Secondary battery manufacturing system

Abstract

According to an exemplary embodiment, a secondary battery manufacturing system is provided. The system includes: a data matrix reader configured to read a data matrix of a cell housing, configured to capture an unrecognized image including the data matrix that fails to read, and configured to match the unrecognized image with a virtual tank 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 of the reading of the interference data matrix based on the unrecognized image transmitted from the first server.

Description

Technical Field

[0001] This disclosure relates to a secondary battery manufacturing system. This application claims priority to Korean Patent Application 10-2024-0006416, filed January 16, 2024, the disclosure of which is incorporated herein by reference. Background Technology

[0002] Unlike primary batteries, secondary batteries can be charged and discharged multiple times. They are widely used as an energy source for various wireless devices, including mobile phones, laptops, and cordless vacuum cleaners. In recent years, due to increased energy density and economies of scale that have significantly reduced the manufacturing cost per unit capacity of secondary batteries and increased the driving range of battery electric vehicles (BEVs) to levels comparable to fuel-powered vehicles, the primary use of secondary batteries has shifted from mobile devices to the transportation sector.

[0003] Secondary batteries are manufactured through electrode processes, assembly processes, and activation processes. To improve the yield and reliability of secondary battery manufacturing processes, ensuring traceability of the manufacturing process is crucial. Therefore, various studies have been conducted to ensure the traceability of secondary battery manufacturing processes. Summary of the Invention

[0004] Technical issues

[0005] The problem addressed by the technical concept of this disclosure is to provide a secondary battery manufacturing system with improved traceability.

[0006] Technical solution

[0007] According to an exemplary embodiment of this disclosure, a secondary battery manufacturing system is provided to address the aforementioned problems. The system includes: a data matrix reader configured to read a data matrix from a battery cell casing, configured to capture an unidentified image including a data matrix that failed to be read, and configured to match the unidentified image with a virtual can ID; a first server configured to store the unidentified images transmitted from the data matrix reader; and a second server configured to determine features interfering with the reading of the data matrix based on the unidentified images transmitted from the first server.

[0008] The title of the unidentified image includes the virtual tank ID.

[0009] The first server is a network-attached storage device.

[0010] The second server includes a deep learning model configured to determine the features of the data matrix based on the unidentified image.

[0011] The second server is configured to generate classification data by matching the symbol representing the feature with the virtual tank ID.

[0012] The system also includes a third server configured to store the classification data.

[0013] The third server is configured to transmit a Uniform Resource Locator (URL) to the client device in response to a request from the client device. The URL includes the unidentified image, the classification data, and source code for displaying metrics based on the classification data.

[0014] The data matrix reader is configured to capture the unidentified image by receiving illumination light from a ring illuminator that is incident on the data matrix.

[0015] The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; darkness of the unidentified image; proximity of the spacing between the battery cell casings in the unidentified image; diffuse reflection; scratches on the data matrix; failure of the data matrix to form within the battery cell casing; absence of the battery cell casing in the unidentified image; timing error of the data matrix reader's shooting trigger; and misalignment of the data matrix reader.

[0016] The data matrix reader is configured to capture the unidentified image by receiving illumination light from a point illuminator onto the data matrix.

[0017] The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; proximity of the spacing between the battery cell casings in the unidentified image; scratches on the data matrix; the data matrix not being formed in the battery cell casing; the battery cell casing not being present in the unidentified image; timing error of the data matrix reader's shooting trigger; the data matrix being outside the focus of the data matrix reader; and reading timeout of the data matrix reader.

[0018] The data matrix reader is configured to capture an unidentified image of the data matrix by receiving illumination light from an illuminator including a cylindrical lens illuminating the data matrix.

[0019] The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; scratches on the data matrix; the data matrix not being formed in the cell casing; the cell casing not being present in the unidentified image; timing error of the data matrix reader's shooting trigger; the data matrix being outside the focus of the data matrix reader; and reading timeout of the data matrix reader.

[0020] Beneficial effects

[0021] A secondary battery manufacturing system according to an exemplary embodiment of this disclosure can be configured to generate categorized data indicating features that lead to read failures in a data matrix. Therefore, monitoring of cell traceability can be provided, and cell tracking with higher accuracy can be offered.

