Battery diagnosis device and operation method thereof

Abstract

A battery diagnosis device according to one embodiment disclosed in the present document may comprise: an interface for acquiring a first image of a battery; and a controller which identifies, from the first image, an electrode image corresponding to an electrode and a separator image corresponding to a separator by using an artificial intelligence model trained to identify a specific area, and which diagnoses the state of the battery on the basis of the electrode image and the separator image.

Description

Battery diagnostic device and its operation method

[0001] Cross-citation with related applications

[0002] The present invention claims the benefit of priority based on Korean Patent Application No. 10-2025-0037208 filed on March 24, 2025, and includes all contents disclosed in the document of said Korean patent application as part of this specification.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a battery diagnostic device and a method of operating the same.

[0005] Recently, active research and development on secondary batteries has been underway. Here, the term "secondary battery" refers to a rechargeable battery, encompassing conventional Ni / Cd and Ni / MH batteries as well as the more recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries have the advantage of significantly higher energy density compared to conventional Ni / Cd and Ni / MH batteries. Furthermore, lithium-ion batteries can be manufactured in a compact and lightweight manner, making them suitable for use as power sources for mobile devices. Recently, their scope of application has expanded to include electric vehicles, drawing attention as a next-generation energy storage medium.

[0006] A battery may comprise multiple chemical components. In particular, the positive electrode, negative electrode, electrolyte, and separator may be key components constituting the battery. Each of these components can affect the performance and safety of the battery. For example, if the negative electrode and separator are not properly wound during the winding process while assembling a cylindrical battery, meandering defects may occur. If the separator is damaged due to meandering defects, a disconnection may occur, posing a risk of explosion due to thermal runaway.

[0007] Accordingly, methods to diagnose the condition of the battery and identify abnormal components at an early stage are being researched; as an example, there is a method of diagnosing abnormalities in components based on images of the battery interior captured using X-ray or CT (computed tomography).

[0008] In the case of battery diagnosis using CT images, there is a problem in that the boundary between the cathode and the separator is not clear. To resolve this issue, high-resolution CT equipment can be used to distinguish the cathode and separator and perform meander diagnosis; however, this method is costly and time-consuming.

[0009] The technical problems of the embodiments disclosed in this document are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below.

[0010] A battery diagnostic device according to one embodiment disclosed in this document may include an interface for acquiring a first image relating to a battery; and a controller for identifying an electrode image corresponding to an electrode and a separator image corresponding to a separator in the first image using an artificial intelligence model trained to identify a specific region, and diagnosing the state of the battery based on the electrode image and the separator image.

[0011] In one embodiment, the controller can use the artificial intelligence model to obtain a second image in which the first image is labeled by the specific region, and can identify the electrode image and the separator image based on the second image.

[0012] In one embodiment, the battery may be a cylindrical battery comprising an electrode assembly in which the electrode and the separator are wound n times (n: natural number) in the form of a jelly roll, and the controller may diagnose whether the winding state of the electrode assembly is normal based on the electrode image and the separator image.

[0013] In one embodiment, the controller identifies a winding turn based on the center point of the electrode assembly in the first image, identifies an area corresponding to m-turns (m: natural number) for the winding turn, identifies a target area including a part of the electrode and a part of the separator corresponding to m-turns, and diagnoses whether the winding state at m-turns is normal based on the target area.

[0014] In one embodiment, the controller can diagnose whether the winding state in the m-turn is normal based on the pixel value corresponding to the electrode included in the target area.

[0015] In one embodiment, the controller can diagnose a meandering defect if the pixel value corresponding to the electrode is not included in a threshold range.

[0016] A method of operation of a battery diagnostic device according to one embodiment disclosed in this document may include: acquiring a first image relating to a battery; identifying an electrode image corresponding to an electrode and a separator image corresponding to a separator in the first image, respectively, using an artificial intelligence model trained to identify a specific region based on pixel values; and diagnosing the state of the battery based on the electrode image and the separator image.

[0017] In one embodiment, the identifying operation may include the operation of obtaining a second image by labeling the first image by specific regions using the artificial intelligence model, and the operation of identifying the electrode image and the separator image based on the second image.

[0018] In one embodiment, the battery may be a cylindrical battery comprising an electrode assembly in which the electrode and the separator are wound n times (n: natural number) in the form of a jelly roll, and the operation of diagnosing the state of the battery may include diagnosing whether the winding state of the electrode assembly is normal based on the electrode image and the separator image.

