Low-voltage battery cell sorting device and operation method thereof

Abstract

A low-voltage battery cell sorting apparatus according to an embodiment disclosed herein includes: a data obtaining unit configured to obtain a processing data set of battery cells included in each of a plurality of battery trays; a data preprocessing unit configured to generate a derived variable data set including at least two types of derived variables for each of the battery cells by using the processing data set, and to standardize the derived variable data set; and a sorting unit configured to sort, as low-voltage battery cells, battery cells having normalized derived variable data sets outside a specified range among the normalized derived variable data sets by using an artificial intelligence model.

Description

Technical Field

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of Korean Patent Application No. 10-2023-0031451, filed on March 9, 2023, in the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference.

[0003] Embodiments disclosed herein relate to a low-voltage battery cell sorting device and an operating method thereof. Background Art

[0004] Recently, research and development of secondary batteries has been actively conducted. In this article, secondary batteries, which are rechargeable / dischargeable batteries, can include all conventional nickel (Ni) / cadmium (Cd) batteries, Ni / metal hydride (MH) batteries, etc., as well as the more recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries have a much higher energy density than conventional Ni / Cd batteries, Ni / MH batteries, etc. Furthermore, lithium-ion batteries can be made small and lightweight, so lithium-ion batteries have already been used as power sources for mobile devices, and more recently, their use has been expanded to include power sources for electric vehicles, attracting much attention as a next-generation energy storage medium.

[0005] In the process of producing battery cells, defective battery cells may be produced. Herein, defects may include defects due to low voltage, defects due to internal short circuits, etc.

[0006] When defective battery cells are installed in electronic products, they may explode and cause fires, resulting in loss of life and property damage. Therefore, it is necessary to sort defective battery cells from the produced battery cells. Summary of the Invention

[0007] [Technical Issues]

[0008] In conventional battery manufacturing processes, a specified number of battery cells are included in one tray to detect low voltage battery cells for each tray. For example, the OCV of the battery cells of each tray can be measured, and the battery cell's The low voltage battery cells are sorted based on the mean and standard deviation of the battery.

[0009] However, since only the deviation within the pallet is considered and the deviation between pallets is not considered, there is no determination standard applicable to all pallets, and therefore it is necessary to perform inspection on each pallet, consuming a lot of inspection time.

[0010] Furthermore, the ratio of low-voltage battery cells among all produced battery cells is about 1% or less, so that when the low-voltage battery cells are sorted for each tray, efficiency is reduced with respect to inspection time required for sorting.

[0011] The technical problems of the embodiments disclosed herein are not limited to the above-mentioned technical problems, and those skilled in the art can clearly understand other unmentioned technical problems from the following description.

[0012] [Technical solution]

[0013] According to an embodiment disclosed herein, a low-voltage battery cell sorting device includes: a data acquisition unit configured to obtain a processed data set of battery cells included in each of a plurality of battery trays; a data preprocessing unit configured to generate a derived variable data set including at least two types of derived variables for each of the battery cells by using the processed data set, and to standardize the derived variable data set; and a sorting unit configured to sort battery cells having a standardized derived variable data set outside a specified range among the standardized derived variable data sets as low-voltage battery cells by using an artificial intelligence model.

[0014] In an embodiment, the data pre-processing unit may be further configured to standardize the derived variable dataset by using a mean value and a standard deviation based on quartiles of the derived variable dataset.

[0015] In an embodiment, the artificial intelligence model may be trained by a training data set for normal battery cells, and may learn a distribution pattern of the training data set by using a distribution graph based on at least two types of derived variables among a plurality of derived variables.

[0016] In an embodiment, the designated range may be a boundary determined based on the distribution pattern, and the sorting unit is further configured to sort battery cells having a normalized derived variable data set outside the determined boundary as low-voltage battery cells.

[0017] In an embodiment, the processed data set may include open circuit voltage (OCV) measured according to a time sequence of the activation process of each of the battery cells.

[0018] An operating method of a low-voltage battery cell sorting device according to an embodiment disclosed herein includes: obtaining a processed data set of battery cells included in each of a plurality of battery trays; generating a derived variable data set including at least two types of derived variables for each of the battery cells by using the processed data set; standardizing the derived variable data set; and sorting, by using an artificial intelligence model, battery cells having a standardized derived variable data set outside a specified range among the standardized derived variable data sets as low-voltage battery cells.

