Battery diagnostic device and method

Abstract

According to some embodiments disclosed in this document, a battery diagnostic device may include a sensor configured to measure battery test data from a battery to be diagnosed, and a processor configured to divide the battery test data into a plurality of charge / discharge state datasets based on a plurality of reference values ​​for a plurality of charge / discharge states, perform a preliminary failure diagnosis on each of the plurality of charge / discharge state datasets based on a preliminary diagnostic model, and determine the battery to be diagnosed as ultimately defective based on the results of the preliminary failure diagnosis.

Description

Technical Field

[0001] This application claims the benefit of priority based on Korean Patent Application No. 10-2023-0076815 filed on June 15, 2023, and all the contents disclosed in the literature of the patent application are incorporated herein by reference as part of this specification. The embodiments disclosed in this document relate to a battery diagnosis apparatus and method.

Background Art

[0002] In recent years, research and development on secondary batteries have been actively conducted. Here, a secondary battery is a battery capable of charging and discharging, and includes both conventional Ni / Cd batteries, Ni / MH batteries, etc. and recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries have the advantage of having a much higher energy density compared to conventional Ni / Cd batteries, Ni / MH batteries, etc. In addition, since lithium-ion batteries can be manufactured in a small and lightweight manner, they are used as power sources for mobile devices. In recent years, their usage range has been extended to power sources for electric vehicles and they have attracted attention as next-generation energy storage media.

[0003] Various diagnostic models can be utilized to diagnose whether battery cells, modules, packs, etc. are operating normally. For example, a test voltage can be measured from a battery under diagnosis during the application of a charge / discharge test voltage, and a diagnostic model can be applied thereto to diagnose whether there is a defect in the battery. Indicators such as a diagnostic rate (discrimination power) indicating the ratio at which a diagnostic model operating in this manner correctly diagnoses a defect, and an over-detection rate indicating the ratio at which a non-defective battery is misdiagnosed as defective can be utilized to evaluate the model performance. However, general diagnostic models have a discrimination power of less than 80% and an over-detection rate of more than 10%, and there is a problem that the model performance cannot be guaranteed for atypical charge / discharge patterns.

Summary of the Invention

Problems to be Solved by the Invention

[0004] One objective of the embodiments disclosed in this document is to provide a battery diagnostic device and method that are highly applicable even to atypical charge-discharge patterns.

[0005] The technical problems of the embodiments disclosed in this document are not limited to those mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0006] According to some embodiments disclosed in this document, a battery diagnostic device may include a sensor configured to measure battery test data from a battery to be diagnosed, and a processor configured to divide the battery test data into a plurality of charge / discharge state datasets based on a plurality of reference values ​​for a plurality of charge / discharge states, perform a preliminary failure diagnosis on each of the plurality of charge / discharge state datasets based on a preliminary diagnostic model, and determine the battery to be diagnosed as ultimately defective based on the results of the preliminary failure diagnosis.

[0007] According to some embodiments, the processor may be configured to determine the battery under diagnosis as having the final defect if two or more of the multiple charge / discharge state data sets are determined to have a preliminary defect.

[0008] According to some embodiments, the processor may be further configured to calculate a diagnostic rate and a false positive rate by comparing the result of determining the battery to be diagnosed as ultimately defective with the actual presence or absence of defects in the battery to be diagnosed.

[0009] According to some embodiments, the plurality of charge and discharge states may include a charge state, a charge-rest state, a discharge state, and a discharge-rest state.

[0010] According to some embodiments, the processor may be further configured to select a combination of two or more states selected from the plurality of charge / discharge states that satisfies at least one of the conditions that the diagnostic rate is equal to or greater than a first threshold and the overdetection rate is equal to or less than a second threshold.

[0011] According to some embodiments, the battery test data may include at least one of the voltage data, current data, and temperature data of the battery being diagnosed, measured during the time interval of the charge-discharge test.

[0012] According to some embodiments, the preliminary diagnostic model may include at least one of the following: an SVC model, an Extra-Trees model, a CatBoost model, an SVM model, and an LSTM model.

[0013] According to some embodiments disclosed herein, a battery diagnostic method may include the steps of: measuring battery test data from a battery to be diagnosed via a sensor; dividing the battery test data into a plurality of charge / discharge state datasets via a processor based on a plurality of reference values ​​relating to a plurality of charge / discharge states; performing a preliminary failure diagnosis on each of the plurality of charge / discharge state datasets via the processor based on a preliminary diagnostic model; and determining the battery to be diagnosed as ultimately defective via the processor based on the results of the preliminary failure diagnosis.

