Method, electronic device and system for managing a battery

Abstract

The present disclosure may provide a method for classifying batteries performed by an electronic device. The method may include: obtaining first information regarding one or more first images generated by scanning a target battery to be classified from a scanner; determining, based on the one or more first images, that the type of the target battery is a target type among one or more types; obtaining second information regarding a second image of a battery corresponding to the target type from a database storing information regarding the one or more types of the battery; determining whether the target battery has a first type of defect based on the first information and the second information; and classifying the target battery as a target for dismantling in response to the determination that the target battery has a first type of defect.

Description

Technology Field

[0001] The present disclosure relates to a technology for managing batteries.

[0002] This research is the result of a project conducted under the "Technology Development Project for Enhancing the Circularity of Secondary Batteries" by the Ministry of Environment and the Korea Environmental Industry & Technology Institute. [Project Title: Development of Demonstration Technology for Automated Dismantling, Separation, and Resource Recovery of Multi-Type Waste Secondary Batteries Based on Eco-friendly Pre-lithium Extraction, Project No.: 00339705] Background Technology

[0003] Recently, batteries used in electric vehicles are lithium-ion batteries composed of four major components: anode material, cathode material, electrolyte, and separator. Among these, lithium-ion batteries are classified into various types depending on the material used as the anode material. Representative examples include nickel ternary batteries (e.g., nickel-cobalt-manganese (NCM), nickel-cobalt-aluminum (NCA)), cobalt-based batteries (e.g., lithium cobalt oxide (LCO)), and manganese-based batteries (e.g., lithium manganese oxide (LMO)). Additionally, lithium iron phosphate (LFP) batteries, which utilize iron to replace cobalt, are also being used. Furthermore, various types of batteries, including all-solid-state batteries, are scheduled to be introduced in the future to reduce the fire risk associated with liquid electrolytes.

[0004] As the scale of waste batteries discarded after use expands with the growth of the electric vehicle market, the recycling industry for the recycling and reuse of waste batteries is becoming more active. Prior art literature

[0005] Patent Document 1: Chinese Published Patent Application No. 118699767 Patent Document 2: Chinese Published Patent Application No. 118536990 Patent Document 3: Chinese Registered Patent Application No. 216736428 Patent Document 4: Chinese Published Patent Application No. 218630112 Patent Document 5: Chinese Published Patent Application No. 112242576 Patent Document 6: Registered Patent Application No. 2800975 Patent Document 7: Registered Patent Application No. 2588460 Patent Document 8: Registered Patent Application No. 2810492 Patent Document 9: Chinese Published Patent Application No. 117254149

[0006] Non-patent Literature 1: "Robotised disassembly of electric vehicle batteries: A systematic literature review", Authors: Tero Kaarlela, Enrico Villagrossi, Alireza Rastegarpanah, Alberto San-Miguel-Tello, Tomi Pitkaaho Non-patent Literature 2: "Recycling and reuse of waste batteries generated from electric vehicles: A review", Authors: Ji-Woo Jung, Jin-Young Choi, Ye-Jin Lee, Ah-Hyun Park, Seok-Hee Jung The problem to be solved

[0007] The present disclosure aims to provide a technology for classifying batteries as reusable or recyclable.

[0008] The present disclosure aims to provide a technology for automatically dismantling batteries classified as recyclable.

[0009] The technical problems of the present disclosure are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by a person skilled in the art from the description in the specification. means of solving the problem

[0010] A method according to one embodiment of the present disclosure may be a method for classifying batteries performed by an electronic device. The method may include: a step of obtaining first information regarding one or more first images generated by scanning a target battery to be classified from a scanner; a step of determining, based on the one or more first images, the type of the target battery as a target type among one or more types; a step of obtaining second information regarding a second image of a battery corresponding to the target type from a database storing information regarding the one or more types of the battery; a step of determining whether the target battery has a first type of defect based on the first information and the second information; and a step of classifying the target battery as a target for dismantling operations in response to the determination that the target battery has a first type of defect.

[0011] In one embodiment, the one or more types may be types associated with one or more manufacturers that manufacture batteries.

[0012] In one embodiment, information regarding one or more types may include information regarding one or more images of a battery corresponding to each of the one or more types.

[0013] In one embodiment, the step of determining the type of the target battery as the target type among the one or more types may include using a first artificial intelligence model trained to output information indicating the type to which the battery belongs from an input image of the battery, and inputting at least one of the one or more first images of the first information into the first artificial intelligence model and determining the type of the target battery as the target type among the one or more types based on the output information.

[0014] In one embodiment, the first type of defect may be a defect that is visible on the exterior of the battery.

[0015] In one embodiment, the step of determining whether there is a first type of defect may include: determining a target image that includes an area of ​​the battery captured in the second image in the second information among the one or more first images in the first information that corresponds at least partially to the area of ​​the battery captured in the second image in the second information; and determining whether there is a first type of defect in the target battery based on the target image and the second image.

[0016] In one embodiment, in response to a determination that the target battery is free of a first type of defect, the method may further include the step of obtaining a first signal generated by measuring a target voltage, which is the voltage between the positive and negative electrodes of each of one or more cells of the target battery, from a voltage measuring device; the step of obtaining a second signal generated by measuring a target temperature, which is the temperature of the target battery, from a temperature sensor; and the step of determining whether to classify the target battery as a target for the dismantling operation based on at least one of the first signal or the second signal, and based on at least one of whether the target deviation, which is the deviation of the target voltage between the one or more cells, is greater than or equal to a predetermined reference deviation or whether the target temperature is greater than or equal to a predetermined reference temperature.

[0017] In one embodiment, the step of determining whether to classify the target battery as a target for the dismantling operation may include the step of classifying the target battery as a target for the dismantling operation in response to a determination that the target deviation is greater than or equal to the reference deviation.

[0018] In one embodiment, the reference deviation may be determined based on the size of the maximum charge capacity of the target battery.

[0019] In one embodiment, the step of determining whether to classify the target battery as a target for the dismantling operation may further include the step of classifying the target battery as a target for the dismantling operation in response to a determination that the target temperature is above the reference temperature.

[0020] In one embodiment, the step of determining whether to classify the target battery as a target for the dismantling operation may further include: a step of obtaining third information indicating the Direct Current Internal Resistance of the target battery in response to a determination that the target deviation is not greater than or equal to the reference deviation and the target temperature is not greater than or equal to the reference temperature; a step of generating Electrochemical Impedance Spectroscopy (EIS) information based on a signal output from the target battery in response to applying one or more alternating current voltages of frequency to the target battery; a step of determining the State of Health (SOH) of the target battery based on information output by inputting at least one of the third information and the EIS information to the second artificial intelligence model, using a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from the input information indicating the Direct Current Internal Resistance of the battery and the EIS information; a step of determining whether the SOH of the target battery is less than or equal to a predetermined reference; and a step of classifying the target battery as a target for the dismantling operation in response to a determination that the SOH of the target battery is less than or equal to a predetermined reference.

[0021] In one embodiment, the EIS information may include information indicating at least one of the electrolyte resistance, solid electrolyte interphase resistance, or Warburg impedance due to lithium ion diffusion of the target battery.

[0022] In one embodiment, the method may further include the step of classifying the target battery as a reusable battery in response to a determination that the SOH of the target battery is not below a predetermined reference value.

[0023] In one embodiment, in response to classifying the target battery as a target for the dismantling operation, the method may further include the step of determining a target automation device among one or more automation devices to perform the dismantling operation of the target battery.

[0024] In one embodiment, the step of determining the target automation device may include determining the automation device that performs the dismantling operation for the target type of battery among the one or more automation devices as the target automation device.

[0025] In one embodiment, the step of transmitting the first information of the target battery to the target automation device may be further included.