[0022] The effects obtainable from the exemplary embodiments of this disclosure are not limited to those described above, and other effects not mentioned can be clearly derived and understood by those skilled in the art from the following description. That is, those skilled in the art can also derive unintended effects from practicing the exemplary embodiments of this disclosure. Attached Figure Description

[0023] Figure 1 This is a block diagram illustrating a secondary battery manufacturing system according to an exemplary embodiment.

[0024] Figures 2 to 4 This is a diagram illustrating an optical system used for imaging a data matrix.

[0025] Figure 5 This is a flowchart illustrating a method for manufacturing a secondary battery according to an exemplary embodiment.

[0026] Figure 6 A secondary battery manufacturing system according to other exemplary embodiments is shown.

[0027] Figure 7 A secondary battery manufacturing system according to other exemplary embodiments is shown. Detailed Implementation

[0028] The preferred embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be noted that the terms and words used in this specification and claims should not be interpreted in their ordinary or dictionary sense, but rather based on the principle that the inventors may define the concepts of the terms as they deem best suited to interpret the disclosure, and to be interpreted in a meaning and concept consistent with the technical spirit of this disclosure.

[0029] Therefore, it should be understood that the embodiments described herein and the configurations shown in the accompanying drawings are only the most preferred embodiments of this disclosure and do not represent all the technical ideas of this disclosure. Furthermore, various equivalents and variations may exist to replace these embodiments at the time of filing this application.

[0030] Furthermore, in describing this disclosure, specific descriptions of the configurations or features of the relevant disclosures are omitted where such detailed descriptions would obscure the substance of this disclosure.

[0031] Because embodiments of this disclosure are provided to illustrate the disclosure more fully to those skilled in the art, the shapes and dimensions of components in the drawings may be enlarged, omitted, or shown schematically for clarity. Therefore, the dimensions or proportions of each component do not necessarily indicate its actual size or proportion.

[0032] (First Implementation)

[0033] Figure 1 This is a block diagram illustrating a secondary battery manufacturing system 10 according to an exemplary embodiment.

[0034] Figures 2 to 4 This is a diagram illustrating an optical system used for imaging a data matrix (DM).

[0035] refer to Figure 1 The secondary battery manufacturing system 10 according to an exemplary embodiment may include a plurality of secondary battery manufacturing facilities 100, servers 210, 220, 230 and client devices 300.

[0036] refer to Figure 1 and Figure 2 The secondary battery manufacturing facility 100 can be configured to perform secondary battery assembly processes. The secondary battery manufacturing facility 100 can also be configured to perform assembly processes for, for example, can-type secondary batteries. Can-type batteries may include a cell casing CC and electrode assemblies within the cell casing CC. The secondary battery manufacturing facility 100 may include a plurality of data matrix readers 110, hubs 120, and processors 130.

[0037] The cell casing CC can be a metal can. The cell casing CC can be a cylindrical can or a prismatic can. The electrode assembly can include a wound structure of a positive electrode, a negative electrode, and a separator, or it can include a stack of a positive electrode, a negative electrode, and a separator. The positive electrode can include a positive current collector and a positive active material, and the negative electrode can include a negative current collector and a negative active material.

[0038] The thickness of the positive electrode current collector can range from about 3 μm to about 500 μm. The positive electrode current collector can have high conductivity and should not cause chemical changes in the final manufactured secondary battery. The positive electrode current collector can include, for example, stainless steel, aluminum, nickel, titanium, calcined carbon, and aluminum alloys. It can also include stainless steel with a surface treated with carbon, nickel, titanium, silver, etc. The surface of the positive electrode current collector can include a micro-uneven structure to increase the adhesion of the active material. The positive electrode current collector can have shapes such as films, sheets, foils, meshes, porous structures, foams, and nonwovens.

[0039] The thickness of the negative electrode current collector can range from approximately 3 μm to approximately 500 μm. The negative electrode current collector can remain chemically unchanged in the final manufactured secondary battery and can exhibit high conductivity. The negative electrode current collector can include copper, stainless steel, aluminum, nickel, titanium, calcined carbon, and aluminum-cadmium alloys. It can also include stainless steel surface-treated with carbon, nickel, titanium, silver, etc. The surface of the negative electrode current collector can include micro-textures to increase the adhesion of the active material. The negative electrode current collector can take the form of a film, sheet, foil, mesh, porous structure, foam, nonwoven fabric, etc.

