Apparatus and method for authenticating battery cell

The battery cell authentication device uses terahertz waves to generate and process electromagnetic pulses, enabling accurate authentication and monitoring of battery cells by identifying unique properties through signature vectors, addressing the limitations of existing technologies.

WO2026240382A1PCT designated stage Publication Date: 2026-11-19SAMSUNG SDI CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2026/005702
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-12
Filing Date
2026-04-29
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing battery certification and status monitoring technologies are limited in their ability to authenticate and monitor batteries at the individual cell level, particularly in high-performance batteries used in electric and hybrid vehicles, lacking the capability to identify unique physical and chemical properties effectively.

Method used

A battery cell authentication device and method utilizing terahertz waves to generate and detect electromagnetic pulses, process the frequency spectrum, and perform authentication based on signature vectors generated through preprocessing, discrete wavelet transform, and deep neural networks.

Benefits of technology

Enables authentication of battery cells at the nanometer level by identifying unique physical and chemical properties, ensuring accurate certification and monitoring, and detecting performance degradation or abnormalities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2026005702_19112026_PF_FP_ABST
    Figure KR2026005702_19112026_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure relates to an apparatus and a method for authenticating a battery cell, and the technical problem to be solved is to provide a mechanism that enables easy authentication of a battery cell. To this end, the present disclosure provides a configuration for generating a frequency spectrum for a battery cell, generating a signature vector for the battery cell on the basis of the generated frequency spectrum, and authenticating the battery cell on the basis of the generated signature vector.
Need to check novelty before this filing date? Find Prior Art

Description

Battery cell authentication device and method

[0001] The present disclosure relates to a battery cell authentication device and method for authenticating a battery cell.

[0002] As the xEV market, including electric and hybrid vehicles, continues to grow, the demand for high-performance batteries is surging. As high-performance batteries are a core component of vehicles, their performance and safety are directly linked to driving range, efficiency, and vehicle reliability.

[0003] Meanwhile, battery quality control, anti-counterfeiting, and performance tracking throughout the lifecycle are emerging as major challenges for the industry. Conventionally, battery certification and status monitoring have been performed based on electrical characteristics, which has limited the ability to certify and monitor batteries at the individual cell level. Consequently, there is a demand for technology that enables battery certification and status monitoring at the cell level.

[0004] The information described above disclosed in the background technology of this invention is intended only to enhance understanding of the background of the present invention and may therefore include information that does not constitute prior art.

[0005] The purpose of the present invention is to provide a battery cell authentication device and method capable of identifying the unique physical and chemical properties of a battery cell at the nanometer level and performing authentication of the battery cell based on the identified properties.

[0006] However, the technical problems that the present invention aims to solve are not limited to those described above, and other unmentioned problems can be clearly understood by those skilled in the art from the description of the invention below.

[0007] A battery cell authentication device according to an embodiment of the present invention for solving the above technical problem comprises: an electromagnetic wave generating module configured to generate an electromagnetic wave pulse; an electromagnetic wave detection module configured to detect the electromagnetic wave pulse; and a processor configured to generate a frequency spectrum for a battery cell using the electromagnetic wave generating module and the electromagnetic wave detection module, generate a signature vector for the battery cell based on the frequency spectrum, and perform authentication for the battery cell based on the signature vector.

[0008] In the present invention, the electromagnetic wave pulse is characterized as being a terahertz wave pulse.

[0009] In the present invention, the processor is characterized by generating the frequency spectrum by repeatedly performing the process of irradiating the battery cell with an electromagnetic wave pulse through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and matching and recording the frequency and intensity of the electromagnetic wave pulse, while changing the frequency of the electromagnetic wave pulse at predetermined unit frequency intervals within a predetermined set frequency range.

[0010] In the present invention, the processor is characterized by irradiating the battery cell with an electromagnetic wave pulse of a predefined frequency through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and generating the frequency spectrum by performing a Fourier transform on the detected electromagnetic wave pulse.

[0011] In the present invention, the processor is characterized by performing preprocessing to remove noise included in the frequency spectrum and normalize the frequency spectrum before generating the signature vector.

[0012] In the present invention, the processor is characterized by extracting features from the frequency spectrum and generating the signature vector based on the features.