[0026] An apparatus according to one embodiment of the present disclosure may be an electronic apparatus for classifying batteries. The apparatus may include one or more processors and one or more memories storing instructions to be executed by the one or more processors. When the instructions are executed, the one or more processors may be configured to obtain first information regarding one or more first images generated by scanning a target battery to be classified from a scanner, determine the type of the target battery as a target type among one or more types based on the one or more first images, obtain second information regarding a second image of a battery corresponding to the target type from at least one of the one or more memories storing information regarding the one or more types of the battery, determine whether the target battery has a first type of defect based on the first information and the second information, and classify the target battery as a target for dismantling operations in response to the determination that the target battery has a first type of defect.

[0027] In one embodiment, the one or more processors may be configured to determine the type of the target battery as the target type among the one or more types by using a first artificial intelligence model trained to output information indicating the type to which the battery belongs from an input image of the battery, and by inputting at least one of the one or more first images of the first information into the first artificial intelligence model and determining the type of the target battery as the target type among the one or more types based on the output information.

[0028] In one embodiment, the one or more processors may be configured to determine whether there is a first type of defect by determining a target image that includes at least a region corresponding to a region of the battery captured in the second image in the second information among the one or more first images in the first information, and to determine whether there is a first type of defect in the target battery based on the target image and the second image.

[0029] In one embodiment, the one or more processors may be further configured to determine whether to classify the target battery as a target for the dismantling operation based on at least one of the following: in response to a determination that the target battery is free of a first type of defect, the processor obtains a first signal generated by measuring a target voltage, which is the voltage between the positive and negative electrodes of each of one or more cells of the target battery, from a voltage measuring device, and obtains a second signal generated by measuring a target temperature, which is the temperature of the target battery, from a temperature sensor, and based on at least one of the first signal or the second signal, whether the target deviation, which is the deviation of the target voltage between the one or more cells, is greater than or equal to a predetermined reference deviation or whether the target temperature is greater than or equal to a predetermined reference temperature.

[0030] In one embodiment, the one or more processors may be further configured to determine whether to classify the target battery as a target for dismantling work by acquiring third information indicating the Direct Current Internal Resistance of the target battery in response to a determination that the target deviation is not greater than or equal to the reference deviation and the target temperature is not greater than or equal to the reference temperature, and by applying one or more alternating current voltages of frequency to the target battery, generating Electrochemical Impedance Spectroscopy (EIS) information based on a signal output from the target battery in response, and using a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from the input information indicating the Direct Current Internal Resistance of the battery and the EIS information, and by inputting at least one of the third information and the EIS information into the second artificial intelligence model and determining the SOH of the target battery based on the output information, determining whether the SOH of the target battery is less than or equal to a predetermined reference, and classifying the target battery as a target for dismantling work in response to a determination that the SOH of the target battery is less than or equal to a predetermined reference.

[0031] In one embodiment, the one or more processors may be further configured to classify the target battery as a reusable battery in response to a determination that the SOH of the target battery is not below a predetermined reference value.

[0032] In one embodiment, the one or more processors may be further configured to determine, among one or more automation devices, a target automation device to perform the dismantling operation of the target battery in response to classifying the target battery as a target to perform the dismantling operation.

[0033] In one embodiment, the one or more processors may be further configured to transmit the first information of the target battery to the target automation device.

[0034] A system according to one embodiment of the present disclosure may be a system for classifying batteries. The system may include an electronic device comprising a scanner, one or more processors, and one or more memories storing instructions to be executed by the one or more processors. The one or more processors may be configured to obtain first information regarding one or more first images generated by scanning a target battery to be classified from the scanner, determine the type of the target battery as a target type among one or more types based on the one or more first images, obtain second information regarding a second image of a battery corresponding to the target type from at least one of the one or more memories storing information regarding the one or more types of the battery, determine whether the target battery has a first type of defect based on the first information and the second information, and classify the target battery as a target for dismantling operations in response to the determination that the target battery has a first type of defect.

[0035] In one embodiment, the one or more processors may be configured to determine the type of the target battery as the target type among the one or more types by using a first artificial intelligence model trained to output information indicating the type to which the battery belongs from an input image of the battery, and by inputting at least one of the one or more first images of the first information into the first artificial intelligence model and determining the type of the target battery as the target type among the one or more types based on the output information.

[0036] In one embodiment, the one or more processors may be configured to determine whether there is a first type of defect by determining a target image that includes at least a region corresponding to a region of the battery captured in the second image in the second information among the one or more first images in the first information, and to determine whether there is a first type of defect in the target battery based on the target image and the second image.

[0037] In one embodiment, the system further comprises a voltage measuring device and a temperature sensor, and the one or more processors may be further configured to determine whether to classify the target battery as a target for dismantling operations based on at least one of whether the target deviation, which is a deviation of the target voltage between the one or more cells, is greater than or equal to a predetermined reference deviation or the target temperature is greater than or equal to a predetermined reference temperature, in response to a determination that the target battery is not of a first type of defect, and the target battery is further configured to obtain a first signal generated by measuring a target voltage, which is a voltage between the positive and negative electrodes of the target battery, from the voltage measuring device, in response to a determination that the target battery is not of a first type of defect, and to obtain a second signal generated by measuring a target temperature, which is a temperature of the target battery, from the temperature sensor, and based on at least one of the first signal or the second signal.

[0038] In one embodiment, the one or more processors may be further configured to determine whether to classify the target battery as a target for dismantling work by acquiring third information indicating the Direct Current Internal Resistance of the target battery in response to a determination that the target deviation is not greater than or equal to the reference deviation and the target temperature is not greater than or equal to the reference temperature, and by applying one or more alternating current voltages of frequency to the target battery, generating Electrochemical Impedance Spectroscopy (EIS) information based on a signal output from the target battery in response, and using a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from the input information indicating the Direct Current Internal Resistance of the battery and the EIS information, and by inputting at least one of the third information and the EIS information into the second artificial intelligence model and determining the SOH of the target battery based on the output information, determining whether the SOH of the target battery is less than or equal to a predetermined reference, and classifying the target battery as a target for dismantling work in response to a determination that the SOH of the target battery is less than or equal to a predetermined reference.

[0039] In one embodiment, the one or more processors may be further configured to classify the target battery as a reusable battery in response to a determination that the SOH of the target battery is not below a predetermined reference value.

[0040] In one embodiment, the system further includes one or more automation devices, and the one or more processors may be further configured to determine, among the one or more automation devices, a target automation device to perform the dismantling operation of the target battery in response to classifying the target battery as a target to perform the dismantling operation.

[0041] In one embodiment, the one or more processors may be further configured to transmit the first information of the target battery to the target automation device. Effects of the invention

[0042] In one embodiment of the present disclosure, a technology for classifying batteries as reusable or recyclable can be provided.

[0043] In one embodiment of the present disclosure, a technology for automatically dismantling batteries classified as recyclables can be provided.

[0044] The effects according to the technical concept of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art of the present disclosure from the description in the specification. Brief explanation of the drawing

[0045] FIG. 1 is a schematic diagram illustrating the configuration of a system for managing a battery according to one embodiment of the present disclosure. FIG. 2 is a drawing showing an electronic device according to one embodiment of the present disclosure. FIG. 3 is a flowchart illustrating a method for classifying target batteries according to one embodiment of the present disclosure. FIG. 4 is a flowchart showing the specific operation of a first classification step in a method for classifying target batteries according to one embodiment of the present disclosure. FIG. 5 is a flowchart illustrating in detail a method for determining whether a target battery has a first type of defect according to one embodiment of the present disclosure. FIG. 6 is a flowchart illustrating the specific operation of a secondary classification step in a method for classifying target batteries according to one embodiment of the present disclosure. FIG. 7 is a flowchart illustrating the specific operation of a third classification step in a method for classifying target batteries according to one embodiment of the present disclosure. FIG. 8 is a flowchart illustrating a method for performing a dismantling operation of a target battery according to one embodiment of the present disclosure. FIG. 9 is a schematic diagram illustrating one example of a system for managing a battery according to one embodiment of the present disclosure. FIG. 10 is a flowchart for explaining a method for determining whether to dispose of a target battery without performing dismantling work when a first type of defect is found in the first classification step of the target battery according to one embodiment of the present disclosure, because the degree of the defect is severe. Specific details for implementing the invention

[0046] The various embodiments described in this disclosure are illustrative for the purpose of clearly explaining the technical concept of this disclosure and are not intended to limit it to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of each embodiment described in this disclosure. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0047] Terms used in this disclosure, including technical or scientific terms, may have the meaning generally understood by those skilled in the art to which this disclosure pertains, unless otherwise defined.