[0040] Positive electrode active materials are materials that can induce electrochemical reactions. Positive electrode active materials can be lithium transition metal oxides. They can be, for example, layered compounds, 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, and compounds of the formula LiNi... 1- y M y O2 represents lithium nickel oxides (where M is any one of Co, Mn, Al, Cu, Fe, Mg, B, Cr, Zn, and Ga, and 0.01 ≤ y ≤ 0.7), derived from Li 1+z Ni b Mn c Co 1-(b+c+d) M d O (2-e) A e Lithium-nickel-cobalt-manganese composite oxides (such as Li) 1+z Ni 1 / 3 Co 1 / 3 Mn 1 / 3 O2, Li 1+z Ni 0.4 Mn 0.4 Co 0.2O2 (where -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)), and by the formula Li 1+x M 1-y M'yPO 4-z X z represented olivine-based lithium metal phosphate (where M is a transition metal, more specifically any one of Fe, Mn, Co, and Ni, M' is any one of Al, Mg, and Ti, and X is any one of F, S, and N; -0.5 ≤ x ≤ +0.5, 0 ≤ y ≤ 0.5, and 0 ≤ z ≤ 0.1).

[0041] The negative electrode active material may include carbon, such as anthracite, graphitized carbon, graphite-based carbon, etc. The negative electrode active material may include metal composite oxides, such as Li x Fe2O3 (0 ≤ x ≤ 1), Li x 1+x WO2 (0 ≤ x ≤ 1), Sn x Me 1-x Me' y O z (where Me is any one of Mn, Fe, Pb, and Ge, Me' is any one of Al, B, P, Si, Group 1, Group 2, and Group 3 elements of the periodic table, and halogens, and 0 < x ≤ 1, 1 ≤ y ≤ 3, and 1 ≤ z ≤ 8). The negative electrode active material may include, for example, lithium metal, lithium alloy, silicon-based alloy, or tin-based alloy. The negative electrode active material may include metal oxides, such as SnO, SnO2, PbO, PbO2, Pb2O3, Pb3O, Sb2O3, Sb2O4, Sb2O5, GeO, GeO2, Bi2O3, Bi2O4, Bi2O5, etc. The negative electrode active material may include, for example, conductive polymers, such as polyacetylene, lithium cobalt nickel-based materials, etc.).

[0042] Hereinafter, the technical idea of the present disclosure will be described with reference to an embodiment in which the cell case CC is a cylindrical can. However, this is for illustrative purposes only and does not limit the technical idea of the present disclosure in any way. Those of ordinary skill in the art will readily arrive at embodiments in which the cell case CC is a prismatic can based on the content described herein.

[0043] Each secondary battery manufacturing facility 100 can be configured to perform a series of sub-processes included in the assembly process of can-type batteries. Sub-processes may include: inserting a lower insulating component into a cell housing CC; inserting an electrode assembly into the cell housing CC; welding the negative terminal and electrode assembly of the cell housing CC; compressing the upper end of the cell to reduce its outer diameter; inserting an upper insulating component into the cell housing CC; shaping the cell housing CC to reduce the diameter of the stepped portion of the cell housing CC, thereby accommodating a top cover assembly; inspecting the cell housing CC using X-rays; injecting electrolyte into the cell housing CC; welding the cover assembly to the positive terminal of the electrode assembly; sealing the battery cell by pressing the cover assembly and gasket together into the cell housing CC; pressurizing the battery cell to adjust its height (e.g., reduce it); marking a batch number on the outside of the cell housing CC; measuring the internal resistance of the battery cell based on open-circuit voltage; and unloading the battery cell from the secondary battery manufacturing facility 100 and loading the battery cell onto a tray. Each subprocess may include reading a data matrix DM for tracking and recording the subprocess. As a non-limiting embodiment, the data matrix DM may be a two-dimensional barcode.

[0044] Reading the data matrix DM may include: taking an image of a portion of the cell casing CC that includes the data matrix DM, or taking an image of the entire cell casing CC that includes the data matrix DM; and reading the information contained in the data matrix DM from the image. The data matrix DM may be read by multiple data matrix readers 110.