[0014] According to some embodiments, the step of determining the final defect may include determining the battery under diagnosis as the final defect if two or more of the multiple charge / discharge state data sets are determined to be preliminary defects.

[0015] According to some embodiments, the battery diagnostic method may further include the step of calculating a diagnostic rate and a false positive rate by comparing the result of determining the target battery as ultimately defective with the actual presence or absence of defects in the target battery.

[0016] According to some embodiments, the plurality of charge and discharge states may include a charge state, a charge-rest state, a discharge state, and a discharge-rest state.

[0017] According to some embodiments, the battery diagnostic method may further include the step of selecting a combination of two or more states selected from the plurality of charge / discharge states that satisfies at least one of the conditions that the diagnostic rate is equal to or greater than a first threshold and the over-detection rate is equal to or less than a second threshold.

[0018] According to some embodiments, the battery test data may include at least one of the voltage data, current data, and temperature data of the battery being diagnosed, measured during the time interval of the charge-discharge test.

[0019] According to some embodiments, the preliminary diagnostic model may include at least one of the following: an SVC model, an Extra-Trees model, a CatBoost model, an SVM model, and an LSTM model. [Effects of the Invention]

[0020] According to the embodiments disclosed in this document, an algorithm is provided that divides battery test data into multiple charge / discharge states, and if two or more of the corresponding charge / discharge state datasets are determined to be defective, the battery under diagnosis is ultimately determined to be defective. Therefore, it is not limited to a specific charge / discharge pattern and can diagnose battery defects with high performance.

[0021] The technical effects of the embodiments disclosed herein are not limited to those mentioned above, and other effects not mentioned herein will be clearly understood by those skilled in the art from the disclosure herein. [Brief explanation of the drawing]

[0022] [Figure 1] This is a diagram for exemplifying elements constituting a battery diagnosis device according to some embodiments disclosed in this document. [Figure 2] This is a diagram for exemplifying battery test data according to some embodiments disclosed in this document. [Figure 3] This is a diagram for exemplifying a plurality of reference values representing a plurality of charge-discharge states according to some embodiments disclosed in this document. [Figure 4] This is a diagram for exemplifying a structure in which a charge state (Charge) according to some embodiments disclosed in this document is divided into a quick charge state (QC) and a constant current charge state (CC). [Figure 5] This is a diagram for exemplifying a plurality of charge-discharge state data sets according to some embodiments disclosed in this document. [Figure 6] This is a diagram for exemplifying model performance that a preliminary diagnosis model according to some embodiments disclosed in this document has for each of a plurality of charge-discharge states. [Figure 7] This is a diagram for exemplifying model performance that an ensemble algorithm according to some embodiments disclosed in this document has. [Figure 8] This is a diagram for exemplifying steps constituting a battery diagnosis method according to some embodiments disclosed in this document.

Best Mode for Carrying Out the Invention

[0023] Hereinafter, the embodiments described in this document will be described with reference to the accompanying drawings. However, this is not intended to limit the disclosure of this document to specific embodiments, and it should be understood to include various modifications, equivalents, and / or alternatives of the embodiments described in this document.

[0024] The embodiments and terminology used herein are not intended to limit the technical features described herein to any particular embodiment, but should be understood to include various modifications, equivalents, or substitutes of such embodiments. In relation to the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more such items unless the context clearly indicates otherwise.

[0025] In this document, each phrase such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B, or C,” “at least one of A, B, and C,” and “at least one of A, B, or C” may include any one of the items listed together with the phrase, or any possible combination thereof. Terms such as “first,” “second,” “first,” “second,” “A,” “B,” “(a),” or “(b)” may be used simply to distinguish one component from other components and, unless otherwise stated, do not limit the component in any other way (e.g., importance or order).

[0026] Wherever a component (e.g., the first) is referred to as being "coupled," "joined," or "connected" to another component (e.g., the second), with or without such terms, it means that the first component may be directly (e.g., wired or wirelessly) or indirectly (e.g., via the third component) connected to the other component.

[0027] Methods according to various embodiments disclosed herein may be provided in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of an instrument-readable storage medium (e.g., compact disc read-only memory, CD-ROM) or online (e.g., download or upload) via an application store or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily generated in an instrument-readable storage medium such as the memory of a manufacturer's server, an application store server, or an intermediary server.

