EIS measurement-based ai diagnostic system and operation method thereof

Abstract

The present invention relates to an EIS measurement-based AI diagnostic system and an operation method thereof, the system comprising: a battery jig unit which is coupled to at least one battery; an EIS measurement unit which is connected to one or more electrodes of the battery jig unit by a physical cable, receives a signal returned by at least some of the one or more electrodes, and measures and collects EIS data from the at least one battery; and a connection terminal unit which is disposed between the EIS measurement unit and the battery jig unit, includes a plurality of terminals coupled to the physical cable, and provides a signal transmission path between the plurality of terminals.

Description

AI diagnosis system based on EIS measurement and its operation method

[0001] The present invention relates to a battery diagnosis technology based on EIS measurement, and more particularly, to an EIS measurement-based AI diagnosis system and its operating method that places a connection terminal block connecting a physical cable between an EIS meter of a battery and a jig device and detects and diagnoses changes in an EIS plot due to a change in a cable connected to the connection terminal.

[0002] Electrochemical Impedance Spectroscopy (EIS) analyzes resistance characteristics according to frequency by applying AC electrical signals of various frequencies and measuring the response. Because EIS is sensitive to battery characteristics, it can provide crucial information necessary for battery diagnosis. However, due to its sensitivity, EIS data can easily fluctuate depending on the manufacturer and measurement environment (e.g., temperature). Therefore, for more precise and robust battery diagnosis, it is necessary to correct battery data in real time and distinguish whether observed abnormalities are due to consistent battery condition changes or mechanical or electrochemical defects.

[0003] Additionally, a jig may be a device used to establish an electrical connection between a battery and an external device or another adjacent battery. If a significant gap exists between the battery's EIS meter and the jig device when the vehicle battery is delivered, a physical cable connection can be made via the connection terminal. However, changes to the cable connected to the connection terminal may cause changes in the battery's EIS data, which could lead to fatal errors in battery diagnosis.

[0004] One embodiment of the present invention is to provide an EIS measurement-based AI diagnostic system and an operating method thereof, which places a connection terminal block connecting a physical cable between an EIS meter of a battery and a jig device, and detects and diagnoses a change in an EIS plot due to a change in a cable connected to the connection terminal.

[0005] Among the embodiments, the EIS measurement-based AI diagnostic device includes a battery jig unit coupled to at least one battery; an EIS measurement unit connected to one or more electrodes of the battery jig unit by a physical cable and receiving a signal returned by at least a portion of the one or more electrodes, and measuring and collecting EIS data from the at least one battery; and a connection terminal unit disposed between the EIS measurement unit and the battery jig unit and including a plurality of terminals coupled to the physical cable, the connection terminal unit providing a signal transmission path between the plurality of terminals.

[0006] The above EIS measurement unit can collect a force return signal returned by the battery jig unit through a pair of force electrodes.

[0007] The above EIS measurement unit can analyze the force return signal to detect changes in the EIS plot due to changes in the physical cable.

[0008] The EIS measurement unit can calculate the impedance of the at least one battery by using signal values ​​of the force return signal collected at different points in time at regular intervals.

[0009] The above EIS measurement unit can predict changes in the characteristics of the physical cable according to the change pattern of the impedance.

[0010] The above connection terminal portion may include a plurality of BNC terminals for connection with the physical cable.

[0011] The above-mentioned connection terminal portion may include a PCB substrate on which the plurality of BNC terminals are fixedly arranged symmetrically side by side.

[0012] Among the embodiments, the AI ​​diagnosis method based on EIS measurement is performed in an AI diagnosis device based on EIS measurement, which includes a battery jig unit coupled to a battery, an EIS measurement unit connected to the battery jig unit by a physical cable, and a connection terminal unit disposed between the EIS measurement unit and the battery jig unit, the AI ​​diagnosis method including the steps of: transmitting a signal for EIS data measurement through a first force electrode of the EIS measurement unit; receiving a signal returned by the battery jig unit through a second force electrode of the EIS measurement unit; and analyzing signal values ​​of a signal received from the second force electrode through the EIS measurement unit to predict a change in characteristics of the physical cable according to a change pattern of impedance with respect to the battery.