[0045] refer to Figure 2 The illuminator LSa can be configured to illuminate the cell housing CC with illumination light ILa. The illuminator LSa can be a ring illuminator, wherein the illumination light ILa can have a ring beam cross-section. The illumination light ILa can reach the entire surface of the cell housing CC along the periphery of the cell housing CC, and the data matrix reader 110 can be configured to capture an image of the cell housing CC, including the data matrix DM, based on the illumination light ILa reflected on the surface of the cell housing CC.

[0046] refer to Figure 3 The illuminator LSb can be configured to illuminate the battery cell housing CC with illumination light ILb. Here, the illuminator LSb can be a point illuminator, and the optics of the illuminator LSb can include a spherical lens such that the illumination light ILb has a beam cross-section that converges to a point. The illumination light ILb can reach a portion of the battery cell housing CC including the data matrix DM, and the data matrix reader 110 can be configured to capture an image of the battery cell housing CC including the data matrix DM based on the illumination light ILb reflected from the surface of the battery cell housing CC.

[0047] refer to Figure 4An illuminator LSc, including a cylindrical lens, can be configured to illuminate the cell housing CC with an illumination light ILc. The illumination light ILc can be linearly focused by means of the cylindrical lens. The illumination light ILc can reach the portion of the cell housing CC including the data matrix DM, and the data matrix reader 110 can be configured to capture an image of the cell housing CC including the data matrix DM based on the illumination light ILc reflected from the surface of the cell housing CC. Figure 3 Compared to the illumination light LSb in the middle, Figure 4 The illumination LSC in the system can be installed at a lower height. That is, Figure 3 and Figure 4 Each optical system in the diagram is a tilted optical system, but Figure 3 The tilt angle in the middle can be greater than Figure 4 The tilt angle in the diagram. Here, the tilt angle is the angle from the normal to the incident surface of the cell casing CC.

[0048] Upon successful reading of the data matrix DM, each of the multiple data matrix readers 110 can be configured to transmit a signal indicating the can ID to the controller. The controller can be configured to collect can ID data based on the signal and can be configured to transmit the can ID data to the cell tracking network. The can ID may include multiple symbols for distinguishing and / or identifying the cell casing CC. Here, the symbols can refer to any sign, character, or mark used to indicate meaning. In other words, the can ID may include information for identifying the cell casing CC, and when reading the data matrix DM by performing a process on the cell casing CC, the cell casing CC can be matched with the process performed on the cell casing CC. Therefore, historical data about the cell casing CC can be collected, and traceability of the secondary battery manufacturing process can be provided.

[0049] The controller here can be a programmable logic controller (PLC). A PLC is a special form 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.

[0050] The controller may include a power supply, a CPU, input interfaces, output interfaces, communication interfaces, and storage devices. The power supply may be configured to provide power to other components of the controller, such as the CPU, input interfaces, output interfaces, communication interfaces, and storage devices, for the operation of the controller. The storage devices may include a read-only memory (ROM) configured to store system programs (such as an operating system) and a random access memory (RAM) configured to store user programs and data (such as status information of input and output devices, and values ​​of timers, counters, and other internal devices). The CPU may be configured to control communication between modules implementing logic and to convert input signals into output behavior signals. The CPU may operate based on system programs and user programs stored in the storage devices. The CPU may be configured to write check data and measurement data to or read check data and measurement data from the data areas of the storage devices based on the system programs and user programs. Conditions or data from industrial equipment and production processes may be transmitted to the CPU via input modules. Results processed by the CPU may be sent to actuators via output modules. The communication interfaces may be configured to relay data to / from the controller and processors 130, 150.

[0051] However, but not limited to, a controller may include any of the following: a simple controller; a complex processor such as a microprocessor, CPU, or GPU; or a processor configured by software, dedicated hardware, and firmware. For example, a controller may be instantiated using a general-purpose computer or dedicated hardware such as a digital signal processor (DSP), a field-programmable gate array (FPGA), or an application-specific integrated circuit (ASIC).

[0052] If the data matrix DM is not successfully read, the data matrix reader 110 can be configured to generate a virtual can ID and match the virtual can ID with an unidentified image (UIM). Therefore, the virtual can ID can be used to store and retrieve the unidentified image (UIM). For example, the header of the unidentified image (UIM) may include the virtual can ID.

