Monitoring device and its operating method

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 the contents disclosed in the document of the Korean patent application are incorporated herein by reference in their entirety.

[0002] The embodiments disclosed in this document relate to a monitoring device and an operating method thereof.

Background Art

[0003] [[ID=^17]] An electric vehicle obtains power by charging a battery cell with electricity supplied from the outside and then driving a motor with the voltage charged in the battery cell. The battery cell of an electric vehicle is manufactured by housing an electrode assembly in a battery case and injecting an electrolyte into the interior of the battery case.

[0004] Battery cells are classified into cylindrical, prismatic, and pouch types according to the type of the battery case. A cylindrical battery cell includes an electrode assembly, a cylindrical metal can battery case for housing the electrode assembly and the electrolyte, and a cap assembly assembled on the upper part of the cylindrical can.

[0005] Here, the positive 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 part falls off due to an impact applied from the outside of the battery cell or a welding defect, there is a possibility that the battery cell may deteriorate or an explosion phenomenon may occur. Therefore, it is important to inspect the battery cell so that the battery cell with a welding defect does not flow out.

Summary of the Invention

Problems to be Solved by the Invention

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

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

[0008] A monitoring device according to one embodiment disclosed herein 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 the welding state of the battery cell and generates a first determination result that determines whether or not the battery cell is defective; and a determination unit that determines whether or not the battery cell is defective based on the first determination result.

[0009] The operation method of the monitoring device according to one embodiment disclosed herein 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 the welding state of the battery cell to generate a first determination result determining whether or not the battery cell is defective; generating a second determination result determining whether or not the battery cell is defective based on the gray level information of the acquired image; and determining whether or not the battery cell is defective based on the first and second determination results. [Effects of the Invention]

[0010] According to one embodiment of the monitoring device and its operation method disclosed in this document, it is possible to accurately analyze the welding condition of battery cells and detect defective battery cells. [Brief explanation of the drawing]

[0011] [Figure 1] This is a diagram illustrating the battery process system according to one embodiment disclosed in this document. [Figure 2] This is a block diagram showing the configuration of a monitoring device according to one embodiment disclosed in this document. [Figure 3] This is a welding state classification table according to one embodiment disclosed in this document. [Figure 4] This graph shows the change in tensile strength due to a change in weld length according to one embodiment disclosed in this document. [Figure 5] This figure shows a classification of battery units according to one embodiment disclosed in this document. [Figure 6] This figure illustrates the welding position of a battery cell according to one embodiment disclosed in this document. [Figure 7] This figure illustrates the welding region of a battery cell according to one embodiment disclosed in this document. [Figure 8] This figure illustrates a welding configuration of a battery cell according to one embodiment disclosed in this document. [Figure 9] This figure illustrates the operation method of a monitoring device according to one embodiment disclosed in this document. [Modes for carrying out the invention]

[0012] Hereinafter, some embodiments disclosed in this document will be described in detail through illustrative drawings. When assigning reference numerals to the components in each drawing, care should be taken to ensure that identical components have the same reference numeral whenever possible, even if they appear in other drawings. Furthermore, when describing the embodiments disclosed in this document, if a specific description of a related known configuration or function is deemed to interfere with understanding the embodiments disclosed in this document, such a detailed description will be omitted.

[0013] In describing the components of the embodiments disclosed herein, terms such as First, Second, A, B, (a), (b), etc., may be used. Such terms are used to distinguish a component from other components, and do not limit the nature, order, or sequence of the component. Furthermore, unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as those generally understood by a person of ordinary skill in the art to which the embodiments disclosed herein belong. Terms similar to those defined in commonly used dictionaries should be interpreted in a way that is consistent with their meaning in the context of the relevant technology, and not in an ideal or overly formal sense unless explicitly defined herein.

[0014] In various embodiments, the battery may include a battery cell, which is the basic unit of a battery that can be charged and discharged to provide electrical energy. 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, and the like. The battery cell can supply power to the device of interest (not shown). For this purpose, the battery cell may be electrically connected to the device of interest. Here, the device of interest may include an electrical, electronic, or mechanical device that operates on power supplied from a battery pack (not shown) containing multiple battery cells. For example, the device of interest may be not only small products such as digital cameras, P-DVDs, MP3Ps, mobile phones, PDAs, portable game devices, power tools, and electric bicycles (E-bikes), but also large products requiring high output, such as electric vehicles and hybrid vehicles, and power storage devices or backup power storage devices that store surplus generated power or renewable energy.