[0019] In an embodiment, the normalization may include normalizing the derived variable dataset by using a mean and a standard deviation based on quartiles of the derived variable dataset.

[0020] In an embodiment, the artificial intelligence model may be trained by a training data set for normal battery cells, and may learn a distribution pattern of the training data set by using a distribution graph based on at least two types of derived variables among a plurality of derived variables.

[0021] In an embodiment, the specified range may be a boundary determined based on the distribution pattern, and the sorting may include sorting battery cells having a normalized derived variable data set outside the determined boundary as low-voltage battery cells.

[0022] In an embodiment, the processed data set may include open circuit voltage (OCV) measured according to a time sequence of the activation process of each of the battery cells.

[0023] [Beneficial Effects]

[0024] The low-voltage battery cell sorting apparatus and operating method according to various embodiments disclosed herein can transform a processing dataset based on multiple derived variables, thereby accounting for intra-tray variations. Furthermore, by standardizing the derived variable dataset, inter-tray variations can be accounted for. In other words, the present disclosure can holistically manage the battery cells included in all trays by simultaneously accounting for intra-tray and inter-tray variations, thereby reducing the number of inspections required to sort low-voltage battery cells.

[0025] Therefore, by shortening the inspection time for sorting low-voltage battery cells during the battery cell manufacturing process, it is possible to quickly respond to the rapidly growing demand for batteries. In addition, due to the reduction in inspection time, a cost reduction effect can also occur.

[0026] Effects of the low-voltage battery cell sorting device and the operating method thereof according to the disclosure of this document are not limited to the above-mentioned effects, and those skilled in the art will clearly understand other unmentioned effects based on the disclosure of this document. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The problems of the method of sorting low-voltage battery cells according to the conventional technology are shown.

[0028] Figure 2 is a block diagram of a low-voltage battery cell sorting device according to an embodiment of the present disclosure.

[0029] Figure 3 A first distribution chart of normalized data based on a first derived variable and a second derived variable according to an embodiment of the present disclosure is shown.

[0030] Figure 4 A second distribution chart of normalized data based on the third derived variable and the second derived variable according to an embodiment of the present disclosure is shown.

[0031] Figure 5 is a flowchart of an operating method of a low-voltage battery cell sorting device according to an embodiment of the present disclosure.

[0032] With respect to the description of the drawings, like reference numerals may be used to refer to like or related components. DETAILED DESCRIPTION

[0033] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, this description is not intended to limit the present disclosure to specific embodiments, and should be understood to include various modifications, equivalents, and / or replacements according to the embodiments of the present disclosure.

[0034] It should be appreciated that the embodiments of this document and the terms used therein are not intended to limit the technical features set forth herein to specific embodiments, and include various changes, equivalents, or alternatives to the corresponding embodiments. In the description of the drawings, similar reference numerals may be used to refer to similar or related elements. It should be understood that the singular form of a noun corresponding to an item may include one or more things, unless the relevant context clearly indicates otherwise.

[0035] As used herein, each of phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B or C” may include any one or all possible combinations of items listed together in the corresponding one of the phrases. Unless otherwise mentioned, terms such as “1st,” “2nd,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used to simply distinguish a corresponding component from another component without limiting the components in other respects (such as importance or order).

[0036] Herein, it should be understood that when an element (e.g., a first element) is referred to as being “connected,” “coupled,” or “linked,” or “coupled to” or “connected to” another element (e.g., a second element), whether or not there is the term “operatively” or “communicatively,” it means that the element can be directly (e.g., wired or wirelessly) or indirectly (e.g., via a third element) connected to the other element.

[0037] The methods according to various embodiments disclosed herein may be included in and provided as a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), distributed online via an app store (e.g., by downloading or uploading), or distributed directly between two user devices. If distributed online, at least a portion of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium, such as a memory on a manufacturer's server, an app store server, or a relay server.

