Electronic device for detecting battery abnormalities and its operating method

Abstract

An electronic device according to an embodiment disclosed herein can acquire input data through a sensing circuit, acquire standardized data for the input data by standardizing each column vector of the input data, acquire judgment criteria data based on the standardized data, and determine a first abnormal state and / or a second abnormal state of each of M battery cells based on values ​​indicated by entries of each row vector of the judgment criteria data. The first abnormal state may be determined based on a learning-based model, and the second abnormal state may be determined based on a method other than the learning-based model.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] The embodiments disclosed in this document claim the benefit of priority based on Korean Patent Application No. 10-2022-0113110, filed on September 6, 2022, and all contents disclosed in the documents of this Korean patent application are incorporated herein by reference.

[0002] SUMMARY OF THE INVENTION The embodiments disclosed herein relate to an electronic device for detecting battery abnormalities and a method of operation thereof. [Background technology]

[0003] Secondary batteries, which are highly applicable to various products and have electrical properties such as high energy density, are widely used not only in portable devices but also in electric vehicles (EVs) and hybrid electric vehicles (HEVs) that are driven by electrical sources.

[0004] Currently widely used types of secondary batteries include lithium-ion batteries, lithium polymer batteries, nickel-cadmium batteries, nickel-metal hydride batteries, and nickel-zinc batteries. The operating voltage of such unit secondary battery cells, i.e., unit battery cells, is approximately 2.5 to 4.5 volts (V). Therefore, when a higher output voltage is required, a battery pack is constructed by connecting a plurality of battery cells in series. Alternatively, a battery pack may be constructed by connecting a number of battery cells in parallel depending on the required charge / discharge capacity of the battery pack. Therefore, the number of battery cells included in the battery pack may be variously set depending on the required output voltage or charge / discharge capacity. Summary of the Invention [Problem to be solved by the invention]

[0005] A battery pack may include a plurality of battery cells connected in series and / or parallel, and therefore, even if an abnormal battery cell exists among the plurality of battery cells, it may not be easy to detect the abnormality of the battery cell.

[0006] Therefore, a method for detecting an abnormal battery cell from among a plurality of battery cells may be required.

[0007] The technical problems of the embodiments disclosed in this document are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0008] According to one embodiment of the present disclosure, an electronic device includes a battery module including M battery cells, M being an integer greater than or equal to 2, a sensing circuit configured to acquire a status value associated with a status of each of the M battery cells, and a processor, wherein the processor acquires input data through the sensing circuit, the input data being representable as an M×N matrix, the M×N entries of the input data indicating a status value of each of the M battery cells, N indicating the number of time periods for acquiring the status value of each of the M battery cells, standardizing each column vector of the input data to acquire standardized data for the input data, the column vectors each consisting of entries acquired in the same unit time, acquiring judgment criterion data based on the standardized data, and determining a first status abnormality and / or a second status abnormality of each of the M battery cells based on values ​​indicated by each entry of a row vector of the judgment criterion data, wherein the first status abnormality may be determined based on a learning-based model, and the second status abnormality may be determined based on a method other than the learning-based model.

[0009] In one embodiment, the processor may identify row vectors among the row vectors of the judgment criteria data that have at least one value less than a reference critical normalized score, obtain an output vector for the identified row vector based on the learning-based model, and determine the first abnormal state of the battery cell corresponding to the identified row vector based on the output vector.

[0010] In one embodiment, the processor may obtain the standardized data by removing an offset of an entry of each of the row vectors of the input data and standardizing each of the column vectors of the input data from which the offset has been removed, wherein the offset is set for each of the row vectors of the input data, and the offset may be set to a value of a first entry among the entries of each of the row vectors of the input data.

[0011] In one embodiment, the processor may obtain the standardized data by flattening entries of each of the row vectors of the input data and standardizing each of the column vectors of the flattened input data.

[0012] In one embodiment, the processor acquires an interval average value of each row vector of the standardized data as the judgment criteria data, and judges the first abnormal state and / or the second abnormal state of each of the M battery cells based on the interval average value of each row vector of the judgment criteria data, wherein the interval average value is an average value of entries of each row vector of the standardized data included in different time intervals, and the time intervals may not overlap with each other.

