Monitoring device and method of operation thereof

Abstract

A monitoring device according to one embodiment disclosed in this document may include an image acquisition unit that acquires an image of at least one process processing device related to the manufacture of a battery cell; an analysis unit that inputs the acquired image into an artificial intelligence model for determining a welding condition of the battery cell to generate a first judgment result determining whether or not the battery cell is defective; and a determination unit that determines whether the battery cell is defective based on the first judgment result.

Description

[Technical field]

[0001] [CROSS REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of priority based on Korean Patent Application No. 10-2022-0005799, filed on January 14, 2022, and all contents disclosed in the documents of that Korean patent application are incorporated herein by reference.

[0002] SUMMARY OF THE DISCLOSURE The embodiments disclosed herein relate to a monitoring device and a method of operation thereof. [Background technology]

[0003] An electric vehicle obtains power by charging a battery cell with electricity supplied from an external source and then driving a motor with the voltage charged in the battery cell. A battery cell for an electric vehicle is manufactured by housing an electrode assembly in a battery case and injecting an electrolyte into the battery case.

[0004] Battery cells are classified into cylindrical, prismatic, and pouch types depending on the type of battery case. A cylindrical battery cell includes an electrode assembly, a cylindrical metal can battery case that contains the electrode assembly and an electrolyte, and a cap assembly that is assembled on the top of the cylindrical can.

[0005] Here, the positive electrode tab of the cylindrical battery cell is welded to the top cap of the cap assembly. However, if a part or the whole of the welded portion comes off due to an external impact or poor welding, the battery cell may deteriorate or explode. Therefore, it is important to inspect the battery cells to prevent poorly welded battery cells from being shipped out. Summary of the Invention [Problem to be solved by the invention]

[0006] One objective of the embodiments disclosed herein is to provide a monitoring device and an operating method thereof that can accurately analyze the welding condition of battery cells to detect defective battery cells.

[0007] The technical problems of the embodiments disclosed in this document are not limited to the technical problems mentioned above, and other technical problems not mentioned may be clearly understood by a person skilled in the art from the following description. [Means for solving the problem]

[0008] A monitoring device according to one embodiment disclosed in this document may include an image acquisition unit that acquires an image of at least one process processing device related to the manufacture of a battery cell; an analysis unit that inputs the acquired image into an artificial intelligence model for determining a welding condition of the battery cell to generate a first judgment result determining whether the battery cell is defective or not; and a judgment unit that determines whether the battery cell is defective or not based on the first judgment result.

[0009] A method of operating a monitoring device according to one embodiment disclosed in this document may include the steps of: acquiring an image of at least one process processing device related to the manufacture of a battery cell; inputting the acquired image into an artificial intelligence model for determining a welding condition of the battery cell to generate a first judgment result determining whether the battery cell is defective or not; generating a second judgment result determining whether the battery cell is defective or not based on gray level information of the acquired image; and determining whether the battery cell is defective or not based on the first judgment result and the second judgment result. Effect of the Invention

[0010] According to an embodiment of the monitoring device and its operating method disclosed herein, the welding condition of the battery cells can be accurately analyzed to detect defective battery cells. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram generally illustrating a battery processing system according to one embodiment disclosed herein. [Diagram 2] FIG. 1 is a block diagram showing the configuration of a monitoring device according to an embodiment disclosed in this document. [Diagram 3] 1 is a welding condition classification table according to one embodiment disclosed herein. [Figure 4] 1 is a graph illustrating the change in tensile strength with change in weld length according to one embodiment disclosed herein. [Diagram 5] FIG. 2 is a diagram of a classification of battery units according to one embodiment disclosed herein. [Figure 6] FIG. 1 illustrates a welding location for a battery cell according to one embodiment disclosed herein. [Figure 7] FIG. 2 illustrates a welded area of ​​a battery cell according to one embodiment disclosed herein. [Figure 8] FIG. 1 illustrates a welding configuration for a battery cell according to one embodiment disclosed herein. [Figure 9] 1 illustrates a method of operation of a monitoring device according to one embodiment disclosed herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Some embodiments disclosed in this document will be described in detail with reference to the drawings. When referring to components in each drawing, attention should be paid to using the same reference numerals as much as possible for the same components even if they are displayed in different drawings. In addition, when describing the embodiments disclosed in this document, if a detailed description of related known configurations or functions is deemed to hinder understanding of the embodiments disclosed in this document, the detailed description will be omitted.

[0013] In describing the components of the embodiments disclosed in this document, terms such as first, second, A, B, (a), (b) and the like may be used. Such terms are intended to distinguish the components from other components, and do not limit the essence, order, or sequence of the components. In addition, unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong. Terms similar to those defined in commonly used dictionaries should be interpreted as meanings consistent with the meanings they have in the context of the relevant art, and should not be interpreted in an ideal and overly formal sense unless expressly defined in this document.