[0013] The disclosed technology may have the following effects. However, this does not mean that a particular embodiment must include all or only the following effects, and thus the scope of the disclosed technology should not be construed as being limited thereby.

[0014] An AI diagnosis system based on EIS measurement according to one embodiment of the present invention and an operation method thereof can detect and diagnose changes in an EIS plot due to a change in a cable connected to a connection terminal block by a physical cable between an EIS meter of a battery and a jig device, and a change in a cable connected to the connection terminal block.

[0015] Figure 1 is a drawing illustrating an AI diagnostic system according to the present invention.

[0016] Fig. 2 is a drawing explaining the system configuration of the AI ​​diagnostic device of Fig. 1.

[0017] Fig. 3 is a drawing explaining the functional configuration of the AI ​​diagnostic device of Fig. 1.

[0018] Figure 4 is a flowchart illustrating an AI diagnosis method based on EIS measurement according to the present invention.

[0019] FIG. 5 is a drawing illustrating one embodiment of an AI diagnostic device according to the present invention.

[0020] Figure 6 is a drawing illustrating one embodiment of a connection terminal block according to the present invention.

[0021] Figure 7 is a drawing explaining an artificial intelligence-based battery diagnosis process according to the present invention.

[0022] The description of the present invention is merely an example for structural and functional explanation, and therefore, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiments can be modified in various ways and can take various forms, the scope of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the purposes or effects presented in the present invention do not mean that a specific embodiment must include all of them or only such effects, and therefore, the scope of the present invention should not be construed as being limited thereby.

[0023] Meanwhile, the meaning of the terms described in this application should be understood as follows.

[0024] Terms such as "first" and "second" are intended to distinguish one component from another, and the scope of the rights should not be limited by these terms. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

[0025] When a component is said to be "connected" to another component, it should be understood that while it may be directly connected to that other component, there may also be other components intervening. Conversely, when a component is said to be "directly connected" to another component, it should be understood that there are no other intervening components. Similarly, other expressions describing relationships between components, such as "between" and "directly between," or "adjacent to" and "directly adjacent to," should be interpreted similarly.

[0026] Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "comprises" or "have" should be understood to specify the presence of a feature, number, step, operation, component, part or combination thereof, but not to exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0027] For each step, the identifiers (e.g., a, b, c, etc.) are used for convenience of explanation and do not describe the order of the steps. The steps may occur in a different order than stated unless the context clearly dictates a specific order. That is, the steps may occur in the same order as stated, may be performed substantially simultaneously, or may be performed in the opposite order.

[0028] The present invention can be implemented as computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. Furthermore, the computer-readable recording medium can be distributed across network-connected computer systems, so that the computer-readable code can be stored and executed in a distributed manner.

[0029] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted to be consistent with their meaning within the context of the relevant technology, and should not be interpreted as having an idealized or overly formal meaning unless explicitly defined herein.

[0030] Figure 1 is a drawing illustrating an AI diagnostic system according to the present invention.

[0031] Referring to FIG. 1, the AI ​​diagnostic system (100) may include a user terminal (110), an AI diagnostic device (130), and a database (150).

[0032] A user terminal (110) may correspond to a terminal device operated by a user. In the embodiment of the present invention, a user may be understood as one or more users, and each of the one or more users may correspond to one or more user terminals (110). That is, although FIG. 1 shows one user terminal (110), a first user may correspond to a first user terminal, a second user may correspond to a second user terminal, ..., an n-th user (where n is a natural number) may correspond to an n-th user terminal.

[0033] In addition, the user terminal (110) can be implemented as one device constituting the AI ​​diagnosis system (100) according to the present invention, and the AI ​​diagnosis system (100) can be implemented in various forms depending on the purpose of AI diagnosis based on EIS measurement.

[0034] In addition, the user terminal (110) may be implemented as a smartphone, laptop, or computer that is connected to and operable with the AI ​​diagnostic device (130), but is not necessarily limited thereto and may also be implemented as various devices including tablet PCs. Meanwhile, the user terminal (110) may be connected to the AI ​​diagnostic device (130) through a network, and multiple user terminals (110) may be connected to the AI ​​diagnostic device (130) simultaneously.