[0028] According to the embodiments disclosed herein, each of the aforementioned components (e.g., a module or a program) may include one or more individuals, and some of the individuals may be separated and arranged in other components. According to the embodiments disclosed herein, one or more of the aforementioned components or operations may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the components of the multiple components before the integration. According to the embodiments disclosed herein, operations performed by a module, program, or other component may be performed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be performed in a different order, omitted, or one or more other operations may be added.

[0029] Figure 1 is a diagram illustrating elements that constitute a battery diagnostic device according to some embodiments disclosed in this document. Referring to Figure 1, the electronic device 10 may include the battery 100 to be diagnosed, and the battery diagnostic device 200 can diagnose whether or not the battery 100 is faulty. The battery 100 and the battery diagnostic device 200 can send and receive data from each other via wired or wireless communication.

[0030] The electronic device 10 may mean a device that uses power supplied by the battery 100 to be diagnosed. For example, the electronic device 10 may be an electric vehicle (EV) or hybrid electric vehicle (HEV) that uses electrical energy, and the battery 100 to be diagnosed may be a secondary battery installed in an electric vehicle (EV) or hybrid electric vehicle (HEV). Alternatively, the electronic device 10 may be a portable device such as a laptop computer, smartphone, or tablet PC, and can be interpreted as any other device having a battery recharging function.

[0031] The battery 100 to be diagnosed may be an electrical energy supply device that supplies power to the electronic device 10. For example, the battery 100 to be diagnosed may be a rechargeable secondary battery that is discharged by supplying power to the electronic device 10 and charged by a battery charger (not shown). According to some embodiments, the battery 100 to be diagnosed may include battery cells, battery modules, battery packs, and / or battery racks.

[0032] The battery diagnostic device 200 may be configured to diagnose whether the cells, modules, packs, and / or racks of the battery 100 to be diagnosed are faulty. The battery diagnostic device 200 may include, but is not limited to, sensors 210 and processors 220, and some components may be omitted from the battery diagnostic device 200, and other general-purpose elements may be further included in the battery diagnostic device 200.

[0033] According to some embodiments, the battery diagnostic device 200 can be integrated with a battery charging device (not shown). According to some embodiments, at least a portion of the sensor 210 and processor 220 may be mounted inside the electronic device 10 instead of the battery diagnostic device 200. That is, the functions performed by the battery diagnostic device 200 may, of course, be performed by a BMS (battery management system) inside the electronic device 10, but may also be performed by various devices such as servers, clouds, chargers, or chargers / dischargers.

[0034] The battery to be diagnosed 100 and the battery diagnostic device 200 can be electrically connected to each other via a wired and / or wireless data communication network. For example, the wired network may be based on LAN (local area network) communication or power line communication, and the wireless network may be based on local area networks such as Bluetooth®, WiFi (wireless fidelity), IrDA (infrared data association), and / or wide area networks such as cellular networks, 4G networks, and 5G networks. According to some embodiments, the communication method between the battery to be diagnosed 100 and the battery diagnostic device 200 may be an inter-device communication method such as a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface).

[0035] The sensor 210 can be configured to measure battery test data from the battery 100 under diagnosis during a charge-discharge test. According to the embodiment, a charge-discharge test may mean applying a specific form of voltage or current to inspect the cells, modules, packs, etc., of the battery 100 under diagnosis for defects. For example, the battery test data measured from the battery 100 under diagnosis by the sensor 210 may include at least one of the voltage data, current data, and temperature data of the battery 100 under diagnosis measured during the time interval of the charge-discharge test.

[0036] The sensor 210 may include at least one sensor for measuring battery-related data such as voltage, current, and / or temperature from the battery 100 under diagnosis.

[0037] The processor 220 may have a structure for executing instructions that enable the operation of the battery diagnostic device 200. The processor 220 can be implemented as an array of multiple logic gates for processing various operations or as a general-purpose microprocessor, and can consist of a single processor or multiple processors. For example, the processor 220 can be implemented in at least one form from among a microprocessor, CPU, GPU, and AP.

[0038] The processor 220 can be configured separately from or integrated with a memory module (not shown) configured to store instruction words, and can execute the instruction words stored in the memory module to process various operations. The memory module can store various data, instruction words, mobile applications, computer programs, etc. For example, the memory module can be implemented using non-volatile memory such as ROM, PROM, EPROM, EEPROM, flash memory, PRAM, MRAM, RRAM®, FRAM®, or volatile memory such as DRAM, SRAM, SDRAM, PRAM, RRAM, FeRAM, and can be implemented in the form of HDD, SSD, SD, Micro-SD, or a combination thereof.