[0019] In one embodiment, the operation of diagnosing whether the winding state is normal may include: identifying a winding turn based on the center point of the electrode assembly in the first image; identifying an area where the winding turn corresponds to m-turns (m: natural number); identifying a target area including a part of the electrode and a part of the separator corresponding to m-turns; and diagnosing whether the winding state at m-turns is normal based on the target area.

[0020] In one embodiment, the operation of diagnosing whether the winding state in the m-turn is normal based on the target area may include the operation of diagnosing whether the winding state in the m-turn is normal based on the pixel value corresponding to the electrode included in the target area.

[0021] In one embodiment, the operation of diagnosing whether the winding state in the m-turn is normal based on the pixel value corresponding to the electrode included in the target area may include diagnosing a meandering defect if the pixel value corresponding to the electrode is not included in a threshold range.

[0022] The battery diagnostic device and the method of operation thereof according to the various embodiments disclosed in this document can identify images of battery components from images of the battery interior captured using an artificial intelligence model, and can diagnose whether there is a meandering defect based on the identified images of the components. Accordingly, it is possible to diagnose abnormalities inside the battery without high-performance imaging equipment.

[0023] The effects of the battery diagnostic device and the method of operation thereof disclosed in this document are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art in accordance with the disclosure of this document.

[0024] FIG. 1 is a block diagram of a battery diagnostic system according to one embodiment disclosed in this document.

[0025] FIGS. 2 and FIGS. 3 illustrate training data for training an artificial intelligence model according to an embodiment disclosed in this document.

[0026] FIG. 4 illustrates a first image according to an embodiment disclosed in this document.

[0027] FIG. 5 illustrates a cathode image, a tab image, and a hole image according to an embodiment disclosed in this document.

[0028] FIG. 6 is an enlarged view of a specific area of ​​an output image according to one embodiment disclosed in this document.

[0029] FIG. 7 illustrates an internal battery image including an electrode image and a separator image identified based on a second image according to an embodiment disclosed in this document.

[0030] Figure 8 is an enlarged view of a specific area of ​​the battery interior image of Figure 7.

[0031] FIGS. 9 and 10 are drawings for explaining a method for a battery diagnostic device according to an embodiment disclosed in this document to diagnose whether there is a meandering defect based on an image.

[0032] FIGS. 11 and 12 illustrate internal images of a battery with a meandering defect according to an embodiment disclosed in this document.

[0033] FIGS. 13 and 14 illustrate internal images of a normal battery according to an embodiment disclosed in this document.

[0034] FIG. 15 is a flowchart illustrating the operation method of a battery diagnostic device according to one embodiment disclosed in this document.

[0035] FIG. 16 illustrates a computing system for executing operations of a battery diagnostic device according to an embodiment disclosed in this document.

[0036] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0037] Hereinafter, embodiments of the present invention are described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present invention.

[0038] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise.

[0039] In this document, each of the phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as “first,” “second,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used simply to distinguish a component from another component and, unless specifically stated otherwise, do not limit the components in any other aspect (e.g., importance or order).

[0040] In this document, where it is stated that any (e.g., 1) component is "connected," "coupled," or "joined" to another (e.g., 2) component, with or without the terms "functionally" or "communicationly," or where it is stated that the component is "coupled" or "connected," it means that the component may be connected to the other component directly (e.g., by wire or wirelessly) or indirectly (e.g., through a 3) component.

[0041] Methods according to the various embodiments disclosed in this document may be provided as part of a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory, CD-ROM) or distributed online (e.g., download or upload) through an application store or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0042] According to the embodiments disclosed in this document, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to the embodiments disclosed in this document, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the components of the multiple components in the same or similar manner as those performed by the corresponding components among the multiple components prior to the integration. According to the embodiments disclosed in this document, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0043] FIG. 1 is a block diagram of a battery diagnostic system (1) according to one embodiment disclosed in this document.

[0044] Referring to FIG. 1, the battery diagnostic system (1) may include a battery diagnostic device (10), a sensing device (12), and a battery unit (16). The battery unit (16) in FIG. 1 may correspond to any one of a battery rack, a battery pack, a battery module, and a battery cell. Depending on the shape of the battery, the battery unit (16) may correspond to a cylindrical battery, a prismatic battery, a pouch battery, or a coin cell battery. According to various embodiments, when the battery unit (16) corresponds to a battery pack having a Cell To Pack (CTP) structure, the battery unit (16) may be configured to include a plurality of battery cells without distinction of battery modules.