[0038] According to the embodiments disclosed herein, each of the above-mentioned components (e.g., a module or a program) may include a single entity or multiple entities, and some of the multiple entities may be separately provided in different components. According to various embodiments disclosed herein, one or more of the above-mentioned components may be omitted, or one or more other components may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, according to various embodiments, the integrated component may still perform one or more functions of each of the multiple components in the same or similar manner as they were performed by the corresponding components in the multiple components before integration. According to the embodiments disclosed herein, the operations performed by a module, a program, or another component may be performed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations may be performed in a different order or one or more of the operations may be omitted, or one or more other operations may be added.

[0039] Figure 1 The problem of the method of sorting defective battery cells according to the conventional technology is shown.

[0040] refer to Figure 1 , the first graph 10 shows the dOCV2 of each battery cell included in the first tray. In this paper, This can be the difference between OCV1 and OCV2 for each battery cell. Here, OCV1 can be the open circuit voltage (OCV) measured earlier than OCV2. OCV can be measured during the activation process. The activation process can be a process used to assess the safety of a battery after assembly. By repeatedly charging or discharging the battery through the activation process, the battery's safety can be tested based on the data measured for the battery.

[0041] The cutoff value 100 for the first pallet may be set based on the average value and standard deviation of the dOCV2 of the battery cells included in the first pallet. Battery cells that are less than the cutoff value 100 for the first pallet may be classified as normal battery cells, and battery cells that are greater than or equal to the cutoff value 100 for the first pallet may be classified as defective battery cells. In this article, a tray is a bundled unit of a certain number of produced battery cells that are sorted, and may be a box including a plurality of battery cells. For example, when 3,000 battery cells are generated, 30 battery cells may be included in each of 100 trays. The cutoff value may be one of the reference values ​​for sorting low-voltage battery cells. The cutoff value may be based on the average value and standard deviation of the battery cells excluding the suspected low-voltage group for each pallet. For example, the cutoff value can be based on the mean of dOCV2 and The value of the sum.

[0042] Hereinafter, a defective battery cell may be referred to as a low-voltage battery cell. However, this is merely a premise for describing the present disclosure, and the defective battery cell is not limited to a low-voltage battery cell and may also be referred to as a battery cell corresponding to various defect types.

[0043] A second chart 11 shows the dOCV2 of each battery cell included in the second tray. A second tray cutoff value 110 can be set based on the average and standard deviation of the dOCV2 of the battery cells included in the second tray. Battery cells with a dOCV2 less than the second tray cutoff value 110 can be classified as normal battery cells, and battery cells with a dOCV2 greater than or equal to the second tray cutoff value 110 can be classified as low-voltage battery cells.

[0044] Referring to the third graph 13, which integrally shows the first graph 10 and the second graph 11, data 102 regarding a battery cell classified as a normal battery cell on the first graph 10 may be greater than or equal to the cutoff value 110 for the second tray, and thus the battery cell may be classified as a low-voltage battery cell. Similarly, data 112 regarding a battery cell classified as a low-voltage battery cell on the second graph 11 is less than the cutoff value 100 for the first tray, and thus the battery cell may be classified as a normal battery.

[0045] That is, since the mean and standard deviation of dOCV2 of battery cells are different, and thus the cutoff value for determining low voltage may also be different for each pallet, it is necessary to derive an overall reference value applicable to any pallet.

[0046] Figure 2 is a block diagram of a low-voltage battery cell sorting device 20 according to an embodiment of the present disclosure.

[0047] refer to Figure 2 , the low-voltage battery cell sorting device 20 may be connected to the user terminal 24 by wire and / or wirelessly.

[0048] In an embodiment, the connection 23 between the low-voltage battery cell sorting device 20 and the user terminal 24 can be a communication connection via a wired and / or wireless network. In an embodiment, the wired network can be based on a local area network (LAN) or power line communication. In an embodiment, the wireless network can be based on a short-range communication network (e.g., Bluetooth, Wireless Fidelity (WiFi), or Infrared Data Association (IrDA)) or a long-range communication network (e.g., a cellular network, a fourth generation (4G) network, or a fifth generation (5G) network).

[0049] In another embodiment, the connection 23 between the low-voltage battery cell sorting apparatus 20 and the user terminal 24 may be a connection using a device-to-device communication scheme (e.g., bus, general purpose input output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)).

[0050] In an embodiment, each of the plurality of trays 221 , 223 , and 225 may include a plurality of manufactured battery cells.

