Secondary battery manufacturing system

Abstract

According to exemplary embodiments, a secondary battery manufacturing system is provided. The system comprises: a data matrix reader configured to read a data matrix of a cell case, configured to capture an unrecognized image including the data matrix having failed to be read, and configured to match the unrecognized image with a virtual CAN ID; a first server configured to store the unrecognized image transmitted from the data matrix reader; and a second server configured to determine a feature interfering with the reading of the data matrix on the basis of the unrecognized image transmitted from the first server.

Description

Secondary battery manufacturing system

[0001] The present invention relates to a secondary battery manufacturing system. This application claims the benefit of Korean Application No. 10-2024-0006416, filed January 16, 2024, which is incorporated herein by reference in its entirety.

[0002] Unlike primary batteries, secondary batteries can be charged and discharged multiple times. They are widely used as a power source for various wireless devices, including handsets, laptops, and cordless vacuum cleaners. Recently, improved energy density and economies of scale have dramatically reduced the per-unit manufacturing cost of secondary batteries. Furthermore, as the range of battery electric vehicles (BEVs) has increased to match that of fuel-powered vehicles, the primary use of secondary batteries is shifting from mobile devices to mobility.

[0003] Secondary batteries are manufactured through electrode processes, assembly processes, and activation processes. To improve yield and reliability in the secondary battery manufacturing process, ensuring traceability is crucial. Accordingly, various studies are being conducted to ensure traceability in the secondary battery manufacturing process.

[0004] The technical idea of ​​the present invention aims to solve a problem by providing a secondary battery manufacturing system with improved traceability.

[0005] According to exemplary embodiments of the present invention for solving the above-described problem, a secondary battery manufacturing system is provided. The system includes a data matrix reader configured to read a data matrix of a cell case, configured to capture an unrecognized image including the data matrix that has failed to be read, and configured to match the unrecognized image with a virtual can ID; a first server configured to store the unrecognized image transmitted from the data matrix reader; and a second server configured to determine a feature that impedes reading of the data matrix based on the unrecognized image transmitted from the first server.

[0006] The title of the above unrecognized image includes the above virtual can ID.

[0007] The above first server is a network attached storage.

[0008] The second server comprises a deep learning model configured to determine the feature of the data matrix based on the unrecognized image.

[0009] The second server is configured to generate classification data by matching a symbol representing the feature with the virtual can ID.

[0010] The system further includes a third server configured to store the classification data.

[0011] The third server is configured to transmit, in response to a request from a client device, a Uniform Resource Locator (URL) including source code for displaying the unrecognized image, the classification data, and metrics based on the classification data to the client device.

[0012] The above data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from a ring-shaped light.

[0013] The features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, darkness of the unrecognized image, close spacing of the cell cases in the unrecognized image, diffuse reflection, scratches on the data matrix, non-formation of the data matrix of the cell cases, absence of the cell cases in the unrecognized image, shooting trigger timing error of the data matrix reader, and misalignment of the data matrix reader.

[0014] The above data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from a spot light.

[0015] The features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, close spacing of the cell cases in the unrecognized image, a scratch on the data matrix, non-formation of the data matrix of the cell cases, absence of the cell cases in the unrecognized image, an error in the shooting trigger timing of the data matrix reader, the data matrix being out of focus of the data matrix reader, and exceeding the reading time of the data matrix reader.

[0016] The above data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from an illuminator including a cylindrical lens.

[0017] The features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, a scratch on the data matrix, non-formation of the data matrix in the cell case, absence of the cell case in the unrecognized image, an error in the shooting trigger timing of the data matrix reader, the data matrix being out of focus of the data matrix reader, and exceeding the read time of the data matrix reader.

[0018] A secondary battery manufacturing system according to exemplary embodiments of the present invention may be configured to generate classification data indicating features that cause failures in reading the data matrix. This allows for monitoring of cell traceability and provides higher-precision cell tracking.

[0019] The effects that can be obtained from the exemplary embodiments of the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly derived and understood by those skilled in the art to which the exemplary embodiments of the present disclosure pertain from the following description. In other words, unintended effects resulting from practicing the exemplary embodiments of the present disclosure can also be derived by those skilled in the art from the exemplary embodiments of the present disclosure.