[0053] Virtual can IDs can have different generation rules (or formats) than can IDs, and virtual can IDs can be easily distinguished from can IDs. For example, virtual can IDs can have a different length than can IDs.

[0054] Unidentified images (UIMs) transmitted from multiple data matrix readers 110 can be aggregated at a hub 120, which can be configured to transmit the aggregated UIMs to a processor 130. By designing the facility network using the hub 120, the resources required to build the facility network can be reduced, and communication between the multiple data matrix readers 110 and the processor 130 can be simplified.

[0055] Each processor 130 of each secondary battery manufacturing facility 100 can be configured to transmit unidentified images (UIMs) to server 210. Server 210 can be configured to store raw data (i.e., images). Server 210 can be configured to store images, such as unidentified images (UIMs). Server 210 can be, for example, but not limited to, a network-attached storage device. Server 210 can be configured to further store images captured by vision machines at each secondary battery manufacturing facility 100.

[0056] Server 210 can be configured to send unidentified images (UIMs) to server 220. Server 220 can be configured to receive unidentified images (UIMs) from server 210. Server 220 can be configured to analyze the unidentified images (UIMs) from server 210. Server 220 can be configured to generate classification data (CD) based on the unidentified images (UIMs). The classification data CD can have formats such as TXT, XLS, and CSV. Server 220 can be configured to determine extracted features of a data matrix interfering with the unidentified images (UIMs). The classification data (CD) can represent features of the readings of the interfering unidentified images (UIMs). The classification data CD can include features of the readings of the interfering unidentified images (UIMs) and virtual tank IDs matching the features. Server 220 can be configured to transmit the classification data (CD) to a third server 230.

[0057] The characteristics that interfere with the reading of unidentified images (UIMs) can be varied depending on the configuration of the optics of the data matrix reader 110. For example, if the optics of the data matrix reader 110 include a light source (LSa) configured to illuminate a ring illumination light ILa (such as... Figure 2 As shown), the characteristics that interfere with reading can include: contamination of the data matrix DM by the electrolyte; contamination of the data matrix DM by substances other than the electrolyte; darkness of the unidentified image (UIM); proximity of the gaps between cell housings (CC); diffuse reflection of components within the secondary battery manufacturing facility 100; scratches on the data matrix DM; failure to form the data matrix DM; absence of cell housings (CC) in the unidentified image (UIM); misalignment of the optics of the data matrix reader 110 (such as shooting trigger timing error of the data matrix reader 110); and tilt of the data matrix reader 110.

[0058] As another embodiment, when the optics of the data matrix reader 110 are configured as a light source (LSb) illuminating a point illumination light (ILb) (e.g.) Figure 3As shown, the characteristics of interference reading include: electrolyte contamination of the data matrix (DM); contamination of the data matrix (DM) by substances other than the electrolyte; proximity of the spacing between cell housings (CC); scratches on the data matrix DM; failure to form the data matrix DM; absence of cell housings (CC) in the unidentified image (UIM); shooting trigger timing error of the data matrix reader 110; the data matrix DM being outside the focus of the data matrix reader 110; and reading timeout of the data matrix reader 110.

[0059] As another embodiment, when the optics of the data matrix reader 110 are configured as a light source (LSc) illuminating linear illumination light (ILc) (e.g.) Figure 4 As shown, the characteristics of interference reading include: electrolyte contamination of the data matrix (DM); contamination of the data matrix (DM) by substances different from the electrolyte; scratches on the data matrix (DM); failure to form the data matrix (DM); absence of the cell housing (CC) in the unidentified image (UIM); shooting trigger timing error of the data matrix reader 110; the data matrix (DM) being outside the focus of the data matrix reader 110; and reading timeout of the data matrix reader 110.

[0060] According to an exemplary embodiment, server 220 may include a deep learning model configured to determine features that interfere with reads. Given an unidentified image (UIM) as input, the deep learning model of server 220 may be pre-trained to output features that interfere with reads appearing in the unidentified image (UIM). The deep learning model of server 220 may be trained using either supervised or unsupervised methods.