[0013] In one embodiment, the processor may acquire the amount of change in each entry of a row vector of the standardized data as the judgment criteria data, and determine the first status abnormality and / or the second status abnormality for each of the M battery cells based on the amount of change in the entry of each of the row vectors of the judgment criteria data.

[0014] In one embodiment, the processor may identify a sum value of the entries of each of the row vectors of the criteria data, identify a row vector among the row vectors of the criteria data having the sum value less than a critical sum value, and determine that the battery cell corresponding to the identified row vector is in the second abnormal state.

[0015] In one embodiment, the learning-based model is an autoencoder, and the autoencoder can be trained based on state values ​​of normal battery cells.

[0016] According to one embodiment of the present disclosure, a method for operating an electronic device includes: acquiring input data through a sensing circuit of the electronic device; the input data may be expressed as an M×N matrix, where the M×N entries of the input data indicate status values ​​of M battery cells of the electronic device, and N indicates the number of time periods for acquiring the status values ​​of the M battery cells; acquiring standardized data for the input data by standardizing each column vector of the input data; each column vector is composed of entries acquired in the same unit time; acquiring judgment criteria data based on the standardized data; and determining a first status abnormality and / or a second status abnormality of each of the M battery cells based on values ​​indicated by each entry of the row vector of the judgment criteria data; the first status abnormality may be determined based on a learning-based model, and the second status abnormality may be determined based on a method other than the learning-based model.

[0017] In one embodiment, the operation of determining the first status abnormality and / or the second status abnormality may include an operation of identifying a row vector having at least one value less than a reference critical normalized score among the row vectors of the determination criteria data, an operation of obtaining an output vector for the identified row vector based on the learning-based model, and an operation of determining the first status abnormality of the battery cell corresponding to the identified row vector based on the output vector.

[0018] In one embodiment, the operation of obtaining the standardized data includes an operation of removing an offset of an entry of each of the row vectors of the input data, and an operation of obtaining the standardized data by standardizing each of the column vectors of the input data from which the offset has been removed, wherein the offset is set for each of the row vectors of the input data, and the offset may be set to a value of a first entry among the entries of each of the row vectors of the input data.

[0019] In one embodiment, obtaining the standardized data may include flattening entries of each of the row vectors of the input data, and standardizing each of the column vectors of the flattened input data to obtain the standardized data.

[0020] In one embodiment, the operation of acquiring the judgment criteria data includes an operation of acquiring interval average values ​​of each row vector of the standardized data as the judgment criteria data, and the operation of determining the first abnormal state and / or the second abnormal state of each of the M battery cells based on the interval average values ​​of each row vector of the judgment criteria data, wherein the interval average values ​​are average values ​​of entries of each row vector of the standardized data included in different time intervals, and the time intervals may not overlap with each other.

[0021] In one embodiment, the operation of acquiring the judgment criteria data includes an operation of acquiring a change amount of each entry of a row vector of the standardized data as the judgment criteria data, and the operation of determining the first status abnormality and / or the second status abnormality may include an operation of determining the first status abnormality and / or the second status abnormality of each of the M battery cells based on the change amount of the entry of each of the row vectors of the judgment criteria data.

[0022] In one embodiment, the operation of determining the first abnormal status and / or the second abnormal status may include an operation of identifying a sum value of the entries of each of the row vectors of the determination criteria data, an operation of identifying a row vector among the row vectors of the determination criteria data having the sum value less than a critical sum value, and an operation of determining that the battery cell corresponding to the identified row vector is in the second abnormal status. [Effects of the Invention]

[0023] The electronic device and the operating method thereof according to various embodiments disclosed herein can detect an abnormal battery cell from among a plurality of battery cells.

[0024] The effects of the electronic device for detecting battery abnormalities and the operating method thereof disclosed in this document are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the disclosure of this document. [Brief explanation of the drawings]

[0025] [Figure 1] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments of the present disclosure. [Figure 2] 10 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure. [Figure 3] 10 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure. [Figure 4a] FIG. 10 is a diagram illustrating an example of input data. [Figure 4b] FIG. 10 is a diagram illustrating smoothed input data. [Figure 4c] FIG. 10 is a diagram illustrating input data from which an offset has been removed. [Figure 4d] FIG. 10 is a diagram illustrating standardized data of input data from which an offset has been removed. [Figure 4e] FIG. 10 is a diagram illustrating standardized data from which an offset has been removed. [Figure 4f] FIG. 10 is a diagram illustrating an example of section average data of standardized data. [Figure 4g] FIG. 10 is a diagram illustrating an example of change amount data of section average data. [Figure 5] 10 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure. [Figure 6] 10 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure.

