Cell ID Restoration Method and Manufacturing Process System Using the Same

Abstract

A manufacturing process system that controls a plurality of unit manufacturing processes for assembling a plurality of battery cells includes a plurality of electronic control devices that control the plurality of unit manufacturing processes, an EDC (Equipment Data Collection) server that receives and stores a plurality of cell IDs that are normally recognized and a plurality of unrecognized cell ID images that are not recognized from the plurality of electronic control devices, and a cell ID restoration unit that restores a candidate cell ID image that is most similar to a first unrecognized cell ID image among a plurality of candidate cell ID images based on a first cell ID position corresponding to a first unrecognized cell ID image among the plurality of unrecognized cell ID images to a cell ID for the first unrecognized cell ID image. When the cell ID restoration unit fails to restore the cell ID for the first unrecognized cell ID image, the cell ID restoration unit may re-read the first unrecognized cell ID image.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims the benefit of priority based on Korean Patent Application No. 10 - 2022 - 0105227 filed on August 23, 2022, and all the contents disclosed in the literature of the Korean patent application are included as part of this specification.

[0002] This disclosure relates to a cell ID restoration method and a manufacturing process system using the same.

Background Art

[0003] During the manufacturing process of a battery pack, tracking of battery cells may fail. Tracking of battery cells in the manufacturing process can utilize means for photographing and recognizing the cell ID entered at a specific position of the battery cell. The cell ID can be an image having a specific pattern like a barcode. If the recognition means fails to recognize the cell ID image during the manufacturing process, tracking of the battery cell corresponding to the cell ID may fail.

[0004] When a quality problem occurs with a battery pack, it is necessary to identify in which unit manufacturing process the cause of the quality problem occurred. If battery cell tracking fails during the manufacturing process of a battery pack with a quality problem, the unit manufacturing process where the cause of the quality problem occurred cannot be determined. Then, a skilled engineer has to manually collect, process, and link all the production histories for each manufacturing process unit. Such work requires a significant amount of time from a skilled engineer.

[0005] Since there is a limit to the accuracy of manual work, all the battery cells produced during a predetermined period based on the time when the cause of the quality problem occurred in the unit manufacturing process have to be discarded. This increases the disposal cost of the battery cells.

Summary of the Invention

Problems to be Solved by the Invention

[0006] Failure to track battery cells during the manufacturing process as described above can cause problems that are quite time-consuming and costly. Therefore, the present invention provides a cell ID restoration method capable of preventing failure to track battery cells and a manufacturing process system using the same.

Means for Solving the Problems

[0007] A manufacturing process system for controlling a plurality of unit manufacturing processes for assembling a plurality of battery cells according to one feature of the invention includes a plurality of electronic control devices for controlling the plurality of unit manufacturing processes, an EDC (Equipment Data Collection) server for receiving and storing a plurality of cell IDs normally recognized from the plurality of electronic control devices and a plurality of unrecognized cell ID images that were not recognized, and among the plurality of unrecognized cell ID images, a cell ID restoration unit that restores, as the cell ID for the first unrecognized cell ID image, the candidate cell ID image that is most similar to the first unrecognized cell ID image among the candidate cell ID images based on the position of the first cell ID corresponding to the first unrecognized cell ID image.

[0008] If the cell ID restoration unit fails to restore the cell ID for the first unrecognized cell ID image, it can re-read the first unrecognized cell ID image.

[0009] The EDC server performs cell ID restoration for the plurality of unrecognized cell ID images according to a predetermined rule corresponding to the method by which the cell ID is assigned, and the first unrecognized cell ID image can be an unrecognized cell ID image for which restoration by the EDC server has failed.

[0010] Among the plurality of electronic control devices, the first electronic control device that controls the first unit manufacturing process in which the first unrecognized cell ID image is generated derives the first cell ID position of the first unrecognized cell ID image, determines a predetermined number of candidate cell IDs based on the first cell ID position, and the candidate cell ID image may be a cell ID image recognized in the second unit manufacturing process before the first unit manufacturing process corresponding to the candidate cell ID.

[0011] The cell ID restoration unit calculates the similarity between the candidate cell ID image and the first unrecognized cell ID image, derives the candidate cell ID image that is most similar to the first unrecognized cell ID image among the candidate cell ID images, and can determine the cell ID corresponding to the derived candidate cell ID image as the cell ID for the first unrecognized cell ID image.

[0012] The cell ID restoration unit can learn a method for calculating the similarity between a plurality of unrecognized cell ID images and a plurality of normal cell ID images through deep learning.

[0013] The plurality of unrecognized cell ID images for learning of the cell ID restoration unit may be clustered due to the cause of unrecognition.

[0014] The manufacturing process system may further include a clustering device that performs learning to classify the plurality of unrecognized cell ID images and determine the cluster to which each unrecognized cell ID image belongs among the plurality of clusters.