[0061] According to some implementations, an unidentified image (UIM) can be matched with a device symbol representing the configuration of an optical system, which includes a data matrix reader 110 from which the UIM originates. In one embodiment, a deep learning model of server 220 can be configured to classify the UIM in different modes based on the device symbol. For example, the deep learning model of server 220 may include: a first mode configured to classify the UIM based on the data matrix reader 110 from which the UIM originates. Figure 2 Unidentified images (UIM) of the optical system generate classification data (CD); a second mode, configured to be based on data derived from... Figure 3 Unidentified images (UIM) of the optical system generate classification data (CD); and a third mode, configured to be based on data derived from... Figure 4 Unidentified images (UIM) of optical systems generate classification data (CD).

[0062] As another embodiment, server 220 may include separate deep learning models for each configuration of the optical system including data matrix reader 110. For example, server 220 may include: a first deep learning model configured to be based on data from... Figure 2 Unidentified images (UIM) derived from the optical system generate classification data (CD); a second deep learning model, configured to be based on... Figure 3 Unidentified images (UIM) derived from the optical system generate classification data (CD); and a third deep learning model, configured to be based on... Figure 4 Unidentified images (UIM) derived from the optical system generate classification data (CD).

[0063] As another embodiment, server 220 may include a deep learning model that operates in a single mode independent of the configuration of an optical system, which includes a data matrix reader 110 that generates unidentified images (UIMs).

[0064] Server 230 can be configured to receive and store categorized data (CD) from server 220. Server 230 can be, for example, a data warehouse, and can store categorized data CD for extended periods, such as based on product warranty periods. Therefore, it is possible to provide tracking of the manufacturing process throughout the product's lifecycle.

[0065] Servers 210, 220, and 230 may include physical servers or cloud servers. Servers 210, 220, and 230 may be instantiated as virtual servers, but are not limited to this. Servers 210, 220, and 230 may provide data and analysis results to operators via various frameworks. Frameworks may include protocols supporting data transmission to allow client devices to visualize data via a user interface and provide updated visualizations as servers 210, 220, and 230 perform data calculations. Protocols supporting data transmission may use HTML, JavaScript, and / or JSON.

[0066] Servers 210, 220, and 230 may include various application programming interfaces (APIs) for storing data in databases and other data management tools. APIs can also be used to retrieve data from databases in various data management systems. Data management systems can provide access to databases, extract data from databases, retrieve data, and generate metrics. In this context, metrics are tools used to visualize data. Metrics include time-series generated measurements and can be used to monitor applications and generate status alerts.

[0067] Client device 300 may send a request to server 230 to query unidentified images (UIM), classification data (CD), and metrics based on the classification data (CD). Server 230 may be configured to retrieve the classification data CD and generate metrics based on the classification data CD in response to a request from client device 300. Server 230 may be configured to send an API request to server 210 for loading the unidentified image (UIM). The API request may be sent via server 220, or alternatively, the API request may be sent directly from server 230 to server 210.

[0068] Here, the categorical data (CD)-based metrics can be represented by graphs regarding the facility’s identified (or unidentified) data matrix (DM) rate, the subprocess’s identified (or unidentified) data matrix (DM) rate, and the unidentified contribution rate of features that interfere with the reading of each facility.

[0069] Server 230 can be configured to send a Uniform Resource Locator (URL) (or pattern) to client device 300, the URL (or pattern) including source code for displaying unidentified images (UIM), classification data (CD), and classification data (CD)-based metrics on client device 300. Client device 300 can access the source code for visualizing and displaying unidentified images (UIM), classification data (CD), and classification data (CD)-based metrics via the URL (or pattern).

[0070] Processor 130 and servers 210, 220, 230 can be instantiated as hardware, firmware, software, or combinations thereof. For example, processor 130 and servers 210, 220, 230 can include computing devices such as workstation computers, desktop computers, laptop computers, tablet computers, etc. Processor 130 and servers 210, 220, 230 can include simple controllers; complex processors such as microprocessors, CPUs, or GPUs; and any of processors configured by software, dedicated hardware, and firmware. Processor 130 and servers 210, 220, 230 can be instantiated by, for example, general-purpose computers or dedicated hardware such as digital signal processors (DSPs), field-programmable gate arrays (FPGAs), or application-specific integrated circuits (ASICs).