[0035] The AI ​​diagnostic device (130) may be implemented as a server corresponding to a computer or program that performs the AI ​​diagnostic method based on EIS measurement according to the present invention. Furthermore, the AI ​​diagnostic device (130) may be connected to a user terminal (110) via a wired network or a wireless network such as Bluetooth, WiFi, or LTE, and may transmit and receive data with the user terminal (110) via the network.

[0036] Additionally, the AI ​​diagnostic device (130) may be implemented to operate in connection with an independent external system (not shown in FIG. 1). For example, the AI ​​diagnostic device (130) may operate in conjunction with a cloud server providing a cloud environment or an artificial intelligence system performing artificial intelligence learning.

[0037] The database (150) may correspond to a storage device that stores various information required during the operation of the AI ​​diagnostic device (130). For example, the database (150) may store EIS data collected from a battery or information regarding learning and diagnostic algorithms, but is not necessarily limited thereto, and may store information collected or processed in various forms during the process of the AI ​​diagnostic device (130) performing the EIS measurement-based AI diagnostic method according to the present invention.

[0038] In addition, in FIG. 1, the database (150) is depicted as a device independent of the AI ​​diagnostic device (130), but it is not necessarily limited thereto, and it can be implemented as a logical storage device included in the AI ​​diagnostic device (130).

[0039] Fig. 2 is a drawing explaining the system configuration of the AI ​​diagnostic device of Fig. 1.

[0040] Referring to FIG. 2, the AI ​​diagnostic device (130) may include a processor (210), a memory (230), a user input / output unit (250), and a network input / output unit (270).

[0041] The processor (210) can execute a procedure for performing an AI diagnosis method based on EIS measurement according to the present invention, manage a memory (230) that is read or written in this process, and schedule a synchronization time between a volatile memory and a non-volatile memory in the memory (230). The processor (210) can control the overall operation of the AI ​​diagnosis device (130), and is electrically connected to the memory (230), the user input / output unit (250), and the network input / output unit (270) to control data flow therebetween. The processor (210) can be implemented as a CPU (Central Processing Unit) of the AI ​​diagnosis device (130), but is not necessarily limited thereto.

[0042] The memory (230) may include an auxiliary memory device implemented as a non-volatile memory such as an SSD (Solid State Disk) or an HDD (Hard Disk Drive) and used to store all data required for the AI ​​diagnostic device (130), and may include a main memory device implemented as a volatile memory such as a RAM (Random Access Memory). In addition, the memory (230) may store a set of commands that are executed by an electrically connected processor (210) to execute the EIS measurement-based AI diagnostic method according to the present invention.

[0043] The user input / output unit (250) includes an environment for receiving user input and an environment for outputting specific information to the user, and may include, for example, an input device including an adapter such as a touchpad, a touch screen, a virtual keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In one embodiment, the user input / output unit (250) may correspond to a computing device connected via remote access, and in such a case, the AI ​​diagnostic device (130) may correspond to an independent node of a network to which the computing device is connected.

[0044] The network input / output unit (270) provides a communication environment for connecting to other devices via a network, and may include, for example, an adapter for communication such as a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), and a Value Added Network (VAN). In addition, the network input / output unit (270) may be implemented to provide a short-range communication function such as WiFi or Bluetooth, or a wireless communication function of 4G or higher for wireless transmission of data.

[0045] Fig. 3 is a drawing explaining the functional configuration of the AI ​​diagnostic device of Fig. 1.

[0046] Referring to FIG. 3, the AI ​​diagnostic device (130) can perform an AI diagnostic method based on EIS measurement according to the present invention. To this end, the AI ​​diagnostic device (130) can include an EIS measurement unit (310), a battery jig unit (330), and a connection terminal unit (350). At this time, the embodiment of the present invention does not have to include all of the above-mentioned components at the same time, and some of the above-mentioned components may be omitted or selectively included in some or all of the above-mentioned components depending on each embodiment. Hereinafter, the operation of each component will be described in detail.