[0045] The battery diagnostic device (10) can be connected to the sensing device (12) via wired and / or wireless connections.

[0046] In one embodiment, the connection between the battery diagnostic device (10) and the sensing device (12) may be a communication connection via a wired and / or wireless network. In one embodiment, the wired network may be based on LAN (local area network) communication or power line communication. In one embodiment, the wireless network may be based on a short-range communication network (e.g., Bluetooth, WiFi (wireless fidelity) or IrDA (infrared data association)), or a long-range communication network (cellular network, 4G network, 5G network).

[0047] In one embodiment, the connection between the battery diagnostic device (10) and the sensing device (12) may be a connection via a device-to-device communication method (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0048] The sensing device (12) may be a device for acquiring an image of the battery unit (16). For example, the sensing device may be an X-ray device capable of acquiring a two-dimensional image of the interior of the battery unit (16) by transmitting radiation, or a CT device capable of acquiring a three-dimensional image of the interior of the battery unit (16).

[0049] The battery diagnostic device (10) can acquire a first image of the battery unit (16). Here, the first image may be an image of the interior of the battery unit (16) taken using a sensing device (12).

[0050] The battery diagnostic device (10) can identify an electrode image corresponding to an electrode (e.g., positive and negative electrode) and a separator image corresponding to a separator in a first image, respectively, using an artificial intelligence model. Here, the artificial intelligence model may be a model based on an image segmentation technique and may be a model trained to identify a specific region (or object) based on the pixel value of each pixel included in the image.

[0051] The battery diagnostic device (10) can diagnose the condition of the battery based on the electrode image and the separator image. The battery diagnostic device (10) can diagnose whether there is a meandering defect in the electrode based on the electrode image and the separator image. The battery diagnostic device (10) can diagnose whether the negative electrode protrudes over the separator based on the negative electrode image and the separator image.

[0052] In one embodiment, the battery diagnostic device (10) may be included in a server or a charger / discharger capable of diagnosing battery cells outside of an electronic device, and operations performed by the battery diagnostic device (10) may be performed on an external server or charger / discharger. In particular, the battery diagnostic device (10) may be utilized in a process for verifying whether the battery is normal during the battery manufacturing process, and may be included in a PC that performs the verification.

[0053] In one embodiment, the battery diagnostic device (10) may be included in a Battery Management System (BMS) capable of diagnosing a battery included in an electronic device, and operations performed by the battery diagnostic device (10) may be performed in the BMS. According to an embodiment, the battery diagnostic device (10) may be included in a battery management system of a battery pack included in an electronic device. Here, the electronic device may be a mobile device (e.g., mobile phone, laptop computer, smartphone, smart pad), an electric vehicle (e.g., EV, HEV, PHEV, fuel cell EV), an energy storage system (ESS), or a battery swapping system (BSS).

[0054] Hereinafter, for the convenience of explanation, assuming that the battery unit (16) is a cylindrical battery in which the positive electrode, the negative electrode, and the separator are wound n times (n: natural number) in the form of a jelly roll, the operation performed by each of the components included in the battery diagnostic device (10) to diagnose whether there is an abnormality in the battery unit (16) will be described.

[0055] The battery diagnostic device (10) may include an interface (100), a memory (1620), and a controller (102). According to an embodiment, the battery diagnostic device (10) illustrated in FIG. 1 may further include at least one component (e.g., a display, an input device, or an output device) other than the components illustrated in FIG. 1.

[0056] The interface (100) can acquire a first image of the battery unit (16). The interface (100) can acquire a first image of the battery unit (16) through wired / wireless communication with the sensing device (12). According to various embodiments, the interface (100) may include various interface circuits for acquiring signals, information and / or data, such as sensors and communication circuits.

[0057] The controller (102) can use an artificial intelligence model to identify an image corresponding to each of the components (e.g., electrode assembly, positive electrode, negative electrode, and separator) included in the battery unit (16) in the first image. Here, the artificial intelligence model may be a model trained to identify a specific region (or object) based on the pixel values ​​of each pixel included in the image. For example, the artificial intelligence model may set a threshold value for each specific region based on the pixel values ​​of a plurality of pixels included in the first image, and may identify a specific region based on said threshold value. By using the artificial intelligence model to distinguish and identify the negative electrode image and the separator image in the first image, the controller (102) can resolve the problem of difficulty in determining whether there is a meandering defect due to the ambiguity of the boundary between the negative electrode and the separator.