[0015] A battery cell may consist of an electrode assembly, a battery case in which the electrode assembly is housed, and an electrolyte solution injected into the battery case to activate the electrode assembly. The electrode assembly is formed by interposing a separator membrane between a positive electrode plate, which is formed by coating a positive electrode active material onto a positive electrode current collector, and a negative electrode plate, which is formed by coating a negative electrode active material onto a negative electrode current collector. Depending on the type of battery case, the electrode assembly may be manufactured in a jelly roll type, stack type, etc., and housed inside the battery case. The battery case serves as an outer casing that maintains the shape of the battery and protects it from external impacts. Depending on the type of battery case, battery cells may be classified into cylindrical, rectangular, or pouch types.

[0016] According to the embodiment, a battery cell may be manufactured through a series of manufacturing processes including an electrode manufacturing process, an assembly process, and a chemical conversion process. Here, the assembly process may include a process of assembling the positive and negative electrode plates manufactured through the electrode manufacturing process and injecting the 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 the process of injecting the electrode assembly and electrolyte into the battery case and sealing it. In the case of a cylindrical battery cell, the electrode assembly is attached to a cylindrical metal can, the negative electrode tab extending from the negative electrode of the electrode assembly is welded to the bottom of the can, and the positive electrode tab extending from the positive electrode of the electrode assembly, with the electrode assembly and electrolyte inside, is welded to the top cap of the cap assembly.

[0018] However, if part or all of the welding site between the positive tab of the electrode assembly and the top cap of the cap assembly detaches due to an impact applied from outside the battery cell or a poor welding, that is, if the positive tab and the top cap are weakly welded, there is a possibility that the battery cell may deteriorate or an explosion phenomenon may occur. Therefore, it is important to inspect the battery cell so that the battery cell with a poor welding does not circulate.

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

[0020] FIG. 1 is a diagram for generally explaining a battery process system according to an embodiment disclosed in this document.

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

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

[0023] For example, the monitoring device 100 can collect and analyze data or graph data generated in the battery process system, such as the progress status of the battery process system, the presence or absence of an alarm, temperature, pressure, quantity, etc.

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

[0025] The monitoring device 100 can determine whether a battery cell is defective based on video footage of at least one process processing device 210, 220, or 230. In one embodiment, the monitoring device 100 can determine whether there is weak welding between the positive electrode tab and the top cap of the battery cell based on video footage of at least one process processing device 210, 220, or 230.

[0026] At least one process processing apparatus 210, 220, 230 may include a first process processing apparatus 210, a second process processing apparatus 220, and a third process processing apparatus 230. In Figure 1, at least one process processing apparatus 210, 220, 230 is shown as having three units, but is not limited to this. Depending on the embodiment, at least one process processing apparatus 210, 220, 230 may include n units (where n is a natural number of 1 or more).

[0027] In one embodiment, at least one process apparatus 210, 220, 230 can weld the positive electrode tab of the battery cell electrode assembly to the top cap of the cap assembly.

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

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

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

[0031] In one embodiment, the monitoring device 100 can determine that the battery unit 105 is in good condition if all rule-based inspection results and artificial intelligence model-based inspection results for the battery unit 105 are normal. In another embodiment, the monitoring device 100 can determine that the battery unit 105 is defective if at least one of the rule-based inspection results or artificial intelligence model-based inspection results for the battery unit 105 is defective.

[0032] The following will provide a general overview of the components of the monitoring device 100, followed by a description of the specific operation method of the monitoring device 100.

[0033] Referring to Figure 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 Figure 2 may further include at least one component other than the components shown in Figure 2 (for example, a display, an input device, or an output device).

[0034] In one embodiment, the communication circuit 110 establishes a wired communication channel and / or a wireless communication channel between the monitoring device 100 and the image acquisition device 103, and can send and receive data with the image acquisition device 103 via the established communication channel.

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

[0036] In one embodiment, the memory 120 can store data used by at least one component of the monitoring device 100 (e.g., the processor 130). For example, the data may include a program 125 (or instructions relating thereto), input data, or output data. In one embodiment, the instructions can cause the monitoring device 100 to perform the operations defined by the instructions at runtime by the processor 130.