[0047] The EIS measurement unit (310) is connected to one or more electrodes of the battery jig unit (330) by a physical cable, receives a signal returned by at least some of the one or more electrodes, and can measure and collect EIS data from at least one battery. The EIS measurement unit (310) can collect battery-related signals for battery diagnosis, and can include one or more electrodes for signal collection. In addition, the EIS measurement unit (310) can operate in conjunction with an EIS measuring device for EIS data collection, and can also collect EIS data directly from the battery jig unit (330).

[0048] In one embodiment, the EIS measurement unit (310) can measure the impedance of the battery in the entire frequency range in conjunction with the battery jig unit (330). Here, the impedance information can be measured from the battery connected to the battery jig unit (330) using a plurality of different sinusoidal signals. In addition, the impedance of the battery can be expressed as (frequency (f), real-axis value (Re), imaginary-axis value (Im)) as an array structure composed of real-axis values ​​and imaginary-axis values ​​according to frequency on a Nyquist diagram. If the battery impedance is measured in a single frequency band, the frequency information can be omitted.

[0049] Specifically, the EIS measurement unit (310) can measure the impedance of the battery by applying a series of frequency-based sine waves to the battery through one or more electrodes connected to the battery jig unit (330) in the entire frequency range. To this end, the EIS measurement unit (310) can operate in conjunction with a signal transmission module that transmits a sine wave signal of a specific frequency through one or more electrodes. In addition, the EIS measurement unit (310) can receive signals related to the voltage and current of the battery from the battery jig unit (330) through one or more electrodes when the sine wave signal is transmitted and applied to the battery through the battery jig unit (330). To this end, the EIS measurement unit (310) can include a voltage measurement module and a current measurement module connected to each electrode. Thereafter, the EIS measurement unit (310) can calculate the impedance of the corresponding battery based on the measured voltage and current.

[0050] In one embodiment, the EIS measurement unit (310) can generate an impedance deviation according to repeated impedance measurements. Since the impedance of a battery is sensitive to disturbances, variations may occur between measurements due to repeated impedance measurements for the same battery. In addition, the EIS measurement unit (310) can generate an impedance deviation according to the cable connection of the connection terminal unit (350). The impedance of a battery may vary between impedance measurements for the same battery not only due to the characteristics of the connection terminal unit but also due to the characteristics of the cables connected to each terminal. Therefore, the impedance deviation may correspond to a difference between impedance measurement values ​​caused by multiple repeated measurements or due to the characteristics of the cables connected to the connection terminal unit.

[0051] In one embodiment, the EIS measurement unit (310) can collect a force return signal returned by the battery jig unit (330) through a pair of force electrodes. For example, the EIS measurement unit (310) can connect a pair of force electrodes having '+' and '-' signs to the battery jig unit (330) and transmit a signal for EIS data measurement through the '+' force electrode. Thereafter, the EIS measurement unit (310) can receive a signal returned by the battery jig unit (330) through the '-' force electrode. At this time, the force return signal can correspond to a current value (cell current) of the battery connected to the battery jig unit (330).

[0052] In addition, the EIS measurement unit (310) can collect a signal for diagnosing a battery connected to a battery jig unit (330) through a pair of sense electrodes. For example, the EIS measurement unit (310) can connect a pair of sense electrodes having '+' and '-' signs to the battery jig unit (330), transmit a signal for EIS data measurement through the '+' sense electrode, and receive a signal measured from the battery through the '-' sense electrode. At this time, the signal received through the sense electrode may correspond to a voltage value (cell voltage) of the battery connected to the battery jig unit (330).

[0053] In one embodiment, the EIS measurement unit (310) can analyze the force return signal to detect a change in the EIS plot due to a change in the physical cable. The EIS meter and the jig device can be connected to each other through a connection terminal, and if the physical cable connected to the connection terminal is changed, a change may also occur in the EIS data measured by the EIS meter. The EIS measurement unit (310) can detect a change in the signal returned via the connection terminal and the cable and detect a change in the EIS data from the change. For example, a change in the EIS data can correspond to a change in an EIS plot expressed in the form of a two-dimensional graph.