[0058] In one embodiment, the controller (102) can obtain a second image by labeling the first image by specific regions (or specific objects) using an artificial intelligence model. The controller (102) can obtain a second image by labeling the first image by components included in the battery unit (16) using an artificial intelligence model. For example, if the battery unit (16) is a cylindrical battery, the controller (102) can obtain a second image by labeling the first image by a region corresponding to a jellyroll-shaped electrode assembly including an electrode and a separator, a region corresponding to a battery outer case, and a region corresponding to a tab. A specific method for the controller (102) to obtain the second image by labeling the first image is described later in FIG. 3.

[0059] The controller (102) can diagnose the condition of the battery unit (16) based on the electrode image and the separator image. The controller (102) can diagnose whether a structural problem (e.g., misalignment) has occurred inside the battery unit (16) based on the electrode image and the separator image. That is, the controller (102) can diagnose whether the position of the electrode and the position of the separator are normal based on the electrode image and the separator image. The controller (102) can diagnose a misalignment if the position of the electrode protrudes above the position of the separator.

[0060] In one embodiment, the controller (102) can determine whether the winding state of the electrode assembly included in the battery unit (16) is normal based on the electrode image and the separator image. The controller (102) can identify the number of winding turns based on the center point of the electrode assembly and identify an area corresponding to a number of winding turns of 1 turn or more and m turns or less (m: natural number). The controller (102) can identify a target area including a part of the electrode and a part of the separator corresponding to m turns, and diagnose whether the winding state at m turns is normal based on the target area. The controller (102) can diagnose whether a meandering defect has occurred at m turns based on the target area. Hereinafter, for convenience of explanation, the description assumes that the electrode is a negative electrode included in a cylindrical battery and the electrode image is a negative electrode image.

[0061] In one embodiment, the controller (102) can diagnose whether the winding state in m-turns is normal based on a first pixel value corresponding to a negative electrode included in the target area. According to an embodiment, the controller (102) may also diagnose whether the winding state in m-turns is normal based on a first pixel value and a second pixel value corresponding to a negative electrode and a separator, respectively. The controller (102) can diagnose it as normal if the first pixel value and the second pixel value fall within a threshold range. The controller (102) can diagnose it as a meandering defect if the first pixel value and the second pixel value fall within a threshold range. For example, if a meandering defect occurs in which the negative electrode protrudes over the separator inside a cylindrical battery, the pixel value of the negative electrode in a normal state and the pixel value of the negative electrode in a state of meandering defect are different; therefore, the controller (102) can diagnose whether the meandering defect is normal based on whether the pixel value of the negative electrode falls within a threshold range (e.g., the range of the pixel value in a normal state).

[0062] Although the above description explains how to diagnose whether there is a meandering defect based on whether each of the first pixel value and the second pixel value falls within a threshold range, according to the embodiment, the controller (102) may also diagnose whether there is a meandering defect based on whether the difference between the first pixel value and the second pixel value falls within a threshold range.

[0063] FIGS. 2 and FIGS. 3 illustrate training data for training an artificial intelligence model according to an embodiment disclosed in this document. Specifically, FIG. 2 may be a CT image (20) taken of the interior of a cylindrical battery including an electrode assembly wound in the shape of a jelly roll, and FIG. 3 may be a labeled image (30) in which the CT image (20) of FIG. 2 is labeled according to the configuration of the battery. Here, the CT image (20) may be training data corresponding to a first image, and the labeled image (30) may be training data corresponding to a second image.

[0064] Hereinafter, with reference to FIGS. 2 and FIGS. 3, a method for a battery diagnostic device (10) to train an artificial intelligence model will be described.

[0065] Referring to FIG. 2, the CT image (20) may include a cross-section of an electrode assembly comprising an anode, a cathode, and a separator. Referring to the CT image (20), it can be seen that the boundary between the cathode and the separator is not clear.