[0013] In the present invention, the processor is characterized by multi-stage decomposing of the frequency spectrum through a discrete wavelet transform to obtain approximation coefficients and detail coefficients for each decomposition level, and performing an operation to extract features from the approximation coefficients and detail coefficients for each decomposition level.

[0014] In the present invention, the processor is characterized by extracting the arithmetic mean, standard deviation, information entropy, and kurtosis of the approximate coefficient and the detailed coefficient as the features.

[0015] In the present invention, the processor is characterized by extracting principal components from the features through principal component analysis and inputting the principal components into a pre-trained deep neural network model to generate the signature vector.

[0016] In the present invention, the processor calculates the Euclidean distance between the signature vector and a predefined reference signature vector, determines that the authentication of the battery cell is successful if the Euclidean distance is less than or equal to the predefined reference distance, and determines that the authentication of the battery cell has failed if the Euclidean distance is not less than or equal to the reference distance.

[0017] A battery cell authentication method according to an embodiment of the present invention for solving the above technical problem comprises: a step in which a processor generates a frequency spectrum for a battery cell using an electromagnetic wave generating module configured to generate an electromagnetic wave pulse and an electromagnetic wave detection module configured to detect the electromagnetic wave pulse; a step in which the processor generates a signature vector for the battery cell based on the frequency spectrum; and a step in which the processor performs authentication for the battery cell based on the signature vector.

[0018] In the present invention, the electromagnetic wave pulse is characterized as being a terahertz wave pulse.

[0019] In the step of generating the frequency spectrum in the present invention, the processor generates the frequency spectrum by repeatedly performing the process of irradiating the battery cell with an electromagnetic wave pulse through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and matching and recording the frequency and intensity of the electromagnetic wave pulse, while changing the frequency of the electromagnetic wave pulse at predetermined unit frequency intervals within a predetermined set frequency range.

[0020] In the step of generating the frequency spectrum in the present invention, the processor is characterized by irradiating the battery cell with an electromagnetic wave pulse of a predefined frequency through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and generating the frequency spectrum by performing a Fourier transform on the detected electromagnetic wave pulse.

[0021] The present invention is characterized in that, prior to the step of generating the signature vector, the processor further includes a step of preprocessing the frequency spectrum, and in the step of preprocessing the frequency spectrum, the processor removes noise included in the frequency spectrum and normalizes the frequency spectrum.

[0022] In the step of generating the signature vector in the present invention, the processor is characterized by extracting features from the frequency spectrum and generating the signature vector based on the features.

[0023] In the step of generating the signature vector in the present invention, the processor is characterized by obtaining approximation coefficients and detail coefficients for each decomposition level by multi-stage decomposition of the frequency spectrum through discrete wavelet transform, and performing the operation of extracting features from the approximation coefficients and detail coefficients for each decomposition level.

[0024] In the step of generating the signature vector in the present invention, the processor is characterized by extracting the arithmetic mean, standard deviation, information entropy, and kurtosis of the approximation coefficient and the detail coefficient as features.

[0025] In the step of generating the signature vector in the present invention, the processor is characterized by extracting principal components from the features through principal component analysis and inputting the principal components into a pre-trained deep neural network model to generate the signature vector.

[0026] In the step of performing the authentication in the present invention, the processor calculates the Euclidean distance between the signature vector and a predefined reference signature vector, determines that the authentication of the battery cell is successful if the Euclidean distance is less than or equal to the predefined reference distance, and determines that the authentication of the battery cell has failed if the Euclidean distance is not less than or equal to the reference distance.

[0027] According to the invention, unique physical and chemical properties of a battery cell can be identified at the nanometer level using terahertz waves, and authentication of the battery cell can be performed based on the identified unique properties of the battery cell.

[0028] However, the effects obtainable through the present invention are not limited to those described above, and other unmentioned technical effects will be clearly understood by those skilled in the art from the description of the invention below.

[0029] The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further enhance understanding of the technical concept of the present invention together with the detailed description of the invention provided below; therefore, the present invention should not be interpreted as being limited only to the matters described in such drawings.

[0030] FIG. 1 is a block diagram showing a battery cell authentication device according to an embodiment of the present invention.

[0031] FIG. 2 is an illustrative diagram for explaining a battery cell authentication device according to an embodiment of the present invention.