[0020] FIG. 1 is a block diagram illustrating a secondary battery manufacturing system according to exemplary embodiments.

[0021] Figures 2 to 4 are drawings showing an optical system for photographing a data matrix.

[0022] FIG. 5 is a flowchart illustrating a method for manufacturing a secondary battery according to exemplary embodiments.

[0023] FIG. 6 illustrates a secondary battery manufacturing system according to other exemplary embodiments.

[0024] FIG. 7 illustrates a secondary battery manufacturing system according to other exemplary embodiments.

[0025] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. Prior to this, it should be noted that the terms and words used in this specification and claims should not be construed as limited to their conventional or dictionary meanings. Based on the principle that the inventor can appropriately define the concepts of terms to best explain his or her invention, they should be interpreted in a way that aligns with the technical spirit of the present invention.

[0026] Accordingly, the embodiments described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of the present invention and do not represent all of the technical ideas of the present invention. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of filing this application.

[0027] In addition, when describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description is omitted.

[0028] Since the embodiments of the present invention are provided to more fully explain the present invention to those skilled in the art, the shapes and sizes of components in the drawings may be exaggerated, omitted, or schematically illustrated for clearer explanation. Accordingly, the sizes and proportions of each component do not fully reflect the actual sizes or proportions.

[0029]

[0030] (Example 1)

[0031] FIG. 1 is a block diagram showing a secondary battery manufacturing system (10) according to exemplary embodiments.

[0032] Figures 2 to 4 are drawings showing an optical system for photographing a data matrix (DM).

[0033] Referring to FIG. 1, a secondary battery manufacturing system (10) according to exemplary embodiments may include a plurality of secondary battery manufacturing facilities (100), servers (210, 220, 230), and a client device (300).

[0034] Referring to FIGS. 1 and 2, secondary battery manufacturing facilities (100) may be configured to perform an assembly process of a secondary battery. The secondary battery manufacturing facilities (100) may be configured to perform, for example, an assembly process of a can-type secondary battery. The can-type secondary battery may include a cell case (CC) and an electrode assembly within the cell case (CC). The secondary battery manufacturing facilities (100) may include a plurality of data matrix readers (110), a hub (120), and a processor (130).

[0035] The cell case (CC) may be a metal can. The cell case (CC) may be either a cylindrical can or a square can. The electrode assembly may include a winding structure of a positive electrode, a negative electrode, and a separator, or may include a stack of a positive electrode, a negative electrode, and a separator. The positive electrode may include a positive electrode current collector and a positive electrode active material, and the negative electrode may include a negative electrode current collector and a negative electrode active material.

[0036] The thickness of the positive electrode current collector may range from about 3 μm to about 500 μm. The positive electrode current collector may not cause chemical changes in the secondary battery to be ultimately manufactured and may have high conductivity. The positive electrode current collector may include, for example, stainless steel, aluminum, nickel, titanium, calcined carbon, and aluminum. The positive electrode current collector may also include stainless steel surface-treated with carbon, nickel, titanium, silver, or the like. The surface of the positive electrode current collector may include a micro-roughened structure to increase the adhesion of the active material. The positive electrode current collector may have a shape such as a film, a sheet, a foil, a net, a porous material, a foam, or a non-woven fabric.

[0037] The thickness of the negative electrode current collector may be in the range of about 3 μm to about 500 μm. The negative electrode current collector may not cause chemical changes in the secondary battery ultimately manufactured and may have high conductivity. The negative electrode current collector may include copper, stainless steel, aluminum, nickel, titanium, sintered carbon, and an aluminum-cadmium alloy. The negative electrode current collector may also include stainless steel surface-treated with carbon, nickel, titanium, silver, etc. The surface of the negative electrode current collector may include a micro-roughened structure to increase the adhesion of the active material. The negative electrode current collector may have a shape such as a film, a sheet, a foil, a net, a porous material, a foam, or a non-woven fabric.