[0048] Expressions used in this disclosure, such as “comprising,” “may compose,” “possessing,” “possessing,” “having,” and “possessing,” mean that the subject feature (e.g., function, operation, or component, etc.) exists and do not exclude the existence of other additional features. That is, such expressions should be understood as open-ended terms implying the possibility of including other embodiments.

[0049] Singular expressions used in this disclosure may include the meaning of the plural form unless otherwise indicated by the context, and this applies likewise to singular expressions described in the claims.

[0050] Expressions such as "first," "second," or "first," "second," etc., used in this disclosure are used to distinguish one object from another when referring to a plurality of objects of the same kind, unless otherwise indicated in the context, and do not limit the order or importance of the objects.

[0051] Expressions used in the present disclosure, such as “A, B and C,” “A, B or C,” “at least one of A, B and C,” or “at least one of A, B or C,” may mean each of the listed items or all possible combinations of the listed items. For example, “at least one of A or B” may refer to (1) at least one A, (2) at least one B, and (3) at least one A and at least one B.

[0052] The expression “based on” as used in this disclosure is used to describe one or more factors affecting an act or action of a decision or judgment described in the phrase or sentence containing this expression, and this expression does not exclude additional factors affecting said act or action of a decision or judgment.

[0053] As used in the present disclosure, the expression that a certain component (e.g., a first component) is "connected" or "connected" to another component (e.g., a second component) may mean that the certain component is directly connected or connected to the other component, as well as being connected or connected through a new other component (e.g., a third component).

[0054] As used in this disclosure, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," or "capable of." This expression is not limited to the meaning of "specifically designed in hardware." For example, a processor configured to perform a specific operation may mean a generic-purpose processor capable of performing that specific operation by executing software, or a special-purpose computer structured through programming to perform that specific operation.

[0055] As used in this specification, the term "battery" may mean any one of a battery pack, a battery module, or a battery cell, and may mean any one of a set of one or more battery modules or a set of one or more battery cells connected through various components; however, it is not limited thereto and includes batteries of various forms and units that can be understood by a person skilled in the art. Accordingly, the term "battery" mentioned in this specification is not limited to a specific product, form, or unit, but may be interpreted as a concept encompassing batteries of various structures and configurations. For example, "battery" may be a battery of various structures and configurations used in various application fields, such as electric vehicles, as well as hybrid electric vehicles, fuel cell electric vehicles, and energy storage systems. Furthermore, in this specification, "battery" may also refer to a waste battery that has completed its use and is subject to disposal or recycling.

[0056] Hereinafter, various embodiments described in this disclosure will be explained with reference to the attached drawings. In the attached drawings and the description thereof, identical or substantially equivalent components may be given the same reference numerals. Furthermore, in the description of the various embodiments below, the description of identical or corresponding components may be omitted, but this does not mean that such components are not included in the embodiments.

[0057] FIG. 1 is a schematic diagram illustrating the configuration of a system for managing a battery according to one embodiment of the present disclosure. The system (100) may include an electronic device (110), a scanner (120), a temperature sensor (130), and / or a voltage measuring device (140). In addition to the components shown in FIG. 1, the system (100) of the present disclosure may further include a device for measuring direct current internal resistance (DCIR) and a device for applying alternating voltage, an automated guided vehicle (AGV), an automated device for dismantling the battery, a workbench, etc., or may be implemented excluding some of the components. The system (100) may be configured to measure the state of a target battery (B) (various signals and / or information of the target battery (B)), classify the target battery (B) as a reusable battery or a battery to be dismantled, and perform a subsequent process (storage or dismantling).

[0058] The target battery (B) may refer to a battery that is subject to diagnosis, classification, and management by the system (100). In one embodiment, the target battery (B) may be a lithium-ion battery pack recovered after use in an electric vehicle or an energy storage system (ESS), etc. For example, the target battery (B) may have non-standardized specifications according to various manufacturers and vehicle models, and may have different defects such as physical damage (external damage), electrical degradation, or risk of thermal runaway depending on its condition. The system (100) of the present disclosure may classify the target battery (B) as either a target for dismantling or a reusable battery.

[0059] The electronic device (110) may be configured to control the overall operation of the system (100), analyze information received from each component, and classify the target battery (B). In one embodiment, the electronic device (110) may include one or more processors and one or more memories. One or more memories may store one or more instructions that cause the processor to perform operations according to various embodiments of the present disclosure and various information processed by the processor.

[0060] In one embodiment, the electronic device (110) may be configured to perform a primary classification, which determines the type of a target battery (B) based on image information (first information) obtained from a scanner (120) and image information (second information) of one or more types of a battery obtained from a database (e.g., one or more memories), and determines whether the target requires dismantling work based on the presence or absence of a first type of defect (exterior damage). In one embodiment, the electronic device (110) may be configured to perform a secondary classification, which determines whether to classify the target for dismantling work by measuring the target temperature of one or more cells of the target battery (B) from a temperature sensor (130) and obtaining the target voltage of one or more cells of the target battery (B) from a voltage measuring device (140) when there is no first type of defect (i.e., when the primary classification is passed). In one embodiment, if the second classification is passed, the electronic device (110) may be configured to perform a third classification, which classifies the target battery (B) into a reusable battery or a target for dismantling by predicting the State of Health (SOH) value of the target battery (B) based on an artificial intelligence model using the DC internal resistance and Electrochemical Impedance Spectroscopy (EIS) information of the target battery (B).

[0061] The electronic device (110) may be implemented as one or more computing devices. For example, all functions of the electronic device (110) may be implemented in a single computing device. As another example, the first function of the electronic device (110) may be implemented in the first computing device, and the second function may be implemented in the second computing device. Even if the first computing device and the second computing device exist physically separated, the first computing device and the second computing device may be referred to as the electronic device (110) as an abstract concept that integrates them.

[0062] The aforementioned computing device may be, for example, a desktop computer, a laptop computer, an application server, a proxy server, or a cloud server, but is not limited thereto, and any type of device equipped with computing functions may be a computing device.

[0063] A scanner (120) may be configured to capture the exterior of a target battery (B) and generate image information regarding the target battery (B). In one embodiment, the scanner (120) may be configured to perform a vision scan of the exterior of the target battery (B), generate first information regarding one or more first images, and transmit it to an electronic device (110). For example, each of the one or more first images may include whether the outer casing, connection part, or accessory of the target battery (B) is damaged. The first information obtained through the scanner (120) may be compared and analyzed with information in a database that stores information regarding one or more types of batteries in advance in the electronic device (110), and may be used to classify the target battery (B) by determining the type of battery and determining whether there is external damage.

[0064] A temperature sensor (130) may be configured to measure a target temperature, which is the temperature of a target battery (B). In one embodiment, the temperature sensor (130) may be further configured to provide a signal containing information indicating the target temperature to an electronic device (110). For example, the temperature sensor (130) may be configured to measure the target temperature by measuring the temperature of the surface of the target battery (B) or a nearby environment, and to transmit a signal (e.g., a second signal) regarding this to the electronic device (110). For example, the electronic device (110) may use the information of the second signal to determine whether the target temperature measured by the temperature sensor (130) is above a predetermined reference temperature for a target battery (B) that has passed a first classification. In one embodiment, if the target temperature exceeds the reference temperature, the target battery (B) may be classified as a target for dismantling operations, taking into account safety issues of the battery and potential risks of thermal runaway.