[0032] FIG. 3 is a flowchart illustrating a battery cell authentication method according to an embodiment of the present invention.

[0033] Preferred embodiments of the present invention will be described in detail below with reference to the attached drawings. Prior to this, terms and words used in this specification and claims should not be interpreted as being limited to their ordinary or dictionary meanings. Instead, based on the principle that the inventor may appropriately define the concepts of terms to best describe his invention, they should be interpreted in a meaning and concept consistent with the technical spirit of the present invention. Therefore, it should be understood that the embodiments described in this specification and the configurations illustrated in the drawings are merely some of the most preferred embodiments of the present invention and do not represent all of the technical spirit of the present invention; thus, various equivalents and modifications that can replace them may exist at the time of filing this application. Furthermore, as used in this specification, "comprise" or "include" and / or "comprising" or "including" specify the presence of the mentioned features, numbers, steps, actions, parts, elements, and / or groups thereof, and do not exclude the presence or addition of one or more other features, numbers, actions, parts, elements, and / or groups. In addition, when describing embodiments of the present invention, "may" and "may" may include "one or more embodiments of the present invention."

[0034] Additionally, to aid in understanding the invention, the attached drawings are not drawn to actual scale, and the dimensions of some components may be exaggerated. Furthermore, the same reference numerals may be assigned to identical components in different embodiments.

[0035] The statement that two subjects of comparison are 'identical' means that they are 'substantially identical.' Therefore, substantial identity may include deviations considered low in the industry, for example, deviations within 5%. Additionally, the statement that a parameter is uniform in a given area may mean that it is uniform from an average perspective.

[0036] Although terms such as "first," "second," etc., are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless specifically stated otherwise, the first component may also be the second component.

[0037] Throughout the specification, unless specifically stated otherwise, each component may be singular or plural.

[0038] The fact that any configuration is placed on the "upper (or lower)" of a component or on the "upper (or lower)" of a component may mean not only that any configuration is placed in contact with the upper (or lower) surface of said component, but also that another configuration may be interposed between said component and any configuration placed on (or below) said component.

[0039] Furthermore, where it is stated that one component is "connected," "coupled," or "connected" to another component, it should be understood that while said components may be directly connected or connected to each other, another component may be "interposed" between each component, or that each component may be "connected," "coupled," or "connected" through another component. Additionally, when it is stated that a part is electrically coupled with another part, this includes not only cases where they are directly connected but also cases where they are connected with another component in between.

[0040] Throughout the specification, "A and / or B" means A, B, or A and B unless specifically stated otherwise. That is, "and / or" includes any combination or any combination of the enumerated items. "C to D" means C or more and D or less, unless specifically stated otherwise.

[0041]

[0042] FIG. 1 is a block diagram showing a battery cell authentication device according to an embodiment of the present invention, and FIG. 2 is an illustrative diagram for explaining a battery cell authentication device according to an embodiment of the present invention.

[0043] Referring to FIGS. 1 and 2, a battery cell authentication device (100) according to an embodiment of the present invention may include an electromagnetic wave generating module (110), an electromagnetic wave detection module (120), a fixing module (130), a direction adjustment module (140), a communication module (150), a memory (160), and a processor (170). The battery cell authentication device (100) according to an embodiment of the present invention may further include various components in addition to the components shown in FIGS. 1 and 2.

[0044] The electromagnetic wave generating module (110) may be a device for irradiating an electromagnetic wave pulse (signal) to a battery cell to be certified (hereinafter referred to as the target battery cell (C)). The electromagnetic wave generating module (110) may generate an electromagnetic wave pulse having a frequency within the range of 0.1 to 10 THz. The electromagnetic wave generating module (110) may also be referred to as an electromagnetic wave generator, a terahertz generator, etc.

[0045] In this embodiment, the electromagnetic wave pulse may be a terahertz wave pulse. Terahertz waves can penetrate non-metallic materials, making them suitable for analyzing the internal structure of a battery cell. Terahertz waves have the property of matching the unique vibrational frequencies of the chemical substances in the battery cell, making them suitable for detecting the unique response of the chemical substances inside the battery cell. Terahertz waves can provide microstructural information of the battery electrode material by interacting with the phonon modes of the crystal lattice structure. Terahertz waves can generate complex interference patterns by interacting with the multilayer structure inside the battery cell, and these interference patterns can be used as a unique fingerprint of the battery cell. Terahertz waves are suitable for detecting the movement of free charge carriers inside the battery cell. However, the electromagnetic wave pulse is not limited to terahertz waves, and frequency signals of various bands may be used as the electromagnetic wave pulse.