[0039] The processor 220 can be configured to divide battery test data into multiple charge / discharge state datasets based on multiple reference values ​​that represent multiple charge / discharge states. According to the embodiment, the multiple reference values ​​may include voltage, current, or temperature values.

[0040] The battery 100 to be diagnosed may have one of several charge / discharge states. According to the embodiment, the type of charge / discharge state can be determined according to the voltage and current values ​​applied to the battery 100 to be diagnosed. For example, if the battery test data is the voltage measured from the battery 100 to be diagnosed during the charge / discharge test interval, the charge / discharge test interval can be divided into multiple intervals according to a specific criterion, and one charge / discharge state can be assigned to each of the multiple intervals. Here, the specific criterion for dividing the charge / discharge test interval into multiple intervals may be the same time interval, or other different criteria may be used.

[0041] For example, when four charge / discharge states are utilized, four reference values ​​can be set, and the charge / discharge state for each section can be determined based on which of the four reference values ​​is closest to a representative value, such as the average voltage value of each section that divides the charge / discharge test interval. A set of sections having the same charge / discharge state can become a dataset of that charge / discharge state, and therefore, the battery test data can be divided into four charge / discharge state datasets. For a more detailed explanation, please refer to Figures 2 to 5 below.

[0042] The processor 220 can be configured to perform preliminary fault diagnosis for each of multiple charge / discharge state datasets based on a preliminary diagnostic model. Here, the preliminary diagnostic model may be one or a combination of various predictive models for diagnosing battery failure. For example, the preliminary diagnostic model may include SVC models, Extra-Trees models, CatBoost models, SVM models, and LSTM models.

[0043] The processor 220 can diagnose the state of the battery 100 to be diagnosed based on the results of the preliminary failure diagnosis. According to one embodiment, the processor 220 can be configured to determine the battery 100 to be final failure if, as a result of the preliminary failure diagnosis, two or more of the multiple charge / discharge state data sets are determined to be preliminary failures. Here, final failure may mean failure determined by the ensemble algorithm. For example, if four charge / discharge states are utilized, the battery test data can be divided into four charge / discharge state data sets, and four preliminary diagnosis results (failure diagnosis T or F) can be obtained for each. Here, the battery 100 to be diagnosed can be determined to be final failure only if two or more preliminary diagnosis results are determined to be failures (T). On the other hand, the number of criteria for final failure determination can be set to one of two, three, or four, depending on performance conditions such as the minimum selection power and maximum overdetection rate of the ensemble algorithm.

[0044] From the above perspective, the processor 220 can be understood to diagnose the state of the battery 100 to be diagnosed based on an ensemble algorithm. According to the embodiment, the ensemble algorithm may mean an algorithm that uses multiple diagnostic results for multiple charge / discharge state datasets of a preliminary diagnostic model to determine whether the battery 100 to be diagnosed is ultimately defective.

[0045] In other words, the ensemble algorithm subdivides the fault diagnosis results into multiple charge / discharge states and uses combinations of these states, enabling stable selection capabilities and a high rate of over-detection even for common charge / discharge patterns. For this purpose, preliminary fault diagnosis can be performed for each of the multiple charge / discharge state datasets via a preliminary diagnostic model.

[0046] According to some embodiments, the processor 220 can be further configured to calculate a diagnostic rate and a false positive rate for determining that the battery 100 under diagnosis is ultimately defective.

[0047] For example, the battery 100 to be diagnosed may contain multiple battery cells, and it is possible to know in advance which of the multiple battery cells is defective. The diagnostic rate can be calculated according to whether the ensemble algorithm correctly diagnoses the presence or absence of defects in multiple battery cells, and the false detection rate can be calculated according to the ratio of non-defective cells that are mistakenly identified as defective.

[0048] According to some embodiments, the multiple charge / discharge states may include a charge state, a charge-rest state, a discharge state, and a discharge-rest state.