[0038] A cathode active material is a material that can cause an electrochemical reaction. The cathode active material may be a lithium transition metal oxide. The cathode active material may be, for example, a layered compound such as lithium cobalt oxide (LiCoO2) and lithium nickel oxide (LiNiO2) substituted with one or more transition metals, lithium manganese oxide substituted with one or more transition metals, or a lithium manganese oxide having the chemical formula LiNi. 1-y M yLithium nickel oxide, Li, expressed as O2 (wherein, M is any one of Co, Mn, Al, Cu, Fe, Mg, B, Cr, Zn, and Ga, and 0.01≤y≤0.7) 1+z Ni 1 / 3 Co 1 / 3 Mn 1 / 3 O2, Li 1+zN i 0.4 Mn 0.4 Co 0.2 Li like O2 1+z Ni b Mn c Co 1-(b+c+d) M d O (2-e) A e (wherein, -0.5≤z≤0.5, 0.1≤b≤0.8, 0.1≤c≤0.8, 0≤d≤0.2, 0≤e≤0.2, b+c+d<1, M is any one of Al, Mg, Cr, Ti, Si, and Y, and A is any one of F, P, and Cl) Lithium nickel cobalt manganese composite oxide, chemical formula Li 1+x M 1-y M' y PO 4-z X z (wherein, M is a transition metal, more specifically, one of Fe, Mn, Co, and Ni, M' is one of Al, Mg, and Ti, X is one of F, S, and N, -0.5≤x≤+0.5, 0≤y≤0.5, and 0≤z≤0.1) and may include an olivine-based lithium metal phosphate.

[0039] The negative active material may include carbon, such as non-graphitizable carbon, graphitic carbon, etc. The negative active material may include, for example, Li x Fe2O3(0≤x≤1), LixWO2(0≤x≤1), Sn x Me 1-x Me' y O z(Here, Me is any one of Mn, Fe, Pb, and Ge, and Me' is any one of Al, B, P, Si, elements of group 1, 2, and 3 of the periodic table, and halogens, and 0 <x≤1 이고, 1≤y≤3 이며, 1≤z≤8) 등의 금속 복합 산화물을 포함할 수 있다. 음극 활물질은, 예컨대, 리튬 금속, 리튬 합금, 규소계 합금, 주석계 합금을 포함할 수 있다. 음극 활물질은, 예컨대, SnO, SnO2, PbO, PbO2, Pb2O3, Pb3O4, Sb2O3, Sb2O4, Sb2O5, GeO, GeO2, Bi2O3, Bi2O4, Bi2O5등의 금속 산화물을 포함할 수 있다. 음극 활물질은, 예컨대, 폴리아세틸렌 등의 도전성 고분자, Li-Co-Ni 계 재료 등을 포함할 수 있다.

[0040] Below, the technical concept of the present invention will be described, focusing on an example in which the cell case (CC) is a cylindrical can. However, this is for illustrative purposes only and does not limit the technical concept of the present invention in any way. Those skilled in the art will readily be able to achieve an example in which the cell case (CC) is a square can based on the description herein.

[0041] Each of the secondary battery manufacturing facilities (100) may be configured to perform a series of sub-processes included in the assembly process of a can-type battery. The above sub-processes may include a process for inserting a lower insulating part into a cell case (CC), a process for inserting an electrode assembly into the cell case (CC), a process for welding a negative tab of the cell case (CC) and the electrode assembly, a process for compressively molding the upper portion of the cell to reduce the outer diameter of the cell, a process for inserting an upper insulating part into the cell case (CC), a process for molding the cell case (CC) so that the diameter of the stepped portion of the cell case (CC) is reduced for the fixation of the upper cap assembly, an inspection process using X-rays, a process for injecting an electrolyte into the cell case (CC), a process for welding the positive tab of the electrode assembly and the cap assembly, a process for sealing the battery cell by compressing the cap assembly and the gasket together to the cell case (CC), a process for pressurizing the battery cell to adjust (e.g., reduce) the height of the cell, a process for marking a lot number on the outside of the cell case (CC), a process for measuring the internal resistance of the battery cell based on the open circuit voltage, and a process for unloading the battery cell from the secondary battery manufacturing equipment (100) and loading it onto a tray. Each sub-process may include the output of a data matrix (DM) for tracking and recording the sub-process. As a non-limiting example, the data matrix (DM) may be a two-dimensional barcode.

[0042] Reading out a data matrix (DM) may include taking an image of a portion of a cell case (CC) containing the data matrix (DM) or an image of the entire cell case (CC) containing the data matrix (DM), and reading out information contained in the data matrix (DM) from the image. The data matrix (DM) may be read out by a plurality of data matrix readers (110).