[0046] The electromagnetic wave generating module (110) may include a femtosecond laser source that generates femtosecond laser pulses and a photoconductive antenna that generates terahertz waves when the femtosecond laser pulse generated from the femtosecond laser source is incident.

[0047] The electromagnetic wave detection module (120) may be a device for detecting electromagnetic wave pulses that have passed through a target battery cell (C). The electromagnetic wave detection module (120) may detect electromagnetic wave pulses that have passed through the target battery cell (C) using an electro-optic sampling method. The electromagnetic wave detection module (120) may also be referred to as an electromagnetic wave detector, a terahertz detector, etc.

[0048] The fixed module (130) may be a device for fixing and moving the target battery cell (C), the electromagnetic wave generating module (110), the electromagnetic wave detection module (120), and the direction adjustment module (140). The fixed module (130) may include a 3-axis piezo stage. The 3-axis piezo stage can move the target battery cell (C), the electromagnetic wave generating module (110), the electromagnetic wave detection module (120), and the direction adjustment module (140) to various positions within a predetermined range.

[0049] The direction adjustment module (140) may be a device for changing the direction of an electromagnetic wave pulse irradiated from an electromagnetic wave generation module (110). The direction adjustment module (140) may include a galvanometer scanner. The galvanometer scanner may include a mirror configured to rotate by an electromagnetic force, and the direction of the electromagnetic wave pulse may be changed through the mirror.

[0050] The communication module (150) can communicate with an external device. The communication module (150) can communicate with various types of external devices according to various types of communication methods. The communication module (150) can communicate with an external server that manages the battery and can transmit the authentication result for the battery cell calculated by the processor (170) described later.

[0051] The memory (160) may store at least one instruction that is executed during the process in which the processor (170) performs authentication of the battery cell. The memory (160) may store basic data required for authentication of the battery cell or data generated during the process in which the processor (170) performs authentication of the battery cell, and the processor (170) may access the data stored in the memory (160) to perform authentication operations for the battery cell. The memory (160) may be implemented as a computer-readable recording medium and may operate so that the processor (170) can access it. Specifically, the memory (160) may be implemented as an optical data storage device such as a hard drive, magnetic tape, memory card, ROM (Read-Only Memory), RAM (Random-Access Memory), DVD (Digital Video Disc), or optical disc.

[0052] The processor (170) is the entity that performs authentication operations for the battery cell and may be implemented as an ASIC (Application Specific Integrated Circuit), DSP (Digital Signal Processor), PLD (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), CPU (Central Processing unit), microcontrollers and / or microprocessors, and may run an operating system or application and control multiple hardware or software components. The processor (170) may be configured to execute at least one instruction stored in memory (160) and store the execution result data in memory (160).

[0053] The processor (170) can generate a frequency spectrum (terahertz spectrum) for a target battery cell (C) using an electromagnetic wave generation module (110) and an electromagnetic wave detection module (120). The processor (170) can generate a frequency spectrum for a target battery cell (C) by repeatedly performing the process of irradiating an electromagnetic wave pulse onto the target battery cell (C) through the electromagnetic wave generation module (110), detecting the electromagnetic wave pulse that has passed through the target battery cell (C) through the electromagnetic wave detection module (120), and matching and recording the frequency (Hz) of the electromagnetic wave pulse irradiated through the electromagnetic wave generation module (110) with the intensity (dB) of the electromagnetic wave pulse detected through the electromagnetic wave detection module (120), while changing the frequency of the electromagnetic wave pulse irradiated through the electromagnetic wave generation module (110) at predetermined unit frequency intervals within a predetermined set frequency range.

[0054] For example, assuming that the set frequency range is 0.1 to 10 THz and the unit frequency is 0.1 THz, the processor (170) can generate a frequency spectrum for the target battery cell (C) by repeatedly performing the operation of irradiating the target battery cell (C) with an electromagnetic pulse, detecting the electromagnetic pulse that has passed through the target battery cell (C), and matching and recording the intensity of the detected electromagnetic pulse with the frequency of the irradiated electromagnetic pulse, while changing the frequency of the electromagnetic pulse irradiated to the target battery cell (C) at intervals of 0.1 THz in the range of 0.1 to 10 THz.

