of the following: whether there is contact between the electrode tab and the electrode assembly; whether there is contact between the electrode tab and the inner wall of the battery; and whether the electrode tab has shape defects.

14. The electrode patch inspection method according to claim 8, wherein, The steps for determining whether the electrode contacts are defective include: The steps involve inputting the vertical cross-sectional image into a diagnostic model that is pre-trained using the vertical cross-sectional image as learning data and obtaining diagnostic result data from the diagnostic model.

15. An electrode patch inspection system, comprising: A computed tomography (CT) device configured to generate battery-powered CT data; as well as An electrode patch inspection device is configured to obtain CT data from the CT device and use the CT data to determine whether there are defects in the electrode patches located inside the battery. The electrode patch inspection device extracts a vertical cross-sectional image of the electrode patch from the CT data and uses the extracted vertical cross-sectional image to determine whether the electrode patch has defects.

Images