[0066] Referring to FIGS. 2 and 3, a labeling image (30) can be generated by performing labeling for each component of a cylindrical battery (e.g., case (300), hole (304) of an electrode assembly, tab (306), positive electrode (not shown), negative electrode (not shown), and separator (not shown), etc.) based on a CT image (20). For example, during a CT scanning process, a CT device (not shown) may emit X-rays toward a cylindrical battery and acquire a CT image (20) based on whether the X-rays are transmitted. In this case, since the transmittance of X-rays varies for each component of the cylindrical battery, the pixel values ​​for each component included in the CT image (20) may vary. That is, a labeling image (30) can be generated by distinguishing the components of the cylindrical battery based on the pixel values ​​of each pixel included in the CT image (20) and performing labeling.

[0067] The CT image (20) can be used as input data to train an artificial intelligence model, and the labeling image (30) can be used as output data based on the CT image (20).

[0068] In the above description, it has been explained on the premise that the CT image (20) and the labeling image (30) are two-dimensional images, but this is for convenience of explanation only and the present invention is not limited thereto. Depending on the embodiment, the CT image (20) and the labeling image (30) may be three-dimensional images.

[0069] FIG. 4 illustrates a first image according to an embodiment disclosed in this document. FIG. 5 illustrates a cathode image, a tab image, and a hole image according to an embodiment disclosed in this document. FIG. 6 is a drawing that enlarges a specific area of ​​an output image according to an embodiment disclosed in this document. Specifically, FIG. 4 is a CT image capturing a cross-section of an electrode assembly including a positive electrode, a negative electrode, and a separator, FIG. 5 may be an image including a cathode image, a tab image, and a hole image identified by inputting the CT image of FIG. 4 into an artificial intelligence model, and FIG. 6 may be an enlarged image that enlarges a specific area in FIG. 5. In the following, the content of diagnosing a meandering defect based on a negative electrode image is described, but this is for convenience of explanation only and the present invention is not limited thereto. For example, the battery diagnostic device (10) may acquire a separator image in the same way as the method of acquiring a negative electrode image.

[0070] Hereinafter, with reference to FIGS. 4 to 6, a method for a battery diagnostic device (10) to identify a negative electrode image through a first image will be described.

[0071] Referring to FIGS. 4 and FIGS. 5, a battery diagnostic device (10) can obtain an output image (50) of FIGS. 5 by inputting a first image (20) of FIGS. 4 into an artificial intelligence model. Here, the artificial intelligence model may be a model trained to output an image (50) of FIGS. 5 based on the result of performing labeling based on the pixel values ​​of each pixel included in the input image (e.g., the first image (40)) based on an image segmentation technique.

[0072] Referring to FIG. 4, the battery diagnostic device (10) can identify a target area (400) in the first image (40). Here, the target area (400) may refer to an area within the cylindrical battery where the frequency of meandering defects is high. By identifying the target area (400), the battery diagnostic device (10) can reduce the time required to diagnose meandering defects.

[0073] Referring to FIGS. 4 and 5, the battery diagnostic device (10) can identify a negative electrode image (500), a tab image (510), and a hole image (520) based on a first image (40). Here, the tab is a component responsible for the electrical connection between the electrode inside the cylindrical battery and the battery case or external terminal, and the hole may be a component corresponding to the innermost part during the process of winding the electrode assembly and may perform the role of releasing heat or gas. In the same manner as the method for identifying the negative electrode image of the cylindrical battery according to the embodiment, the battery diagnostic device (10) may further identify a separator image (not shown).

[0074] Referring to FIGS. 4 and FIGS. 6, the battery diagnostic device (10) can diagnose whether a meandering defect has occurred in turns 1 to 4 based on a specific area (60) that includes a part of an electrode assembly corresponding to turns 1 to 4 included in the target area (400) of FIG. 4. Here, m-turn (m: natural number) may refer to the m-th winding turn based on the center of the electrode assembly. The specific area (60) may include an area corresponding to turns 1 to 4 of the negative electrode image (500) of FIG. 5. According to an embodiment, the battery diagnostic device (10) may also identify a specific area (not shown) that includes an area corresponding to turns 1 to 4 of a separator image (not shown).

[0075] FIG. 7 illustrates an internal battery image including an electrode image and a separator image identified based on a second image according to an embodiment disclosed in this document. FIG. 8 is an enlarged view of a specific area of ​​the internal battery image of FIG. 7.

[0076] Referring to Figures 7 and 8, it can be seen that the boundary between the negative electrode and the separator becomes clear by extracting images for each battery configuration through an artificial intelligence model.