[0015] Among the plurality of electronic control devices, the first electronic control device that controls the first unit manufacturing process may include a barcode reader that reads the plurality of cell IDs that have passed through the first unit manufacturing process, and a first client that transmits the cell IDs and unrecognized cell ID images normally recognized from the barcode reader to the EDC server.

[0016] When the first unrecognized cell ID image is generated in the first unit manufacturing process, the first client can derive the first cell ID position of the first unrecognized cell ID image and determine a predetermined number of candidate cell IDs based on the first cell ID position.

[0017] Among the plurality of electronic control devices, a second electronic control device that controls a second unit manufacturing process before the first unit manufacturing process may include a second client that determines, as the candidate cell ID image, a cell ID image corresponding to the candidate cell ID among the plurality of cell IDs recognized in the second unit manufacturing process.

[0018] The cell ID restoration unit may be provided in the second electronic control device.

[0019] When the first unrecognized cell ID occurs during the lamination process among the plurality of unit manufacturing processes, the cell ID restoration unit can restore, as the cell ID for the first unrecognized cell ID image, the candidate cell ID image that is most similar to the first unrecognized cell ID image among the candidate cell ID images recognized in the notching process, which is a stage before the lamination process.

[0020] When the cell ID restoration for the first unrecognized cell ID image fails, the cell ID restoration unit can perform rereading for the first unrecognized cell ID image.

[0021] The cell ID restoration method according to other features of the invention includes: in a plurality of unit manufacturing processes, a first electronic control device that controls the first unit manufacturing process derives an unrecognized cell ID position that is the position of a first unrecognized cell ID image; the first electronic control device determines a predetermined number of candidate cell IDs based on the unrecognized cell ID position; a second electronic control device that controls a second unit manufacturing process before the first unit manufacturing process determines a candidate cell ID image recognized in the second unit manufacturing process corresponding to the candidate cell ID; and the second electronic control device calculates a similarity between the candidate cell ID image and the first unrecognized cell ID image, and derives a candidate cell ID image that is most similar to the first unrecognized cell ID image among the candidate cell ID images.

[0022] The cell ID restoration method may further include: the first electronic control device transmits a plurality of unrecognized cell ID images that the first electronic control device failed to recognize to an EDC server; the EDC server performs cell ID restoration for the plurality of unrecognized cell ID images according to a predetermined rule; and the EDC server derives a first unrecognized cell ID image that could not be restored based on the restoration execution result.

[0023] The step in which the first electronic control device determines the candidate cell ID may include: determining cell IDs at a predetermined number of leading positions and trailing positions based on the unrecognized cell ID position as candidate cell IDs.

[0024] The cell ID restoration method may further include: the second electronic control device restores the cell ID corresponding to the derived candidate cell ID image as the cell ID for the first unrecognized cell ID image; and transmits the restored cell ID to the first electronic control device.

[0025] The first unit manufacturing process may be a lamination process, and the second unit manufacturing process may be a notching process.

[0026] When the cell ID restoration method fails to restore the cell ID for the first unrecognized cell ID image, it may further include a step of rereading the first unrecognized cell ID image.

Advantages of the Invention

[0027] The present invention provides a cell ID restoration method capable of preventing failure in battery cell tracking and a manufacturing process system using the same.

Brief Description of the Drawings

[0028]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0029] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. The same or similar reference numerals are assigned to the same or similar components, and redundant descriptions thereof are omitted. The suffixes "module" and / or "section" for the components used in the following description are given or mixed only for the ease of preparing the specification, and do not have meanings or roles that are distinguishable from each other by themselves. Also, when explaining the embodiments disclosed in this specification, if it is determined that a specific description of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof is omitted. Further, the attached drawings are only for facilitating the understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the attached drawings, and it should be understood that all modifications, equivalents, and alternatives included in the idea and technical scope of the present invention are included.

[0030] Terms including ordinal numbers such as first, second, etc. can be used to describe various components, but the components are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

[0031] When it is mentioned that a certain component is "connected to" or "attached to" another component, it should be understood that it can be directly connected to or attached to the other component, but there can also be other components in between. On the contrary, when it is mentioned that a certain component is "directly connected to" or "directly attached to" another component, it should be understood that there are no other components in between.

[0032] In this application, terms such as "comprising" or "having" are intended to specify the presence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should not be construed as precluding the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0033] Hereinafter, in this specification, "cell" can refer to one of the negative electrode and the positive electrode constituting a battery cell, a battery cell, or one of the stacked battery cells in which a predetermined number of battery cells are stacked.