[0026] In connection with the description of the figures, the same or similar reference numerals may be used for the same or similar components. DETAILED DESCRIPTION OF THE INVENTION

[0027] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, this is not intended to limit the present invention to the specific embodiments, but should be understood as including various modifications, equivalents, and / or alternatives of the embodiments of the present invention.

[0028] The embodiments and terms used in this document are not intended to limit the technical features described in this document to a specific embodiment, but should be understood to include various modifications, equivalents, or alternatives of the embodiment. In connection with the description of the figures, 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 of the item, unless otherwise clearly stated in the relevant context.

[0029] In this document, each of the phrases "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 that phrase, or all possible combinations thereof. Terms such as "first," "second," "primary," "second," "A," "B," "(a)," or "(b)" may be used merely to distinguish one element from other elements, and do not limit the element in other respects (e.g., importance or order) unless specifically stated to the contrary.

[0030] When this document refers to a (e.g., first) component being "coupled," "coupled," or "connected" to another (e.g., second) component, with or without the terms "functionally" or "communicatively," it means that the component can be coupled to the other component directly (e.g., by wire or wirelessly) or indirectly (e.g., via a third component).

[0031] Methods according to various embodiments disclosed herein may be provided in a computer program product. The computer program product may be traded between a seller and a buyer as a commodity. The computer program product may be distributed in the form of a machine-readable recording medium (e.g., a compact disc read-only memory (CD-ROM)) or may be distributed online (e.g., downloaded or uploaded) through 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 on a machine-readable recording medium, such as the memory of a manufacturer's server, an application store server, or an intermediary server.

[0032] According to the embodiments disclosed herein, each of the aforementioned components (e.g., modules or programs) may include one or more entities, and some of the entities may be located separately 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 additional components or operations may be added. Generally or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In such cases, 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 respective components of the multiple components prior to the integration. According to the embodiments disclosed herein, the 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 additional operations may be added.

[0033] FIG. 1 is a block diagram of an electronic device 101 according to one embodiment of the present disclosure.

[0034] As shown in FIG. 1 , the electronic device 101 may include a battery module 110, a sensor circuit 120, a communication circuit 130, a memory 140, and a processor 150. According to an embodiment, at least one component (e.g., the battery module 110) of the electronic device 101 shown in FIG. 1 may be replaced with another component (e.g., a battery cell including multiple battery modules 110). According to an embodiment, at least one component (e.g., the battery module 110) of the electronic device 101 shown in FIG. 1 may be composed of multiple components. According to an embodiment, at least one component (e.g., the sensor circuit 120 or the communication circuit 130) of the electronic device 101 shown in FIG. 1 may be excluded from the electronic device 101. According to an embodiment, the electronic device 101 may further include at least one component (e.g., a power unit (e.g., a motor), a display, an input device, or an output device) other than the components shown in FIG. 1 .

[0035] In one embodiment, the electronic device 101 may be a battery management system (BMS). When the electronic device 101 is embodied as a battery management system, the electronic device 101 may supply power from the battery module 110 to an external component (e.g., a motor).

[0036] In one embodiment, the electronic device 101 may be a battery swapping station (BSS). When the electronic device 101 is embodied as a battery swapping station, the electronic device 101 may include multiple slots for storing and / or charging multiple battery modules 110.

[0037] In one embodiment, the battery module 110 can provide power to one or more components of the electronic device 101. In one embodiment, the battery module 110 can be detachable from the electronic device 101.

[0038] In one embodiment, the battery module 110 may include one or more battery cells 111, 113, or 115. The one or more battery cells 111, 113, or 115 may be included in the battery module 110 in a state where they are electrically connected to each other. For example, the one or more battery cells 111, 113, or 115 may be connected to each other in series and / or in parallel. Depending on the embodiment, the one or more battery cells 111, 113, or 115 may be included in the battery module 110 in a state where they are electrically separated from each other.

[0039] In one embodiment, the sensor circuit 120 may acquire information related to the battery module 110. In one embodiment, the sensor circuit 120 may acquire a value (or information) related to a status of each of one or more battery cells 111, 113, or 115. In one embodiment, the value related to the status may indicate one or more values ​​for the voltage, current, resistance, state of charge (SOC), state of health (SOH), or temperature of the battery cell, or a combination thereof. Hereinafter, the value related to the status may be referred to as a "status value."