[0043] Referring to FIG. 2, the illuminator (LSa) may be configured to irradiate the cell case (CC) with illumination light (ILa). Here, the illuminator (LSa) may be a ring-shaped illuminator, and thus, the illumination light (ILa) may have a ring-shaped beam cross-section. The illumination light (ILa) may reach the entire surface of the cell case (CC) along the outer periphery of the cell case (CC), and the data matrix reader (110) may be configured to capture an image of the cell case (CC) including the data matrix (DM) based on the illumination light (ILa) reflected on the surface of the cell case (CC).

[0044] Referring to FIG. 3, the illuminator (LSb) may be configured to irradiate the cell case (CC) with illumination light (ILb). Here, the illuminator (LSb) may be a spot light, and the optical system of the illuminator (LSb) may include a spherical lens, so that the illumination light (ILb) may have a beam cross-section converging to a spot. The illumination light (ILb) may reach a portion of the cell case (CC) including the data matrix (DM), and the data matrix reader (110) may be configured to capture an image of the cell case (CC) including the data matrix (DM) based on the illumination light (ILb) reflected on the surface of the cell case (CC).

[0045] Referring to FIG. 4, an illuminator (LSc) including a cylindrical lens may be configured to irradiate an illuminating light (ILc) onto a cell case (CC). The illuminating light (ILc) may be linearly focused by the cylindrical lens. The illuminating light (ILc) may reach a portion of the cell case (CC) including a data matrix (DM), and the data matrix reader (110) may be configured to capture an image of the cell case (CC) including the data matrix (DM) based on the illuminating light (ILc) reflected on the surface of the cell case (CC). The illuminator (LSc) of FIG. 4 may be installed at a lower level than the illuminator (LSb) of FIG. 3. That is, each of the optical systems of FIGS. 3 and 4 is a tilted optical system, but the tilt angle of FIG. 3 may be greater than the tilt angle of FIG. 4. Here, the tilt angle is an angle from a normal to an incident surface of the cell case (CC).

[0046] When the data matrix (DM) is successfully read, each of the plurality of data matrix readers (110) may be configured to transmit a signal indicating a can ID to the controller. The controller may be configured to collect can ID data based on the signal, and may be configured to transmit the can ID data to a cell tracking network. The can ID may include a plurality of symbols for distinguishing and / or identifying the cell case (CC). Here, the symbols may collectively refer to symbols, letters, and marks that represent a certain meaning. That is, the can ID may include information for identifying the cell case (CC), and by reading the data matrix (DM) when a process is performed on the cell case (CC), the process performed on the cell case (CC) may be matched with the cell case (CC). Accordingly, historical data on the cell case (CC) may be collected, and tracking of the secondary battery manufacturing process may be provided.

[0047] Here, the controller may be a Programmable Logic Controller (PLC). A PLC is a specialized type of microprocessor-based controller that uses programmable memory to store instructions and implement functions such as logic, sequencing, timing, counting, and arithmetic to control machines and processes. PLCs are easy to operate and program.

[0048] The controller may include a power supply, a central processing unit (CPU), an input interface, an output interface, a communication interface, and memory devices. The power supply may be configured to supply power to other components of the controller, such as the CPU, the input interface, the output interface, the communication interface, and the memory devices, for the operation of the controller. The memory devices may include a read-only memory (ROM) configured to store a system program, such as an operating system, and a random access memory (RAM) configured to store data, such as user programs, status information of input and output devices, timers, counters, and other internal device values. The CPU may be configured to implement logic and control communication between modules that convert input signals into output operation signals. The CPU may operate based on the system program and user program stored in the memory devices. The CPU may be configured to write or read inspection data and measurement data to the data area of ​​the memory devices based on the system program and user program. Conditions or data of industrial devices and production processes may be transmitted to the CPU through the input module. Results processed by the CPU may be transmitted to an actuator through the output module. The communication interface may be configured to relay the transmission and reception of data between the controller and the processors (130, 150).

[0049] However, the controller is not limited thereto, and may include any of a simple controller, a complex processor such as a microprocessor, a CPU, a GPU, a processor configured by software, dedicated hardware, and firmware. The controller may be implemented by, for example, a general-purpose computer or application-specific hardware such as a digital signal processor (DSP), a field programmable gate array (FPGA), and an application-specific integrated circuit (ASIC).