[0034] A cell tracking method according to an embodiment can include a step of restoring a cell ID that has failed to be recognized when an event of failure to recognize a cell ID occurs in a plurality of unit manufacturing steps constituting an assembly step such as a notching step, a lamination step, a stacking step, a folding step, a packaging step, etc. Embodiments regarding a method for restoring a cell ID and a manufacturing process system using the same are described in this specification.

[0035] FIG. 1 is a drawing schematically showing a manufacturing process system according to an embodiment.

[0036] The manufacturing process system 1 shown in FIG. 1 can control a notching step, a lamination step, a stacking step, and a packaging step. A cell tracking method according to an embodiment can be applied to the manufacturing process system 1. The manufacturing process system 1 tracks the manufacturing process history of a cell based on the cell ID recognized in each unit manufacturing step. The manufacturing process system 1 recognizes the cell ID for the cell that has passed through each unit manufacturing step, and can know through which manufacturing step among a plurality of manufacturing steps the cell has been manufactured.

[0037] FIG. 2 is a drawing schematically showing a battery pack manufacturing process according to an embodiment.

[0038] In FIG. 2, each of the unit manufacturing processes to assist in understanding battery cell tracking is schematically shown. Among the plurality of manufacturing processes shown in FIG. 2, a certain manufacturing process may be omitted, and a certain manufacturing process not shown in FIG. 2 may be added. For example, in FIG. 2, the folding process is not shown, but the folding process may be added instead of the stacking process.

[0039] First, in the notching process, the negative electrode member or the positive electrode member wound in a roll form can be cut into an electrode shape suitable for the form of the battery cell. Laser notching equipment or press notching equipment can be used to cut the electrodes for each member. As shown in FIG. 2, a tab connected to the non-coated (noc-coating) part where the negative electrode active material is not applied is located on the negative electrode member, and each tab may be marked with a cell ID ID_1. The cell ID ID_1 can be engraved on each tab using a laser. In FIG. 2, the cell ID ID_1 is marked on the negative electrode tab, but the invention is not limited thereto, and the cell ID may be marked on the positive electrode tab.

[0040] Next, in the lamination process, the positive electrode and the negative electrode, and a separator are attached therebetween. As shown in FIG. 2, the structure of the battery cell may be one of a monocell, a bicell, and a half-cell structure. As shown in FIG. 2, the cell ID ID_2 is printed on the negative electrode tabs of the monocell, bicell, and half-cell. In FIG. 2, the cell ID is printed on the negative electrode tab, but the invention is not limited thereto, and the cell ID may be printed on the positive electrode tab. The cell ID ID_2 and the cell ID ID_1 may be the same cell ID.

[0041] Next, in the stacking process, a predetermined number of battery cells are stacked in layers with a separator membrane placed therebetween. A stacked battery cell in which a predetermined number of battery cells are stacked through the stacking process is manufactured, and a cell ID ID_3 is printed on the negative electrode tab of each battery cell constituting each stacked battery cell. A battery cell in which the cell ID is directly exposed to the outside in the stacked battery cell, for example, the battery cell CELL1 located at the uppermost part in FIG. 2, can represent the stacked battery cell. The stack virtual ID for the stacked battery cell can be matched with the cell ID ID_3 of the battery cell CELL1. The cell ID ID_2 and the cell ID ID_3 can be the same cell ID. Or, the battery cell having the cell ID ID_2 can be included in the stacked battery cell represented by the cell ID ID_3.

[0042] On the entire circumference tape surrounding the outside of the battery pack manufactured through the stacking process, a cell ID ID_4 corresponding to the stack virtual ID may be printed. The cell ID ID_3 and the cell ID ID_4 can be matched through the stack virtual ID. Although the cell ID ID_4 is shown as being printed on the entire circumference tape, the invention is not limited thereto. The cell ID ID_4 may be printed at a recognizable position outside the stacked battery cell.

[0043] In the packing process, the battery pack can be packaged to complete the assembly stage of the battery pack. On the outside of the packaged battery pack, a pack ID ID_5 that matches the stack cell ID ID_4 may be printed.

[0044] Based on the cell IDs recognized in each unit manufacturing process in this way, the manufacturing process system 1 can track the manufacturing process history that the cell has gone through. Hereinafter, in the specification, the position of the cell can be determined by the order in which the manufacturing process is applied to any cell when the unit manufacturing process is applied to each of the plurality of cells. For example, the earlier the order in which the manufacturing process is applied, the earlier the position of the cell. The position of the cell ID is determined by the position of the cell, and the earlier the position of the cell, the earlier the position of the corresponding cell ID image.

[0045] The manufacturing process system 1 can include a plurality of electronic control devices 10_1 to 10_4 that control a plurality of unit manufacturing processes, an EDC (Equipment Data Collection) server 20, and a clustering device 30.