[0014] According to various embodiments, the battery may include a battery cell, which is a basic unit of a battery that can charge and discharge electrical energy for use. The battery cell may be, but is not limited to, a lithium ion (Li-ion) battery, a lithium ion polymer (Li-ion polymer) battery, a nickel cadmium (Ni-Cd) battery, a nickel metal hydride (Ni-MH) battery, or the like. The battery cell may supply power to a target device (not shown). To this end, the battery cell may be electrically connected to the target device. Here, the target device may include an electrical, electronic, or mechanical device that operates by receiving power from a battery pack (not shown) including a plurality of battery cells. For example, the target device may be, but is not limited to, small products such as digital cameras, P-DVDs, MP3Ps, mobile phones, PDAs, portable game devices, power tools, and electric bicycles, as well as large products that require high output such as electric vehicles and hybrid vehicles, and power storage devices or backup power storage devices that store surplus generated power or new raw energy.

[0015] A battery cell may include an electrode assembly, a battery case in which the electrode assembly is housed, and an electrolyte that is injected into the battery case to activate the electrode assembly. The electrode assembly is formed by interposing a separator between a positive electrode plate formed by coating a positive electrode collector with a positive electrode active material and a negative electrode plate formed by coating a negative electrode collector with a negative electrode active material, and the electrode assembly may be manufactured into a jelly roll type, a stack type, or the like according to the type of battery case and housed inside the battery case. The battery case serves as an exterior material that maintains the shape of the battery and protects it from external impact, and the battery cells may be classified into a cylindrical type, a square type, and a pouch type according to the type of battery case.

[0016] According to the embodiment, the battery cell may be manufactured through a series of manufacturing processes including an electrode manufacturing process, an assembly process, a chemical formation process, etc. Here, the assembly process may include a process of assembling a positive electrode plate and a negative electrode plate manufactured through an electrode manufacturing process and injecting an electrolyte, and may include a notching process, a winding process, an assembly process, and a packaging process.

[0017] The packaging process can be defined as a process of injecting an electrode assembly and an electrolyte into a battery case and sealing it. In the case of a cylindrical battery cell, the electrode assembly is attached to a cylindrical metal can, a negative electrode tab extending from the negative electrode of the electrode assembly is welded to the bottom of the can, and a positive electrode tab extending from the positive electrode of the electrode assembly with the electrode assembly and electrolyte built in is welded to a top cap of a cap assembly.

[0018] However, if a part or the entire welded portion of the positive electrode tab of the electrode assembly and the top cap of the cap assembly come off due to an external impact or poor welding, i.e., if the positive electrode tab and the top cap are weakly welded, the battery cell may deteriorate or explode. Therefore, it is important to inspect battery cells to prevent poorly welded battery cells from being distributed.

[0019] Hereinafter, the battery process system will be described by taking an assembly process system as an example.

[0020] FIG. 1 is a diagram generally illustrating a battery processing system according to one embodiment disclosed herein.

[0021] Referring to FIG. 1, a battery processing system may include a monitoring device 100 and at least one processing device 210 , 220 , 230 .

[0022] The monitoring device 100 may collect and analyze data from at least one of the process processing devices 210, 220, and 230 operating in the battery processing system in real time. The monitoring device 100 may collect and analyze data from at least one of the process processing devices 210, 220, and 230.

[0023] For example, the monitoring device 100 may collect and analyze data or graph data generated in the battery processing system, such as the progress of the battery processing system process, whether an alarm has occurred, temperature, pressure, quantity, and the like.

[0024] The monitoring device 100 can acquire images of at least one of the process processing devices 210, 220, and 230 captured by a plurality of camera modules (not shown).

[0025] The monitoring device 100 may determine whether a battery cell is defective based on an image captured by at least one of the process treatment devices 210, 220, and 230. According to an embodiment, the monitoring device 100 may determine whether there is weak welding between a positive electrode tab and a top cap of a battery cell based on an image captured by at least one of the process treatment devices 210, 220, and 230.

[0026] The at least one process processing device 210, 220, 230 may include a first process processing device 210, a second process processing device 220, and a third process processing device 230. Although the at least one process processing device 210, 220, 230 is illustrated as being three in FIG. 1, the number is not limited to three. According to an embodiment, the at least one process processing device 210, 220, 230 may include n devices (n is a natural number equal to or greater than 1).

[0027] According to an embodiment, at least one of the process processing devices 210, 220, 230 may weld a positive electrode tab of an electrode assembly of a battery cell and a top cap of a cap assembly.