[0040] In one embodiment, the sensor circuit 120 can provide information (eg, status values) of one or more battery cells 111, 113, or 115, respectively, to the processor 150.

[0041] In one embodiment, the communication circuit 130 can establish a wired communication channel and / or a wireless communication channel between the electronic device 101 and the external electronic device 102, and send / receive data to / from the external electronic device 102 through the established communication channel.

[0042] In one embodiment, the communication circuitry 130 can perform communication based on at least one radio access technology (RAT). In one embodiment, the communication circuitry 130 can send / receive data to / from the external electronic device 102 using at least one RAT.

[0043] In one embodiment, memory 140 may include volatile memory and / or non-volatile memory.

[0044] In one embodiment, memory 140 may store data used by at least one component of electronic device 101 (e.g., processor 150 or sensor circuitry 120). For example, the data may include software (or associated instructions), input data, or output data. In one embodiment, the instructions, when executed by processor 150, may cause electronic device 101 to perform the operations defined by the instructions.

[0045] In one embodiment, processor 150 can execute software to control at least one other component (e.g., hardware or software component) of electronic device 101 coupled to processor 150 and perform various data processing or calculations.

[0046] A method for determining whether one or more battery cells 111, 113, or 115 included in the battery module 110 are abnormal, in which the electronic device 101 according to an embodiment of the present disclosure is described below.

[0047] In one embodiment, the electronic device 101 may acquire status values ​​(e.g., one or more values ​​related to voltage, current, resistance, state of charge, state of health, or temperature) of one or more battery cells 111, 113, or 115. In one embodiment, the electronic device 101 may acquire status values ​​of one or more battery cells 111, 113, or 115 during a specified time interval (e.g., 180 seconds). In one embodiment, the electronic device 101 may acquire status values ​​of one or more battery cells 111, 113, or 115 at specified time periods (e.g., 0.1 seconds) during the specified time interval. For example, the electronic device 101 may acquire voltage values ​​of one or more battery cells 111, 113, or 115. As another example, the electronic device 101 may acquire current values ​​of one or more battery cells 111, 113, or 115.

[0048] In one embodiment, the status values ​​of each of the one or more battery cells 111, 113, or 115 acquired at specified time periods during a specified time interval may be referred to as "input data." In one embodiment, the input data may be represented as a matrix (e.g., an M×N matrix) consisting of N values ​​for each of the M battery cells 111, 113, or 115. For example, the input data may consist of N voltage values ​​for each of the M battery cells 111, 113, or 115. As another example, the input data may consist of N values ​​for one of a current, a resistance, a state of charge, a state of health, or a temperature for each of the M battery cells 111, 113, or 115. For example, an entry of the input data may indicate a voltage value for each of the battery cells 111, 113, or 115. As another example, an entry of the input data may indicate a value for one of a resistance, a state of charge, a state of health, or a temperature for each of the M battery cells 111, 113, or 115. Here, M may be the number of battery cells 111, 113, or 115, and N may be the number of time periods for acquiring the status values ​​of the battery cells 111, 113, or 115. For example, if the number of battery cells 111, 113, or 115 is 100, the specified time interval is 180 seconds, and the specified time period is 0.1 seconds, M may be 100 and N may be 1800.

[0049] In one embodiment, the input data (D input ) may be expressed as the following Equation 1: [Formula 1]

number

[0050] In one embodiment, the electronic device 101 can obtain standardized data based on the input data. In one embodiment, the standardized data for the arbitrary matrix data can be obtained based on standardization between the entries of each column vector of the arbitrary matrix data. In one embodiment, the standardization can be converting values ​​into standardized scores (or Z scores). For example, the standardization can be based on the following Equation 2: [Formula 2]

number

[0051] In one embodiment, the electronic device 101 may determine a first abnormal state and / or a second abnormal state of the battery cell 111, 113, or 115 based on the standardized data. In one embodiment, the electronic device 101 may determine a first abnormal state and / or a second abnormal state of the battery cell 111, 113, or 115 using reference data based on the standardized data. In one embodiment, the reference data may be the standardized data itself. In one embodiment, the reference data may be data obtained by performing data processing (e.g., offset removal, interval averaging, variation acquisition, and / or concatenation) on the standardized data. In one embodiment, the first abnormal state may refer to an abnormal state in which an instantaneous voltage of the battery cell drops when the battery cell is charged. In one embodiment, the second abnormal state may refer to an abnormal state in which a slope of the voltage of the battery cell decreases (or becomes low) when the battery cell is charged. In one embodiment, the first abnormal state may be determined based on a learning-based model, and the second abnormal state may be determined based on a method other than the learning-based model (e.g., a rule-based model).