[0050] If the data matrix (DM) reading fails, the data matrix readers (110) can be configured to generate a virtual can ID and match the virtual can ID to the unidentified image (UIM). Accordingly, the virtual can ID can be used for storing and retrieving the unidentified image (UIM). For example, the title of the unidentified image (UIM) can include the virtual can ID.

[0051] A virtual can ID may have a different generation rule (or format) than the can ID, and the virtual can ID may be easily distinguished from the can ID. For example, the length of the virtual can ID may be different from the can ID.

[0052] Unrecognized images (UIM) transmitted from a plurality of data matrix readers (110) can be collected in a hub (120), and the hub (120) can be configured to transmit the collected unrecognized images (UIM) to a processor (130). By designing a facility network using the hub (120), resources required for constructing a facility network can be reduced, and communication between a plurality of data matrix readers (110) and the processor (130) can be made efficient.

[0053] Each processor (130) of the secondary battery manufacturing facilities (100) may be configured to transmit an unrecognized image (UIM) to a server (210). The server (210) may be configured to store original data (i.e., images). The server (210) may be configured to store images such as the unrecognized image (UIM). The server (210) may be, for example, a network attached storage, but is not limited thereto. The server (210) may be configured to further store images captured by a vision machine of each of the secondary battery manufacturing facilities (100).

[0054] The server (210) may be configured to transmit an unrecognized image (UIM) to the server (220). The server (220) may be configured to receive the unrecognized image (UIM) from the server (210). The server (220) may be configured to analyze the unrecognized image (UIM) from the server (210). The server (220) may be configured to generate classification data (CD) based on the unrecognized image (UIM). The classification data (CD) may have a format such as TXT, XLS, and CSV. The server (220) may be configured to determine a feature that interferes with the reading of a data matrix of the unrecognized image (UIM). The classification data (CD) may represent a feature that interferes with the reading of the unrecognized image (UIM). The classification data (CD) may include a feature that interferes with the reading of the unrecognized image (UIM) and a virtual can ID matched to the feature. The server (220) may be configured to transmit classification data (CD) to a third server (230).

[0055] Features that interfere with the reading of an unidentified image (UIM) may vary depending on the configuration of the optical system of the data matrix reader (110). For example, when the optical system of the data matrix reader (110) includes an illuminator (LSa) configured to irradiate a ring-shaped illumination light (ILa), as in FIG. 2, features that interfere with reading may include misalignment of the optical system including the data matrix reader (110), such as contamination of the data matrix (DM) by an electrolyte, contamination of the data matrix (DM) by a substance other than the electrolyte, darkness of an unidentified image (UIM), close spacing between cell cases (CC), diffuse reflections by elements within the secondary battery manufacturing facility (100), scratches on the data matrix (DM), non-formation of the data matrix (DM), absence of cell cases (CC) in an unidentified image (UIM), shooting trigger timing error of the data matrix reader (110), and tilting of the data matrix reader (110).

[0056] As another example, when the optical system of the data matrix reader (110) is an illuminator (LSb) configured to irradiate a spot illumination light (ILb), as in FIG. 3, features that interfere with readout may include contamination of the data matrix (DM) by an electrolyte, contamination of the data matrix (DM) by a substance other than the electrolyte, close spacing between cell cases (CC), scratches on the data matrix (DM), non-formation of the data matrix (DM), absence of a cell case (CC) in an unidentified image (UIM), a shooting trigger timing error of the data matrix reader (110), the data matrix (DM) being out of focus of the data matrix reader (110), and exceeding the readout time of the data matrix reader (110).

[0057] As another example, when the optical system of the data matrix reader (110) is an illumination (LSc) configured to irradiate linear illumination light (ILc), as in FIG. 4, features that interfere with readout may include contamination of the data matrix (DM) by an electrolyte, contamination of the data matrix (DM) by a substance other than the electrolyte, scratches on the data matrix (DM), non-formation of the data matrix (DM), absence of a cell case (CC) in an unidentified image (UIM), a shooting trigger timing error of the data matrix reader (110), the data matrix (DM) being out of focus of the data matrix reader (110), and exceeding the readout time of the data matrix reader (110).

