Monitoring device and operation method thereof

Abstract

A monitoring device according to an embodiment disclosed in the present document may include: an image acquisition unit that acquires a captured image of at least one process processing device related to manufacturing of a battery cell; a state determination unit that inputs the acquired image into an artificial intelligence model to determine a state of a top insulator of the battery cell, and generates a first determination result by determining whether the battery cell has a defect; and a determination unit which determines whether the battery cell has a defect based on the first determination result.

Description

Technical Field

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of Korean Patent Application No. 10-2023-0043688 filed in the Korean Intellectual Property Office on April 3, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] Embodiments disclosed herein relate to monitoring devices and methods of operating the same. Background Art

[0004] Battery cells are classified into cylindrical, prismatic, and pouch types according to the type of battery case, and a cylindrical battery cell may include an electrode assembly, a battery case of a cylindrical metal can containing the electrode assembly and an electrolyte solution, and a cap assembly assembled over the cylindrical can.

[0005] The electrode assembly is formed by inserting a separator between the positive electrode plate and the negative electrode plate, the positive electrode plate is formed by coating the positive electrode collector with the positive electrode active material, and the negative electrode plate is formed by coating the negative electrode collector with the negative electrode active material, and the electrode assembly can be manufactured into a core-wound type, a stacked type, etc. according to the type of the battery case and accommodated in the battery case.

[0006] Battery cells can be manufactured through a series of manufacturing processes including electrode manufacturing, assembly, and forming. Here, the assembly process may include the operation of assembling the positive and negative plates manufactured by the electrode manufacturing process and injecting an electrolyte solution therein, and includes a slotting operation, a winding operation, an assembly operation, and a packaging operation.

[0007] The packaging process can be defined as the process of injecting and sealing the electrode assembly and electrolyte into the battery case. Cylindrical battery cells are manufactured by mounting the electrode assembly on a cylindrical metal can; welding the negative electrode tab extending from the negative electrode of the electrode assembly to the lower end of the can; and welding the positive electrode tab extending from the positive electrode of the electrode assembly to the top cap of the cap assembly while the electrode assembly and electrolyte are embedded.

[0008] A top insulator for covering an upper end of the electrode assembly is installed on an upper surface of the electrode assembly to electrically insulate the electrode assembly and the cap assembly, and the electrode terminal may be connected to an electrode lead and to an external terminal. Summary of the Invention

[0009] Technical issues

[0010] Embodiments disclosed herein are directed to providing a monitoring device capable of detecting a defective battery cell by accurately analyzing a state of a top insulator of the battery cell and an operating method thereof.

[0011] The objects of the embodiments disclosed herein are not limited to the above objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

[0012] Technical Solution

[0013] According to one embodiment disclosed herein, a monitoring device may include: an image acquisition unit configured to acquire images taken of at least one process processing device related to the manufacture of a battery cell; a state determination unit configured to generate a first determination result for determining whether the battery cell is defective by inputting the acquired image into an artificial intelligence model configured to determine the state of a top insulator of the battery cell; and a determination unit configured to determine whether the battery cell is defective based on the first determination result.

[0014] A method for operating a monitoring device according to an embodiment disclosed herein may include: an operation of acquiring an image taken of at least one process processing device related to the manufacture of a battery cell; an operation of inputting the acquired image into an artificial intelligence model configured to determine a state of a top insulator of the battery cell to generate a first determination result for determining whether the battery cell is defective; and an operation of determining whether the battery cell is defective based on the first determination result.

[0015] Beneficial effects

[0016] According to a monitoring device and an operating method thereof according to one embodiment disclosed herein, a defective battery cell may be detected by accurately analyzing the state of a top insulator of the battery cell.

[0017] Effects of the monitoring device and the operating method thereof according to the disclosure of this document are not limited to the above-mentioned effects, and those skilled in the art will be able to clearly understand other effects that are not mentioned based on the disclosure of this document. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a block diagram of a monitoring device according to one embodiment of the present disclosure.

[0019] Figure 2 A tank assembly according to one embodiment of the present disclosure is shown.

[0020] Figure 3 is a view illustrating a battery cell having a top insulator and a battery cell without a top insulator according to one embodiment disclosed herein.

[0021] Figure 4An image showing foreign matter present inside a top insulator of a battery cell according to one embodiment disclosed herein is shown.