[0046] The EDC server 20 can store the data acquired during the manufacturing process. Necessary information can be transmitted and received between the plurality of electronic control devices 10_1 to 10_4 and the EDC server 20 through wired or wireless communication. In FIG. 1, it is shown that a communication bus 40 is constructed between the plurality of electronic control devices 10_1 to 10_4 and the EDC server 20, but the communication method between the components is not limited to this.

[0047] Each of the plurality of electronic control devices 10_1 to 10_4 can control the corresponding unit manufacturing process and perform cell ID recognition for tracking each battery cell. Since the method by which each of the plurality of electronic control devices 10_1 to 10_4 controls the manufacturing process can be implemented through known techniques, detailed description is omitted. This specification describes the cell estimation method.

[0048] Each of the plurality of electronic control devices 10_1 to 10_4 can match the production equipment number of the process line where the unit manufacturing process is performed, the LOT information of the object manufactured in the unit manufacturing process, and the cell ID reading time of the object to be manufactured with the cell ID recognition image. The cell ID reading time is the time when the cell ID is read by the barcode recognition unit of each unit manufacturing process, and the cell ID recognition image can be the image of the cell ID read by the barcode recognition unit. Each of the plurality of electronic control devices 10_1 to 10_4 can obtain the presence or absence of cell ID recognition failure and information regarding the cell ID. The cell ID can be the cell ID read by the barcode recognition unit.

[0049] The EDC server 20 can database and store the information received from the plurality of electronic control devices 10_1 to 10_4. For example, the EDC server 20 can classify and database the cell ID reading time, the cell ID recognition image, the presence or absence of cell ID recognition failure, the cell ID, the production equipment number, and the LOT information according to a predetermined criterion. At this time, the predetermined criterion can be the cell ID reading time.

[0050] Also, when the EDC server 20 receives an unrecognized cell ID image from the electronic control devices 10_1 to 10_4 through the communication bus 40, it can perform cell ID restoration for the unrecognized cell ID image according to a predetermined rule. For example, the predetermined rule is according to the method by which the cell ID is assigned. When a plurality of cell IDs are assigned to have values that sequentially increase in predetermined units, the EDC server 20 can derive the cell ID corresponding to the unrecognized cell ID image based on the cell IDs of the cells located before and after the cell corresponding to the unrecognized cell ID image.

[0051] As shown in FIG. 1, the electronic control device 1 applied to the notching process includes a bar code reader 110, a cell ID restoration unit 120, and a client 130. In FIG. 1, the cell ID restoration unit 120 is shown as being provided in the electronic control device 1, but the invention is not limited thereto. For example, the cell ID restoration unit 120 may be provided externally to the electronic control devices 10_1 to 10_4 in a separate configuration, or may be provided in any one of the electronic control device 10_2, the electronic control device 10_3, and the electronic control device 10_4.

[0052] The bar code reader 110 can read the cell ID ID_1 of the negative electrode cut through the notching process to generate a cell ID image, and recognize the cell ID from the generated cell ID image. If the bar code reader 110 fails to recognize the cell ID from the generated cell ID image, it can reproduce the cell ID image. The bar code reader 110 can recognize the cell ID from the reproduced cell ID image. If the bar code reader 110 finally fails to recognize the cell ID, the electronic control device 1 can save the manufacturing process information corresponding to the cell for which the cell ID recognition has failed, and transmit the saved manufacturing process information to the upper controller.

[0053] The client 130 can transmit the cell ID recognized by the bar code reader 110 and the unrecognized cell ID image to the EDC server 20. At this time, the unrecognized cell ID image can be one of the initially generated cell ID image, the reproduced cell ID image, and both of the two images.

[0054] The cell ID restoration unit 120 can perform restoration on unrecognized cell ID images that failed to be restored by the EDC server 20. The cell ID restoration unit 120 can learn a method for restoring unrecognized cell ID images through deep learning and can restore unrecognized cell ID images generated in each unit manufacturing process. The cell ID restoration unit 120 can train a method for restoring a plurality of unrecognized cell ID images through deep learning. The cell ID restoration unit 120 can utilize accumulated learning data including a plurality of unrecognized cell ID images and a plurality of corresponding normal cell ID images in deep learning.

[0055] In addition, the cell ID restoration unit 120 can restore an unrecognized cell ID image by using cell ID images (hereinafter referred to as candidate cell ID images) for a predetermined number of cells based on the positions of cells corresponding to unrecognized cell IDs in the unit process before the unit manufacturing process in which the unrecognized situation occurred.

[0056] The cell ID restoration unit 120 can calculate the similarity between the candidate cell ID image and the unrecognized cell ID image and derive the candidate cell ID image that is most similar to the unrecognized cell ID image among the overall candidate cell ID images. The cell ID restoration unit 120 can determine the cell ID corresponding to the derived candidate cell ID image as the cell ID for the unrecognized cell ID image. The cell ID restoration unit 120 can transmit the restored cell ID to the client 130, and the client 130 can transmit the cell ID to the EDC server 20 and the clients of the electronic control devices of other unit manufacturing processes where unrecognized cell ID images occurred. The EDC server 20 can save the database by replacing the unrecognized cell ID image with the received cell ID.