[0028] FIG. 2 is a block diagram showing a configuration of a monitoring device 100 according to an embodiment disclosed in this document.

[0029] In one embodiment, the monitoring device 100 can determine the status of the battery unit 105 based on images of the battery unit 105 acquired by the image acquisition device 103. Here, the image acquisition device 103 can correspond to the multiple camera modules (not shown) described in FIG. 1. Here, the battery unit 105 can be a battery cell.

[0030] In one embodiment, the monitoring device 100 may determine the status of the battery unit 105 based on a rule-based inspection result and / or an artificial intelligence model-based inspection result for the battery unit 105. In one embodiment, the rule-based inspection may include inspection for at least one of the presence or absence of a can of the battery unit 105, the presence or absence of a top cap of the can assembly, the center distance between the can and the top cap, the position of the positive tab, or the presence or absence of over-welding. In one embodiment, the artificial intelligence model-based inspection may include inspection for at least one of the presence or absence of a top cap of the cap assembly, the welding position, the welding area, or the welding shape.

[0031] In one embodiment, the monitoring device 100 may determine that the battery unit 105 is in a good condition when the rule-based test result and the artificial intelligence model-based test result for the battery unit 105 are all normal. In one embodiment, the monitoring device 100 may determine that the battery unit 105 is in a bad condition when at least one of the rule-based test result or the artificial intelligence model-based test result for the battery unit 105 is bad.

[0032] Below, the components of the monitoring device 100 will be briefly described, and then a specific operation method of the monitoring device 100 will be described.

[0033] 2, the monitoring device 100 may include a communication circuit 110, a memory 120, and a processor 130. Depending on the embodiment, the monitoring device 100 shown in FIG. 2 may further include at least one component (e.g., a display, an input device, or an output device) other than the components shown in FIG.

[0034] In one embodiment, the communication circuitry 110 can establish a wired and / or wireless communication channel between the monitoring device 100 and the image capture device 103 and transmit and receive data to and from the image capture device 103 via the established communication channel.

[0035] In one embodiment, memory 120 may include volatile memory and / or non-volatile memory.

[0036] In one embodiment, memory 120 may store data for use by at least one component (e.g., processor 130) of monitoring device 100. For example, the data may include programs 125 (or instructions therefor), input data, or output data. In one embodiment, the instructions, when executed by processor 130, may cause monitoring device 100 to perform operations defined by the instructions.

[0037] In one embodiment, the memory 120 may include programs 125 (e.g., an artificial intelligence model learning unit 141, artificial intelligence models 145, 146, 147, 148, an image acquisition unit 150, a state determination unit 160, a position detection unit 170, an area detection unit 180, an analysis unit 190, and / or a judgment unit 195).

[0038] In one embodiment, the 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.

[0039] In one embodiment, the processor 130 can execute the program 125 (e.g., the artificial intelligence model learning unit 141, the artificial intelligence models 145, 146, 147, 148, the image acquisition unit 150, the state judgment unit 160, the position detection unit 170, the area detection unit 180, the analysis unit 190, and / or the judgment unit 195) to control at least one other component (e.g., a hardware or software component) of the monitoring device 100 connected to the processor 130, and can perform various data processing or calculations.

[0040] In one embodiment, the artificial intelligence model learning unit 141 can train the artificial intelligence models 145, 146, 147, and 148 based on the learning data. In one embodiment, the artificial intelligence models 145, 146, 147, and 148 may be models trained to generate output results with different purposes based on different learning data.

[0041] In one embodiment, the image acquiring unit 150 can acquire an image of the battery unit 105 from the image acquiring device 103. In one embodiment, the image acquiring unit 150 can automatically log an image captured by the image acquiring device 103 of at least one process processing device 210, 220, 230. For example, the image acquiring unit 150 can collect an image captured by at least one process processing device 210, 220, 230 by setting a sampling period of automatic logging of image data to 0.1 sec. Here, the image acquiring device 103 can acquire operation data of at least one process processing device 210, 220, 230. The image acquiring device 103 can acquire an image captured by at least one process processing device 210, 220, 230 related to the manufacturing of the battery unit 105. In one embodiment, the image acquiring device 103 can acquire an image of at least one process processing device 210, 220, 230 welding a positive electrode tab of an electrode assembly of the battery unit 105 and a top cap of a cap assembly.

[0042] In one embodiment, the status determination unit 160 may determine the status of the can assembly based on an image of the battery unit 105. In one embodiment, the position detection unit 170 may determine the status of the welding position based on an image of the battery unit 105. In one embodiment, the area detection unit 180 may detect and / or crop the welding area in an image of the welding position of the battery unit 105. In one embodiment, the analysis unit 190 may analyze the welding status based on an image cropped from the welding position. In one embodiment, the determination unit 195 may determine whether the quality of the battery unit 105 is good or bad based on the determination results of the status determination unit 160, the position detection unit 170, and / or the analysis unit 190.