[0049] For example, the four charge / discharge states described above can indicate the current state of the battery 100 being diagnosed and can be distinguished based on the battery voltage. The Charge state can correspond to a high-intensity positive voltage, the Charge-rest state to a low-intensity positive voltage, the Discharge-rest state to a high-intensity negative voltage, and the Discharge state to a low-intensity negative voltage. According to some embodiments, the Charge state can be further divided into a Quick Charge (QC) state and an Equicurrent Charge (CC) state, allowing for a total of five charge / discharge states to be utilized.

[0050] According to some embodiments, the processor 220 can be further configured to select a combination of two or more states selected from a plurality of charge / discharge states that satisfies at least one of the following conditions: the diagnostic rate is equal to or greater than a first threshold and the overdetection rate is equal to or less than a second threshold.

[0051] For example, when four charge / discharge states are utilized, there can be six possible combinations of two charge / discharge states, four possible combinations of three charge / discharge states, and one possible combination of four charge / discharge states. From these 11 possible combinations, a combination with high model performance can be selected based on the diagnostic rate and the false positive rate. Specifically, if the preliminary diagnostic model is an SVM model, and the combination of the charge-rest state and the discharge-rest state shows a high diagnostic rate and a low false positive rate, then that combination can be matched to the SVM model and stored in the battery diagnostic device 200.

[0052] According to some embodiments, the preliminary diagnostic model may include at least one of the following: an SVC model, an Extra-Trees model, a CatBoost model, an SVM model, and an LSTM model.

[0053] The models exemplified above correspond to algorithms that have traditionally been used for battery failure diagnosis and can be used as preliminary diagnostic models in ensemble algorithms. As mentioned earlier, it is possible to analyze which combinations of charge and discharge states match each model. In addition to the exemplified models, various other algorithms and models that can be used for battery failure diagnosis can also be used as preliminary diagnostic models.

[0054] Figure 2 is a diagram illustrating battery test data according to some embodiments disclosed in this document. Referring to Figure 2, a graph 20 is shown that displays battery test data measured from the battery 100 under diagnosis during a charge-discharge test. The battery test data in graph 20 may be pre-processed data to which the process for the ensemble algorithm has not been applied. For example, the horizontal axis 21 of graph 20 may represent time, and the vertical axis 22 may represent voltage.

[0055] The battery test data in Graph 20 can be divided into multiple cycles. For example, each cycle may be any one of the first to third cycles. However, it is not limited to this, and the battery test data can show current or voltage and consist of more or fewer cycles. On the other hand, the battery test data may have an atypical general pattern rather than a combination of charge-discharge cycles.

[0056] Figure 3 is a diagram illustrating several reference values ​​that represent several charge and discharge states according to some embodiments disclosed in this document. Referring to Figure 3, Graph 30 is shown, which displays multiple reference values ​​representing multiple charge / discharge states. Each reference value in Graph 30 may represent the voltage level corresponding to each charge / discharge state.

[0057] For example, battery test data may be voltage data measured during a charge-discharge test, and four charge-discharge states can be utilized. For the four charge-discharge states, a charge state reference value 31, a post-charge rest state reference value 32, a discharge state reference value 34, and a post-discharge rest state reference value 33 can be set. Each charge-discharge state may represent a specific range of voltages, and the reference value can be set to an average value, median value, or any other representative value that represents that range.

[0058] Figure 4 is a diagram illustrating a structure in which the charge state (Charge) according to some embodiments disclosed in this document is divided into a rapid charge state (QC) and an equicurrent charge state (CC).

[0059] Referring to Figure 4, Graph 40 shows a structure in which the charge state is divided into a quick charge state (QC) and an equicurrent charge state (CC). In Graph 40, the charge state reference value 31 can be subdivided into a quick charge state reference value 41 and an equicurrent charge state reference value 42.

[0060] The charge state can be divided into a quick charge state (QC) corresponding to a higher voltage range and an equicurrent charge state (CC) corresponding to a lower voltage range, and the reference values ​​can be subdivided accordingly. Of the four charge / discharge states consisting of the charge state, charge-rest state, discharge state, and discharge-rest state, the charge state, which has the widest range, can be subdivided into two states, allowing the ensemble algorithm to operate more precisely.

[0061] Figure 5 is a diagram illustrating multiple charge / discharge state data sets according to some embodiments disclosed in this document. Referring to Figure 5, among the five charge / discharge state datasets corresponding to the five charge / discharge states, the equicurrent charging state dataset 51 and the post-charge rest state dataset 52 are shown.