[0037] In one embodiment, the memory 120 may include a program 125 (for example, 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, a region detection unit 180, an analysis unit 190, and / or a determination 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 (for example, the artificial intelligence model learning unit 141, the artificial intelligence models 145, 146, 147, 148, the image acquisition unit 150, the state determination unit 160, the position detection unit 170, the region detection unit 180, the analysis unit 190, and / or the determination unit 195) to control at least one other component (for example, a hardware or software component) of the monitoring device 100 connected to the processor 130, and perform various data processing or calculations.

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

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

[0042] In one embodiment, the state determination unit 160 can determine the state of the can assembly based on an image of the battery unit 105. In one embodiment, the position detection unit 170 can determine the state of the welding position based on an image of the battery unit 105. In one embodiment, the area detection unit 180 can 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 can analyze the welding state based on an image of the cropped welding position. In one embodiment, the determination unit 195 can determine the quality of the battery unit 105 based on the determination results of the state determination unit 160, the position detection unit 170, and / or the analysis unit 190.

[0043] The following will specifically describe how the monitoring device 100 determines the state of the battery unit 105 via the artificial intelligence model learning unit 141, artificial intelligence models 145, 146, 147, 148, image acquisition unit 150, state determination unit 160, position detection unit 170, region detection unit 180, analysis unit 190, and / or determination unit 195, with reference to Figures 3 to 8.

[0044] Figure 3 is a welding state classification table according to one embodiment disclosed in this document. Figure 4 is a graph showing the change in tensile strength due to a change in weld length according to one embodiment disclosed in this document.

[0045] The battery unit 105 can be judged as normal or abnormal based on various criteria. For example, the battery unit 105 can be judged as normal or abnormal based on criteria related to the welding condition and / or tensile strength. The criteria for determining whether the battery unit 105 is normal or abnormal can be set in advance. For example, the welding condition of the battery unit 105 can be judged as 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 can be judged as normal if it is 0.4 kgf or more. Here, the weld bead can be the weld metal that solidifies on the base material when welding is performed along the weld line.

[0046] The welding condition of the battery unit 105 can be confirmed by taking an image of the battery unit 105, but the tensile strength of the battery unit 105 is difficult to confirm by image.

[0047] Referring to Figure 3, in type #1, the welding condition of the battery unit 105 can be determined to be normal because the welding length of the two welding lines is 100% of the welding section. In type #2, the welding condition of the battery unit 105 can be determined to be normal because the welding length of one welding line is 75% or more of the welding section. Furthermore, in both type #1 and type #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 to be normal.

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

[0049] By referring to types #1 and #2, and types #3 and #4, it can be seen that if the criteria for the welded state are met, then the battery unit 105 is likely to also meet the criteria for tensile strength.

[0050] Referring to Figure 4, it can be seen that the weld length of the battery unit 105 and the tensile strength of the battery unit 105 are linearly proportional. For example, the Pearson correlation coefficient (PCC) between the tensile strength of the battery unit 105 and the weld length of the battery unit 105 can 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 can be calculated by multiplying the weld length (mm) of the battery unit 105 by the Pearson correlation coefficient of 0.764.

[0051] Considering the experimental results in Figures 3 and 4, it can be determined whether the battery unit 105 satisfies the tensile strength criteria by considering only the welding condition criteria of the battery unit 105. Therefore, it is important to determine whether the battery unit 105 meets the welding condition criteria by examining the image taken of the battery unit 105.

[0052] Learning an artificial intelligence model Figure 5 is a diagram showing a classification of battery units according to one embodiment disclosed in this document.

[0053] In one embodiment, the artificial intelligence model learning unit 141 can input images of the battery unit to the artificial intelligence model 145. In one embodiment, the artificial intelligence model 145 may be a multi-class classification model (for example, a model based on a CNN (convolutional neural network)). In one embodiment, the artificial intelligence model 145 may be trained to classify the presence or absence of the cans 515, 535 and the top cap 511 based on 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 in which the can 515 and top cap 511 are normally present, an image 530 of a battery unit in which only the can 535 is present without the top cap, and an image 550 of a battery unit without the can and top cap. In one embodiment, the images 510, 530, and 550 used for training the artificial intelligence model 145 may be provided in advance.

[0055] In one embodiment, the artificial intelligence model 145 may be trained to classify an input image into at least three states based on training data. Here, the at least three states may include a state in which the can and top cap are present normally, a state in which only the can is present without the top cap, and a state in which neither the can nor the top cap is present.