[0057] The cell ID restoration unit 120 may fail to restore the first unrecognized cell ID image. For example, when the overall similarity between the overall candidate cell ID image and the first unrecognized cell ID image is less than a predetermined threshold, the cell ID restoration unit 120 can determine that the restoration of the first unrecognized cell ID image has failed. In this case, the cell ID restoration unit 120 can perform rereading for the first unrecognized cell ID image. For example, the cell ID restoration unit 120 can perform rereading for the first unrecognized cell ID image that has failed to be restored through a method of restoring an unrecognized cell ID image learned through deep learning. The reading rate for the unrecognized cell ID image can be improved through such TW0-TRACK restoration.

[0058] The cell ID restoration unit 120 can learn a method of calculating the similarity between a plurality of unrecognized cell ID images and a normally recognized cell ID image (hereinafter referred to as a normal cell ID image), which is a candidate cell ID image, through deep learning. A plurality of normal cell ID images and a plurality of unrecognized cell ID images can be used as learning data for the deep learning of the cell ID restoration unit 120. At this time, when the plurality of unrecognized cell ID images are clustered due to the cause of unrecognition, the learning accuracy can be improved. The unrecognized cell ID images used for the learning of the cell ID restoration unit 120 according to an embodiment can be clustered.

[0059] For this purpose, the manufacturing process system 1 can include a separate configuration for clustering the unrecognized cell ID image. For example, the manufacturing process system 1 can further include a clustering device 30. Although the cell ID image has a predetermined size, if this is used as it is, the degree of data becomes excessively high. Therefore, t-SNE (t-distributed Stochastic Neighbor Embedding) can be used to lower the degree of a plurality of images to two dimensions. K-Means Clustering can be applied to the two-dimensional image to perform clustering for the two-dimensional image.

[0060] The clustering device 30 can perform learning to classify a plurality of unrecognized cell ID images and determine the cluster to which each unrecognized cell ID image belongs among the plurality of clusters. The learning can be performed by deep learning techniques, and the deep learning techniques can be, for example, the CNN (Convolution Neural Network) algorithm. The clustering device 30 can program and store a classification model that performs the CNN algorithm, and can learn to classify an unrecognized cell ID image into one of the plurality of clusters by operating the program. By the CNN algorithm, the clustering device 30 performs feature extraction on the unrecognized cell ID image, which is the input data, through a convolution layer, a ReLU layer, and a pooling layer, and inputs the extracted features into a flattening layer. The clustering device 30 includes a classifier that takes as input the features corresponding to the flattening layer, and the classifier can classify the unrecognized cell ID image into one of the plurality of clusters. The classifier can include an input layer, at least one hidden layer, and an output layer.

[0061] The clustering device 30 can be implemented using one or a combination of two or more of various known deep learning techniques. The clustering device 30 is not limited by the content described in this specification. The present invention can improve the accuracy of cluster classification for unrecognized cell ID images by classifying unrecognized cell ID images into a plurality of clusters and learning through deep learning to classify an unrecognized cell ID image into one of the plurality of clusters.

[0062] In FIG. 1, the clustering device 30 is shown as providing learning data through the communication bus 40 according to the configuration included in the manufacturing process system 1, but the invention is not limited thereto. The clustering device 30 can be implemented as a separate configuration from the manufacturing process system 1 and can transmit learning data to the manufacturing process system 1 through a network.

[0063] As shown in FIG. 1, the electronic control device 10_2 applied to the lamination process includes a bar code reader 210 and a client 220.

[0064] The bar code reader 210 can read the battery cell ID ID_2 formed through the lamination process to generate a cell ID image, and recognize the cell ID from the generated cell ID image. If the bar code reader 210 fails to recognize the cell ID from the generated cell ID image, the cell ID image can be designated as an unrecognized cell ID image and transmitted to the client 220. The cell ID normally recognized by the bar code reader 210 can also be transmitted to the client 220. If the cell ID for the unrecognized cell ID image cannot be restored by the EDC server 20 and the cell ID restoration unit 120 either, the bar code reader 210 can read the cell ID of the cell again to generate a cell ID image.

[0065] The client 220 can transmit the recognized cell ID and the unrecognized cell ID image to the EDC server 20.

[0066] As shown in FIG. 1, the electronic control device 10_3 applied to the stacking process includes two bar code readers 310, 320, a client 330, and a stacked cell management unit 340.