[0077] Referring to FIG. 7, the battery internal image (70) may be an image in which pixel values ​​included in the CT image (40) of FIG. 4 are adjusted based on the negative electrode image, positive electrode image, case image, and separator image identified through labeling of the CT image (40, see FIG. 4) of FIG. 4 using an artificial intelligence model. The battery diagnostic device (10) can clearly distinguish the boundaries of the battery components by adjusting the brightness of the pixel values ​​included in the CT image (40) of FIG. 4.

[0078] The battery diagnostic device (10) can identify a specific area corresponding to 1 turn to n turns based on the center of the electrode assembly in the battery internal image (70) as a target area. Here, the center of the electrode assembly may be included in the hole area of ​​the electrode assembly and may be identified based on the average of the coordinate values ​​of pixels corresponding to the outermost winding turn in the jelly roll shape.

[0079] Referring to FIG. 8, the battery diagnostic device (10) can obtain an enlarged drawing (80) of a specific area of ​​FIG. 7. Here, the specific area of ​​FIG. 7 may be an area corresponding to the specific area (400) of FIG. 4 as a target area.

[0080] Referring to the enlarged drawing (80), it can be seen that the pixel values ​​of the pixels corresponding to the positive electrode, the negative electrode, and the separator are distinguished. Based on this, the battery diagnostic device (10) can diagnose whether there is a meandering defect based on whether the pixel values ​​of the negative electrode and the separator in the enlarged drawing (80) fall within a threshold range. Here, the threshold range can be calculated based on the average and standard deviation of the pixel values ​​included in the battery internal images of a plurality of normal batteries. For example, 100 negative electrode images can be obtained by inputting the CT images of each of 100 normal batteries into an artificial intelligence model, and the threshold range for the pixel values ​​of the negative electrode can be calculated based on the average and standard deviation of the pixel values ​​of the 100 negative electrode images.

[0081] FIGS. 9 and 10 are drawings for explaining a method for a battery diagnostic device according to an embodiment disclosed in this document to diagnose whether there is a meandering defect based on an image.

[0082] Referring to FIG. 9, the battery diagnostic device (10) can obtain a first image (90) of the battery. Here, the first image may be a CT image of the inside of a cylindrical battery.

[0083] Referring to the first image (90), the battery diagnostic device (10) can identify a target area (900). Here, the target area (900) can be identified based on statistical data regarding an area where the frequency of meandering defects is high.

[0084] Referring to FIGS. 9 and 10, the battery diagnostic device (10) can perform labeling according to the configuration of the battery included in the image corresponding to the target area (900) using an artificial intelligence model, and can identify a negative electrode image (1010), a tap image (1020), and a hole image (1030) based on the labeled image.

[0085] The battery diagnostic device (10) can clarify the boundaries between components included in the cylindrical battery by adjusting the pixel values ​​of the pixels included in the first image (90) of FIG. 9 based on the negative electrode image (1010), the tap image (1020), and the hole image (1030). For example, the battery diagnostic device (10) can identify the coordinates (e.g., (x, y)) of each pixel corresponding to the negative electrode in the negative electrode image (1010), and can clarify the boundaries between the negative electrode and the separator by adjusting the pixel values ​​of the pixels corresponding to said coordinates in the first image (90).

[0086] FIGS. 11 and 12 illustrate internal images of a battery with a meandering defect according to an embodiment disclosed in this document. FIGS. 13 and 14 illustrate internal images of a normal battery according to an embodiment disclosed in this document. Specifically, FIGS. 11 and FIGS. 13 may correspond to an internal image of a battery with a meandering defect and an internal image of a normal battery in a first specific area, and FIGS. 12 and FIGS. 14 may correspond to an internal image of a battery with a meandering defect and an internal image of a normal battery in a second specific area.

[0087] Referring to FIGS. 11 and FIGS. 13, it can be seen that the contrast difference of the pixels included in the first defective image (1100) and the first normal image (1300) is distinguishable. It can be seen that the pixels (1110) corresponding to the negative electrode in the first defective image (1100) are distinguished from the pixels (1310) corresponding to the negative electrode in the first normal image (1300). That is, it can be seen that the pixel values ​​(e.g., contrast values) of the pixels (1310) of the first normal image (1300) are uniform, whereas the pixel values ​​of the pixels (1110) of the first defective image (1100) are irregular. Similarly, referring to FIGS. 12 and FIGS. 14, it can be seen that the pixel values ​​of the pixels (1210) included in the second defective image (1200) and the pixel values ​​of the pixels (1410) included in the second normal image (1400) are distinguishable.