[0022] Figure 5 An image showing a raised top insulator of a battery cell according to one embodiment disclosed herein is shown.

[0023] Figure 6 is a view showing a state in which cracks exist in a beading region of a battery cell according to one embodiment disclosed herein.

[0024] Figure 7 is a flowchart illustrating a method of operating a monitoring device according to one embodiment of the present disclosure.

[0025] In the description of the drawings, the same or similar reference numerals may be used for the same or similar components. DETAILED DESCRIPTION

[0026] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that this is not intended to limit the present invention to specific embodiments and includes various modifications, equivalents and / or alternatives of the embodiments of the present invention.

[0027] It should be understood that the embodiments of this document and the terms used herein are not intended to limit the technical features described herein to specific embodiments, and include various variations, equivalents, and / or alternatives of the corresponding embodiments. In 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 item or multiple items, unless the relevant context clearly dictates otherwise.

[0028] In this document, each of 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 or all possible combinations of items listed together in the corresponding phrases among these phrases. Terms such as “first,” “second,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used simply to distinguish a corresponding component from another component and do not limit the corresponding component in another aspect (e.g., importance or order).

[0029] When a component (e.g., a first component) is described as being “coupled,” “connected,” or “engaged” to another component (e.g., a second component) with or without the term “functionally” or “communicatively” or “coupled” or “connected,” it means that the component may be connected to the other component directly (e.g., in a wired or wireless manner) or indirectly (e.g., via a third component).

[0030] The methods according to various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or distributed via an application store (e.g., downloading or uploading), or distributed directly online between two user devices. In the case of online distribution, at least some of the computer program product may be at least temporarily stored or temporarily generated in a device-readable storage medium (such as a memory of a manufacturer's server, an application store's server, or a relay server).

[0031] According to embodiments disclosed herein, each component (e.g., module or program) of the above-mentioned components may include a single object or multiple objects, and some of the multiple objects may be individually arranged in another component. According to embodiments disclosed herein, one or more components or operations in the above-mentioned corresponding components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (e.g., module or program) may be integrated into one component. In this case, the integrated component may bring into play one or more functions of each component in multiple components, which are identical or similar to the functions brought into play by the corresponding components in multiple components before integration. According to embodiments disclosed herein, the operations performed by modules, programs or other components may be performed sequentially, in parallel, repeatedly or heuristically, or one or more operations may be performed or omitted in different orders, or one or more other operations may be added.

[0032] Figure 1 is a block diagram illustrating a configuration of a monitoring device 100 according to one embodiment disclosed herein. Figure 2 A tank assembly 200 is shown according to one embodiment disclosed herein.

[0033] In one embodiment, the monitoring device 100 can determine the status of the battery cell 105 based on an image of the battery cell 105 captured by the image acquisition device 103. Here, the image acquisition device 103 may include a camera module. Here, the battery cell 105 may be a battery cell or a can assembly 200 included in the battery cell. Here, the can assembly 200 may include a cylindrical can 210, a top insulator (TI) 220, a hole 230 within the TI 220, and a joint 240 exposed through the hole 230.

[0034] In one embodiment, the monitoring device 100 can determine the status of the battery cell 105 based on the results of a rule-based inspection of the battery cell 105 and / or the results of an artificial intelligence model-based inspection. In one embodiment, the rule-based inspection can include checking at least one of whether the battery cell 105's TI 220 is present, whether a foreign object is present in the TI 220, whether a foreign object is present outside the TI 220, or whether the TI 220 is lifted. In one embodiment, the artificial intelligence model-based inspection can include checking at least one of whether the TI 220 is present, whether a foreign object is present in the TI 220, whether a foreign object is present outside the TI 220, whether the TI 220 is lifted, and whether a curling crack is present. Depending on the embodiment, the artificial intelligence model-based inspection can include more items that can be inspected than the rule-based inspection. Here, the exterior of the TI 220 refers to the area between the outer periphery of the TI 220 and the cylindrical can 210, and can be the area where the TI 220 is connected to the cylindrical can 210 in a curling manner. Additionally, the interior of the TI 220 is an area within the outer periphery of the TI 220 and may be an area within the curling region.