[0052] The operation of the electronic device 101 to determine whether the battery cell 111, 113, or 115 is in the first abnormal state will be described below.

[0053] In one embodiment, the electronic device 101 may identify row vectors including entries with values ​​equal to or less than the reference critical standardized score among the entries of each row vector of the criterion data. According to an embodiment, the electronic device 101 may identify row vectors including entries with values ​​equal to or greater than the reference critical standardized score among the entries of each row vector of the criterion data. According to an embodiment, the electronic device 101 may identify row vectors including entries with values ​​outside the range of the reference critical standardized score among the entries of each row vector of the criterion data. In one embodiment, the reference critical standardized score may be a score determined experimentally to extract possible candidates for the first status abnormality. Hereinafter, it will be illustrated that the electronic device 101 identifies row vectors including entries with values ​​equal to or less than the reference critical standardized score among the entries of each row vector of the criterion data.

[0054] In one embodiment, the electronic device 101 may obtain an output vector of a learning-based model based on a row vector of reference data. In one embodiment, the electronic device 101 may obtain an output vector for a row vector including entries having a value equal to or less than a reference critical normalized score based on the learning-based model. In one embodiment, the learning-based model may be an autoencoder. In one embodiment, the autoencoder may be an artificial neural network trained to reconstruct reference data according to normal behavior. In one embodiment, the autoencoder may be an artificial neural network trained in an unsupervised manner. In one embodiment, the autoencoder may include an encoder and a decoder. In one embodiment, the encoder of the autoencoder may compress the input to a lower dimension, and the decoder of the autoencoder may restore the compressed output of the autoencoder to the previous dimension. As a result, the input and output of the autoencoder may have the same dimension, and the output of the autoencoder may have a form that includes a reconstruction error (or reconstruction loss) at the input of the autoencoder.

[0055] In one embodiment, the electronic device 101 may determine a first abnormal state of the battery cell based on an output vector of the learning-based model. In one embodiment, the electronic device 101 may determine a first abnormal state of the battery cell based on a restoration error of the autoencoder. In one embodiment, the restoration error for an arbitrary row vector may be a root mean square (RMS) value of a vector obtained by subtracting the output vector for the arbitrary row vector from the arbitrary row vector.

[0056] In one embodiment, the electronic device 101 may identify row vectors of the criteria data whose restoration errors exceed a specified reference restoration error. In one embodiment, the electronic device 101 may determine that a battery cell associated with a row vector whose restoration error exceeds the reference restoration error is in a first abnormal state. In one embodiment, the reference restoration error may be an error experimentally determined to determine the first abnormal state.

[0057] The operation of the electronic device 101 to determine whether the battery cell 111, 113, or 115 is in the second abnormal state will be described below.

[0058] In one embodiment, the electronic device 101 can determine a second abnormal state of the battery cell 111, 113, or 115 based on the sum of the entries of each row vector of the determination criteria data. In one embodiment, the electronic device 101 can identify row vectors whose sum is less than a specified reference sum. In some embodiments, the electronic device 101 can identify row vectors whose sum is greater than or equal to a specified reference sum. In some embodiments, the electronic device 101 can identify row vectors whose sum is outside a specified reference sum range. In the following example, the electronic device 101 identifies row vectors whose sum is greater than or equal to a specified reference sum. In one embodiment, the reference sum may be a value determined experimentally to determine a second abnormal state.

[0059] In one embodiment, the electronic device 101 may determine that a battery cell associated with a row vector whose sum is equal to or less than a specified reference sum is in a second abnormal state.

[0060] In one embodiment, when a battery cell is identified as having an abnormal state, the electronic device 101 can provide a notification to a user via an output device (or a display, communication circuitry 130). In one embodiment, the notification provided to the user can include a notification to prompt the user to check the battery cell for an abnormality, a notification to prompt the user to replace the battery cell, or a combination thereof.