[0051] In an embodiment, the user terminal 24 may be a mobile device (eg, a mobile phone, a laptop computer, a smart phone, a smart tablet) or a personal computer (PC), which controls the low-voltage battery cell sorting apparatus 20 .

[0052] In an embodiment, the low voltage battery cell sorting device 20 may include a communication circuit 200, a sensor 220, a memory 240, and a processor 260. According to an embodiment, Figure 2 The low voltage battery cell sorting device 20 shown in FIG. Figure 2 At least one component other than the ones shown may be included (eg, a display, an input device, or an output device).

[0053] In an embodiment, the communication circuit 200 may establish a wired communication channel and / or a wireless communication channel between the low-voltage battery cell sorting device 20 and the user terminal 24 , and send and receive data to and from the user terminal 24 through the established communication channel.

[0054] In an embodiment, sensor 220 may obtain a processed data set of battery cells included in a plurality of trays 221, 223, and 225. In an embodiment, the processed data set may include data regarding the OCV of the battery cells. Herein, the processed data set may include OCVs measured according to a time sequence of activation processes for each battery cell. For example, the processed data set may include the first measured OCV (OCV1), the second measured OCV (OCV2), and the third measured OCV (OCV3) for each battery cell, and each sequence may be identified according to the time sequence of the activation processes.

[0055] In an embodiment, memory 240 may include volatile memory and / or non-volatile memory.

[0056] In an embodiment, the memory 240 may store data used by at least one component of the low-voltage battery cell sorting device 20 (e.g., the processor 260). For example, the data may include software (or instructions related thereto), input data, or output data. In an embodiment, when executed by the processor 260, the instructions may cause the low-voltage battery cell sorting device 20 to perform the operations defined by the instructions.

[0057] In an embodiment, the memory 240 may include one or more software (eg, a data acquisition unit 242 , a data pre-processing unit 244 , a sorting unit 246 , and a model training unit 248 ).

[0058] In embodiments, the processor 260 may include a central processing unit, an application processor, a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor.

[0059] In an embodiment, the processor 260 can execute software (e.g., the data acquisition unit 242, the data preprocessing unit 244, the sorting unit 246, and the model training unit 248) to control at least one other component (e.g., a hardware or software component) of the low-voltage battery cell sorting device 20 connected to the processor 260 and perform various data processing or operations.

[0060] In the following, reference Figures 2 to 5, a method of sorting low-voltage battery cells among produced battery cells through the data obtaining unit 242 , the data preprocessing unit 244 , the sorting unit 246 , and the model training unit 248 performed by the low-voltage battery cell sorting apparatus 20 will be described.

[0061] The data acquisition unit 242 may acquire the processed data sets of the plurality of battery trays. The data acquisition unit 242 may acquire the processed data sets of the battery cells included in the plurality of battery trays through the sensor 220 .

[0062] The data preprocessing unit 244 can preprocess the raw data. The data preprocessing unit 244 can preprocess the processed data set.

[0063] The data preprocessing unit 244 may preprocess the processed data set by converting the processed data set into a derived variable data set. The data preprocessing unit 244 may convert the processed data set into derived variable data for each of a plurality of derived variables by using the OCV of the processed data set. In this context, the derived variable data set may include derived variable data for each of the plurality of derived variables. For example, the data preprocessing unit 244 may generate a derived variable data set including derived variable data, wherein the processed data set is converted into each of three derived variables by using the OCV of a battery cell. The data preprocessing unit 244 may further preprocess the processed data set by normalizing the derived variable data set based on the processed data set. The data preprocessing unit 244 may generate a standardized derived variable data set by normalizing each of the derived variable data included in the derived variable data set.

[0064] In an embodiment, the data preprocessing unit 244 may convert the OCV value included in the processed data set of the battery cell into a format specific to each of a plurality of derived variables. The data preprocessing unit 244 may generate derived variable data in which the OCV value included in the processed data set of the battery cell is converted into a format specific to each of the plurality of derived variables. Herein, a derived variable may be a variable based on the OCV value of the battery cell. For example, the number of derived variables may be three, and the three derived variables may be represented based on Formulas 1 to 3.