[0055] In various embodiments, the processor (170) may generate a frequency spectrum for each region of the target battery cell (C), merge the frequency spectra generated for each region of the target battery cell (C) to generate a three-dimensional frequency spectrum image for the target battery cell (C), and use the generated three-dimensional frequency spectrum image as the frequency spectrum for the target battery cell (C). That is, instead of a frequency spectrum in a specific region defined in advance, a frequency spectrum for the entire target battery cell (C) may be used as the frequency spectrum for the target battery cell (C). At this time, the processor (170) may move at least one of the target battery cell (C), the electromagnetic wave generation module (110), and the electromagnetic wave detection module (120) through a fixed module (130) in order to generate a frequency spectrum for each region of the target battery cell (C). Additionally, the processor (170) may change the direction of the electromagnetic wave pulse irradiated through the electromagnetic wave generation module (110) through a direction adjustment module (140) in order to generate a frequency spectrum for each region of the target battery cell (C). The processor (170) can generate a frequency spectrum of the target battery cell (C) by region while controlling the fixed module (130) and the direction adjustment module (140).

[0056] In various embodiments, the processor (170) may irradiate an electromagnetic wave pulse of a preset frequency onto a target battery cell (C) through an electromagnetic wave generation module (110), detect the electromagnetic wave pulse transmitted through the target battery cell (C) through an electromagnetic wave detection module (120), and generate a frequency spectrum for the target battery cell (C) by performing a Fourier transform on the detected signal.

[0057] The processor (170) can preprocess the frequency spectrum for the target battery cell (C). When preprocessing the frequency spectrum for the target battery cell (C), the processor (170) can remove noise included in the frequency spectrum for the target battery cell (C). The processor (170) can remove noise included in the frequency spectrum for the target battery cell (C) by applying a median filter. For example, the window size of the median filter may be 5*5, and the processor (170) can remove noise included in the frequency spectrum for the target battery cell (C) by repeatedly performing the process of identifying the median value among the values ​​(dB) of the points included in the window centered on the target point (frequency) and setting the identified median value as the new value of the target point for all points.

[0058] The processor (170) can normalize the frequency spectrum of the target battery cell (C) when preprocessing the frequency spectrum of the target battery cell (C). The processor (170) can normalize the frequency spectrum of the target battery cell (C) by identifying the maximum and minimum values ​​among the values ​​of the points (frequencies) included in the frequency spectrum of the target battery cell (C), and by repeatedly performing the process of dividing the value of the target point minus the minimum value by the value of the maximum value minus the minimum value for all points.

[0059] The processor (170) can generate a signature vector for the target battery cell (C) based on the frequency spectrum for the target battery cell (C). In this embodiment, the signature vector may represent a value representing the unique physical and chemical characteristics of the battery cell. The processor (170) can extract features from the frequency spectrum for the target battery cell (C) and generate a signature vector for the target battery cell (C) based on the extracted features.

[0060] The processor (170) can obtain approximation coefficients and detail coefficients for each decomposition level by multi-stage decomposition (e.g., 5-stage decomposition) of the frequency spectrum of a target battery cell (C) through a Discrete Wavelet Transform (DWT), and can extract features from the approximation coefficients and detail coefficients obtained for each decomposition level. The processor (170) can perform the process of extracting features from the approximation coefficients and detail coefficients for each decomposition level.

[0061] The processor (170) can extract the arithmetic mean of the approximate coefficients and detailed coefficients (arithmetic mean of the coefficients), the standard deviation of the approximate coefficients and detailed coefficients (standard deviation of the coefficients), the information entropy of the approximate coefficients and detailed coefficients (information entropy of the coefficients), and the kurtosis of the approximate coefficients and detailed coefficients (kurtosis of the distribution of the coefficients) as features. The processor (170) can perform the process of calculating the arithmetic mean, the standard deviation, the information entropy, and the kurtosis at each decomposition level, and can obtain a plurality of features as a result.