[0058] According to exemplary embodiments, the server (220) may include a deep learning model configured to determine features that impede reading. The deep learning model of the server (220) may be pre-trained to output features that impede reading in an unrecognized image (UIM) when input. The deep learning model of the server (220) may be trained using either a supervised or unsupervised method.

[0059] According to some embodiments, the unidentified image (UIM) may be matched with a device symbol representing the configuration of an optical system including a data matrix reader (110) from which the unidentified image (UIM) originated. For example, the deep learning model of the server (220) may be configured to classify the unidentified image (UIM) in different modes according to the device symbol. For example, the deep learning model of the server (220) may include a first mode configured to generate classification data (CD) based on the unidentified image (UIM) originated from the optical system of FIG. 2, a second mode configured to generate classification data (CD) based on the unidentified image (UIM) originated from the optical system of FIG. 3, and a third mode configured to generate classification data (CD) based on the unidentified image (UIM) originated from the optical system of FIG. 4.

[0060] As another example, the server (220) may include separate deep learning models for each configuration of the optical system including the data matrix reader (110). For example, the server (220) may include a first deep learning model configured to generate classification data (CD) based on an unrecognized image (UIM) derived from the optical system of FIG. 2, a second deep learning model configured to generate classification data (CD) based on an unrecognized image (UIM) derived from the optical system of FIG. 3, and a third deep learning model configured to generate classification data (CD) based on an unrecognized image (UIM) derived from the optical system of FIG. 4.

[0061] As another example, the server (220) may include a deep learning model that operates in a single mode regardless of the configuration of the optical system including the data matrix reader (110) from which the unidentified image (UIM) is derived.

[0062] The server (230) may be configured to receive and store classification data (CD) from the server (220). The server (230) may be, for example, a data warehouse and may store the classification data (CD) for a long period of time based on the product's quality assurance period, etc. Accordingly, tracking of the manufacturing process according to the product's life cycle may be provided.

[0063] The servers (210, 220, 230) may include physical servers or cloud servers. The servers (210, 220, 230) may be implemented as virtual servers, but are not limited thereto. The servers (210, 220, 230) may provide data and analysis results to workers through various frameworks. The frameworks may include protocols that support data transmission, allowing client devices to visualize data through a user interface and provide updated visualizations as the data is calculated by the servers (210, 220, 230). The protocols that support the data transmission may use HTML, JavaScript, and / or JSON.

[0064] The servers (210, 220, 230) may include various Application Programming Interfaces (APIs) for storing data in databases and other data management tools. The APIs may also be used to retrieve data from databases in various data management systems. The data management systems may provide access to the databases, pull data from the databases, retrieve data, and generate metrics. Metrics are tools for visualizing data. Metrics include time-series measurements and can be used for monitoring applications and generating status alerts.

[0065] A client device (300) may transmit a request to a server (230) to retrieve unidentified images (UIM), classification data (CD), and metrics based on the classification data (CD). The server (230) may be configured to retrieve the classification data (CD) in response to the request from the client device (300) and generate metrics based on the classification data (CD). The server (230) may be configured to transmit an API request to the server (210) to load the unidentified images (UIM). The API request may be transmitted via the server (220), or may be transmitted directly from the server (230) to the server (210).

[0066] Here, metrics based on classification data (CD) can be expressed in graphs and tables, such as the recognition rate (or non-recognition rate) of the data matrix (DM) by facility, the recognition rate (or non-recognition rate) of the data matrix (DM) by sub-process, and the non-recognition contribution rate by feature that interferes with the reading of each facility.

[0067] The server (230) may be configured to transmit a Uniform Resource Locator (URL) (or schema) containing source code for displaying an unrecognized image (UIM), classified data (CD), and metrics based on the classified data (CD) to the client device (300). The client device (300) may access the source code for visualizing and displaying the unrecognized image (UIM), classified data (CD), and metrics based on the classified data (CD) through the URL (or schema).

[0068] The processor (130) and servers (210, 220, 230) may be implemented by hardware, firmware, software, or a combination thereof. For example, the processor (130) and servers (210, 220, 230) may include computing devices such as workstation computers, desktop computers, laptop computers, and tablet computers. The processor (130) and servers (210, 220, 230) may also include any one of simple controllers, complex processors such as microprocessors, CPUs, and GPUs, processors configured by software, dedicated hardware, and firmware. The processor (130) and servers (210, 220, 230) may be implemented by, for example, general-purpose computers or application-specific hardware such as digital signal processors (DSPs), field programmable gate arrays (FPGAs), and application specific integrated circuits (ASICs).