[0065] [Formula 1]

[0066] First derived variable =

[0067] Herein, dOCV2 may be the difference between OCV1 and OCV2 measured for a battery cell, μ may be the average value of dOCV2 for the battery cells of each tray, and It can be the standard deviation of dOCV2 of the battery cells for each tray.

[0068] [Formula 2]

[0069] Second derived variable =

[0070] Herein, cutoff may be one of the reference values ​​for sorting conventionally used low-voltage battery cells. Cutoff may be a value set based on the average value and standard deviation of battery cells excluding the suspected low-voltage group for each tray. For example, cutoff may correspond to the average value and standard deviation of dOCV2. sum.

[0071] [Formula 3]

[0072] The third derived variable =

[0073] In an embodiment, the data preprocessing unit 244 may standardize the derived variable dataset by using the mean and standard deviation based on the quartiles of the derived variable dataset. The data preprocessing unit 244 may calculate the mean and standard deviation of the derived variable datasets present in the first quartile Q1 to the third quartile Q3 based on the IQR of the derived variable dataset, and standardize the derived variable dataset by using the calculated mean and standard deviation. In this article, IQR, which is the interquartile range, can indicate the degree of distribution of data other than the upper 25% and lower 25% of data when the derived variable datasets for all battery cells are listed in ascending order for each of a plurality of derived variables. The derived variable dataset may be standardized based on Formula 4.

[0074] [Formula 4]

[0075]

[0076] Herein, X may be at least one derived variable data included in the derived variable data set. Q1 may be derived variable data corresponding to the first quartile, and Q3 may be derived variable data corresponding to the third quartile. and It can be the mean and standard deviation of the derived variable data present in the first and third quartiles.

[0077] Among all the data sets, the data sets distributed at both ends may be data sets corresponding to defective battery cells due to reasons other than low voltage, so that the data pre-processing unit 244 can perform normalization. Since the data pre-processing unit 244 performs normalization among all the data sets except the data sets distributed at both ends, the present disclosure can ultimately improve the accuracy of sorting low-voltage battery cells.

[0078] The data preprocessing unit 244 can reflect intra-pallet variations by converting the values ​​of the processed dataset into a derived variable dataset based on the derived variables, and can also reflect inter-pallet variations by normalizing the derived variable dataset. Therefore, the present disclosure can manage data having different distribution charts for each pallet by integrating the data into standardized data.

[0079] Hereinafter, a method of training an artificial intelligence model for sorting low-voltage battery cells based on preprocessed data and a method of sorting low-voltage battery cells by using the pre-trained artificial intelligence model will be described.

[0080] Methods for training AI models

[0081] The model training unit 248 can train the artificial intelligence model using a training data set. In this context, the training data set can be a processed data set of a normal battery cell, a derived variable data set of a normal battery cell, or a standardized derived variable data set of a normal battery cell.

[0082] The model training unit 248 may learn the distribution pattern of normal battery cells by using the training data set. For example, the model training unit 248 may learn the distribution pattern of normal battery cells based on the distribution of the first derived variable and the second derived variable of the training data set.

[0083] Method for sorting low-voltage battery cells

[0084] The sorting unit 246 may sort the low-voltage battery cells by using a pre-trained artificial intelligence model. The sorting unit 246 may sort the low-voltage battery cells by using an artificial intelligence model trained by the model training unit 248.

[0085] In an embodiment, the sorting unit 246 may sort battery cells having normalized processed data sets that are outside a specified range from a learned distribution pattern.

[0086] In an embodiment, the sorting unit 246 may determine the boundary between normal battery cells and low-voltage battery cells. The sorting unit 246 may determine the boundary between normal battery cells and low-voltage battery cells based on the learned distribution pattern. The sorting unit 246 may sort battery cells having a standardized processed data set that does not fall within the determined boundary as low-voltage battery cells. In this article, the determined boundary may be a boundary value of an area based on the distribution pattern of normal battery cells. The area within the boundary determined based on the determined boundary may be an area determined to be a normal battery cell, and the area outside the determined boundary may be an area determined to be a low-voltage battery cell.

[0087] Figure 3 A first distribution chart 30 of normalized data based on a first derived variable and a second derived variable according to an embodiment of the present disclosure is shown.