[0062] Of the five charge / discharge state datasets, the three not shown in the diagram—namely, the rapid charge state dataset, the discharge state dataset, and the post-discharge idle state dataset—can be generated in a similar manner. Each charge / discharge state dataset may be a subset of the battery test data. For example, summing the five charge / discharge state datasets can result in the battery test data shown in Graph 20.

[0063] Figure 6 illustrates the model performance of a preliminary diagnostic model according to some embodiments disclosed in this document for each of several charge-discharge states. Referring to Figure 6, Table 60 is shown, which displays the diagnostic rate and overdetection rate that the preliminary diagnostic model has for each of several charge / discharge states. The first column 61 of Table 60 indicates the model name of the preliminary diagnostic model, the first row 62 indicates the charge / discharge state, and the second row 63 indicates the classification of the diagnostic rate and overdetection rate.

[0064] The charge / discharge states in the first row 62 may refer to three of the four charge / discharge states, which consist of the charge state, the charge-rest state after charging, the discharge state, and the discharge-rest state after discharging. Alternatively, the charge / discharge states in the first row 62 may refer to three of the five charge / discharge states, which consist of the rapid charge state (QC), the equicurrent charge state (CC), the charge-rest state after charging, the discharge state, and the discharge-rest state after discharging.

[0065] For example, the preliminary diagnostic model in column 61 could represent a conventionally used battery failure diagnostic model. As shown in the value range of Table 60, while some of the preliminary diagnostic models in column 61 show high diagnostic rates, it can be confirmed that there are no models that possess both a high diagnostic rate and a low false positive rate.

[0066] Figure 7 illustrates the model performance of an ensemble algorithm according to some embodiments disclosed in this document. Referring to Figure 7, Table 70 is shown to illustrate the model performance of the ensemble algorithm. For example, Table 70 can show an ensemble algorithm that determines a device to be ultimately defective if two or more of the three charge / discharge states in row 62 of Table 60 are determined to be pre-defective.

[0067] For example, of the three charge / discharge states in row 62, two or more states may be any one of the four combinations (state 1, state 2), (state 1, state 3), (state 2, state 3), and (state 1, state 2, state 3) that exhibit the highest performance. As shown in Table 70, when the preliminary diagnostic model is "SVM2", the ensemble algorithm can achieve a diagnostic rate of over 90% and a false positive rate of less than 10%.

[0068] Figure 8 is a diagram illustrating the steps that constitute a battery diagnostic method according to some embodiments disclosed in this document. Referring to Figure 8, the battery diagnostic method 800 may include steps 810 to 850. However, it is not limited to this, and some steps may be omitted or other general steps may be added, and the steps of the battery diagnostic method 800 may be performed in an order different from that shown.

[0069] The battery diagnostic method 800 can consist of steps processed sequentially in the battery diagnostic device 200. Therefore, even if some details are omitted below, the information described above regarding the battery diagnostic device 200 can be applied similarly to the battery diagnostic method 800.

[0070] Steps 810 to 850 of the battery diagnostic method 800 can be performed by the sensor 210 and processor 220 of the battery diagnostic device 200. In step 810, the battery diagnostic device 200 can measure battery test data from the battery to be diagnosed via a sensor.

[0071] In step 820, the battery diagnostic device 200 can, via the processor, divide the battery test data into multiple charge / discharge state data sets based on multiple reference values ​​for multiple charge / discharge states.

[0072] In step 830, the battery diagnostic device 200 can perform a preliminary fault diagnosis for each of the multiple charge / discharge state datasets based on a preliminary diagnostic model via the processor.

[0073] In step 840, the battery diagnostic device 200 can determine, via the processor, that the battery under diagnosis is ultimately defective based on the results of the preliminary failure diagnosis.

[0074] On the other hand, the battery diagnostic method 800 can be implemented in the form of a computer program stored on a computer-readable storage medium. That is, the computer program may include instructions for implementing the battery diagnostic method 800, and the instructions of the program may be stored on a computer-readable storage medium. The computer program may include a mobile application.

[0075] For example, computer-readable storage media can include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute computer program instructions, such as ROM, RAM, and flash memory. Computer program instructions can include machine code created by a compiler and high-level language code that can be executed by a computer using an interpreter or the like.

[0076] The terms “contain,” “constitute,” or “have,” as used above, mean “may contain,” and should not be interpreted as meaning that they may contain, unless otherwise specified, other components, rather than excluding them. All terms, including technical or scientific terms, should have the same meaning as that generally understood by a person of ordinary skill in the art to which the embodiments disclosed herein belong, unless otherwise specified. Commonly used terms, such as those defined in dictionaries, should be interpreted to be consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined herein.