[0065] A voltage measuring device (140) may be configured to measure the voltage between the positive and negative electrodes of a target battery (B). In one embodiment, the voltage measuring device (140) may be configured to measure the open circuit voltage (OCV) of each of one or more cells of the target battery (B) to measure the target voltage and transmit a first signal regarding this to an electronic device (110). For example, for a target battery (B) that has passed a primary classification, the electronic device (110) may determine a target deviation, which is a deviation of the target voltage between one or more cells measured by the voltage measuring device (140), and use this information to determine whether the target deviation is greater than or equal to a predetermined reference deviation. In one embodiment, if the target deviation is not greater than or equal to the reference deviation, it proceeds to an additional SOH prediction step, and if the target deviation is greater than or equal to the reference deviation, the target battery (B) may be classified as a target for dismantling.

[0066] One embodiment of the system (100) of the present disclosure sequentially performs a first classification based on vision scanning using a scanner (120) and a second classification based on OCV / temperature using a temperature sensor (130) and a voltage measuring device (140), thereby enabling rapid selection of batteries with initial defects and high risk as targets for dismantling work during the initial diagnosis stage of the target battery (B). Accordingly, the time and cost required for battery diagnosis and classification can be improved. Subsequently, for batteries that have passed the second classification, a third classification can be performed to determine whether the target battery (B) is a reusable battery by predicting the SOH value of the target battery (B) based on an artificial intelligence model using the DC internal resistance and EIS information of the target battery (B). If the condition of the target battery (B) is good, it is decided to reuse the target battery (B) without the need to dismantle it, thereby reducing the resources and time required to dismantle and separate the target battery (B).

[0067] FIG. 2 is a drawing showing an electronic device (110) according to one embodiment of the present disclosure. The electronic device (110) may include one or more processors (210) and one or more memories (220). The electronic device (110) may further include a communication circuit (230).

[0068] In the present disclosure, one or more processors (210) may be referred to as processors (210). Unless the context clearly indicates otherwise, the term processors (210) may mean a set of one or more processors. Additionally, in the present disclosure, one or more memories (220) may be referred to as memories (220). Unless the context clearly indicates otherwise, the term memories (220) may mean a set of one or more memories (220).

[0069] The processor (210) can perform operations or information processing regarding the control or communication of each component of the electronic device (110). Specifically, the processor (210) can control at least one component of the electronic device (110) connected to the processor (210) by running software (or computer program) received from another component. As an example, the processor (210) can load instructions (e.g., instructions, code, or code segments) or information into memory (220), process the instructions or information stored in memory (220), and store result information resulting from the processing in memory (220). Additionally, the processor (210) can be operatively connected to the components of the electronic device (110) to perform various operations such as operations, processing, generation, or processing related to the present disclosure.

[0070] The memory (220) may store various information. The information stored in the memory (220) may include software, which is information acquired, processed, or used by at least one component of the electronic device (110). The software may include one or more instructions that cause the processor (210) to perform operations according to various embodiments of the present disclosure when loaded into the memory (220). That is, the processor (210) may perform operations according to various embodiments of the present disclosure by executing the one or more instructions described above. The memory (220) may include, for example, volatile or non-volatile memory. In one embodiment, the program may be software stored in the memory (220) and may include an operating system for controlling the resources of the electronic device (110), an application, or middleware that provides various functions to the application so that the application can utilize the resources of the electronic device (110).

[0071] The communication circuit (230) can establish a wired or wireless communication channel with another device and transmit and receive various information with the other device. In one embodiment, the electronic device (110) can exchange various information and / or signals with each device of the system (100) (e.g., one or more sensors (210), cameras (130), etc.) through the communication circuit (230). In one embodiment, the communication circuit (230) may include at least one port for connecting to another device via a wired cable in order to communicate with the other device via a wired connection. In this case, the communication circuit (230) can perform communication with the other device connected via a wired connection through at least one port. In one embodiment, the communication circuit (230) may be configured to include a cellular communication module to be connected to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). In one embodiment, the communication circuit (230) may include a short-range communication module to transmit and receive information with another device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB). In one embodiment, the communication circuit (230) may include a contactless communication module for contactless communication. Contactless communication may include at least one contactless proximity communication technology, such as, for example, Near Field Communication (NFC) communication, Radio Frequency Identification (RFID) communication, or Magnetic Secure Transmission (MST) communication. In addition to the various examples described above, the electronic device (110) may be implemented in various known ways for communicating with another device, and the scope of the present disclosure is not limited by the examples described above.

[0072] The processor (210), memory (220), and communication circuit (230) are connected to each other via a bus, GPIO (General Purpose Input / Output), SPI (Serial Peripheral Interface), or MIPI (Mobile Industry Processor Interface), etc., so that they can give or receive information or signals.

[0073] FIG. 3 is a flowchart illustrating a method for classifying a target battery (B) according to one embodiment of the present disclosure. The method may be performed by one or more processors (210) (hereinafter, "processor (210)") of an electronic device (110) of a system (100).

[0074] In step S310, the processor (210) may perform a primary classification of the target battery (B). In one embodiment, the processor (210) may determine, as a primary classification, whether to classify the target battery (B) as a target for dismantling operations based on first information regarding a first image of the target battery (B) obtained from the scanner (120). In one embodiment, the processor (210) may determine whether the target battery (B) has passed the primary classification based on whether there is physical damage to the target battery (B), i.e., whether there is a first type of defect. In response to the determination that there is a first type of defect, the processor (210) may classify the target battery (B) as a target for dismantling operations by determining that the target battery (B) has not passed the primary classification ("failed"). In one embodiment, in response to the determination that there is no first type of defect, the processor (210) may determine that the target battery (B) has passed the primary classification.

[0075] In one embodiment of the present disclosure, batteries that are difficult to reuse due to external defects can be quickly classified as targets for dismantling without additional performance testing. The specific configuration and operation of step S310 will be described in detail through FIG. 4, which will be described later.

[0076] In step S320, the processor (210) may perform a second classification on the target battery (B) in response to passing the first classification. In one embodiment, the processor (210) may determine whether to classify the target battery (B) as a target for dismantling operations based on various signals (target voltage and target temperature) obtained from the voltage measuring device (140) and the temperature sensor (130). In one embodiment, the processor (210) may determine whether to pass the second classification based on at least one of whether the target deviation is greater than or equal to a predetermined reference deviation or whether the target temperature is greater than or equal to a predetermined reference temperature. The processor (210) may classify the target battery (B) as a target for dismantling operations based on the determination that the target battery (B) did not pass the second classification ("failed"). In one embodiment, in response to a determination that the target deviation is not greater than a predetermined reference deviation and the target temperature is not greater than a predetermined reference temperature, the processor (210) may determine that the target battery (B) has passed the secondary classification.

[0077] A large deviation in target voltage between cells implies that certain cells degrade or are damaged faster than others, resulting in severe cell imbalance, which can be a major cause of overall battery performance degradation and safety issues. Additionally, a battery pack temperature above a reference level suggests that an internal short circuit or abnormal heat generation is occurring, and that safety risks such as thermal runaway may be imminent. In one embodiment of the present disclosure, secondary classification is performed to quickly classify batteries that pose safety risks or are already severely degraded as targets for dismantling without additional long-term performance testing. The specific operation of step S320 will be described in detail through FIG. 6, which will be described later.

[0078] In step S330, the processor (210) may perform a third classification on the target battery (B) in response to passing the second classification. In one embodiment, the processor (210) may determine whether to classify the target battery (B) as a target for dismantling or as a reusable battery based on at least one of the DC internal resistance or EIS information of the target battery (B). In one embodiment, the processor (210) may predict the SOH of the target battery (B) using an artificial intelligence model based on at least one of the DC internal resistance or EIS information. If the predicted SOH is less than a predetermined reference SOH, the processor (210) may classify the target battery (B) as a target for dismantling, and if the predicted SOH is greater than or equal to the reference SOH, it may be classified as a reusable battery. The specific configuration and operation of step S330 will be described in detail through FIG. 7, which will be described later.

[0079] Conventional battery diagnostic methods have the problem of requiring complex performance tests, which incurs significant time and cost, and in particular, there were difficulties in rapid diagnosis because charge-discharge curve information is required for SOH prediction. In one embodiment of the present disclosure, through a primary classification based on images obtained by scanning the battery, a secondary classification based on OCV / temperature, and a tertiary classification utilizing machine learning SOH prediction based on DC internal resistance / EIS, the accuracy and speed of battery diagnosis and classification can be improved, and the efficiency of battery reuse and recycling processes can be enhanced.