[0088] refer to Figure 3 On the first distribution graph 30 based on the normalized data of the first and second derived variables, the distribution of the normalized derived variable data sets of the plurality of battery cells may be shown.

[0089] The model training unit 248 can learn the distribution pattern of normal battery cells based on the distribution of the standardized derived variable data. In one embodiment, the model training unit 248 can cause the artificial intelligence model to learn the distribution pattern of normal battery cells based on the data density on the first distribution chart 30. In another embodiment, the model training unit 248 can cause the artificial intelligence model to learn the distribution pattern of normal battery cells based on the mean and standard deviation of the standardized derived variable data set.

[0090] The sorting unit 246 may sort battery cells corresponding to data outside a specified range from the distribution pattern derived by the model training unit 248 as defective battery cells due to low voltage.

[0091] A determination boundary 300 may also be indicated on the first distribution graph 30. Herein, the determination boundary 300 may mean a reference boundary value for determining whether a corresponding battery cell is a normal battery cell based on the learned distribution pattern.

[0092] The sorting unit 246 may sort the battery cells corresponding to the normalized derived variable data sets that do not fall within the determined boundary 300 as defective battery cells due to low voltage. For example, the sorting unit 246 may sort the battery cells having the normalized derived variable data sets distributed within the determined boundary 300 as normal battery cells based on the determined boundary 300.

[0093] Figure 4A second distribution chart 40 of normalized data based on the third derived variable and the second derived variable according to an embodiment of the present disclosure is shown.

[0094] refer to Figure 4 On the second distribution graph 40 based on the normalized data of the third and second derived variables, the distribution of the normalized derived variable data set of each of the plurality of battery cells may be shown.

[0095] and Figure 3 Similarly, the model training unit 248 can learn the distribution pattern of normal battery cells based on the distribution of the standardized derived variable data set.

[0096] The sorting unit 246 may sort battery cells having a normalized derived variable data set outside a specified range from the distribution pattern derived by the model training unit 248 as defective battery cells due to low voltage.

[0097] The second distribution graph 40 may also indicate the determined boundary 400. The sorting unit 246 may sort the battery cells having the normalized derived variable data sets that do not fall within the determined boundary 400 as defective battery cells due to low voltage. For example, the sorting unit 246 may sort the battery cells having the normalized derived variable data sets that fall within the determined boundary 400 as normal battery cells based on the determined boundary 400.

[0098] Reference above Figure 3 and Figure 4 The first and second distribution maps 30 and 40 are described as planar distribution maps based on two derived variables, but this is only an example and the present disclosure is not limited thereto. The present disclosure can sort low-voltage battery cells by using spatial distribution maps based on three derived variables.

[0099] Figure 5 is a flowchart illustrating an operating method of the low battery cell sorting device 20 according to an embodiment of the present disclosure.

[0100] refer to Figure 5 In operation 500 , the data acquisition unit 242 may acquire the processed data sets of the plurality of battery trays. The data acquisition unit 242 may acquire the processed data sets of the battery cells included in the plurality of battery trays through the sensor 220 .

[0101] In operation 502, the data pre-processing unit 244 may pre-process the raw data. The data pre-processing unit 244 may pre-process the processing data set.

[0102] The data pre-processing unit 244 may pre-process the processed data set by converting the processed data set into a derived variable data set. The data pre-processing unit 244 may convert the processed data set into derived variable data for each of a plurality of derived variables by using the OCV of the processed data set.

[0103] In an embodiment, the data pre-processing unit 244 may convert the OCV value included in the processed data set of the battery cell into a form for each of a plurality of derived variables. The data pre-processing unit 244 may generate derived variable data in which the OCV value included in the processed data set of the battery cell is converted into a form for each of a plurality of derived variables.

[0104] In an embodiment, the data preprocessing unit 244 may standardize the derived variable dataset by using the mean and standard deviation based on the quartiles of the derived variable dataset. The data preprocessing unit 244 may calculate the mean and standard deviation of the derived variable datasets existing in the first quartile Q1 to the third quartile Q3 based on the IQR of the derived variable dataset, and standardize the derived variable dataset by using the calculated mean and standard deviation.

[0105] In operation 504 , the sorting unit 246 may sort the low-voltage battery cells by using the pre-trained artificial intelligence model. The sorting unit 246 may sort the low-voltage battery cells by using the artificial intelligence model trained by the model training unit 248 .