[0067] The barcode reader 310 can read the battery cell ID ID_3 representing the stacked battery cells formed through the stacking process to generate a cell ID image, and can recognize the cell ID ID_3 from the generated cell ID image. If the barcode reader 310 fails to recognize the cell ID from the generated cell ID image, it can reproduce the cell ID image. The barcode reader 310 can recognize the cell ID from the reproduced cell ID image. The barcode reader 310 can transmit the recognized cell ID and the unrecognized cell ID image to the client 330.

[0068] The barcode reader 320 can read the stack cell ID for the stacked battery cells to generate a stack cell ID image. As described above, the stack cell ID may be printed on the entire peripheral tape surrounding the outside of the stacked battery cells. The barcode reader 320 can recognize the stack cell ID from the stack cell ID image and transmit the recognized stack cell ID to the client 330 and the stack cell management unit 340.

[0069] The client 330 can transmit the recognized cell ID, the unrecognized cell ID image, and the stack cell ID to the EDC server 20. At this time, the unrecognized cell ID image can be one of the initially generated cell ID image, the reproduced cell ID image, and both of the two images.

[0070] The stack cell management unit 340 can receive the cell ID representing the stacked battery cells from either the barcode reader 310 or the client 330, match the stack cell ID received from the barcode reader 320 with the representative cell ID, and save the matching result.

[0071] As shown in FIG. 1, the electronic control device 10_4 applied to the stacking process includes a barcode reader 410 and a client 420.

[0072] The barcode reader 410 reads the pack ID ID_4 printed on the outside of the battery pack formed through the packaging process to generate a pack ID image, and can recognize the pack ID ID_4 from the generated pack ID image. If the barcode reader 410 fails to recognize the pack ID from the generated pack ID image, it can reproduce the pack ID image. The barcode reader 410 can recognize the pack ID ID_5 from the reproduced pack ID image. The barcode reader 410 can transmit the recognized pack ID and the unrecognized pack ID image to the client 420.

[0073] The client 420 can transmit the recognized pack ID and the unrecognized pack ID image to the EDC server 20. At this time, the unrecognized pack ID image can be the initially generated pack ID image, the reproduced pack ID image, or one of both images. The client 420 can match the cell ID of the plurality of stacked battery cells constituting the battery pack with the pack ID and transmit the matching result to the EDC server 20.

[0074] FIG. 3 and FIG. 4 are flowcharts showing a cell ID restoration method according to an embodiment.

[0075] FIG. 3 and FIG. 4 show a method for restoring the cell ID for the unrecognized image generated in the lamination process.

[0076] First, the cell ID of the cell after the lamination process is completed is recognized by the barcode reader 210. The client 220 transmits the plurality of cell IDs recognized by the barcode reader 210 and the plurality of unrecognized cell ID images that failed to be recognized to the EDC server 20 in the recognition order (S1). The information transmitted by the client 220 to the EDC server 20 is generally referred to as cell information.

[0077] The EDC server 20 can perform cell ID restoration for a plurality of unrecognized cell ID images according to a predetermined rule (S2). The predetermined rule can follow the method by which cell IDs are assigned as described above. When one cell ID image among consecutive cell IDs is unrecognized, the EDC server 20 can restore the unrecognized cell ID image by using the cell ID at the immediately preceding position and the cell ID at the immediately following position adjacent to the unrecognized cell ID image.

[0078] An example of the restoration operation of the EDC server 20 is as follows. Among the cell IDs at consecutive positions, if the cell ID at the immediately preceding position of the unrecognized cell ID is "ABC1234" and the cell ID at the immediately following position is "ABC1236", the EDC server 20 can restore the cell ID of the unrecognized cell ID image to "ABC1235". However, if there are two or more unrecognized cell IDs among consecutive cell IDs, the EDC server 20 cannot perform the restoration.

[0079] The EDC server 20 can derive a first unrecognized cell ID image that cannot be restored from among the plurality of unrecognized cell ID images received from the client 220 (S3).

[0080] The client 220 can query the EDC server 20 for the first unrecognized cell ID image at each set predetermined period (S4). For example, the client 220 can request the transmission of the first unrecognized cell ID image derived by the EDC server 20.

[0081] The EDC server 20 can transmit the first unrecognized cell ID image to the client 220 as a response to the request of the client 220 (S5).

[0082] The client 220 can derive the position of the first unrecognized cell ID image (hereinafter, the unrecognized cell ID position) (S6).

[0083] Based on the unrecognized cell ID position, the client 220 can determine a predetermined number of candidate cell IDs from among a plurality of cell IDs (S7). The client 220 can determine the cell IDs at positions ahead and positions behind a predetermined number of positions based on the unrecognized cell ID position as candidate cell IDs.

[0084] The client 220 can transmit the first unrecognized cell ID image, the restoration request therefor, and the candidate cell IDs to the client 130 of the electronic control device 1 in the notching process, which is a unit manufacturing process before the lamination process (S8).