[0080] FIG. 4 is a flowchart showing the specific operation of a first classification step (S310) of a method for classifying a target battery (B) according to one embodiment of the present disclosure.

[0081] In step S410, the processor (210) may obtain first information regarding one or more first images generated by scanning a target battery (B) to be classified from the scanner (120). In one embodiment, each first image may be a high-resolution image of the entire exterior or at least a part of the main parts of the target battery (B) pack captured by the scanner (120). For example, the first image may be an image generated by capturing the exterior shape, size, part arrangement, and the location of minute damage that is difficult to identify with the naked eye (e.g., micro-cracks in the casing, discoloration of the terminal area, etc.) of the target battery (B) pack.

[0082] In step S420, the processor (210) may determine the type of the target battery (B) as a target type among one or more types based on one or more first images. In one embodiment, one or more types may be types associated with one or more manufacturers that manufacture batteries. In one embodiment, the processor (210) may determine the target type of the target battery (B) using a first artificial intelligence model trained to output information indicating the type to which the battery belongs (e.g., EV battery pack model X of manufacturer A, ESS battery pack model Y of manufacturer B, etc.) from an input image of the battery. For example, the first artificial intelligence model, or the second artificial intelligence model, may be a machine learning (e.g., Support Vector Machine, Gaussian Process Regression) or deep learning (e.g., Convolutional Neural Network, Recurrent Neural Network) model. For example, the processor (210) can input at least a portion of one or more first images of the first information into the first artificial intelligence model and, based on the information output from the first artificial intelligence model, determine the type of the target battery (B) as one or more types.

[0083] In step S430, the processor (210) can obtain second information regarding a second image of a battery corresponding to a target type from a database that stores information regarding one or more types of batteries.

[0084] In one embodiment, the database may be a database that stores second information regarding one or more second images of a battery corresponding to each of one or more types of batteries. The one or more second images may include at least one of an image of the normal state of each type of battery or a standard image for each type of damage. For example, after a target type (e.g., Model X) is determined, the processor (210) may load normal appearance image information (second information) of the corresponding Model X from the database and prepare to compare and analyze it with actual image information (first information) of the target battery (B) in a subsequent step.

[0085] In one embodiment, the database may be implemented using at least a portion of one or more memories (220) of the electronic device (110). In one embodiment, the database may be a database implemented on an external server, in which case the electronic device (110) may obtain second information from the database of the external server through a communication circuit.

[0086] In step S440, the processor (210) may determine whether the target battery (B) has a first type of defect based on the first information and the second information. The first type of defect is a type of defect that is visible on the exterior of the battery and may include, for example, damage to the battery, corrosion, abnormal deformation, etc. For example, the processor (210) may determine whether the target battery (B) has a first type of defect by analyzing the similarity between the first information and the second information, or by determining whether the first information contains defect features defined in the second information (e.g., casing damage, severe corrosion, abnormal deformation). The specific configuration and operation of step S440 will be described in detail through FIG. 5, which will be described later.

[0087] In step S450, the processor (210) may classify the target battery (B) as a target for dismantling operations in response to a determination that the target battery (B) has a first type of defect.

[0088] In the case of conventional technology, since a significant amount of time was spent on electrical performance testing during battery condition diagnosis, there was a problem in that even if there was serious external damage, it could not be classified early, resulting in unnecessary diagnostic time and costs. In one embodiment of the present disclosure, the type of target battery (B) can be identified through vision scanning using a scanner (120) and comparative analysis based on an image database, and the presence or absence of a first type of external defect can be quickly determined. Accordingly, batteries with external defects can be quickly screened out at the beginning of the diagnostic process, thereby improving the processing speed and reducing the load on subsequent diagnostic steps.

[0089] FIG. 5 is a flowchart illustrating in detail a method for determining whether a target battery (B) has a first type of defect according to one embodiment of the present disclosure.

[0090] In step S510, the processor (210) may determine a target image that includes at least a partially corresponding area to the area of ​​the battery captured in the second image of the second information among one or more first images of the first information. In one embodiment, the processor (210) may align the first image of the first information and the second image of the second information with each other, extract a specific area (ROI, Region of Interest) necessary for analysis, and determine whether there is damage in the specific area of ​​the battery. For example, if the second image is a standard image of the front terminal connection area of ​​the battery pack, the processor (210) may determine a specific area corresponding to the terminal connection area of ​​the second image using an image alignment algorithm, a feature point matching technique, etc., and set an image containing the specific area among one or more first images as the target image.

[0091] In step S520, the processor (210) can determine whether the target battery (B) has a first type of defect based on the target image and the second image. In one embodiment, the processor (210) can perform an analysis of the pixel value difference between the target image and the second image to determine whether there is a pixel value difference of a certain level or more between the two images. In one embodiment, the processor (210) can compare the target image and the second image and determine that there is a first type of defect if an abnormal area (e.g., crack pattern, severe contamination, missing parts, etc.) that is not present in the second image is detected in the target image.

[0092] Conventionally, it was difficult to accurately identify and locate various specification variations or positional errors of non-standardized battery components, resulting in problems where minor damage was not recognized as a defect or was misidentified. In one embodiment of the present disclosure, by comparing one or more first images of a target battery (B) in detail with a second image which is a standard image, it is possible to determine whether there is a localized damaged area. Accordingly, the accuracy of damage identification in battery appearance diagnosis can be improved, and the reliability of the primary classification can be enhanced.

[0093] FIG. 6 is a flowchart showing the specific operation of a secondary classification step (S320) in a method for classifying a target battery (B) according to one embodiment of the present disclosure.

[0094] In step S610, the processor (210) may obtain a first signal generated by measuring a target voltage, which is the voltage between the positive and negative electrodes of each of one or more cells of the target battery (B), from the voltage measuring device (140). In one embodiment, the target battery (B) pack may include one or more cells. For example, one or more cells may be connected in series and / or parallel. In one embodiment, the target voltage may be the open circuit voltage (OCV) between the positive and negative electrodes of each cell. For example, the voltage measuring device (140) may be configured to individually measure the open circuit voltage of each cell inside the battery.

[0095] In step S620, the processor (210) can obtain a second signal generated by measuring a target temperature, which is the temperature of the target battery (B), from the temperature sensor (130). In one embodiment, the temperature sensor (130) may include at least one of a non-contact temperature sensor or a thermal imaging camera.

[0096] In step S630, the processor (210) may determine whether to classify the target battery (B) as a target for dismantling operations based on at least one of the first signal or the second signal, and based on at least one of whether the target deviation, which is a deviation of the target voltage between one or more cells, is greater than or equal to a predetermined reference deviation or whether the target temperature is greater than or equal to a predetermined reference temperature.

[0097] In one embodiment, the processor (210) may determine a target deviation, which is a deviation of the target voltage between one or more cells, based on the target voltage of each of one or more cells based on a first signal. For example, the target deviation may be determined as the difference between the smallest target voltage and the largest target voltage among the target voltages of one or more cells. In one embodiment, the processor (210) may determine whether the target deviation is greater than or equal to a reference deviation, and in response to the determination that the target deviation is greater than or equal to a reference deviation, the target battery (B) may be classified as a target for dismantling operations. In one embodiment, the reference deviation may be determined based on the size of the maximum charge capacity of the target battery (B). The processor (210) may set the reference deviation by obtaining information indicating the maximum charge capacity of the target type, which is the type of the target battery (B). For example, if the target battery (B) is a high-capacity battery with a maximum charge capacity greater than a certain capacity, the reference deviation may be set to 1.0 V, and if it is a low-capacity battery with a maximum charge capacity less than or equal to a certain capacity, the reference deviation may be set to 0.5 V.

[0098] As the OCV deviation between cells of a battery pack increases, specific cells may be overloaded during charging and discharging, accelerating further degradation and increasing safety risks. In one embodiment of the present disclosure, the target deviation is determined by measuring the target voltage (OCV) of one or more cells, and batteries that have no value for reuse or have inherent safety issues can be selected for dismantling.