[0077] The above description is merely illustrative of the technical concept disclosed herein, and any person with ordinary skill in the art to which the embodiments disclosed herein belong can make various modifications and variations without departing from the essential characteristics of the embodiments disclosed herein. Therefore, the embodiments disclosed herein are for illustrative purposes only, not to limit the technical concept of the embodiments disclosed herein, and the scope of the technical concept disclosed herein is not limited by such embodiments. The scope of protection of the technical concept disclosed herein must be interpreted according to the claims described below, and all technical concepts within an equivalent scope should be interpreted as being included in the scope of rights of this document. [Explanation of symbols]

[0078] 10:Electronic equipment 100: Battery to be diagnosed 200: Battery diagnostic device 210: Sensor 220: Processor

Claims

1. A sensor configured to measure battery test data from the battery to be diagnosed, A processor configured to divide the battery test data into multiple charge / discharge state datasets based on multiple reference values ​​for multiple charge / discharge states, perform a preliminary failure diagnosis on each of the multiple charge / discharge state datasets based on a preliminary diagnostic model, and determine the battery under diagnosis as ultimately defective based on the results of the preliminary failure diagnosis, Battery diagnostic device, including

2. When the processor determines that the final defect has occurred, The battery diagnostic device according to claim 1, configured to determine the battery to be diagnosed as the final defective battery when two or more of the plurality of charge / discharge state data sets are determined to be preliminary defective.

3. The battery diagnostic device according to claim 1, wherein the processor is further configured to calculate a diagnostic rate and an overdetection rate by comparing the result of determining the battery to be diagnosed as ultimately defective with the actual presence or absence of defects in the battery to be diagnosed.

4. The battery diagnostic device according to claim 3, wherein the plurality of charge / discharge states include a charging state, a paused state after charging, a discharge state, and a paused state after discharge.

5. The battery diagnostic device according to claim 4, wherein the processor is further configured to select a combination of two or more states selected from the plurality of charge / discharge states that satisfies at least one of the conditions that the diagnostic rate is equal to or greater than a first threshold and the over-detection rate is equal to or less than a second threshold.

6. The battery diagnostic device according to claim 1, wherein the battery test data includes at least one of the voltage data, current data, and temperature data of the battery to be diagnosed, measured during the time interval of the charge-discharge test.

7. The battery diagnostic device according to claim 1, wherein the preliminary diagnostic model includes at least one of the SVC model, extra tree model, CatBoost model, SVM model, and LSTM model.

8. The steps include measuring battery test data from the battery to be diagnosed via a sensor, The steps include: dividing the battery test data into multiple charge / discharge state datasets based on multiple reference values ​​for multiple charge / discharge states via a processor; The steps include performing a preliminary fault diagnosis on each of the multiple charge / discharge state datasets based on a preliminary diagnostic model via the aforementioned processor, The steps include determining, via the processor, that the battery to be diagnosed is ultimately defective based on the results of the preliminary failure diagnosis, Battery diagnostic methods, including those mentioned above.

9. The step of determining the final defect is as follows: The battery diagnostic method according to claim 8, further comprising the step of determining the battery to be diagnosed as the final defective battery when two or more of the plurality of charge / discharge state datasets are determined to be preliminary defective.

10. The battery diagnostic method according to claim 8, further comprising the step of calculating a diagnostic rate and a false detection rate by comparing the result of determining the battery to be diagnosed as having the final defect with the actual presence or absence of defects in the battery to be diagnosed.

11. The battery diagnostic method according to claim 10, wherein the plurality of charge / discharge states include a charging state, a paused state after charging, a discharge state, and a paused state after discharge.

12. The battery diagnostic method according to claim 11, further comprising the step of selecting a combination of two or more states selected from the plurality of charge / discharge states, such that the diagnostic rate is equal to or greater than a first threshold and the over-detection rate is equal to or less than a second threshold.

13. The battery diagnostic method according to claim 8, wherein the battery test data includes at least one of the voltage data, current data, and temperature data of the battery to be diagnosed, measured during the time interval of the charge-discharge test.

14. The battery diagnostic method according to claim 8, wherein the preliminary diagnostic model includes at least one of the SVC model, extra tree model, CatBoost model, SVM model, and LSTM model.

Images