[0062] The processor (170) can extract principal components from features extracted from the frequency spectrum of the target battery cell (C) through Principal Component Analysis (PCA), and input the extracted principal components into a pre-trained Deep Neural Network (DNN) model to generate a signature vector for the target battery cell (C). The processor (170) can select features that can explain more than 95% of the total data variance as principal components. The processor (170) can input the principal components into a pre-trained Deep Neural Network model to obtain a 16-dimensional signature vector. In various embodiments, the processor (170) may use the principal components obtained through Principal Component Analysis as signature vectors.

[0063] The unique characteristics (e.g., signature vector) of a battery cell may change as the battery cell ages. This embodiment can compensate for changes in characteristics due to the aging of the battery cell through the deep neural network model. The deep neural network model can be continuously updated by considering the usage history and environmental conditions of the battery cell. The processor (170) can collect data on the frequency spectrum during the usage period from various battery cells and update the deep neural network model using the collected data. The processor (170) can continuously update the deep neural network model through transfer learning.

[0064] The deep neural network model may consist of an input layer containing as many neurons as the number of features reduced by principal component analysis, a first hidden layer containing 64 neurons and using the ReLU activation function, a second hidden layer containing 32 neurons and using the ReLU activation function, and an output layer containing 16 neurons and using the Sigmoid activation function. The deep neural network model may use the Mean Squared Error (MSE) as the loss function during the training process. During the training process of the deep neural network model, its weights may be updated through the Adam (Adaptive Moment Estimation) optimization algorithm.

[0065] The processor (170) can perform authentication for the target battery cell (C) based on a signature vector for the target battery cell (C). The processor (170) can calculate the Euclidean distance between the signature vector for the target battery cell (C) and a predefined reference signature vector, and perform authentication for the target battery cell (C) based on the calculated Euclidean distance. The reference signature vector may be acquired in advance and stored in memory (160). Immediately after production, the signature vector of the target battery cell (C) may be acquired through the process described above, and the acquired signature vector may be used as the reference signature vector.

[0066] The processor (170) may determine that the authentication of the target battery cell (C) is successful if the Euclidean distance between the signature vector for the target battery cell (C) and the reference signature vector is less than or equal to a predefined reference distance. The processor (170) may determine that the authentication of the battery cell is failed if the Euclidean distance between the signature vector for the target battery cell (C) and the reference signature vector exceeds a predefined reference distance.

[0067] In various embodiments, the electromagnetic wave generating module (110) and the electromagnetic wave detection module (120) may be mounted in the form of sensors on each of the battery cells included in the battery pack. In this case, the processor (170) may perform authentication on each of the battery cells and transmit the result to the Battery Management System (BMS) of the battery pack through the communication module (150).

[0068] In various embodiments, the frequency spectrum of the battery cell may be used to determine whether the battery cell is abnormal. In this case, the processor (170) can detect performance degradation or abnormalities of the battery cell by analyzing the frequency spectrum of the battery cell using an AI-based model.

[0069]

[0070] FIG. 3 is a flowchart illustrating a battery cell authentication method according to an embodiment of the present invention.

[0071] Hereinafter, the process of authenticating a battery cell will be described with reference to FIG. 3. Some of the steps described below may be performed in a different order than the order described below or may be omitted.

[0072] First, the processor (170) can generate a frequency spectrum for a target battery cell (C) using an electromagnetic wave generation module (110) and an electromagnetic wave detection module (120) (S301). In step S301, the processor (170) can generate a frequency spectrum for a target battery cell (C) by repeatedly performing the process of irradiating an electromagnetic wave pulse to the target battery cell (C) through the electromagnetic wave generation module (110), detecting the electromagnetic wave pulse that has passed through the target battery cell (C) through the electromagnetic wave detection module (120), and matching and recording the frequency (Hz) of the electromagnetic wave pulse irradiated through the electromagnetic wave generation module (110) with the intensity (dB) of the electromagnetic wave pulse detected through the electromagnetic wave detection module (120), while changing the frequency of the electromagnetic wave pulse irradiated through the electromagnetic wave generation module (110) at predetermined unit frequency intervals within a predetermined set frequency range.

[0073] Next, the processor (170) can preprocess the frequency spectrum for the target battery cell (C) (S303). In step S303, the processor (170) can remove noise included in the frequency spectrum for the target battery cell (C). In step S303, the processor (170) can normalize the frequency spectrum for the target battery cell (C).