[0099] In one embodiment, the processor (210) may determine, based on a second signal, whether the target temperature of the target battery (B) is above a predetermined reference temperature, and in response to the determination that the target temperature is above the reference temperature, may classify the target battery (B) as a target for dismantling operations. In one embodiment of the present disclosure, a temperature criterion in addition to a voltage criterion may be applied to select batteries with a high safety risk.

[0100] FIG. 7 is a flowchart showing the specific operation of a third classification step (S330) in a method for classifying a target battery (B) according to one embodiment of the present disclosure.

[0101] In step S710, the processor (210) can obtain third information indicating the DC internal resistance of the target battery (B) in response to a determination that the target deviation is not greater than the reference deviation and the target temperature is not greater than the reference temperature.

[0102] In one embodiment, the system may further include a DC internal resistance measuring device, and information indicating the DC internal resistance may be information generated by applying a DC current to the target battery (B) for a short period of time and measuring the voltage change. For example, the DC internal resistance may refer to the sum of the ohmic resistance and / or polarization resistance inside the target battery (B) and may be used as an indicator indicating the degree of performance degradation of the battery. For example, the DC internal resistance measuring device may generate third information by applying a standardized pulse current to the target battery (B) and measuring the resulting voltage drop to determine the DC internal resistance of the target battery (B), and the processor (210) may obtain the third information from the DC internal resistance measuring device.

[0103] In step S720, the processor (210) may generate EIS information based on a signal output from the target battery (B) in response to applying an alternating voltage of one or more frequencies to the target battery (B). For example, EIS may be a technique for analyzing dynamic characteristics such as electrochemical reactions, charge transfer, and material diffusion occurring at the battery electrode and electrolyte interface in the frequency domain. In one embodiment, the EIS information may include information indicating at least one of the Ohmic Resistance, Solid Electrolyte Interphase Resistance, or Warburg Impedance due to lithium ion diffusion of the target battery (B).

[0104] In one embodiment, the system may further include an EIS measuring device (e.g., an impedance spectrometer), and the EIS measuring device may apply an alternating current signal having a frequency of a certain band (e.g., 10 mHz to 10 kHz) to a target battery (B), measure voltage and current response signals output from the target battery (B) to determine a complex impedance value, generate a Nyquist plot that organizes the complex impedance value (Z*) by frequency, and generate EIS information using the Nyquist plot.

[0105] For example, the Nyquist plot may be a graph representing impedance information by frequency with the real part of the complex impedance (Z*) on the x-axis and the imaginary part on the y-axis. The processor (210) can determine a frequency band for extracting each of the various electrochemical resistance components inside the battery from the Nyquist plot, and determine the corresponding resistance component based on the graph of the Nyquist plot in the corresponding frequency band.

[0106] In one embodiment, the electrolyte resistance may be determined based on the graph of the first frequency band (e.g., 100 Hz to 10 kHz), which is the highest frequency band in the Nyquist plot. For example, the processor (210) may determine the value of the real part of the first point where the graph of the Nyquist plot in the first frequency band intersects the x-axis. For example, the electrolyte resistance may refer to the ohmic resistance of battery components such as the electrolyte, current collector, and separator of the target battery (B).

[0107] In one embodiment, the solid electrolyte interface resistance may be determined based on a graph of a second frequency band (e.g., 1 Hz to 100 Hz) with a frequency lower than that of a first frequency band, as a high frequency band of the Nyquist plot. For example, the processor (210) may determine the diameter of a semicircle of the Nyquist plot graph in the second frequency band as the value of the solid electrolyte interface resistance. For example, the solid electrolyte interface resistance may refer to the lithium ion movement resistance or charge movement resistance passing through the solid electrolyte interface layer formed on the electrode surface of the target battery (B).

[0108] In one embodiment, the Warburg impedance may be determined based on a graph of a third frequency band (e.g., 10 mHz to 10 Hz or less) with a frequency lower than that of the second frequency band, in the low-frequency region of the Nyquist plot. For example, the processor (210) may determine the Warburg impedance based on the real and imaginary parts of a graph that increases linearly with a constant slope of the Nyquist plot in the third frequency band. For example, the Warburg impedance may refer to the impedance generated by the diffusion phenomenon in which lithium ions are inserted into or exit the electrode active material.

[0109] In step S730, the processor (210) can determine the SOH of the target battery (B) based on at least one of information indicating the DC internal resistance of the input battery and EIS information. For example, SOH may mean the ratio of the current maximum charge capacity to the initial maximum charge capacity when the battery was manufactured.

[0110] In one embodiment, the processor (210) can predict the SOH of a target battery (B) by using a second artificial intelligence model trained to output information indicating a predicted value of the SOH of the battery as input information regarding the DC internal resistance of the battery or EIS information. For example, the second artificial intelligence model may be a machine learning or deep learning model. In one embodiment, the second artificial intelligence model may be trained to predict the SOH of the battery as input information indicating the DC internal resistance of the battery. In one embodiment, the second artificial intelligence model may be trained to predict the SOH of the battery as input EIS information of the battery. For example, the processor (210) may determine the predicted value of the SOH of the target battery (B) indicated in the information output by the second artificial intelligence model as the SOH of the target battery (B).

[0111] In the embodiment of the present disclosure, the DC internal resistance or EIS information of the target battery (B) that can be measured within a short time is input into a pre-established artificial intelligence model to predict the SOH of the target battery (B), so the SOH of the target battery (B) can be predicted quickly.

[0112] In step S740, the processor (210) can determine whether the SOH of the target battery (B) is below a predetermined standard. In one embodiment, the predetermined standard is a value representing the minimum performance standard for which the battery is reusable, and may be determined, for example, to be 80%. For example, if the SOH of the target battery (B) is 80% or higher, the target battery (B) is determined to be suitable for reuse and may be classified as a reusable battery. For example, if the SOH of the target battery (B) is less than 80%, the target battery (B) is determined not to be suitable for reuse and may be classified as a target for dismantling.

[0113] FIG. 8 is a flowchart illustrating a method for performing a dismantling operation on a target battery (B) according to one embodiment of the present disclosure. In one embodiment, in response to the target battery (B) being classified as a target for a dismantling operation, an electronic device (110) may perform the following steps.

[0114] In step S810, the processor (210) can determine whether the target battery (B) is a target for dismantling operations. For example, depending on whether the target battery (B) is classified as a 'target for dismantling operations' in any of the preceding first, second, or third classifications, the processor (210) can determine the target battery (B) as a target for dismantling operations.

[0115] In step S820, the processor (210) may determine, in response to classifying the target battery (B) as a target for dismantling operations, one or more automation devices to perform the dismantling operations on the target battery (B). For example, one or more automation devices may be various types of automated dismantling robots or automated dismantling stations.

[0116] In one embodiment, the processor (210) may determine, depending on the target type of the target battery (B), an automation device equipped with a tool optimized for dismantling one or more automation devices of the corresponding type (e.g., the corresponding model) as the target automation device.

[0117] In one embodiment, the processor (210) may determine the automation dismantling device with the lowest current workload as the target automation device based on information regarding the workload of one or more automation devices.

[0118] In step S830, the processor (210) may transmit first information to a target automation device. In one embodiment, the first information may include one or more first images obtained by scanning a target battery (B).

[0119] In one embodiment, the processor (210) may obtain information regarding the dismantling order of the target battery (B) and / or the movement path of the robot arm from a database and further transmit it to the target automation device. The target automation device may use this information to generate the optimal dismantling order and the movement path of the robot arm for the target battery (B) in real time and perform a dismantling operation for the target battery (B).

[0120] In step S840, the processor (210) may generate a signal to move the target battery (B) to the workbench of the target automation device. In one embodiment, this signal may include information such as the transfer path and destination of the target battery (B).

[0121] In one embodiment, this signal may be a signal for controlling an unmanned forklift as an unmanned transport robot. For example, the processor (210) may generate a signal for controlling an unmanned forklift to move to a workbench of a target automation device for a target battery (B) for which dismantling work has been determined, and transmit the signal to the unmanned forklift.