[0043] Hereinafter, with reference to Figures 3 to 8, a method in which the monitoring device 100 determines the status of the battery unit 105 through the artificial intelligence model learning unit 141, the artificial intelligence models 145, 146, 147, 148, the image acquisition unit 150, the status judgment unit 160, the position detection unit 170, the area detection unit 180, the analysis unit 190, and / or the judgment unit 195 will be described in detail.

[0044] Fig. 3 is a weld condition classification table according to one embodiment disclosed herein. Fig. 4 is a graph showing the change in tensile strength with the change in weld length according to one embodiment disclosed herein.

[0045] The battery unit 105 may determine whether it is normal or not based on various criteria. For example, the battery unit 105 may determine whether it is normal or not based on a criterion regarding the welding state and / or a criterion regarding the tensile strength. The criterion for determining whether the battery unit 105 is normal or not may be set in advance. For example, the welding state of the battery unit 105 may be determined to be normal if the welding length (or bead length) of at least one welding line is 75% or more of the welding section, and the tensile strength of the battery unit 105 may be determined to be normal if it is 0.4 kgf or more. Here, the weld bead may be a deposited metal solidified on a base material when a welding operation is performed along a welding line.

[0046] Although the welding state of the battery unit 105 can be confirmed by photographing an image of the battery unit 105, it is difficult to confirm the tensile strength of the battery unit 105 by an image.

[0047] 3, in type #1, the welding state of the battery unit 105 can be determined as normal since the welding length of two welding lines is 100% of the welding section. In type #2, the welding state of the battery unit 105 can be determined as normal since the welding length of one welding line is 75% or more of the welding section. And in types #1 and #2, the tensile strength of the battery unit 105 is 1.90 kgf and 1.61 kgf, respectively, so the battery unit 105 can be determined as normal.

[0048] However, in types #3 and #4, the weld length of the weld line is more than 50% or less than 50% of the welded section, so the welded state of the battery unit 105 can be determined to be weakly welded. Nevertheless, in types #3 and #4, the tensile strength of the battery unit 105 is 1.10 kgf and 0.73 kgf, so the battery unit 105 can be determined to be normal.

[0049] With reference to Types #1, #2, #3, and #4, it can be seen that if the criteria for the welding condition are met, the battery unit 105 is highly likely to also meet the criteria for tensile strength.

[0050] 4, it can be seen that the weld length of the battery unit 105 and the tensile strength of the battery unit 105 show a linear proportional relationship. For example, a Pearson correlation coefficient (PCC) between the tensile strength of the battery unit 105 and the weld length of the battery unit 105 may be calculated to be 0.764. Here, the Pearson correlation coefficient may be a numerical value that quantifies the linear correlation between two variables. That is, the tensile strength of the battery unit 105 may be calculated by multiplying the weld length (mm) of the battery unit 105 by the Pearson correlation coefficient of 0.764.

[0051] 3 and 4, whether the criteria for the tensile strength of the battery unit 105 are satisfied can be determined by considering only the criteria for the welding state of the battery unit 105. Therefore, it can be seen that it is important to determine whether the criteria for the welding state of the battery unit 105 are satisfied based on a photographed image of the battery unit 105.

[0052] Training artificial intelligence models FIG. 5 is a diagram of a classification of battery units according to one embodiment disclosed herein.

[0053] In one embodiment, the artificial intelligence model learning unit 141 may input images of the battery unit to the artificial intelligence model 145. In one embodiment, the artificial intelligence model 145 may be a model capable of multi-class classification (e.g., a model based on a convolutional neural network (CNN)). In one embodiment, the artificial intelligence model 145 may be trained to classify the presence or absence of the can 515, 535 and the top cap 511 based on the images 510, 530, 550 of the battery unit.

[0054] In one embodiment, the data for training the artificial intelligence model 145 may include an image 510 of a battery unit with a can 515 and a top cap 511 normally present, an image 530 of a battery unit with only a can 535 present without a top cap, and an image 550 without the can and top cap. In one embodiment, the images 510, 530, 550 used to train the artificial intelligence model 145 may be pre-provided.

[0055] In one embodiment, the artificial intelligence model 145 may be trained to classify an input image into at least three states based on the training data, where the at least three states may include a state in which the can and top cap are normally present, a state in which only the can is present without the top cap, and a state in which the can and top cap are absent.