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

[0057] In one embodiment, the artificial intelligence model learning unit 141 can input an image of the battery unit to the artificial intelligence model 146. In one embodiment, the artificial intelligence model 146 may be a multi-classification model. In one embodiment, the artificial intelligence model 146 may be trained to identify and / or crop welding locations 621, 641 based on images 610, 630 of the battery unit, where the welding locations may include the area 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 welding exists only in the region where the top cap 611 and the positive electrode tab 613 overlap, and an image 630 in which welding exists in at least part of the region where the top cap 631 and the positive electrode tab 633 do not overlap. In one embodiment, the images 610 and 630 used for training the artificial intelligence model 146 may be provided in advance.

[0059] 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 in which welding exists only in the region where the top cap and the positive electrode tab overlap, and a state in which welding exists at least partially in the portion where the top cap and the positive electrode tab do not overlap.

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

[0061] Figure 7 illustrates the welding area of ​​a battery cell according to one embodiment disclosed in this document.

[0062] In one embodiment, the artificial intelligence model learning unit 141 can input an image of the battery unit to the artificial intelligence model 147. In one embodiment, the artificial intelligence model 147 may be a multi-classification model. In one embodiment, the artificial intelligence model 147 may be trained to identify and / or crop welding areas 721 and 741 based on images 710 and 730 of the battery unit. Here, the welding area may mean the area within the welding section of the welding location where actual welding was performed. Here, the welding location 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 of welding positions having welding lengths between 0 and 100% of welding sections 711, 713, 741, and 743. In one embodiment, the images 710 and 730 used for training the artificial intelligence model 147 may be provided in advance.

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

[0065] Figure 8 illustrates the welding state of a battery cell according to one embodiment disclosed in this document.

[0066] In one embodiment, the artificial intelligence model learning unit 141 can 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 an image cropped to show 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 image 810 having weld lengths within a reference length range (e.g., 75-100%) in weld sections 811 and 813, image 820 having weld lengths below the reference length range (e.g., 0-75%) in weld sections 821 and 823, and welding images 830, 840, and 850 having other defects. Here, other defects may include over-welding conditions (e.g., weld lengths exceeding the reference length range), top cap damage conditions (e.g., top cap burning), or tab damage conditions. In one embodiment, the images 810, 820, 830, 840, and 850 used to train the artificial intelligence model 148 may be pre-configured.

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

[0069] State determination using an artificial intelligence model In one embodiment, the state determination unit 160 can determine the state of the can assembly based on an image of the battery unit 105. In one embodiment, the state determination unit 160 can determine the state of the can assembly by inputting an image of the battery unit 105 to an artificial intelligence model 145. In one embodiment, the state determination unit 160 can 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 can determine the state of the can assembly of the battery unit 105 based on the states of the battery unit 105 classified by the artificial intelligence model 145 (for example, a state where the can and top cap are present normally (for example, image 510), a state where only the can is present without a top cap (for example, image 530), and a state where neither the can nor the top cap is present (for example, image 550).

[0070] In one embodiment, if the can and top cap are present in the battery unit 105 in a normal state, the state determination unit 160 can determine that the can assembly is in a normal state. In another embodiment, if only the can is present without the top cap, or if neither the can nor the top cap is present, the state determination unit 160 can determine that the can assembly is in a defective state.

[0071] In one embodiment, the state determination unit 160 can transmit to the position detection unit 170 an image of the battery unit 105 in which the state of the can assembly has been determined to be normal from among a plurality of images. In one embodiment, the state determination unit 160 can transmit the determination result of the state of the can assembly of the battery unit 105 to the determination unit 195.

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

[0073] In one embodiment, the position detection unit 170 can determine the state of the welding position based on an image of the battery unit 105. For example, the position detection unit 170 can 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 (for example, a state in which welding exists only in the area where the top cap and positive electrode tab overlap, and a state in which welding exists in at least a portion of the area where the top cap and positive electrode tab do not overlap).

[0074] In one embodiment, if welding exists only in the area where the top cap and positive electrode tab overlap on the battery unit 105, the position detection unit 170 can determine that the welding position is in a normal state. In another embodiment, if welding exists in at least a portion of the area where the top cap and positive electrode tab do not overlap, the position detection unit 170 can determine that the welding position is in a poor state.

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

[0076] In one embodiment, the region detection unit 180 can detect and / or tag welding regions using an image of the welding location of the battery unit 105. In one embodiment, the region detection unit 180 can input an image of the welding location of the battery unit 105 (e.g., 710, 730) to the artificial intelligence model 147 and detect and / or tag welding regions (e.g., welding regions 721, 741).