[0071] The operation of processor 130 and servers 210, 220, 230 can be instantiated as instructions stored on a machine-readable medium, which can be read and executed by one or more processors. Here, the machine-readable medium can include any mechanism for storing and / or transmitting information in a machine-readable (e.g., computing device) form. For example, a machine-readable medium can include read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, flash memory, electrical, optical, acoustic, or other forms of propagation signals (e.g., carrier waves, infrared signals, digital signals, etc.), and any other signals.

[0072] Processor 130 and servers 210, 220, 230 may be configured with firmware, software, routines, and instructions to perform the foregoing operations or any of the processes described herein. For example, processor 130 and servers 210, 220, 230 may be instantiated in memory.

[0073] Client device 300 can be any device used to communicate with server 230, such as a workstation computer, laptop computer, notebook computer, desktop computer, mobile device (such as a tablet, smartphone), and wearable device. Client device 300 can be configured to generate requests to query about categorical data (CD), unidentified images (UIM), and metrics based on categorical data (CD) and unidentified images (UIM). Client device 300 may include input tools for entering requests and display devices for displaying categorical data, unidentified images (UIM), and metrics based on categorical data and unidentified images.

[0074] The secondary battery manufacturing system 10 can instantiate a plug-in architecture with APIs for data acquisition to provide plug-and-play connectivity for sensors, instruments, and inspectors. Therefore, resources at specific process steps and sites can be easily transferred to other processes and sites, or new resources can be easily introduced at each process step and site.

[0075] In some embodiments, the secondary battery manufacturing system 10 may also include a manual input system that allows operators to input manufacturing data. The secondary battery manufacturing system 10 may allow operator data input using input tools and computer-based input of manufacturing data, such as capturing Excel files. The manual input system may be a human-machine interface (HMI) for example, a supervisory control and data acquisition system. SCADA typically includes a combination of software and hardware, such as a PLC and a remote terminal unit (RTU). The HMI is a key component of the SCADA system because it is the interface that enables operators to communicate with the SCADA system. Manual input to the HMI may include, for example, selecting defect types and reflecting performance upon completion.

[0076] (Second Implementation)

[0077] Figure 5 This is a flowchart illustrating a method for manufacturing a secondary battery according to an exemplary embodiment.

[0078] refer to Figure 1 and Figure 5 At P110, unidentified images (UIMs) can be received. Unidentified images (UIMs) can be received by server 220. Server 220 can be configured to retrieve and load unidentified image UIMs stored on server 210 based on virtual tank IDs.

[0079] Next, at P120, classification data (CD) can be generated. Classification data CD can be generated by a deep learning model on server 220. Generating classification data CD may include: determining the features of the interference data matrix (DM) read from the unidentified image (UIM); and matching the symbols representing the features with the virtual tank IDs of the unidentified image (UIM).

[0080] (Third implementation)

[0081] Figure 6 A secondary battery manufacturing system 11 according to another exemplary embodiment is shown.

[0082] refer to Figure 6 The secondary battery manufacturing system 11 according to an exemplary embodiment may include a plurality of secondary battery manufacturing facilities 100, a server 240 and a client device 300.

[0083] Multiple secondary battery manufacturing facilities 100 and client devices 300 and reference Figures 1 to 4 The descriptions are essentially the same, so repeated descriptions of them have been omitted.

[0084] Server 240 can be an integrated server. Server 240 can be configured to execute... Figure 1 The functionality of each of servers 210, 220, and 230. According to an exemplary embodiment, server 240 may be a network-attached storage device configured to store unidentified images (UIMs), and may be configured to generate classification data (CDs) based on the unidentified images (UIMs), see [link to documentation]. Figure 1 It can also be configured to transmit a Uniform Resource Locator (URL) (or schema) to the client device 300 in response to a request from the client device 300. This URL includes source code for displaying unidentified images (UIMs) on the client device 300, classification data (CD, see below). Figure 1 ) and classification-based data (CD, see Figure 1 ) measurement.

[0085] (Fourth implementation)

[0086] Figure 7 A secondary battery manufacturing system 12 according to another exemplary embodiment is shown. (Reference) Figure 7 The secondary battery manufacturing system 12 according to an exemplary embodiment may include a plurality of secondary battery manufacturing facilities 100, servers 211, 220 and client devices 300.