[0056] 6 is a diagram illustrating the welding positions of a battery unit according to one embodiment disclosed herein. FIG. 6 includes images 610, 630 of a battery unit including top caps 611, 631 and positive electrode tabs 613, 633, and images 620, 640 that are enlarged views of a portion of the images 610, 630.

[0057] In one embodiment, the artificial intelligence model learning unit 141 may input images of the battery unit to the artificial intelligence model 146. In one embodiment, the artificial intelligence model 146 may be a model capable of multi-class classification. In one embodiment, the artificial intelligence model 146 may be trained to identify and / or crop the welding locations 621, 641 based on the images 610, 630 of the battery unit. Here, the welding locations may include areas where welding has been performed.

[0058] In one embodiment, the data for training the artificial intelligence model 146 may include an image 610 in which the weld is present only in the area where the top cap 611 and the positive electrode tab 613 overlap, and an image 630 in which the weld is at least partially present in an area where the top cap 631 and the positive electrode tab 633 do not overlap. In one embodiment, the images 610, 630 used to train the artificial intelligence model 146 may be pre-provided.

[0059] In one embodiment, the artificial intelligence model 146 may be trained to classify an input image into at least two states based on the training data, where the at least two states may include a state in which the weld is present only in the area where the top cap and the positive tab overlap, and a state in which the weld is at least partially present in an area where the top cap and the positive tab do not overlap.

[0060] In one embodiment, the artificial intelligence model 146 may be trained to crop the weld locations in the input image based on the training data. For example, the artificial intelligence model 146 may be trained to crop the weld locations 621, 641 in the images 610, 630. In one embodiment, the artificial intelligence model 146 may attach metadata to the cropped weld locations indicative of at least two states of the input image.

[0061] FIG. 7 is a diagram illustrating the welding areas of a battery cell according to one embodiment disclosed herein.

[0062] In one embodiment, the artificial intelligence model learning unit 141 may input an image of the battery unit to the artificial intelligence model 147. In one embodiment, the artificial intelligence model 147 may be a model capable of multi-class classification. In one embodiment, the artificial intelligence model 147 may be trained to identify and / or crop the welding areas 721, 741 based on the images 710, 730 of the battery unit. Here, the welding area may refer to an area where actual welding was performed among the welding sections within the welding position. Here, the welding position may be identified and / or cropped by the artificial intelligence model 146.

[0063] In one embodiment, the data for training the artificial intelligence model 147 may include images for weld locations having weld lengths between 0-100% of the weld sections 711, 713, 741, 743. In one embodiment, the images 710, 730 used to train the artificial intelligence model 147 may be pre-provided.

[0064] In one embodiment, the artificial intelligence model 147 may be trained to identify weld regions 721, 741 in an input image based on the training data. In one embodiment, the artificial intelligence model 147 may be trained to crop weld locations in an input image based on the training data. For example, the artificial intelligence model 147 may be trained to crop weld regions 721, 741 in images 710, 730. In one embodiment, the artificial intelligence model 147 may be trained to output images 720, 740 with weld regions 721, 741 cropped therefrom.

[0065] FIG. 8 is a diagram illustrating a welding state of a battery cell according to one embodiment disclosed herein.

[0066] In one embodiment, the artificial intelligence model learning unit 141 may input an image of the battery unit to 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 welding state of the battery unit based on a cropped image of the welding position. In one embodiment, the artificial intelligence model 148 may be a model capable of multi-class classification.

[0067] In one embodiment, the data for training the artificial intelligence model 148 may include an image 810 having a weld length in a reference length range (e.g., 75-100%) in the welded sections 811 and 813, an image 820 having a weld length less than the reference length range (e.g., 0-75%) in the welded sections 821 and 823, and weld images 830, 840, and 850 having other defects. Here, the other defects may include an over-weld condition (e.g., a condition having a weld length exceeding the reference length range), a top cap damage condition (e.g., a top cap burnt), or a tab damage condition. In one embodiment, the images 810, 820, 830, 840, and 850 used for training the artificial intelligence model 148 may be provided in advance.

[0068] In one embodiment, the artificial intelligence model 148 may be trained to classify input images into at least three states based on the training data, where the at least three states may include a state having a weld length within the nominal length range, a state having a weld length below the nominal length range, and a state having other defects.

[0069] State determination using artificial intelligence models In one embodiment, the state determination unit 160 may determine the state of the can assembly based on an image of the battery unit 105. In one embodiment, the state determination unit 160 may determine the state of the can assembly by inputting the image of the battery unit 105 to the artificial intelligence model 145. In one embodiment, the state determination unit 160 may determine the state of the can assembly of the battery unit 105 based on the output of the artificial intelligence model 145. For example, the state determination unit 160 may determine the state of the can assembly of the battery unit 105 based on the state of the battery unit 105 classified by the artificial intelligence model 145 (e.g., a state in which a can and a top cap are normally present (e.g., image 510), a state in which only a can is present without a top cap (e.g., image 530), and a state in which there is no can or top cap (e.g., image 550).