[0077] In one embodiment, the region detection unit 180 can transmit images 720 and 740 tagged with welding regions 721 and 741 to the analysis unit 190.

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

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

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

[0081] In one embodiment, the determination unit 195 can determine whether the battery unit 105 is of good or bad quality 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 if 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 if 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 defect.

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

[0083] For example, the determination unit 195 can determine at least one of the following based on the gray level information of the image of the battery unit 105: whether or not the battery unit 105 has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, and generate a determination result. In one embodiment, the determination unit 195 can sequentially determine whether or not the battery cell has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, based on the gray level information of the image of the battery unit 105. The determination unit 195 can determine at least one of the following based on the gray level information of the image of the battery unit 105: whether or not the battery cell has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, and generate a determination result that determines whether or not the battery cell is over-welded, whether or not there is soot on the top cap, or whether or not the tab is damaged. The determination unit 195 can determine whether the battery unit 105 is defective based on the determination results based on the artificial intelligence model and the determination results based on the rule-based inspection. In other words, the determination unit 195 can ultimately determine whether the battery unit 105 is defective based on the determination results for whether there is weak welding on the battery unit 105 and the determination results for whether the battery unit 105 is defective or has over-welding.

[0084] In one embodiment, the determination unit 195 can determine whether or not the battery unit 105 is defective based on a previously saved image file. Specifically, the determination unit 195 can determine whether or not the battery unit 105 is defective based on a previously saved image file of a defective battery unit. Here, the image file of a defective battery unit may include images of a weakly welded battery unit, images of a battery unit judged to be over-welded with soot exceeding a standard size, images of a battery unit judged to have a degree of soot exceeding a standard level, images of a battery unit judged to be a solidified weld, and images of a battery unit judged to have a damaged top cap. Therefore, the determination unit 195 can determine whether or not the battery unit is defective based on the defective battery unit image file.

[0085] As described above, the monitoring device 100 according to one embodiment disclosed in this document can accurately analyze the welding condition of the battery unit and detect defective battery units.

[0086] The monitoring device 100 can improve its ability to detect weak welding defects in battery units by superimposing a deep learning algorithm to address the problem of difficulty in clearly classifying welded areas due to gray-level noise in images of the process equipment used to manufacture battery units.

[0087] Furthermore, the monitoring device 100 can prevent the leakage of weakly welded battery units and improve the stability and quality of products equipped with battery units.

[0088] Furthermore, since the monitoring device 100 can determine in real time whether a battery unit is defective or not without the need for additional equipment or connection, it can reduce the cost and time required for defect detection.

[0089] In Figure 2, the various program modules of program 125 are shown as separate entities, but this is merely an example. In one embodiment, the state determination unit 160, the position detection unit 170, the region detection unit 180, and / or the analysis unit 190 can be integrated as a single program module. For example, the state determination unit 160, the position detection unit 170, the region detection unit 180, and / or the analysis unit 190 can be integrated as the analysis unit 190.

[0090] In Figure 2, the artificial intelligence models for program 125 are shown to be separate, but this is merely illustrative. In one embodiment, artificial intelligence models 145, 146, 147, and 148 can be realized as a single artificial intelligence model.

[0091] Figure 9 is a diagram illustrating the operation method of the monitoring device 100 according to one embodiment disclosed in this document. Figure 9 can be explained with reference to Figures 2 to 8.

[0092] Referring to Figure 9, in operation 910, the monitoring device 100 can acquire an image. Here, the image may be an image of the battery unit 105 acquired by the image acquisition device 103.

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

[0094] For example, the monitoring device 100 can determine at least one of the following based on the gray-level information of the image of the battery unit 105: whether or not the battery unit 105 has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, and generate a determination result. In one embodiment, the monitoring device 100 can sequentially determine whether or not the battery cell has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, based on the gray-level information of the image of the battery unit 105. The monitoring device 100 can determine at least one of the following based on the gray-level information of the image of the battery unit 105: whether or not the battery cell has a can, whether or not it has a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and whether or not the positive electrode tab is over-welded, and generate a determination result determining whether or not the battery cell is over-welded, whether or not there is soot on the top cap, or whether or not the tab is damaged.

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

[0096] In one embodiment, the monitoring device 100 can determine the state of the can assembly based on an image of the battery unit 105. In one embodiment, the monitoring device 100 can determine the state of the welding location based on an image of the battery unit 105. In one embodiment, the monitoring device 100 can analyze the welding state based on a cropped image of the welding location.