[0106] In an embodiment, the sorting unit 246 may sort battery cells having normalized processed data sets that are outside a specified range from a learned distribution pattern.

[0107] In an embodiment, the sorting unit 246 may determine a boundary between normal cells and low-voltage cells. The sorting unit 246 may determine the boundary between normal cells and low-voltage cells based on the learned distribution pattern. The sorting unit 246 may sort cells with a normalized processed data set that does not fall within the determined boundary as low-voltage cells.

[0108] Unless otherwise specified, the above terms such as "including", "consisting of" or "having" may mean that the corresponding components may be inherent and should therefore be interpreted as also including other components rather than excluding other components. Unless otherwise defined, all terms including technical or scientific terms have the same meaning as commonly understood by ordinary technicians in the field to which the embodiments disclosed herein belong. Commonly used terms, such as terms defined in dictionaries, should be interpreted as having the same meaning as the contextual meaning of the relevant technology, and should not be interpreted as having ideal or overly formal meanings unless they are clearly defined in this document.

[0109] The above description only illustrates the technical ideas of the present disclosure, and a person skilled in the art to which the embodiments disclosed herein belong may make various modifications and changes without departing from the basic characteristics of the embodiments disclosed herein. Therefore, the embodiments disclosed herein are intended to describe rather than limit the technical spirit of the embodiments disclosed herein, and the scope of the technical spirit of the present disclosure is not limited by these embodiments disclosed herein. The scope of protection of the technical spirit disclosed herein should be interpreted by the attached claims, and all technical spirits within the same scope should be interpreted as being included within the scope of this document.

Claims

1. A low-voltage battery cell sorting device, comprising: a data obtaining unit configured to obtain a processed data set of battery cells included in each of the plurality of battery trays; a data pre-processing unit configured to generate a derived variable data set including at least two types of derived variables for each of the battery cells by using the processed data set, and to normalize the derived variable data set; as well as A sorting unit is configured to sort battery cells having a standardized derived variable data set outside a specified range among the standardized derived variable data sets as low-voltage battery cells by using an artificial intelligence model.

2. The low-voltage battery cell sorting device according to claim 1, wherein: The data pre-processing unit is further configured to normalize the derived variable dataset by using a mean value and a standard deviation based on quartiles of the derived variable dataset.

3. The low-voltage battery cell sorting device according to claim 1, wherein: The artificial intelligence model is trained using a training data set for normal battery cells and learns a distribution pattern of the training data set by using a distribution chart based on at least two types of derived variables among a plurality of derived variables.

4. The low-voltage battery cell sorting device according to claim 3, wherein: The designated range is a boundary determined based on the distribution pattern, and the sorting unit is further configured to sort the battery cells having the normalized derived variable data set outside the determined boundary as the low-voltage battery cells.

5. The low-voltage battery cell sorting device according to claim 1, wherein: The processed data set includes open circuit voltage (OCV) measured according to a time sequence of an activation process of each of the battery cells.

6. A method for operating a low-voltage battery cell sorting device, the method comprising: obtaining a processed data set of battery cells included in each of a plurality of battery trays; generating, for each of the battery cells, a derived variable data set including at least two types of derived variables by using the processed data set; standardizing the derived variable dataset; and By using the artificial intelligence model, battery cells having a normalized derived variable data set outside a specified range among the normalized derived variable data sets are sorted as low-voltage battery cells.

7. The operating method according to claim 6, wherein: The normalization includes normalizing the derived variable dataset by using a mean and a standard deviation based on quartiles of the derived variable dataset.

8. The operating method according to claim 6, wherein: The artificial intelligence model is trained using a training data set for normal battery cells and learns a distribution pattern of the training data set by using a distribution chart based on at least two types of derived variables among a plurality of derived variables.

9. The operating method according to claim 8, wherein: The designated range is a boundary determined based on the distribution pattern, and the sorting includes sorting battery cells having a normalized derived variable data set outside the determined boundary as the low-voltage battery cells.

10. The operating method according to claim 6, wherein: The processed data set includes open circuit voltage (OCV) measured according to a time sequence of an activation process of each of the battery cells.

Images