[0070] In one embodiment, if the can and the top cap are properly present in the battery unit 105, the status determination unit 160 may determine that the status of the can assembly is normal. In one embodiment, if only the can is present without the top cap, or if the can and the top cap are absent, the status determination unit 160 may determine that the status of the can assembly is bad.

[0071] In one embodiment, the status determination unit 160 may transmit an image of the battery unit 105 for which the status of the can assembly is determined to be normal among the plurality of images to the position detection unit 170. In one embodiment, the status determination unit 160 may transmit a determination result of the status of the can assembly of the battery unit 105 to the determination unit 195.

[0072] In one embodiment, the position detection unit 170 may detect and / or crop a welding position in an image of the battery unit 105. In one embodiment, the state determination unit 160 may input an image of the battery unit 105 to the artificial intelligence model 146 to detect and / or crop a welding position (e.g., welding positions 621, 641).

[0073] In one embodiment, the position detection unit 170 may determine the state of the welding position based on an image of the battery unit 105. For example, the position detection unit 170 may determine the state of the welding position of the battery unit 105 based on the state of the battery unit 105 classified by the artificial intelligence model 146 (e.g., a state in which welding exists only in an area where the top cap and the positive electrode tab overlap, and a state in which welding exists at least partially in an area where the top cap and the positive electrode tab do not overlap).

[0074] In one embodiment, if the weld is present only in an area where the top cap and the positive electrode tab overlap on the battery unit 105, the position detection unit 170 may determine that the condition of the weld position is normal. In one embodiment, if the weld is at least partially present in an area where the top cap and the positive electrode tab do not overlap, the position detection unit 170 may determine that the condition of the weld position is poor.

[0075] In one embodiment, the position detection unit 170 may transmit an image of the battery unit 105, for which the state of the welding position is determined to be normal, among the plurality of images, to the region detection unit 180. In one embodiment, the position detection unit 170 may transmit an image of the welding position (e.g., welding position 621) of the battery unit 105, for which the state of the welding position is determined to be normal, among the plurality of images, to the region detection unit 180. In one embodiment, the position detection unit 170 may transmit a determination result of the state of the welding position of the battery unit 105 to the determination unit 195.

[0076] In one embodiment, the area detection unit 180 may detect and / or tag a welding area in an image of a welding position of the battery unit 105. In one embodiment, the area detection unit 180 may input an image (e.g., 710, 730) of a welding position of the battery unit 105 to the artificial intelligence model 147 to detect and / or tag a welding area (e.g., welding areas 721, 741).

[0077] In one embodiment, the area detector 180 can transmit the images 720 , 740 tagged with the weld areas 721 , 741 to the analyzer 190 .

[0078] In one embodiment, the analysis unit 190 may analyze the weld condition based on the image tagged with the weld area. In one embodiment, the analysis unit 190 may input the image tagged with the weld area to the artificial intelligence model 148 to analyze the weld condition. In one embodiment, the analysis unit 190 may determine the weld condition of the weld area based on the output of the artificial intelligence model 148. For example, the analysis unit 190 may analyze the weld condition based on the weld condition of the weld area classified by the artificial intelligence model 148 (e.g., a condition having a weld length within a reference length range (e.g., image 810), a condition having a weld length less than the reference length range (e.g., image 820), and a condition having other defects (e.g., images 830, 840, 850).

[0079] In one embodiment, if the battery unit 105 has a weld length within the reference length range, the analysis unit 190 may determine that the weld condition is normal. In one embodiment, if the battery unit 105 has a weld length less than the reference length range or has other defects, the analysis unit 190 may determine that the weld condition is poor.

[0080] In one embodiment, the analysis unit 190 can transmit the determination result of the welding condition to the determination unit 195 .

[0081] In one embodiment, the determination unit 195 can determine whether the quality of the battery unit 105 is good or bad based on the determination results of the state determination unit 160, the position detection unit 170, and / or the analysis unit 190. For example, the determination unit 195 can determine that the battery unit 105 is a good product when the determination results of the state determination unit 160, the position detection unit 170, and the analysis unit 190 all indicate normal. For example, the determination unit 195 can determine that the battery unit 105 is not a good product when at least one of the determination results of the state determination unit 160, the position detection unit 170, or the analysis unit 190 indicates a defective product.

[0082] Furthermore, the determination unit 195 can determine the quality of the battery unit 105 based on not only the determination result based on the artificial intelligence model but also the determination result based on the rule-based inspection. Here, the rule-based inspection may be an inspection that determines whether the battery unit 105 is defective based on gray level information of an image of the battery unit 105.