[0035] In one embodiment, when both the rule-based inspection result and the artificial intelligence model-based inspection result of the battery cell 105 indicate normal, the monitoring device 100 may determine that the battery cell 105 is in good condition. In one embodiment, when at least one of the rule-based inspection result or the artificial intelligence model-based inspection result of the battery cell 105 indicates a fault, the monitoring device 100 may determine that the battery cell 105 is a defective product.

[0036] Hereinafter, components of the monitoring device 100 will be schematically described, and then a specific method of operating the monitoring device 100 will be described.

[0037] refer to Figure 1 , the monitoring device 100 may include a communication circuit 110, a memory 120 and a processor 130. According to this embodiment, Figure 1 The monitoring device 100 shown may also include Figure 1 At least one component other than those shown (eg, a display, an input device, or an output device).

[0038] In one embodiment, the communication circuit 110 may establish a wired communication channel and / or a wireless communication channel between the monitoring device 100 and the image acquisition device 103 , and transmit and receive data with the image acquisition device 103 via the established communication channel.

[0039] In one embodiment, memory 120 may include volatile memory and / or non-volatile memory.

[0040] In one embodiment, memory 120 may store data used by at least one component of monitoring device 100 (e.g., processor 130). For example, the data may include program 125 (or instructions related thereto), input data, or output data. In one embodiment, the instructions, when executed by processor 130, may enable monitoring device 100 to perform the operations defined by the instructions.

[0041] In one embodiment, the memory 120 may include a program 125 (e.g., an artificial intelligence model learning unit 141, artificial intelligence models 145, 146, 147 and 148, an image acquisition unit 150, a state determination unit 160, an analysis unit 170 and / or a determination unit 180).

[0042] In one embodiment, processor 130 may include a central processing unit, an application processor, a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor.

[0043] In one embodiment, the processor 130 can control at least one other component (e.g., a hardware or software component) of the monitoring device 100 connected to the processor 130 by means of the execution program 125 (e.g., the artificial intelligence model learning unit 141, artificial intelligence models 145, 146, 147 and 148, the image acquisition unit 150, the state determination unit 160, the analysis unit 170 and / or the determination unit 180) and perform various data processing or calculations.

[0044] In one embodiment, the artificial intelligence model learning unit 141 may train artificial intelligence models 145, 146, 147, and 148 based on the training data. In one embodiment, the artificial intelligence models 145, 146, 147, and 148 may be models trained to generate output results for different purposes based on different training data.

[0045] In one embodiment, the image acquisition unit 150 may acquire an image of the battery cell 105 from the image acquisition device 103. In one embodiment, the state determination unit 160 may determine the state of the TI 210 in the tank assembly 200 based on the image of the battery cell 105. In one embodiment, the state determination unit 160 may determine the state of the TI 210 in the tank assembly 200 by inputting the image of the battery cell 105 into the artificial intelligence models 145, 146, 147, and 148. In one embodiment, the analysis unit 170 may analyze the state of the TI 210 in the tank assembly 200 by performing a rule-based inspection on the image of the battery cell 105. In one embodiment, the determination unit 180 may determine whether the battery cell 105 is a qualified product based on the determination results of the state determination unit 160 and / or the analysis unit 170.

[0046] In the following, reference will be made to Figures 3 to 6 A detailed description of a method allows the monitoring device 100 to determine the state of the battery cell 105 with the help of the artificial intelligence model learning unit 141, artificial intelligence models 145, 146, 147 and 148, the image acquisition unit 150, the state determination unit 160, the analysis unit 170 and / or the determination unit 180.

[0047] Training of AI models

[0048] Figure 3 is a view showing a battery cell with IT and a battery cell without TI according to one embodiment disclosed herein.

[0049] In one embodiment, the artificial intelligence model learning unit 141 may input the battery cell image into the artificial intelligence model 145. In one embodiment, the artificial intelligence model 145 may be a model capable of polynomial classification (a convolutional neural network (CNN)-based model). In one embodiment, the artificial intelligence model 145 may be configured to classify whether TI is present based on the battery cell images 310 and 320.

[0050] In one embodiment, the data used to train the artificial intelligence model 145 may include an image 310 of a battery cell in which TI normally exists and an image 320 without TI. In one embodiment, the images 310 and 320 used to train the artificial intelligence model 145 may be provided in advance.

[0051] In one embodiment, the artificial intelligence model 145 can be configured to classify an input image into at least two states based on training data. Here, the at least two states can include a state where TI normally exists in the tank assembly and a state where TI does not exist in the tank assembly.