[0054] In one embodiment, the EIS measurement unit (310) can calculate the impedance of at least one battery using signal values ​​of force return signals collected at different points in time at regular intervals. For example, the EIS measurement unit (310) can calculate the impedance of the battery by applying a Hamming window algorithm, a Discrete Fourier Transform (DFT), etc., using a plurality of current values ​​and voltage values ​​collected at different points in time at regular intervals, and using a Nyquist plot, etc. In addition, the EIS measurement unit (310) can generate an impedance waveform based on the impedance distribution of the battery measured and collected in the entire frequency domain. At this time, the impedance waveform can be generated on the Nyquist plot, and the shape of the impedance waveform can be determined according to the distribution of impedances at various frequencies.

[0055] In one embodiment, the EIS measurement unit (310) can predict changes in the characteristics of a physical cable based on a change pattern of impedance. To this end, the EIS measurement unit (310) can pre-construct data on changes in the characteristics of a cable corresponding to the change pattern of impedance. That is, when an impedance change pattern is detected, the EIS measurement unit (310) can search for similar change pattern information from a pre-constructed database (150) and then determine a specific change in the cable corresponding to the change pattern information. In addition, the EIS measurement unit (310) can of course apply various methods for predicting changes in the characteristics of a cable based on the impedance change pattern.

[0056] The battery jig unit (330) can be coupled with at least one battery. To this end, the battery jig unit (330) can be implemented by including one or more jigs that are implemented in a structure that can be connected to each battery. The battery jig unit (330) can be electrically connected to the EIS measurement unit (310) and can provide an interface for measuring and diagnosing the battery. That is, the battery jig unit (330) can be connected to the EIS measurement unit (310) through an interface and can operate. In addition, the battery jig unit (330) can be directly connected to a battery cell (Cell) depending on the physical structure of the jig, or can be connected to a battery module (Module) or a battery pack (Pack).

[0057] The connection terminal unit (350) is disposed between the EIS measurement unit (310) and the battery jig unit (330) and includes a plurality of terminals coupled with physical cables, and can provide a signal transmission path between the plurality of terminals. The connection terminal unit (350) can include a connection terminal block that connects cables connected to each of the EIS measurement unit (310) and the battery jig unit (330). The connection terminal block can be implemented in various specifications depending on the type of cable used.

[0058] In one embodiment, the connection terminal portion (350) may include a plurality of BNC terminals for connection to a physical cable. Here, the BNC terminal may correspond to a BNC connector (Bayonet Neill-Concelman) and may correspond to an RF terminal that supports high-speed connection and disconnection of miniature connectors used in coaxial cables. The BNC terminal may be applied to frequencies below 4 GHz and voltages below 500 V.

[0059] In one embodiment, the connection terminal unit (350) may include a PCB substrate on which a plurality of BNC terminals are fixedly arranged symmetrically in parallel. The connection terminal block of the connection terminal unit (350) may be implemented in a shape that includes the PCB substrate internally, and by combining the BNC terminals on the PCB substrate, durability can be secured and EIS measurement sensitivity can be reduced. In addition, each BNC terminal on the PCB substrate can be independently connected to a physical cable, thereby facilitating cable maintenance.

[0060] Figure 4 is a flowchart illustrating an AI diagnosis method based on EIS measurement according to the present invention.

[0061] Referring to FIG. 4, the AI ​​diagnostic device (130) can transmit a signal for EIS data measurement through the first force electrode of the EIS measurement unit (310) (step S410). The AI ​​diagnostic device (130) can receive a signal returned by the battery jig unit (330) through the second force electrode of the EIS measurement unit (310) (step S410).

[0062] The AI ​​diagnostic device (130) can analyze the signal values ​​of the signal received from the second force electrode of the EIS measurement unit (310) to detect a change pattern of impedance of the battery (step S450), and can predict a change in the characteristics of the physical cable according to the detected change pattern (step S470).

[0063] For example, the change pattern of the impedance can be defined by the zero crossing impedance frequency defined in the impedance waveform and the impedance change pattern at the first and second inflection impedance frequencies. Here, the zero crossing impedance frequency can correspond to the frequency at the intersection point between the impedance waveform and the x-axis (or Re-axis) on a two-dimensional graph (e.g., Nyquist plot) in which the impedance waveform is defined. In addition, the first and second inflection impedance frequencies can correspond to the frequencies at each of the different inflection points formed on the impedance waveform. The AI ​​diagnostic device (130) can perform an operation of predicting a change in the characteristics of a physical cable by using information on the change in impedance for each frequency detected in the impedance waveform.