[0088] Referring to FIGS. 11 to 14, the battery diagnostic device (10) can diagnose the battery as having a meandering defect based on a first defective image (1100) and a second defective image (1300). The battery diagnostic device (10) can diagnose the battery as being normal based on a first normal image (1200) and a second normal image (1400).

[0089] FIG. 15 is a flowchart illustrating the operation method of a battery diagnostic device according to one embodiment disclosed in this document.

[0090] Referring to FIG. 15, in operation 1500, the battery diagnostic device (10) can obtain a first image of the battery.

[0091] In operation 1510, the battery diagnostic device (10) can identify each of the electrode image corresponding to the electrode and the separator image corresponding to the separator in the first image using an artificial intelligence model.

[0092] In one embodiment, the controller (102) can obtain a second image in which the first image is labeled by specific regions (or specific objects) using an artificial intelligence model. The controller (102) can obtain a second image in which the first image is labeled by components included in the battery unit (16) using an artificial intelligence model.

[0093] In operation 1520, the battery diagnostic device (10) can diagnose the condition of the battery based on the electrode image and the separator image.

[0094] The battery diagnostic device (10) can diagnose whether a structural problem (e.g., a misalignment) has occurred inside the battery based on the electrode image and the separator image. That is, the battery diagnostic device (10) can diagnose whether the position of the electrode and the position of the separator are normal based on the electrode image and the separator image. The battery diagnostic device (10) can diagnose a misalignment if the position of the electrode protrudes above the position of the separator.

[0095] In one embodiment, the battery diagnostic device (10) can determine whether the winding state of the electrode assembly included in the battery is normal based on the electrode image and the separator image. The battery diagnostic device (10) can identify the number of winding turns based on the center point of the electrode assembly and identify an area corresponding to a number of winding turns of 1 turn or more and m turns or less (m: natural number). The battery diagnostic device (10) can identify a target area including a part of the electrode and a part of the separator included in the area, and diagnose whether the winding state at m turns is normal based on the target area. The battery diagnostic device (10) can diagnose whether a meandering defect has occurred at m turns based on the target area.

[0096] In one embodiment, the battery diagnostic device (10) can determine whether the winding state in m-turns is normal based on a first pixel value corresponding to a negative electrode included in the target area. According to an embodiment, the battery diagnostic device (10) may also diagnose whether the winding state in m-turns is normal based on a first pixel value and a second pixel value corresponding to each of the negative electrode and separator included in the target area. The battery diagnostic device (10) can diagnose it as normal if the first pixel value and the second pixel value fall within a threshold range. The battery diagnostic device (10) can diagnose it as a meandering defect if the first pixel value and the second pixel value fall within a threshold range.

[0097] FIG. 16 illustrates a computing system for executing operations of a battery diagnostic device according to an embodiment disclosed in this document.

[0098] Referring to FIG. 16, a computing system (1600) according to one embodiment disclosed in this document may include an MCU (1610), memory (1620), an input / output I / F (1630), and a communication I / F (1640).

[0099] The MCU (1610) may be a processor that executes various programs (e.g., battery diagnostic programs) stored in memory (1620), processes various data from these programs, and performs the functions of the battery diagnostic device (10) shown in FIGS. 1 to 15.

[0100] The memory (1620) can store various programs regarding the operation of the battery diagnostic device (10). In addition, the memory (1620) can store operation data of the battery diagnostic device (10).

[0101] These memories (1620) may be provided in multiple quantities as needed. The memories (1620) may be volatile memories or non-volatile memories. As volatile memories, the memory (1620) may use RAM, DRAM, SRAM, etc. As non-volatile memories, the memory (1620) may use ROM, PROM, EAROM, EPROM, EEPROM, flash memory, etc. The memories (1620) listed above are merely examples and are not limited to these examples.

[0102] The input / output I / F (1630) can provide an interface that enables data transmission and reception between an input device (not shown), such as a keyboard, mouse, or touch panel, an output device (not shown), and an MCU (1610).

[0103] The communication I / F (1640) is configured to transmit and receive various data to and from a server and may be various devices capable of supporting wired or wireless communication. For example, through the communication I / F (1640), programs for diagnosing abnormalities or various data may be transmitted and received from a separately provided external server.