[0122] In step S850, the processor (210) may decide to move the target battery (B) to a storage area in response to the fact that the target battery (B) was not classified as a target for dismantling work in step S810 (that the target battery (B) was classified as a reusable battery). In one embodiment, for example, the storage area may be an area for storing reusable batteries. For example, the target battery (B) that has passed all classification procedures and whose SOH is determined to be above a standard is classified as a resource for reuse, thereby preventing unnecessary transfer to the battery dismantling process and deciding to transfer it to a storage area.

[0123] In step S860, the processor (210) may generate a signal to move the target battery (B) to a storage area. In one embodiment, this signal may include information such as the transfer path and destination of the target battery (B).

[0124] In one embodiment, this signal may be a signal for controlling an unmanned transport robot, similar to step S840. For example, the processor (210) may generate a signal to control an unmanned forklift to move a target battery (B) classified as a reusable battery to a pre-designated storage area and transmit it to the unmanned forklift.

[0125] In one embodiment of the present disclosure, a subsequent automated device or storage area to which the target battery (B) is to be moved is determined based on the classification result of the target battery (B), a signal to control an unmanned transport robot is generated, and optimized information (such as dismantling order) required for the dismantling operation is transmitted to the automated device. Accordingly, the automation and efficiency of the battery processing process can be improved.

[0126] FIG. 9 is a schematic diagram illustrating one example in which a system (100) for managing batteries according to one embodiment of the present disclosure is implemented. In one embodiment, the system (100) may be configured to process the classification, transfer, and dismantling / storage of target batteries (B) in an integrated and automated manner.

[0127] In one embodiment, the system (100) may include a workbench (910) for performing diagnosis and classification of a target battery (B). In one embodiment, various devices such as a scanner (120), a temperature sensor (130), and a voltage measuring device (140) may be installed on the workbench (910). In one embodiment, various devices such as the scanner (120), the temperature sensor (130), and the voltage measuring device (140) of the system (100) may not be installed directly on the workbench (910) but may be placed around the workbench (910). Additionally, unlike what is illustrated, the workbench (910) may be implemented as one or more workbench, and the scanner (120), the temperature sensor (130), and the voltage measuring device (140) may each be placed on different workbench. When the target battery (B) is placed on the workbench (910), a series of operations can be performed under the control of the electronic device (110), in which a scanner (120) photographs the target battery (B), a temperature sensor (130) measures the temperature, and a voltage measuring device (140) measures the voltage of each of one or more cells of the target battery (B).

[0128] An unmanned transport robot (920) may be configured to transport a target battery (B). In one embodiment, the unmanned transport robot (920) may move a target battery (B) that has been diagnosed at a workbench (910) to one or more dismantling workbenches (941, 942, 943) or a storage area (950) according to a control signal of an electronic device (110). Among the one or more dismantling workbenches (941, 942, 943), the first dismantling workbench (941) may be a workbench for performing dismantling work in a first automation device (931), the second dismantling workbench (942) may be a workbench for performing dismantling work in a second automation device (932), and the third dismantling workbench (943) may be a workbench for performing dismantling work in a third automation device (933). For example, the unmanned transport robot (920) can move a target battery (B) classified as a target for dismantling work to one or more dismantling workbenches (941, 942, 943) based on a signal obtained from an electronic device (110), or transfer a target battery (B) classified as a reusable battery to a storage area (950).

[0129] Each of one or more automation devices (931, 932, 933) may be configured to perform the dismantling operation of the target battery (B). For example, each automation device may dismantle the battery using a robot arm and various tools mounted on the robot arm (e.g., bolt driver, laser cutter, pliers, saw, etc.). Laser cutting tools, bolting processing tools, cable cutting tools, cover handling tools, scrap handling tools, cable handling tools, etc. are provided around the automation device, and the automation device may replace the tools attached to the robot arm as needed. The automation device may be configured to transport components separated from the battery to another location. The automation device may transfer parts dismantled from the battery (upper cover, lower cover, wiring, connector, BMS (Battery Management System) module, battery module, battery cell, bolt, nut, etc.) to a storage box (e.g., upper cover storage box, lower cover storage box, cell box, dismantling box, etc.).

[0130] In one embodiment, among one or more automation devices (931, 932, 933), the first automation device (931) may be equipped with a robot arm, the second automation device (932) may be equipped with a robot arm and other dismantling tools, and the third automation device (933) may be specialized for dismantling a specific type of battery. For example, the electronic device (110) may determine an automation device capable of performing an optimal dismantling process based on the type of target battery (B) as the target automation device, and may control an unmanned transport robot (920) to transport the target battery (B) to a dismantling workbench where the device performs the dismantling work.

[0131] The storage area (950) may be configured to store reusable batteries according to the final classification result of the target battery (B).

[0132] In one embodiment of the present disclosure, a workbench (910), an unmanned transport robot (920), one or more automation devices (931, 932, 933), and a storage area (950) in a system (100) can be linked under the integrated control of an electronic device (110). Accordingly, the level of automation of the entire battery management process, from diagnosis to transport, dismantling, and storage, can be improved.

[0133] FIG. 10 is a flowchart for explaining a method for determining whether to dispose of a target battery (B) without performing dismantling work when a first type of defect is found in the first classification step (S310) of a target battery (B) according to one embodiment of the present disclosure, because the degree of the defect is severe.

[0134] In step S1010, the processor (210) may determine whether the defect state of the target battery (B) corresponds to a predetermined reference state in response to a determination that the target battery (B) has a first type of defect. The reference state may refer to a condition in which the defect is severe enough to require disposal before dismantling, such as extensive damage to the battery casing, exposure of internal cells, traces of severe leakage, or signs of fire / explosion (e.g., thermal discoloration, severe swelling). For example, the processor (210) may determine whether the defect state of the target battery (B) corresponds to a reference state based on first information regarding one or more first images of the target battery (B).

[0135] In step S1020, the processor (210) may decide to dispose of the target battery (B) based on the determination that the defective state is a reference state. In one embodiment, the processor (210) may generate a signal to transfer the target battery (B) to a separate waste disposal procedure instead of introducing it into a recycling process (dismantling operation). For example, the processor (210) may generate a signal to transfer the battery to an isolation and disposal zone dedicated to severely defective batteries and transmit it to an unmanned transport robot (920).

[0136] In one embodiment of the present disclosure, if a battery has a severe defect and there is a high probability that a fire may occur during dismantling, the safety risk to subsequent processes can be reduced by excluding it before it is introduced into the dismantling process.

[0137] In the flowcharts of the present disclosure, the operations of the method or algorithm are described in a sequential order, but may be performed in any combination other than sequentially. The description of the flowcharts of the present disclosure does not exclude changes or modifications to the method or algorithm and does not imply that any operation is essential or desirable. In one embodiment, at least some operations may be performed in parallel, iteratively, or heuristically. In another embodiment, at least some operations may be omitted or other operations may be added.

[0138] Various embodiments of the present disclosure may be implemented as software on a machine-readable storage medium (MRSM). The software may be software for implementing various embodiments of the present disclosure. The software may be inferred from the various embodiments of the present disclosure by programmers in the art to which the present disclosure belongs. For example, the software may be a computer program containing instructions that can be read by a computing device. A computing device is a device capable of operating according to instructions called from a storage medium, and may be referred to interchangeably with, for example, an electronic device (110). In one embodiment, a processor of the computing device may execute the called instructions to cause the components of the computing device to perform functions corresponding to these instructions. A storage medium may refer to any type of recording medium in which information is stored that can be read by a device. A storage medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical information storage device. In one embodiment, the storage medium may be implemented in a distributed form in a computer system connected by a network, etc. In this case, the software may be stored and executed in a distributed manner in a computer system, etc. In another embodiment, the storage medium may be a non-transitory storage medium. A non-transitory storage medium refers to a medium that exists regardless of whether information is stored semi-permanently or temporarily, and does not include signals that are transmitted transitorily.