[0069] The operations of the processor (130) and the servers (210, 220, 230) may be implemented as instructions stored on a machine-readable medium that can be read and executed by one or more processors. Here, the machine-readable medium may include any mechanism for storing and / or transmitting information in a form readable by a machine (e.g., a computing device). For example, the machine-readable medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium, an optical storage medium, a flash memory, an electrical, optical, acoustical or other form of radio signal (e.g., a carrier wave, an infrared signal, a digital signal, etc.), and any other signal.

[0070] The processor (130) and servers (210, 220, 230) may be configured with firmware, software, routines, and instructions for performing the operations described above or any of the processes described below. For example, the processor (130) and servers (210, 220, 230) may be instantiated within a memory.

[0071] The client device (300) may be any device capable of communicating with the server (230), such as a workstation computer, a notebook computer, a laptop computer, a desktop computer, a tablet computer, a mobile device such as a smart phone, a wearable device, etc. The client device (300) may be configured to generate a request for querying classification data (CD), unidentified images (UIM), and metrics based thereon. The client device (300) may include input tools for inputting the request and a display device for displaying the classification data (CD), unidentified images (UIM), and metrics based thereon.

[0072] The secondary battery manufacturing system (10) can implement a plug-in architecture with an API for data acquisition to provide plug-and-play connectivity for sensors, measuring instruments, and testers. This allows resources from a specific process step and site to be easily transferred to other processes and sites, or new resources to be easily introduced to each process step and site.

[0073] In some embodiments, the secondary battery manufacturing system (10) may further include a manual input system that allows a worker to input manufacturing data. The secondary battery manufacturing system (10) may allow a worker to input data using an input tool and computer-based input of manufacturing data, such as scraping an Excel file. The manual input system may be, for example, a Human-Machine Interface (HMI) of a Supervisory Control And Data Acquisition (SCADA) system. SCADA may typically include a combination of software and hardware, such as a PLC and a Remote Terminal Unit (RTU). The HMI is a screen that supports communication between the operator and the SCADA system and is a key element of the SCADA system. For example, manual input by the HMI may include selecting a defect type and reflecting performance upon completion.

[0074]

[0075] (Example 2)

[0076] FIG. 5 is a flowchart illustrating a method for manufacturing a secondary battery according to exemplary embodiments.

[0077] Referring to FIGS. 1 and 5, at P110, an unrecognized image (UIM) may be received. The unrecognized image (UIM) may be received by a server (220). The server (220) may be configured to search for and load the unrecognized image (UIM) stored in the server (210) based on a virtual can ID.

[0078] Next, classification data (CD) can be generated at P120. The classification data (CD) can be generated by a deep learning model of the server (220). The generation of the classification data (CD) can include determining features of an unrecognized image (UIM) that interfere with the reading of a data matrix (DM), and matching symbols representing the features with virtual can IDs of the unrecognized image (UIM).

[0079]

[0080] (Example 3)

[0081] Fig. 6 illustrates a secondary battery manufacturing system (11) according to other exemplary embodiments.

[0082] Referring to FIG. 6, a secondary battery manufacturing system (11) according to exemplary embodiments may include a plurality of secondary battery manufacturing facilities (100), a server (240), and a client device (300).

[0083] Since the multiple secondary battery manufacturing facilities (100) and client devices (300) are substantially the same as those described with reference to FIGS. 1 to 4, redundant descriptions thereof are omitted.

[0084] The server (240) may be an integrated server. The server (240) may be configured to perform the functions of each of the servers (210, 220, 230) of FIG. 1. According to exemplary embodiments, the server (240) may be a network-attached storage configured to store an unidentified image (UIM), configured to generate classification data (CD, see FIG. 1) based on the unidentified image (UIM), configured to store the classification data (CD, see FIG. 1), and configured to transmit to the client device (300) a Uniform Resource Locator (URL) (or schema) including source code for displaying the unidentified image (UIM), the classification data (CD, see FIG. 1), and metrics based on the classification data (CD, see FIG. 1) in response to a request from the client device (300).