[0085] The client 130 can derive the cell ID image in the notching process corresponding to the candidate cell ID (S9). Hereinafter, the cell ID image at the previous stage corresponding to the candidate cell ID is referred to as the candidate cell ID image. In one embodiment, the "previous stage" may mean the notching process stage, which is a unit manufacturing process before the lamination process.

[0086] The client 130 transmits the first unrecognized cell ID image and the candidate cell ID image to the cell ID restoration unit 120 (S10).

[0087] The cell ID restoration unit 120 calculates the similarity between the candidate cell ID image and the first unrecognized cell ID image, and derives the candidate cell ID image having the highest similarity among the overall similarities between the overall candidate cell ID image and the first unrecognized cell ID image, and can restore the cell ID corresponding to the derived candidate cell ID image as the cell ID for the first unrecognized cell ID image (S11).

[0088] The cell ID restoration unit 120 transmits the restored cell ID (hereinafter, the restored cell ID) to the client 130 (S12).

[0089] Client 130 can transmit the restored cell ID to Client 220 and EDC Server 20 (S13). Alternatively, Client 130 can transmit the restored cell ID to Client 220, and Client 220 can transmit the restored cell ID to EDC Server 20.

[0090] EDC Server 20 can update the cell ID received for the first unrecognized cell ID image with the restored cell ID.

[0091] In FIGS. 3 and 4, a method for restoring an unrecognized cell ID image generated in the lamination process is shown, but the invention is not limited thereto. The cell ID can be restored in the same manner for the unrecognized cell ID image generated in the stacking process. For example, the client 330 can derive the position of the unrecognized cell ID generated in the stacking process to determine the candidate cell ID, and transmit a restoration request together with the unrecognized cell ID image and the candidate cell ID to the client 130. However, the cell ID in the stacking process is different from the cell IDs in the lamination process and the notching process. At this time, since the candidate cell ID in the stacking process is the cell ID for the stack, the client 330 can derive the candidate cell ID image corresponding to the candidate cell ID and transmit it to the client 130 together with the unrecognized cell ID image. The cell ID restoration unit 120 calculates the similarity between the candidate cell ID image and the unrecognized cell ID image, and derives the candidate cell ID image that is most similar to the unrecognized cell ID image among the overall candidate cell ID images, and can restore the cell ID corresponding to the derived candidate cell ID image as the cell ID for the unrecognized cell ID image. The cell ID restoration unit 120 transmits the restored cell ID to the client 130, and the client 130 can transmit the restored cell ID to the client 330 and the EDC server 20 (S13). Or the client 130 transmits the restored cell ID to the client 330, and the client 330 can transmit the restored cell ID to the EDC server 20. The EDC server 20 can update the received restored cell ID with the cell ID for the unrecognized cell ID image.

[0092] Although the embodiments of the present invention have been described in detail above, the scope of the rights of the present invention is not limited thereto, and forms variously modified and improved by those having ordinary knowledge in the field to which the present invention belongs also belong to the scope of the rights of the present invention.

Explanation of Reference Numerals

[0093] 1 Manufacturing Process System 10_1~10_4 Electronic Control Device 20 EDC Server 30 Clustering Device 40 Communication Bus 110 Barcode Reader 120 Cell ID Restoration Unit 130 Client 210 Barcode Reader 220 Client 310 Barcode Reader 320 Barcode Reader 330 Client 340 Stack Cell Management Unit 410 Barcode Reader 420 Client

Claims

1. A manufacturing process system for controlling a plurality of unit manufacturing processes for assembling a plurality of battery cells, comprising: a plurality of electronic control devices for controlling the plurality of unit manufacturing processes; an EDC (Equipment Data Collection) server that receives and stores a plurality of cell IDs recognized normally and a plurality of unrecognized cell ID images not recognized from the plurality of electronic control devices; a cell ID restoration unit that restores, as a cell ID for the first unrecognized cell ID image, the candidate cell ID image most similar to the first unrecognized cell ID image among a plurality of candidate cell ID images based on a first cell ID position corresponding to the first unrecognized cell ID image among the plurality of unrecognized cell ID images; A manufacturing process system comprising the above.

2. The EDC server: performs cell ID restoration for the plurality of unrecognized cell ID images according to a predetermined rule corresponding to the method by which cell IDs are assigned; The manufacturing process system according to Claim 1, wherein the first unrecognized cell ID image is an unrecognized cell ID image for which restoration by the EDC server has failed.

3. Among the plurality of electronic control devices, a first electronic control device that controls a first unit manufacturing process in which the first unrecognized cell ID image is generated: derives a first cell ID position of the first unrecognized cell ID image, determines a predetermined number of candidate cell IDs based on the first cell ID position; The plurality of candidate cell ID images: are cell ID images recognized in a second unit manufacturing process before the first unit manufacturing process corresponding to the predetermined number of candidate cell IDs. The manufacturing process system according to Claim 1.