[0074] Next, the processor (170) can obtain approximate coefficients and detailed coefficients for each decomposition level by multi-stage decomposing the frequency spectrum of the target battery cell (C) through discrete wavelet transform (S305).

[0075] Next, the processor (170) can extract features from the approximate coefficients and detailed coefficients obtained for each decomposition level (S307). In step S307, the processor (170) can extract the arithmetic mean of the approximate coefficients and detailed coefficients (arithmetic mean of the coefficients), the standard deviation of the approximate coefficients and detailed coefficients (standard deviation of the coefficients), the information entropy of the approximate coefficients and detailed coefficients (information entropy of the coefficients), and the kurtosis of the approximate coefficients and detailed coefficients (kurtosis of the distribution of the coefficients) as features.

[0076] Next, the processor (170) can extract principal components from the features through principal component analysis (S309). In step S309, the processor (170) can select a feature that can explain 95% or more of the variance of the entire data as a principal component.

[0077] Next, the processor (170) can input the principal components into a pre-trained deep neural network model to generate a signature vector for the target battery cell (C) (S311).

[0078] Next, the processor (170) can calculate the Euclidean distance between the signature vector for the target battery cell (C) and a predefined reference signature vector (S313).

[0079] Next, the processor (170) can determine whether the Euclidean distance is less than or equal to a predefined reference distance (S315).

[0080] If the above Euclidean distance is less than or equal to the reference distance, the processor (170) can determine that the authentication of the target battery cell (C) has been successful (S317).

[0081] If the above Euclidean distance is not less than or equal to the reference distance, the processor (170) may determine that the authentication for the target battery cell (C) has failed (S319).

[0082]

[0083] As such, according to the present invention, unique physical and chemical properties of a battery cell can be identified at the nanometer level by utilizing terahertz waves, and authentication of the battery cell can be performed based on the identified unique properties of the battery cell.

[0084] As used herein, the terms “part” and “module” may include units implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. “Part” and “module” may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, “part” and “module” may be implemented in the form of an Application-Specific Integrated Circuit (ASIC).

[0085] The implementations described herein may be implemented, for example, as methods or processes, devices, software programs, data streams, or signals. Even if discussed only in the context of a single form of implementation (e.g., discussed only as a method), the implementation of the discussed features may also be implemented in other forms (e.g., devices or programs). Devices may be implemented in appropriate hardware, software, and firmware, etc. Methods may be implemented in devices such as processors, which generally refer to processing devices including, for example, computers, microprocessors, integrated circuits, or programmable logic devices. Processors also include communication devices such as computers, cell phones, portable / personal digital assistants ("PDAs"), and other devices that facilitate the communication of information between end-users.

[0086] Although the present invention has been described above by limited embodiments and drawings, the present invention is not limited thereto, and it is obvious that various modifications and variations are possible within the scope of the technical spirit of the present invention and the equivalent scope of the claims described below by those skilled in the art to which the present invention belongs.

Claims

1. An electromagnetic wave generating module configured to generate electromagnetic wave pulses; An electromagnetic wave detection module configured to detect electromagnetic wave pulses; and A battery cell authentication device comprising a processor configured to generate a frequency spectrum for a battery cell using the electromagnetic wave generation module and the electromagnetic wave detection module, generate a signature vector for the battery cell based on the frequency spectrum, and perform authentication for the battery cell based on the signature vector.

2. In Paragraph 1, A battery cell authentication device in which the above electromagnetic wave pulse is a terahertz wave pulse.

3. In Paragraph 1, A battery cell authentication device, wherein the processor generates the frequency spectrum by repeatedly performing the process of irradiating the battery cell with an electromagnetic wave pulse through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and matching and recording the frequency and intensity of the electromagnetic wave pulse, while changing the frequency of the electromagnetic wave pulse at predetermined unit frequency intervals within a predetermined set frequency range.

4. In Paragraph 1, A battery cell authentication device, wherein the processor irradiates the battery cell with an electromagnetic wave pulse of a preset frequency through the electromagnetic wave generation module, detects the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and generates the frequency spectrum by performing a Fourier transform on the detected electromagnetic wave pulse.