[0085]

[0086] (Example 4)

[0087] Fig. 7 illustrates a secondary battery manufacturing system (12) according to other exemplary embodiments. Referring to Fig. 7, the secondary battery manufacturing system (12) according to the exemplary embodiments may include a plurality of secondary battery manufacturing facilities (100), servers (211, 220), and a client device (300).

[0088] Since the multiple secondary battery manufacturing facilities (100), server (220), and client device (300) are substantially the same as those described with reference to FIGS. 1 to 4, redundant descriptions thereof are omitted.

[0089] The server (211) may be a network-attached storage configured to store unidentified images (UIMs), similar to the server (210) of FIG. 1. The server (211) may be configured to store classification data (CDs) generated by the server (220). The server (211) may be configured to transmit, in response to a request from the client device (100), a Uniform Resource Locator (URL) (or schema) to the client device (300) that includes source code for displaying the unidentified images (UIMs), classification data (CDs, see FIG. 1), and metrics based on the classification data (CDs, see FIG. 1).

[0090]

[0091] The present invention has been described in more detail through drawings and examples. However, the configurations described in the drawings or examples described in this specification are merely embodiments of the present invention and do not represent all of the technical ideas of the present invention. Therefore, it should be understood that various equivalents and modified examples may exist as of the time of this application.

Claims

1. A data matrix reader configured to read out a data matrix of a cell case, configured to capture an unrecognized image including the data matrix that has failed to be read out, and configured to match the unrecognized image with a virtual can ID; A first server configured to store unrecognized images transmitted from the data matrix reader; and A secondary battery manufacturing system comprising a second server configured to determine a feature that impedes reading of the data matrix based on the unrecognized image transmitted from the first server.

2. In paragraph 1, A secondary battery manufacturing system, characterized in that the title of the above unrecognized image includes the virtual can ID.

3. In paragraph 1, A secondary battery manufacturing system, characterized in that the first server is a network attached storage.

4. In paragraph 1, A secondary battery manufacturing system, wherein the second server comprises a deep learning model configured to determine the feature of the data matrix based on the unrecognized image.

5. In paragraph 1, A secondary battery manufacturing system, characterized in that the second server is configured to generate classification data by matching a symbol representing the feature with the virtual can ID.

6. In paragraph 5, A secondary battery manufacturing system further comprising a third server configured to store the above classification data.

7. In paragraph 6, A secondary battery manufacturing system, characterized in that the third server is configured to transmit, to the client device, a Uniform Resource Locator (URL) including source code for displaying the unrecognized image, the classification data, and metrics based on the classification data in response to a request from the client device.

8. In paragraph 1, A secondary battery manufacturing system, characterized in that the data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from a ring-shaped light.

9. In paragraph 8, A secondary battery manufacturing system, characterized in that the features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, darkness of the unrecognized image, close spacing of the cell cases in the unrecognized image, diffuse reflection, scratches on the data matrix, non-formation of the data matrix of the cell cases, absence of the cell cases in the unrecognized image, shooting trigger timing error of the data matrix reader, and misalignment of the data matrix reader.

10. In paragraph 1, A secondary battery manufacturing system, characterized in that the data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from a spot light.

11. In paragraph 10, A secondary battery manufacturing system, characterized in that the features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, closeness of the gap between the cell cases in the unrecognized image, a scratch on the data matrix, non-formation of the data matrix of the cell case, absence of the cell case in the unrecognized image, an error in the shooting trigger timing of the data matrix reader, the data matrix being out of focus of the data matrix reader, and exceeding the reading time of the data matrix reader.

12. In paragraph 1, A secondary battery manufacturing system, characterized in that the data matrix reader is configured to capture the unrecognized image by receiving illumination light irradiated onto the data matrix from an illumination including a cylindrical lens.

13. In paragraph 12, A secondary battery manufacturing system, characterized in that the features of the unrecognized image include contamination of the data matrix by an electrolyte, contamination of the data matrix by a substance other than the electrolyte, a scratch on the data matrix, non-formation of the data matrix in the cell case, absence of the cell case in the unrecognized image, an error in the shooting trigger timing of the data matrix reader, the data matrix being out of focus of the data matrix reader, and exceeding the reading time of the data matrix reader.

Images