[0052] Figure 4 An image showing foreign matter present inside the TI of a battery cell according to one embodiment disclosed herein is shown. Figure 4 The image 410 includes an image 410 , in which a foreign object 415 exists inside the TI, and an image 420 , which magnifies some areas of the image 410 including the foreign object 415 .

[0053] In one embodiment, the artificial intelligence model learning unit 141 may input the image of the battery cell into the artificial intelligence model 146. In one embodiment, the artificial intelligence model 146 may be a model capable of polynomial classification. In one embodiment, the artificial intelligence model 146 may be trained to identify the foreign object 415 based on the image 410 of the battery cell. Here, Figure 4 Only images 410 in which foreign matter 415 is present are shown, but this is merely an example. In one embodiment, the artificial intelligence model 146 can be trained to perform multinomial classification using images 410 in which foreign matter 415 is present and images (not shown) without foreign matter 415.

[0054] In one embodiment, the artificial intelligence model 146 may be trained to classify an input image into at least two states based on training data. Here, the at least two states may include a state where a foreign object exists and a state where no foreign object exists.

[0055] Figure 5 An image showing improved TI of a battery cell according to one embodiment disclosed herein. Figure 5 The image 510 includes an image 510 in which there is elevation within the TI, and an image 520 that zooms in on a region 515 of the image 510 where there is elevation.

[0056] In one embodiment, the artificial intelligence model learning unit 141 may input the battery cell image into the artificial intelligence model 147. In one embodiment, the artificial intelligence model 147 may be a model capable of polynomial classification. In one embodiment, the artificial intelligence model 147 may be trained to identify whether the TI is elevated based on the battery cell image 510. Here, the elevated TI may occur in the inner region of the TI adjacent to the cylindrical can.

[0057] In one embodiment, the data used to train the artificial intelligence model 147 may include images 510 in which TI is improved and images (not shown) in which TI is not improved. In one embodiment, images used to train the artificial intelligence model 147 may be provided in advance.

[0058] In one embodiment, the artificial intelligence model 147 may be trained to identify lifted regions 515 in an input image based on training data.

[0059] Figure 6 is a view showing a state in which cracks exist in a beading region of a battery cell according to one embodiment disclosed herein. Figure 6 The image 610 includes images 610, in which a crack exists in the curling region outside the TI, and 620, which magnifies the region 615 where the crack exists in the image 610. Referring to the image 620, it can be seen that a crack exists in a region 625.

[0060] In one embodiment, the artificial intelligence model learning unit 141 may input the image of the battery cell into the artificial intelligence model 148. In one embodiment, the artificial intelligence model learning unit 141 may train the artificial intelligence model 148 to classify the curling state of the can assembly of the battery cell based on the image 610. In one embodiment, the artificial intelligence model 148 may be a model capable of polynomial classification.

[0061] In one embodiment, the data for the artificial intelligence model 148 may include an image 610 in which cracks are present in the hem region and an image (not shown) in which cracks are not present in the hem region. In one embodiment, images for training the artificial intelligence model 148 may be provided in advance.

[0062] In one embodiment, the artificial intelligence model 148 may be trained to classify an input image into at least two states based on training data, wherein the at least two states may include a state in which cracks are present in the hem region and a state in which cracks are not present in the hem region.

[0063] Status determination with the help of artificial intelligence models

[0064] In one embodiment, the state determination unit 160 may determine the state of the tank assembly based on the image of the battery cell 105. In one embodiment, the state determination unit 160 may determine the state of the tank assembly by inputting the image of the battery cell 105 into the artificial intelligence model 145. In one embodiment, the state determination unit 160 may determine the state of the tank assembly of the battery cell 105 based on the output of the artificial intelligence model 145. For example, the state determination unit 160 may determine the state of the tank assembly of the battery cell 105 based on the state of the battery cell 105 classified by the artificial intelligence models 145 to 148 (e.g., whether there is a TI, whether there is a foreign object inside the TI, whether there is a foreign object outside the TI, whether there is a lift of the TI, or whether there is a crack in the hem area).

[0065] In one embodiment, when TI is normally present in the battery cell 105, the state determination unit 160 may determine that the state of the tank assembly is normal. In one embodiment, when TI is not present, the state determination unit 160 may determine that the state of the tank assembly is defective.