[0104] Terms such as "include," "compose," or "have" as used above, unless specifically stated otherwise, mean that the relevant component may be inherent; therefore, they should be interpreted as allowing for the inclusion of additional components rather than excluding them. All terms, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments disclosed in this document pertain, unless otherwise defined. Commonly used terms, such as those defined in advance, should be interpreted in accordance with their meaning in the context of the relevant technology and, unless explicitly defined in this document, should not be interpreted in an ideal or overly formal sense.

[0105] The foregoing description is merely an illustrative explanation of the technical concept disclosed in this document, and a person skilled in the art to which the embodiments disclosed in this document pertain can make various modifications and variations within the scope of the essential characteristics of the embodiments disclosed in this document. Accordingly, the embodiments disclosed in this document are intended to explain, not limit, the technical concept of the embodiments disclosed in this document, and the scope of the technical concept disclosed in this document is not limited by these embodiments. The scope of protection of the technical concept disclosed in this document shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this document.

Claims

1. An interface for acquiring a first image regarding a battery; Using an artificial intelligence model trained to identify specific regions, an electrode image corresponding to the electrode and a separator image corresponding to the separator in the first image are each identified, and A controller comprising diagnosing the state of the battery based on the electrode image and the separator image, Battery diagnostic device.

2. In Claim 1, The above controller is, Using the above artificial intelligence model, a second image is obtained by labeling the first image according to the specific region, and Identifying the electrode image and the separator image based on the second image above, Battery diagnostic device.

3. In Claim 1, The above battery is a cylindrical battery comprising an electrode assembly in which the electrode and the separator are wound n times (n: natural number) in the form of a jelly roll, and The above controller is, Diagnosing whether the winding state of the electrode assembly is normal based on the electrode image and the separator image. Battery diagnostic device.

4. In Claim 3, The above controller is, Identifying the number of winding turns based on the center point of the electrode assembly in the first image above, and Identify the area where the above winding number corresponds to m-turns (m: natural number), and Identifying a target region including a portion of the electrode and a portion of the separator corresponding to the m-turn, and Diagnosing whether the winding state in the m-turn is normal based on the above target area, Battery diagnostic device.

5. In Claim 4, The above controller is, Diagnosing whether the winding state in the m-turn is normal based on the pixel value corresponding to the electrode included in the target area, Battery diagnostic device.

6. In Claim 5, The above controller is, Diagnosing as a meandering defect when the pixel value corresponding to the above electrode is not included in the threshold range, Battery diagnostic device.

7. The operation of acquiring a first image regarding the battery; The operation of identifying, respectively, an electrode image corresponding to an electrode and a separator image corresponding to a separator in the first image using an artificial intelligence model trained to identify a specific region based on pixel values; and A method including an operation to diagnose the state of the battery based on the electrode image and the separator image. Method of operation of a battery diagnostic device.

8. In Claim 7, The above-mentioned identifying operation is, The operation of obtaining a second image by labeling the first image according to the specific region using the artificial intelligence model, and A method comprising identifying the electrode image and the separator image based on the second image above. Method of operation of a battery diagnostic device.

9. In Claim 7, The above battery is a cylindrical battery comprising an electrode assembly in which the electrode and the separator are wound n times (n: natural number) in the form of a jelly roll, and The operation of diagnosing the condition of the above battery is, A method including diagnosing whether the winding state of the electrode assembly is normal based on the electrode image and the separator image. Method of operation of a battery diagnostic device.

10. In Claim 9, The operation of diagnosing whether the above winding state is normal is, The operation of identifying the number of winding turns based on the center point of the electrode assembly in the first image above, An operation to identify an area corresponding to m-turns (m: natural number) of the above winding rotation, An operation to identify a target region including a portion of the electrode and a portion of the separator corresponding to the m-turn, and A method including diagnosing whether the winding state in the m-turn is normal based on the above target area, Method of operation of a battery diagnostic device.

11. In Claim 10, The operation of diagnosing whether the winding state in the m-turn is normal based on the above target area is, A method including an operation to diagnose whether the winding state in the m-turn is normal based on a pixel value corresponding to the electrode included in the target area. Method of operation of a battery diagnostic device.

12. In Claim 11, The operation of diagnosing whether the winding state in the m-turn is normal based on the pixel value corresponding to the electrode included in the target area is, A method including diagnosing a meandering defect when the pixel value corresponding to the electrode is not included in a threshold range. Method of operation of a battery diagnostic device.

Images