[0097] In operation 940, the monitoring device 100 can determine whether or not the battery unit 105 is defective based on the inspection results.

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

[0099] The above explanation is merely illustrative of the technical concept of this disclosure, and a person with ordinary skill in the art to which this disclosure belongs can make various modifications and variations without deviating from the essential characteristics of this disclosure.

[0100] Accordingly, the embodiments disclosed herein are for illustrative purposes only, and not to limit the technical concept of the disclosure, and such embodiments do not limit the scope of the technical concept of the disclosure. The scope of protection of this disclosure should be interpreted in accordance with the following claims, and all technical concepts within an equivalent scope should be interpreted as being included within the scope of the rights of this disclosure. [Explanation of Symbols]

[0101] 100 Monitoring devices 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 Models 146 Artificial Intelligence Models 147 Artificial Intelligence Models 148 Artificial Intelligence Models 150 Image Acquisition Unit 160 State determination unit 170 Position detection unit 180 Area detection unit 190 Analysis Department 195 Judgment section 210 First Process Processing Equipment 220 Second Process Apparatus 230 Third Process Apparatus 510 Images 511 Top Cap 515 cans 530 images 535 cans 550 images 610 Images 611 Top Cap 613 Positive Tab 620 images 621 Welding position 630 images 631 Top Cap 633 Positive 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 Image 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 acquisition unit that captures an image of at least one process apparatus related to the manufacturing of battery cells, An analysis unit inputs the acquired image into an artificial intelligence model for determining the welding condition of the battery cell and generates a first judgment result determining whether or not the battery cell is defective. A monitoring device comprising: a determination unit that performs a rule-based inspection on the gray level information of the acquired image and generates a second determination result that determines whether or not the battery cell is defective, and if both the first and second determination results indicate normal, determines that the battery cell is a good product.

2. The monitoring device according to claim 1, characterized in that the artificial intelligence model includes an artificial intelligence model for detecting the welding area of ​​the battery cell based on the image, and an artificial intelligence model for analyzing the welding state of the welding area.

3. The monitoring device according to claim 2, wherein the artificial intelligence model for analyzing the welding state of the welding region classifies the welding state into states having a welding length within a reference length range, states having a welding length less than the reference length range, and states having other defects.

4. The monitoring device according to claim 1, characterized in that the determination unit determines, based on the gray level information of the acquired image, at least one of the following: the presence or absence of a can of the battery cell, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and the presence or absence of over-welding of the positive electrode tab, and generates the second determination result.

5. The monitoring device according to claim 1, characterized in that the artificial intelligence model includes an artificial intelligence model for determining the state of the battery cell can assembly based on the image, and an artificial intelligence model for detecting and / or cropping the welding position in the image when the state of the can assembly is normal.

6. The steps include: acquiring an image of at least one process equipment related to the manufacturing of battery cells; The steps include: inputting the acquired image into an artificial intelligence model for determining the welding condition of the battery cell to generate a first judgment result that determines whether or not the battery cell is defective; A step of performing a rule-based inspection on the gray-level information of the acquired image and generating a second judgment result that determines whether or not the battery cell is defective, A method for operating a monitoring device, which includes the step of determining that the battery cell is a good product if both the first and second judgment results indicate normality.

7. The method for operating the monitoring device according to claim 6, characterized in that the artificial intelligence model includes an artificial intelligence model for detecting the welding area of ​​the battery cell based on the image, and an artificial intelligence model for analyzing the welding state of the welding area.

8. The method for operating the monitoring device according to claim 7, characterized in that the artificial intelligence model for analyzing the welding state of the welding area classifies the welding state into a state having a welding length within a reference length range, a state having a welding length less than the reference length range, and other states having defects.

9. The step of generating the second judgment result is: A method for operating a monitoring device according to claim 6, characterized in that, based on the gray level information of the acquired image, it determines at least one of the following: the presence or absence of a can of the battery cell, the presence or absence of a top cap, the center distance between the can and the top cap, the position of the positive electrode tab, and the presence or absence of over-welding of the positive electrode tab, and generates the second determination result.

10. The method for operating the monitoring device according to claim 6, characterized in that the artificial intelligence model includes an artificial intelligence model for determining the state of the battery cell can assembly based on the image, and an artificial intelligence model for detecting and / or cropping the welding position in the image when the state of the can assembly is normal.

Images