[0066] In one embodiment, when there is no foreign matter inside and / or outside the TI in the battery cell 105, the state determination unit 160 may determine that the state of the tank assembly is normal. In one embodiment, when there is foreign matter inside and / or outside the TI, the state determination unit 160 may determine that the tank assembly is in a defective state.

[0067] In one embodiment, the state determination unit 160 may determine that the state of the tank assembly is normal when the TI is not lifted in the battery unit 105. In one embodiment, the state determination unit 160 may determine that the state of the tank assembly is defective when the TI is lifted.

[0068] In one embodiment, when there is no crack in the curling of the battery cell 105, the state determination unit 160 may determine that the state of the tank assembly is normal. In one embodiment, when there is a crack in the curling, the state determination unit 160 may determine that the tank assembly is defective.

[0069] In one embodiment, the state determination unit 160 may send a state determination result of the battery cell 105 to the determination unit 180 .

[0070] In one embodiment, the analysis unit 170 may analyze the status of the TI 210 in the tank assembly 200 by performing a rule-based inspection on the image of the battery cell 105. Here, the rule-based inspection may be an inspection that determines whether the battery cell 105 is defective based on grayscale information of the image of the battery cell 105.

[0071] For example, the analysis unit 170 may determine at least one of whether the TI 220 is present in the battery cell 105, whether a foreign object is present inside the TI 220, whether a foreign object is present outside the TI 220, or whether the TI 220 is elevated based on the grayscale information of the image of the battery cell 105, and generate a determination result. According to one embodiment, the analysis unit 170 may sequentially determine whether the TI 220 is present in the battery cell 105, whether a foreign object is present inside the TI 220, whether a foreign object is present outside the TI 220, or whether the TI 220 is elevated based on the grayscale information of the image of the battery cell 105.

[0072] In one embodiment, the analyzing unit 170 may send a determination result of the state of the battery unit 105 to the determining unit 180 .

[0073] In one embodiment, the number of inspection items that can be checked by the state determination unit 160 can be greater than the number of inspection items that can be checked by the analysis unit 170. In other words, the number of inspection items based on the artificial intelligence model can be greater than the number of inspection items based on grayscale information. For example, while the state determination unit 160 can check whether there are cracks in the bead, the analysis unit 170 may not check for them.

[0074] In one embodiment, the determination unit 180 may determine whether the battery cell 105 is a qualified product based on the determination results of the status determination unit 160 and / or the analysis unit 170. For example, when the determination results of the status determination unit 160 and the analysis unit 170 both indicate normal, the determination unit 180 may determine that the battery cell 105 is a qualified product. For example, when the determination result of at least one of the status determination unit 160 or the analysis unit 170 indicates a defect, the determination unit 180 may determine that the battery cell 105 is not a qualified product.

[0075] As described above, the monitoring device 100 according to one embodiment disclosed herein may detect a defective battery cell by accurately analyzing the TI state of the battery cell.

[0076] exist Figure 1 , the artificial intelligence model of program 125 is shown separately, but this is only an example. In one embodiment, artificial intelligence models 145, 146, 147 and 148 can be implemented as one artificial intelligence model.

[0077] Figure 7 FIG. 1 is a diagram illustrating a method of operating the monitoring device 100 according to an embodiment disclosed herein. Figures 1 to 6 To describe Figure 7 .

[0078] refer to Figure 7 In operation 710 , the monitoring device 100 may acquire an image. Here, the image may be an image of the battery cell 105 acquired by the image acquisition device 103 .

[0079] In operation 720, the monitoring device 100 may perform a rule-based inspection. In one embodiment, the monitoring device 100 may perform a rule-based inspection based on grayscale information of the image.

[0080] For example, the monitoring device 100 may determine at least any one of the following based on the grayscale information of the image of the battery cell 105: whether the TI 220 exists in the battery cell 105, whether a foreign object exists inside the TI 220, whether a foreign object exists outside the TI 220, or whether the TI 220 is elevated, and generate a determination result. According to one embodiment, the monitoring device 100 may sequentially determine whether the TI 220 exists in the battery cell 105, whether a foreign object exists inside the TI 220, whether a foreign object exists outside the TI 220, or whether the TI 220 is elevated based on the grayscale information of the image of the battery cell 105.