[0064] In one embodiment, the AI ​​diagnostic device (130) can predict changes in the characteristics of a physical cable connected to a connection terminal (350) from a change pattern of signal values ​​collected by the EIS measurement unit (310) by utilizing an artificial intelligence model. That is, the artificial intelligence model can be learned and built in advance by the AI ​​diagnostic device (130), and can be learned to receive characteristic information collected from signal values ​​as input and generate a predicted value regarding a change in the characteristics of the cable as output.

[0065] In one embodiment, the AI ​​diagnostic device (130) can predict a change in the characteristics of a cable connecting the EIS measurement unit (310) and the battery jig unit (330) based on the impedance deviation, and learn the impedance information of the battery and the characteristic information of the cable together to build a diagnostic model that predicts a defective state of the battery system assembly (BSA). That is, the AI ​​diagnostic device (130) can derive a correlation between the characteristic change of the cable and the impedance deviation based on impedance measurement data according to various cable connections, and can predict a characteristic change of the cable according to the change in impedance based on the derived correlation. The AI ​​diagnostic device (130) can diagnose a defective state of a battery connected to the battery jig unit (330) by providing the impedance information of the battery collected through the EIS measurement unit (310) and the predicted characteristic information of the cable as inputs of a pre-built diagnostic model.

[0066] FIG. 5 is a drawing illustrating one embodiment of an AI diagnostic device according to the present invention.

[0067] Referring to FIG. 5, the AI ​​diagnostic device (130) may be configured to include an EIS measurement module (510), a jig module (530), and a connection terminal block (550). The AI ​​diagnostic device (130) may connect the EIS measurement module (510) and the jig module (530) using a physical cable (e.g., a solartron cable, etc.), and may form a signal transmission path between the cables by combining the connection terminal blocks (550) according to the gap between the EIS measurement module (510) and the jig module (530).

[0068] In addition, the AI ​​diagnostic device (130) can collect signals for diagnosing a battery connected to a jig module (530) through an EIS module (510), and can detect subtle changes according to the type of cable connected to the connection terminal block (550) during the signal collection process. For example, the AI ​​diagnostic device (130) can detect changes in an EIS plot according to changes in a cable connected to the connection terminal block (550), and can predict changes in the characteristics of the cable based on the changes in the EIS plot.

[0069] Meanwhile, coaxial cables can be primarily used for connection to the terminal block, but are not necessarily limited to this. Cable characteristics may include insulation resistance (MΩ / Km), capacitance (PF / m), characteristic impedance (Ω), and standard attenuation by frequency (dB / km).

[0070] Figure 6 is a drawing illustrating one embodiment of a connection terminal block according to the present invention.

[0071] Referring to FIG. 6, the AI ​​diagnostic device (130) may be implemented by including a plurality of terminals (610) that are arranged between the EIS measurement unit (310) and the battery jig unit (330) and are coupled with physical cables, and a connection terminal unit (350) that provides a signal transmission path between the plurality of terminals (610). At this time, the connection terminal unit (350) may include a connection terminal block that forms a physical signal transmission path between the cables.

[0072] The connection terminal block can be implemented by including a plurality of BNC terminals that can be connected to a cable. The exterior of the connection terminal block (Figure (a)) can be implemented in a shape similar to the terminal block, and can be implemented to be suitable for use when the distance between the meter and the measuring equipment is far, specifically for the BNC terminal used in the EIS meter. In addition, the maintenance of the cable connected to the EIS meter or equipment can be implemented conveniently, and only the damaged part can be easily replaced without replacing the entire cable. The interior of the connection terminal block (Figure (b)) is manufactured as an integrated PCB, so that the structure is simple, and the BNC terminal is coupled to the PCB board (630) to ensure durability, and the BNC terminal is fixed, so that the EIS measurement sensitivity can be reduced.

[0073] Figure 7 is a drawing explaining an artificial intelligence-based battery diagnosis process according to the present invention.