4. The cell ID restoration unit: calculates a similarity between the plurality of candidate cell ID images and the first unrecognized cell ID image, derives the candidate cell ID image most similar to the first unrecognized cell ID image among the plurality of candidate cell ID images, and determines the cell ID corresponding to the derived candidate cell ID image as the cell ID for the first unrecognized cell ID image. The manufacturing process system according to Claim 1.

5. The cell ID restoration unit: learns a method for calculating a similarity between a plurality of unrecognized cell ID images and a plurality of normal cell ID images through deep learning. The manufacturing process system according to Claim 4.

6. The manufacturing process system according to claim 5, wherein the plurality of unrecognized cell ID images for learning of the cell ID restoration unit are clustered due to causes of unrecognition.

7. The manufacturing process system according to claim 6, further comprising a clustering device that performs learning to classify the plurality of unrecognized cell ID images and determine a cluster to which each unrecognized cell ID image corresponds among the plurality of clusters.

8. Among the plurality of electronic control devices, a first electronic control device that controls a first unit manufacturing process, a barcode reader that reads the plurality of cell IDs that have undergone the first unit manufacturing process, and a first client that transmits the cell IDs normally recognized from the barcode reader and unrecognized cell ID images to the EDC server The manufacturing process system according to claim 1.

9. When the first unrecognized cell ID image is generated in the first unit manufacturing process, the first client, derives a first cell ID position of the first unrecognized cell ID image, and determines a predetermined number of candidate cell IDs based on the first cell ID position. The manufacturing process system according to claim 8.

10. Among the plurality of electronic control devices, a second electronic control device that controls a second unit manufacturing process before the first unit manufacturing process, The manufacturing process system according to claim 9, comprising a second client that determines, as the plurality of candidate cell ID images, cell ID images corresponding to the predetermined number of candidate cell IDs among the plurality of cell IDs recognized in the second unit manufacturing process.

11. The manufacturing process system according to claim 10, wherein the cell ID restoration unit is provided in the second electronic control device.

12. When the first unrecognized cell ID image is generated during the lamination process among the plurality of unit manufacturing processes, the cell ID restoration unit, restores, as a cell ID for the first unrecognized cell ID image, a candidate cell ID image that is most similar to the first unrecognized cell ID image among the plurality of candidate cell ID images recognized in the notching process, which is a stage before the lamination process. The manufacturing process system according to claim 1.

13. The manufacturing process system according to any one of claims 1 to 12, wherein when the cell ID restoration for the first unrecognized cell ID image fails, the cell ID restoration unit performs rereading for the first unrecognized cell ID image.

14. Among a plurality of unit manufacturing processes, a first electronic control device that controls the first unit manufacturing process derives an unrecognized cell ID position that is the position of a first unrecognized cell ID image; the first electronic control device determines a predetermined number of candidate cell IDs based on the unrecognized cell ID position; a second electronic control device that controls a second unit manufacturing process before the first unit manufacturing process determines a plurality of candidate cell ID images recognized in the second unit manufacturing process corresponding to the predetermined number of candidate cell IDs; the second electronic control device calculates a similarity between the plurality of candidate cell ID images and the first unrecognized cell ID image, and derives a candidate cell ID image that is most similar to the first unrecognized cell ID image among the plurality of candidate cell ID images; A cell ID restoration method including the above.

15. A step of transmitting a plurality of unrecognized cell ID images that the first electronic control device has failed to recognize to an EDC server; a step of the EDC server performing cell ID restoration for the plurality of unrecognized cell ID images according to a predetermined rule; a step of the EDC server deriving a first unrecognized cell ID image that could not be restored due to the result of performing the cell ID restoration for the plurality of unrecognized cell ID images according to the predetermined rule; The cell ID restoration method according to claim 14, further including the above.

16. The step in which the first electronic control device determines the candidate cell ID includes a step of determining cell IDs at a predetermined number of preceding positions and cell IDs at subsequent positions as candidate cell IDs based on the unrecognized cell ID position. The cell ID restoration method according to claim 14.

17. a step in which the second electronic control device restores the cell ID corresponding to the derived candidate cell ID image as the cell ID for the first unrecognized cell ID image; a step of transmitting the restored cell ID to the first electronic control device; The cell ID restoration method according to claim 14, further including the above.

18. The cell ID restoration method according to claim 14, wherein the first unit manufacturing process is a lamination process, and the second unit manufacturing process is a notching process.

19. The cell ID restoration method according to claim 14, further including a step of re-reading the first unrecognized cell ID image when cell ID restoration for the first unrecognized cell ID image fails.

Images