[0083] For example, the determination unit 195 may generate a determination result by determining at least one of the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery unit 105 based on gray level information of the image of the battery unit 105. According to an embodiment, the determination unit 195 may sequentially determine the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery cell based on gray level information of the image of the battery unit 105. The determination unit 195 may generate a determination result by determining the presence or absence of overwelding of the battery cell, the presence or absence of soot on the top cap, or the presence or absence of tab damage by determining at least one of the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery cell based on gray level information of the image of the battery unit 105. The determination unit 195 may determine whether the battery unit 105 is defective based on the determination result based on the artificial intelligence model and the determination result based on the rule-based inspection. That is, the determination unit 195 may ultimately determine whether the battery unit 105 is defective based on the determination result of whether or not the battery unit 105 is weakly welded and the determination result of whether or not the battery unit 105 is defective or over-welded.

[0084] According to an embodiment, the determination unit 195 may determine whether the battery unit 105 is defective based on a previously stored image file. Specifically, the determination unit 195 may determine whether the battery unit 105 is defective based on a previously stored image file of a defective battery unit. Here, the image file of the defective battery unit may include an image of a weakly welded battery unit, an image of a battery unit determined to be over-welded with the size of soot being greater than a reference size, an image of a battery unit determined to have a level of soot greater than a reference level, an image of a battery unit determined to have a lump of weld, and an image of a battery unit determined to have a top cap violation. Thus, the determination unit 195 may determine whether the battery unit is defective based on the defective battery unit image file.

[0085] As described above, the monitoring device 100 according to an embodiment disclosed herein can accurately analyze the welding state of the battery unit to detect a defective battery unit.

[0086] The monitoring device 100 can improve the ability to detect weak weld defects in battery units by superimposing a deep learning algorithm to solve the problem of making it difficult to clearly classify welded areas due to gray level noise in images taken of process processing equipment that manufactures battery units.

[0087] In addition, the monitoring device 100 can prevent the weakly welded battery unit from being discharged, thereby improving the stability and quality of the product in which the battery unit is mounted.

[0088] In addition, the monitoring device 100 can determine whether a battery unit is defective in real time without the need for a separate device or connection, thereby reducing the cost and time required for defect detection.

[0089] 2, the various program modules of the program 125 are shown as separate, but this is for illustrative purposes only. In one embodiment, the state determiner 160, the location detector 170, the region detector 180, and / or the analyzer 190 may be integrated into one program module. For example, the state determiner 160, the location detector 170, the region detector 180, and / or the analyzer 190 may be integrated into the analyzer 190.

[0090] 2, the artificial intelligence models of program 125 are shown as separate, but this is for illustration purposes only. In one embodiment, artificial intelligence models 145, 146, 147, 148 may be embodied as a single artificial intelligence model.

[0091] 9 is a diagram illustrating a method of operation of the monitoring device 100 according to one embodiment disclosed herein. FIG. 9 can be described with reference to FIGS.

[0092] 9, in operation 910, the monitoring device 100 may capture an image, where the image may be an image of the battery unit 105 captured by the image capture device 103.

[0093] In operation 920, the monitoring device 100 may perform rule-based testing. In one embodiment, the monitoring device 100 may perform rule-based testing based on gray level information of the image.

[0094] For example, the monitoring device 100 may generate a determination result by determining at least one of the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery unit 105 based on gray level information of the image of the battery unit 105. According to an embodiment, the monitoring device 100 may sequentially determine the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery cell based on gray level information of the image of the battery unit 105. The monitoring device 100 may generate a determination result by determining the presence or absence of overwelding of the battery cell, the presence or absence of soot on the top cap, or the presence or absence of tab damage by determining at least one of the presence or absence of a can, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive tab, and the presence or absence of overwelding of the positive tab of the battery cell based on gray level information of the image of the battery unit 105.

[0095] In operation 930, the monitoring device 100 may perform artificial intelligence model-based testing. For example, the monitoring device 100 may perform artificial intelligence model-based testing on the image based on the trained artificial intelligence models 145, 146, 147, and 148.

[0096] In one embodiment, the monitoring device 100 can determine the condition of the can assembly based on an image of the battery unit 105. In one embodiment, the monitoring device 100 can determine the condition of the welding position based on an image of the battery unit 105. In one embodiment, the monitoring device 100 can analyze the welding status based on an image cropped from the welding position.

[0097] In operation 940, the monitoring device 100 may determine whether the battery unit 105 is defective based on the test results.

[0098] In one embodiment, the monitoring device 100 may determine that the battery unit 105 is a good product if the results of the rule-based test and the artificial intelligence model-based test are all normal.