[0074] Referring to FIG. 7, the AI ​​diagnostic device (130) can generate battery diagnostic results by utilizing one or more artificial intelligence models constructed for battery diagnostics. For example, in FIG. 7, the AI ​​diagnostic device (130) can predict changes in the characteristics of a physical cable according to an impedance change pattern using the first model (710). Here, the first model (710) receives as input the impedance deviation of the battery collected through the EIS measurement unit (310), and can predict changes in the characteristics of the cable connecting the EIS measurement unit (310) and the battery jig unit (330).

[0075] In particular, the first model (710) can be trained to predict changes in cable characteristics when the EIS measurement unit (310) and the battery jig unit (330) are connected to each other through a connection terminal. In addition, the impedance deviation used as an input of the first model (710) may correspond to a difference between impedances in specific frequency bands measured at different points in time, and may also be expressed as a combination of difference values ​​in one or more frequency bands.

[0076] In addition, the AI ​​diagnostic device (130) can generate a battery diagnostic result according to the battery impedance and cable characteristics using the second model (730). Here, the second model (730) can receive as input the impedance of the battery collected through the EIS measurement unit (310) and the cable characteristics connecting the EIS measurement unit (310) and the battery jig unit (330), and generate a diagnostic result of the battery connected to the battery jig unit (330). At this time, the AI ​​diagnostic device (130) can generate characteristic information of the cable connecting the current EIS measurement unit (310) and the battery jig unit (330) based on the characteristic change of the cable predicted by the first model (710), and provide the information as an input to the second model (730).

[0077] In one embodiment, the second model (730) can predict a battery's fault condition and generate a diagnostic result. For example, the second model (730) may correspond to a diagnostic model. Meanwhile, the inputs and outputs of each of the first model (710) and the second model (730) may be expressed in vector form, although this is not necessarily limited to this.

[0078] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A battery jig unit coupled with at least one battery; An EIS measuring unit connected to one or more electrodes of the battery jig section by a physical cable and receiving a signal returned by at least some of the one or more electrodes, and measuring and collecting EIS data from the at least one battery; and An EIS measurement-based AI diagnostic device, comprising: a connection terminal section, which includes a plurality of terminals arranged between the EIS measurement section and the battery jig section and connected to the physical cable, and which provides a signal transmission path between the plurality of terminals; 2. In the first paragraph, the EIS measurement unit An AI diagnostic device based on EIS measurement, characterized by collecting a force return signal returned by the battery jig unit through a pair of force electrodes.

3. In the second paragraph, the EIS measurement unit An EIS measurement-based AI diagnostic device characterized by analyzing the force return signal to detect changes in the EIS plot due to changes in the physical cable.

4. In the second paragraph, the EIS measurement unit An AI diagnostic device based on EIS measurement, characterized in that the impedance of at least one battery is calculated using signal values ​​of the force return signal collected at different points in time at regular intervals.

5. In the fourth paragraph, the EIS measurement unit An AI diagnostic device based on EIS measurement, characterized in that it predicts a change in the characteristics of the physical cable according to the change pattern of the impedance.

6. In the first paragraph, the connection terminal part An EIS measurement-based AI diagnostic device characterized by including a plurality of BNC terminals for connection with the above physical cable.

7. In the 6th paragraph, the connecting terminal part An EIS measurement-based AI diagnostic device characterized by including a PCB substrate on which the plurality of BNC terminals are fixedly arranged symmetrically in parallel with each other.

8. An AI diagnostic method performed in an AI diagnostic device based on EIS measurement, comprising a battery jig portion coupled to a battery, an EIS measuring portion physically connected to the battery jig portion by a cable, and a connection terminal portion arranged between the EIS measuring portion and the battery jig portion, A step of transmitting a signal for EIS data measurement through the first force electrode of the above EIS measurement unit; A step of receiving a signal returned by the battery jig unit through the second force electrode of the EIS measuring unit; and An EIS measurement-based AI diagnostic method, comprising: a step of analyzing signal values ​​of signals received from the second force electrode through the EIS measurement unit to predict changes in the characteristics of the physical cable according to a change pattern of impedance with respect to the battery.

Images