[0081] In operation 730 , the monitoring device 100 may perform an artificial intelligence model-based inspection. For example, the monitoring device 100 may perform an artificial intelligence model-based inspection of the image based on previously trained artificial intelligence models 145 , 146 , 147 , and 148 .

[0082] In one embodiment, for example, the monitoring device 100 may determine the state of the tank assembly by inputting an image of the battery cell 105 into the artificial intelligence model 145. In one embodiment, the monitoring device 100 may determine the state of the tank assembly of the battery cell 105 based on the output of the artificial intelligence model 145. For example, the monitoring device 100 may determine the state of the tank assembly of the battery cell 105 based on the state of the battery cell 105 classified by the artificial intelligence models 145 to 148 (e.g., whether there is a TI, whether there is a foreign object inside the TI, whether there is a foreign object outside the TI, whether there is a lift of the TI, or whether there is a crack in the hem area).

[0083] In one embodiment, when TI is normally present in the battery cell 105, the monitoring device 100 may determine that the state of the tank assembly is normal. In one embodiment, when TI is not present, the monitoring device 100 may determine that the state of the tank assembly is defective.

[0084] In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is normal when there is no foreign matter inside and / or outside the TI in the battery cell 105. In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is defective when there is foreign matter inside and / or outside the TI.

[0085] In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is normal when the TI is not lifted in the battery unit 105. In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is defective when the TI is lifted.

[0086] In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is normal when there is no crack in the crimp of the battery cell 105. In one embodiment, the monitoring device 100 may determine that the state of the tank assembly is defective when there is a crack in the crimp.

[0087] In operation 740 , the monitoring device 100 may determine whether a defect exists based on the inspection result.

[0088] In one embodiment, when both the rule-based inspection result and the artificial intelligence model-based inspection result indicate normality, the monitoring device 100 may determine that the battery cell 105 is a qualified product.

Claims

1. A monitoring device, comprising: an image acquisition unit configured to acquire an image of at least one process device related to the manufacture of the battery cell; a state determination unit configured to generate a first determination result for determining whether the battery cell is defective by inputting the acquired image into an artificial intelligence model configured to determine a state of a top insulator of the battery cell; as well as A determining unit is configured to determine whether the battery cell is defective based on the first determination result.

2. The monitoring device according to claim 1, further comprising an analyzing unit configured to generate a second determination result for determining whether the battery cell is defective based on grayscale information of the acquired image. in, The determination unit determines whether the battery cell is defective based on the first determination result and the second determination result.

3. The monitoring device according to claim 2, wherein: The number of inspection items based on the artificial intelligence model is greater than the number of inspection items based on the grayscale information.

4. The monitoring device according to claim 1, wherein: The artificial intelligence model includes an artificial intelligence model configured to detect whether the top insulator is in the battery cell, whether a foreign object is inside the top insulator, whether a foreign object is outside the top insulator, or whether the top insulator is lifted based on the image.

5. The monitoring device according to claim 1, wherein: The artificial intelligence model includes an artificial intelligence model configured to detect whether there is a crack in the crimp of the battery cell based on the image.

6. A method of operating a monitoring device, the method comprising: An operation of acquiring an image captured of at least one process device associated with the manufacture of a battery cell; an operation of generating a first determination result for determining whether the battery cell is defective by inputting the acquired image into an artificial intelligence model configured to determine a state of a top insulator of the battery cell; as well as An operation of determining whether the battery cell is defective based on the first determination result.

7. The method according to claim 6, further comprising an operation of generating a second determination result for determining whether the battery cell is defective based on grayscale information of the acquired image, in, The operation of determining whether the battery cell is defective includes determining whether the battery cell is defective based on the first determination result and the second determination result.

8. The method according to claim 7, wherein: The number of inspection items based on the artificial intelligence model is greater than the number of inspection items based on the grayscale information.

9. The method according to claim 6, wherein: The artificial intelligence model includes an artificial intelligence model configured to detect whether the top insulator is in the battery cell, whether a foreign object is inside the top insulator, whether a foreign object is outside the top insulator, or whether the top insulator is lifted based on the image.

10. The method according to claim 6, wherein: The artificial intelligence model includes an artificial intelligence model configured to detect whether there is a crack in the crimp of the battery cell based on the image.

Images