[0139] Although the technical concept according to the present disclosure has been described by various embodiments above, the technical concept according to the present disclosure includes various substitutions, modifications, and changes that can be made within the scope of understanding of a person skilled in the art to which the present disclosure pertains. Furthermore, it should be understood that such substitutions, modifications, and changes may be included within the scope of the appended claims.

Claims

Claim 1 A method for classifying batteries performed by an electronic device comprises: a step of obtaining first information regarding one or more first images generated by scanning a target battery to be classified from a scanner; a step of determining the type of the target battery as a target type among one or more types based on the one or more first images; a step of obtaining second information regarding a second image of a battery corresponding to the target type from a database storing information regarding the one or more types of the battery; and a step of determining whether the target battery has a first type of defect based on the first information and the second information. A method comprising: a step of classifying the target battery as a target for dismantling work in response to a determination that the target battery has a first type of defect; a step of obtaining third information indicating the Direct Current Internal Resistance of the target battery in response to a determination that the target battery does not have a first type of defect; a step of determining the State of Health (SOH) of the target battery based on information output by inputting the third information into the second artificial intelligence model, using a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from information indicating the input Direct Current Internal Resistance of the battery; a step of determining whether the SOH of the target battery is below a predetermined standard; and a step of classifying the target battery as a target for dismantling work in response to a determination that the SOH of the target battery is below a predetermined standard. Claim 2 In claim 1, the method wherein one or more types are types associated with one or more manufacturers of batteries. Claim 3 A method according to claim 1, wherein information regarding one or more types includes information regarding one or more images of a battery corresponding to each of the one or more types. Claim 4 A method according to claim 1, wherein the step of determining the type of the target battery as the target type among the one or more types comprises the step of determining the type of the target battery as the target type among the one or more types based on information output by inputting at least one of the one or more first images of the first information into the first artificial intelligence model, using a first artificial intelligence model trained to output information indicating the type to which the battery belongs from an input battery image. Claim 5 In claim 1, the method wherein the first type of defect is a defect that is visible on the exterior of the battery. Claim 6 A method according to claim 1, wherein the step of determining whether there is a first type of defect comprises: determining a target image that includes at least a partially corresponding area to the area of ​​the battery captured in the second image in the second information among the one or more first images in the first information; and determining whether there is a first type of defect in the target battery based on the target image and the second image. Claim 7 A method according to claim 1, further comprising: a step of obtaining a first signal generated by measuring a target voltage, which is the voltage between the positive and negative electrodes of each of one or more cells of the target battery, from a voltage measuring device in response to a determination that the target battery is free of a first type of defect; a step of obtaining a second signal generated by measuring a target temperature, which is the temperature of the target battery, from a temperature sensor; and a step of determining whether to classify the target battery as a target for dismantling operations based on at least one of the first signal or the second signal, based on at least one of whether the target deviation, which is the deviation of the target voltage between the one or more cells, is greater than or equal to a predetermined reference deviation or whether the target temperature is greater than or equal to a predetermined reference temperature. Claim 8 In claim 7, the step of determining whether to classify the target battery as a target for the dismantling operation comprises the step of classifying the target battery as a target for the dismantling operation in response to a determination that the target deviation is greater than or equal to the reference deviation. Claim 9 In paragraph 8, the method wherein the above-mentioned standard deviation is determined based on the size of the maximum charge capacity of the target battery. Claim 10 In claim 7, the step of determining whether to classify the target battery as a target for the dismantling operation further comprises the step of classifying the target battery as a target for the dismantling operation in response to a determination that the target temperature is above the reference temperature. Claim 11 In claim 7, the step of determining whether to classify the target battery as a target for the dismantling operation further comprises: a step of generating Electrochemical Impedance Spectroscopy (EIS) information based on a signal output from the target battery in response to applying one or more alternating current voltages of frequency to the target battery in response to a determination that the target deviation is not greater than or equal to the reference deviation and the target temperature is not greater than or equal to the reference temperature; a step of determining the State of Health (SOH) of the target battery based on information output by inputting the EIS information into the second artificial intelligence model, using the second artificial intelligence model further trained to output information indicating the State of Health (SOH) of the battery from the input EIS information; a step of determining whether the SOH of the target battery is less than or equal to a predetermined reference; and a step of classifying the target battery as a target for the dismantling operation in response to a determination that the SOH of the target battery is less than or equal to a predetermined reference. Claim 12 A method according to claim 11, wherein the EIS information comprises information indicating at least one of the electrolyte resistance, solid electrolyte interphase resistance, or Warburg impedance due to lithium ion diffusion of the target battery. Claim 13 A method according to claim 11, further comprising the step of classifying the target battery as a reusable battery in response to a determination that the SOH of the target battery is not below a predetermined reference value. Claim 14 A method according to claim 1, further comprising the step of determining, among one or more automation devices, a target automation device to perform the dismantling operation of the target battery in response to classifying the target battery as a target for the dismantling operation. Claim 15 In claim 14, the step of determining the target automation device comprises the step of determining the automation device among the one or more automation devices that performs dismantling work on the battery of the target type as the target automation device. Claim 16 A method according to claim 14, further comprising the step of transmitting the first information of the target battery to the target automation device. Claim 17 In an electronic device for classifying batteries, one or more processors; and includes one or more memories storing instructions to be executed by the one or more processors, and when the instructions are executed, the one or more processors acquire first information regarding one or more first images generated by scanning a target battery to be classified from a scanner, and based on the one or more first images, determine the type of the target battery as a target type among one or more types, acquire second information regarding a second image of a battery corresponding to the target type from at least one of the one or more memories storing information regarding the one or more types of the battery, and based on the first information and the second information, determine whether the target battery has a first type of defect, and in response to the determination that the target battery has a first type of defect, classify the target battery as a target for dismantling work, and in response to the determination that the target battery does not have a first type of defect, acquire third information indicating the Direct Current Internal Resistance of the target battery, and using a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from the input information indicating the Direct Current Internal Resistance of the battery, the second An electronic device configured to determine the SOH of the target battery based on information output by inputting the third information into an artificial intelligence model, determine whether the SOH of the target battery is below a predetermined standard, and classify the target battery as a target for dismantling operations in response to the determination that the SOH of the target battery is below the predetermined standard. Claim 18 An electronic device according to claim 17, wherein the one or more processors are configured to determine the type of the target battery as the target type among the one or more types by using a first artificial intelligence model trained to output information indicating the type to which the battery belongs from an input image of the battery, and by inputting at least one of the one or more first images of the first information into the first artificial intelligence model and determining the type of the target battery as the target type among the one or more types based on the output information. Claim 19 An electronic device according to claim 17, wherein the one or more processors are configured to determine, in determining whether there is a first type of defect, a target image comprising an area of ​​the battery captured in the second image in the second information among the one or more first images in the first information that corresponds at least partially to the area of ​​the battery captured in the second image in the second information, and to determine whether there is a first type of defect in the target battery based on the target image and the second image. Claim 20 In a system for classifying batteries, a scanner; The electronic device comprises one or more processors and one or more memories storing instructions to be executed by the one or more processors, wherein the one or more processors acquire first information regarding one or more first images generated by scanning a target battery to be classified from the scanner, and based on the one or more first images, determine the type of the target battery as a target type among one or more types, acquire second information regarding a second image of a battery corresponding to the target type from at least one of the one or more memories storing information regarding the one or more types of the battery, determine whether the target battery has a first type of defect based on the first information and the second information, classify the target battery as a target for dismantling work in response to the determination that the target battery has a first type of defect, acquire third information indicating the Direct Current Internal Resistance of the target battery in response to the determination that the target battery does not have a first type of defect, and use a second artificial intelligence model trained to output information indicating the State of Health (SOH) of the battery from the input information indicating the Direct Current Internal Resistance of the battery, thereby the second A system configured to determine the SOH of the target battery based on information output by inputting the third information into an artificial intelligence model, determine whether the SOH of the target battery is below a predetermined standard, and classify the target battery as a target for dismantling operations in response to the determination that the SOH of the target battery is below the predetermined standard.

Images