[0099] The above description is merely an illustrative example of the technical ideas of the present disclosure, and various modifications and variations can be made by a person having ordinary knowledge in the technical field to which the present disclosure pertains without departing from the essential characteristics of the present disclosure.

[0100] Therefore, the embodiments disclosed in this disclosure are intended to explain, not to limit, the technical idea of ​​the disclosure, and such embodiments do not limit the scope of the technical idea of ​​the disclosure. The scope of protection of the disclosure should be interpreted according to the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of rights of the disclosure. [Explanation of symbols]

[0101] 100 Monitoring Device 103 Image Acquisition Device 105 Battery Unit 110 Communication Circuit 120 Memory 125 Programs 130 processors 141 Artificial Intelligence Model Learning Department 145 Artificial Intelligence Model 146 Artificial Intelligence Model 147 Artificial Intelligence Model 148 Artificial Intelligence Models 150 Image Acquisition Department 160 Status judgement unit 170 Position detection unit 180 Area detection unit 190 Analysis Department 195 Judgment section 210 First process treatment device 220 Second process treatment equipment 230 3rd process treatment equipment 510 Images 511 Top Cap 515 cans 530 Images 535 cans 550 Images 610 Images 611 Top Cap 613 Positive electrode tab 620 Images 621 Welding position 630 Images 631 Top Cap 633 Positive electrode tab 640 Images 641 Welding position 710 Images 711 Welding Section 713 Welding Section 720 Images 721 Welding Area 730 Images 740 Images 741 Welding Area 743 Welding Section 810 Images 811 Welding Section 813 Welding Section 820 Images 821 Welding Section 823 Welding Section 830 Welding image 840 Welding image 850 Welding image

Claims

1. an image capture unit for capturing an image of at least one process processing device related to the manufacturing of the battery cell; an analysis unit that inputs the acquired image into an artificial intelligence model for determining a welding state of a battery cell to generate a first determination result that determines whether the battery cell is defective; a determination unit that determines whether the battery cell is defective based on the first determination result.

2. The monitoring device of claim 1 , wherein the determining unit further generates a second determination result determining whether the battery cell is defective based on gray level information of the acquired image.

3. The monitoring device according to claim 2 , wherein the determining unit determines whether the battery cell is defective based on the first determination result and the second determination result.

4. 2. The monitoring device of claim 1, wherein the artificial intelligence model includes an artificial intelligence model for detecting a welding area of ​​the battery cell based on the image, and an artificial intelligence model for analyzing a welding state of the welding area.

5. The monitoring device of claim 4, wherein the artificial intelligence model for analyzing the welding condition of the welded area classifies the welding condition into a state having a weld length within a reference length range, a state having a weld length less than the reference length range, and a state having other defects.

6. 3. The monitoring device of claim 2, wherein the determining unit determines at least one of the presence or absence of a can of the battery cell, the presence or absence of a top cap, a center distance between the can and the top cap, a position of a positive electrode tab, and the presence or absence of overwelding of the positive electrode tab based on gray level information of the acquired image to generate the second determination result.

7. 2. The monitoring device of claim 1, wherein the artificial intelligence model includes an artificial intelligence model for determining a state of the can assembly of the battery cell based on the image, and an artificial intelligence model for detecting and / or cropping a welding position in the image when the state of the can assembly is normal.

8. acquiring an image of at least one processing device related to the manufacture of the battery cell; generating a first determination result of whether the battery cell is defective by inputting the acquired image into an artificial intelligence model for determining a welding state of the battery cell; generating a second determination result of whether the battery cell is defective based on gray level information of the acquired image; determining whether the battery cell is defective based on the first determination result and the second determination result.

9. 9. The method of claim 8, wherein the artificial intelligence model includes an artificial intelligence model for detecting a welding area of ​​the battery cell based on the image, and an artificial intelligence model for analyzing a welding state of the welding area.

10. 10. The method of claim 9, wherein the artificial intelligence model for analyzing the welding condition of the welded area classifies the welding condition into a condition having a weld length within a reference length range, a condition having a weld length below a reference length range, and a condition having other defects.

11. The generating of the second determination result includes:

9. The method of claim 8, further comprising determining at least one of the presence or absence of a can of the battery cell, the presence or absence of a top cap, a center distance between the can and the top cap, a position of a positive electrode tab, and the presence or absence of overwelding of the positive electrode tab based on gray level information of the acquired image to generate the second determination result.

12. 9. The method of claim 8, wherein the artificial intelligence model includes an artificial intelligence model for determining a state of the can assembly of the battery cell based on the image, and an artificial intelligence model for detecting and / or cropping a welding position in the image when the state of the can assembly is normal.

Images