[0087] Multiple secondary battery manufacturing facilities 100, server 220, and client device 300 and reference Figures 1 to 4 The descriptions are essentially the same, so repeated descriptions of them have been omitted.

[0088] Server 211 may be a network-attached storage device configured to store unidentified images (UIM), similar to Figure 1 Server 210. Server 211 can be configured to store classification data (CD) generated by server 220. Server 211 can be configured to transmit a Uniform Resource Locator (URL) (or schema) to client device 300 in response to a request from client device 100. The Uniform Resource Locator includes a URL for displaying unidentified images (UIM) and classification data (CD) on client device 300. Figure 1 ) and classification-based data (CD, see Figure 1 The source code for the metric.

[0089] The present disclosure has been described in more detail above with reference to the accompanying drawings and embodiments. However, it should be understood that the configurations shown in the drawings or embodiments described herein are merely one embodiment of the present disclosure and do not represent all the technical ideas of the present disclosure. Furthermore, various equivalents and variations may exist at the time of filing this application.

Claims

1. A secondary battery manufacturing system, the secondary battery manufacturing system comprising: A data matrix reader, configured to read a data matrix from a battery cell casing, configured to capture an unidentified image including a data matrix that failed to be read, and configured to match the unidentified image with a virtual tank ID; A first server, configured to store the unidentified images transmitted from the data matrix reader; as well as A second server is configured to determine features that interfere with the reading of the data matrix based on the unidentified image transmitted from the first server.

2. The secondary battery manufacturing system according to claim 1, wherein, The title of the unidentified image includes the virtual tank ID.

3. The secondary battery manufacturing system according to claim 1, wherein, The first server is a network-attached storage device.

4. The secondary battery manufacturing system according to claim 1, wherein, The second server includes a deep learning model configured to determine the features of the data matrix based on the unidentified image.

5. The secondary battery manufacturing system according to claim 1, wherein, The second server is configured to generate classification data by matching symbols representing the features with the virtual tank ID.

6. The secondary battery manufacturing system according to claim 5, further comprising: A third server is configured to store the categorized data.

7. The secondary battery manufacturing system according to claim 6, wherein, The third server is configured to transmit a Uniform Resource Locator (URL) to the client device in response to a request from the client device. The URL includes the unidentified image, the classification data, and source code for displaying metrics based on the classification data.

8. The secondary battery manufacturing system according to claim 1, wherein, The data matrix reader is configured to capture the unidentified image by receiving illumination light from a ring illuminator that is incident on the data matrix.

9. The secondary battery manufacturing system according to claim 8, wherein, The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; darkness of the unidentified image; proximity of the spacing between the battery cell casings in the unidentified image; diffuse reflection; scratches on the data matrix; failure of the data matrix to form within the battery cell casing; absence of the battery cell casing in the unidentified image; timing error of the data matrix reader's shooting trigger; and misalignment of the data matrix reader.

10. The secondary battery manufacturing system according to claim 1, wherein, The data matrix reader is configured to capture the unidentified image by receiving illumination light from a point illuminator onto the data matrix.

11. The secondary battery manufacturing system according to claim 10, wherein, The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; proximity of the spacing between the battery cell casings in the unidentified image; scratches on the data matrix; the data matrix not being formed in the battery cell casing; the battery cell casing not being present in the unidentified image; timing error of the data matrix reader's shooting trigger; the data matrix being outside the focus of the data matrix reader; and reading timeout of the data matrix reader.

12. The secondary battery manufacturing system according to claim 1, wherein, The data matrix reader is configured to capture an unidentified image of the data matrix by receiving illumination light from an illuminator including a cylindrical lens illuminating the data matrix.

13. The secondary battery manufacturing system according to claim 12, wherein, The features of the unidentified image include: contamination of the data matrix by the electrolyte; contamination of the data matrix by a substance different from the electrolyte; scratches on the data matrix; the data matrix not being formed in the cell casing; the cell casing not being present in the unidentified image; timing error of the data matrix reader's shooting trigger; the data matrix being outside the focus of the data matrix reader; and reading timeout of the data matrix reader.

Images