5. In Paragraph 4, A battery cell authentication device, wherein the processor performs preprocessing to remove noise included in the frequency spectrum and normalize the frequency spectrum before generating the signature vector.

6. In Paragraph 1, A battery cell authentication device, wherein the processor extracts features from the frequency spectrum and generates the signature vector based on the features.

7. In Paragraph 6, A battery cell authentication device, wherein the processor performs, at each decomposition level, an operation to obtain approximate coefficients and detailed coefficients by multi-stage decomposition of the frequency spectrum through discrete wavelet transform, and extracts the features from the approximate coefficients and detailed coefficients.

8. In Paragraph 7, A battery cell authentication device, wherein the processor extracts the arithmetic mean, standard deviation, information entropy, and kurtosis for the approximation coefficient and the detail coefficient as the features.

9. In Paragraph 6, A battery cell authentication device, wherein the processor extracts principal components from the features through principal component analysis and inputs the principal components into a pre-trained deep neural network model to generate the signature vector.

10. In Paragraph 1, A battery cell authentication device, wherein the processor calculates the Euclidean distance between the signature vector and a predefined reference signature vector, determines that the authentication of the battery cell is successful if the Euclidean distance is less than or equal to the predefined reference distance, and determines that the authentication of the battery cell has failed if the Euclidean distance is not less than or equal to the reference distance.

11. A step in which a processor generates a frequency spectrum for a battery cell using an electromagnetic wave generating module configured to generate electromagnetic wave pulses and an electromagnetic wave detection module configured to detect electromagnetic wave pulses; The above processor generates a signature vector for the battery cell based on the frequency spectrum; and A battery cell authentication method comprising the step of the processor performing authentication of the battery cell based on the signature vector.

12. In Paragraph 11, A battery cell authentication method in which the above electromagnetic wave pulse is a terahertz wave pulse.

13. In Paragraph 11, In the step of generating the above frequency spectrum, A battery cell authentication method, wherein the processor generates a frequency spectrum by repeatedly performing the process of irradiating an electromagnetic wave pulse to the battery cell through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and matching and recording the frequency and intensity of the electromagnetic wave pulse, while changing the frequency of the electromagnetic wave pulse at predetermined unit frequency intervals within a predetermined set frequency range.

14. In Paragraph 11, In the step of generating the above frequency spectrum, A battery cell authentication method comprising: a processor irradiating an electromagnetic wave pulse of a predefined frequency onto the battery cell through the electromagnetic wave generation module, detecting the electromagnetic wave pulse transmitted through the battery cell through the electromagnetic wave detection module, and generating the frequency spectrum by Fourier transforming the detected electromagnetic wave pulse.

15. In Paragraph 14, Prior to the step of generating the above signature vector, The above processor further includes a step of preprocessing the frequency spectrum, In the step of preprocessing the above frequency spectrum, The above processor removes noise included in the frequency spectrum and normalizes the frequency spectrum, a battery cell authentication method.

16. In Paragraph 11, In the step of generating the above signature vector, A battery cell authentication method in which the processor extracts features from the frequency spectrum and generates the signature vector based on the features.

17. In Paragraph 16, In the step of generating the above signature vector, A battery cell authentication method wherein the processor obtains approximation coefficients and detail coefficients for each decomposition level by multi-stage decomposition of the frequency spectrum through discrete wavelet transform, and performs the operation of extracting features from the approximation coefficients and detail coefficients for each decomposition level.

18. In Paragraph 17, In the step of generating the above signature vector, A battery cell authentication method in which the processor extracts the arithmetic mean, standard deviation, information entropy, and kurtosis of the approximate coefficient and the detailed coefficient as the features.

19. In Paragraph 16, In the step of generating the above signature vector, A battery cell authentication method wherein the processor extracts principal components from the features through principal component analysis and inputs the principal components into a pre-trained deep neural network model to generate the signature vector.

20. In Paragraph 11, In the step of performing the above authentication, A battery cell authentication method wherein the processor calculates the Euclidean distance between the signature vector and a predefined reference signature vector, determines that the authentication of the battery cell is successful if the Euclidean distance is less than or equal to the predefined reference distance, and determines that the authentication of the battery cell has failed if the Euclidean distance is not less than or equal to the reference distance.