[0061] 1 illustrates an example in which the electronic device 101 acquires standardized data of input data and determines a first status abnormality and / or a second status abnormality based on the judgment criteria data of the standardized data, but this is merely an example. Depending on the embodiment, the electronic device 101 may perform a process to process the input data and determine a first status abnormality and / or a second status abnormality based on the processed standardized data of the input data. Also, the electronic device 101 may perform a process to process the standardized data of the input data and determine a first status abnormality and / or a second status abnormality based on the processed standardized data (or judgment criteria data). Depending on the embodiment, processing of the input data and / or processing of the standardized data may be selectively performed.

[0062] An example in which the electronic device 101 according to an embodiment of the present disclosure processes input data will be described below.

[0063] In one embodiment, the electronic device 101 may obtain smoothed data (or moving average data) of the input data. In one embodiment, the smoothing of the arbitrary matrix data may be performed between each entry of a row vector of the arbitrary matrix data. For example, the smoothing of the arbitrary matrix data may be performed based on the following Equation 3: [Formula 3]

number

[0064] In one embodiment, the electronic device 101 can obtain smoothed data (or moving average data) of the input data, obtain standardized data of the obtained smoothed data (or moving average data), and determine the first status abnormality and / or the second status abnormality based on the standardized data.

[0065] In one embodiment, the electronic device 101 can obtain data in which an offset has been removed from the input data. In one embodiment, an offset for the arbitrary matrix data may be set for each row vector of the arbitrary matrix data. In one embodiment, the offset for the arbitrary matrix data may be the value of the first entry of each row vector of the arbitrary matrix data. In one embodiment, removing the offset for the arbitrary matrix data may be by subtracting the offset for each row vector from the entry of each row vector of the arbitrary matrix data.

[0066] In one embodiment, the electronic device 101 can acquire data from which an offset has been removed from the input data, acquire standardized data from the acquired offset-removed data, and determine the first status abnormality and / or the second status abnormality based on the standardized data.

[0067] In one embodiment, the electronic device 101 may sequentially perform offset removal and smoothing on the input data. In one embodiment, the electronic device 101 may acquire standardized data of the acquired data by sequentially performing offset removal and smoothing, and determine the first state abnormality and / or the second state abnormality based on the standardized data. Depending on the embodiment, offset removal may be performed first on the input data and then smoothing may be performed, or offset removal may be performed first on the input data and then smoothing.

[0068] The following describes an example in which the electronic device 101 according to an embodiment of the present disclosure processes the standardized data to obtain the reference data. The standardized data described below may be the standardized data of the input data, the standardized data of the smoothed input data, the standardized data of the input data from which the offset has been removed, or the standardized data of the input data from which the offset has been removed and which has been smoothed.

[0069] In one embodiment, the electronic device 101 can obtain the reference data by removing an offset from the standardized data. In one embodiment, the electronic device 101 can determine the first status abnormality and / or the second status abnormality based on the standardized data from which the offset has been removed (i.e., the reference data).

[0070] In one embodiment, the electronic device 101 may obtain interval average data of the standardized data as the criterion data. In one embodiment, the interval average may be obtained by averaging each entry of a row vector of the arbitrary matrix data for a specified time interval (e.g., 18 seconds). In one embodiment, the time intervals may not overlap with each other. For example, if the specified time interval is 18 seconds, the specified time interval is 180 seconds, and the specified time period is 0.1 seconds, the number of columns of the interval average data may be 10, and the columns of the interval average data may represent the average of the 180 columns of the standardized data.

[0071] In one embodiment, the electronic device 101 can determine the first abnormal status and / or the second abnormal status based on the interval average data (i.e., the determination criteria data).

[0072] In one embodiment, the electronic device 101 can acquire change amount data of the standardized data as the criterion data. In one embodiment, the change amount may be a difference value between adjacent entries of each row vector of the arbitrary matrix data. For example, the change amount of an arbitrary entry may be a value obtained by subtracting the value of the entry before the arbitrary entry from the value of the arbitrary entry.

[0073] In one embodiment, the electronic device 101 can determine the first abnormal condition and / or the second abnormal condition based on the variation data (i.e., the determination criterion data).

[0074] In one embodiment, the electronic device 101 may obtain concatenated data of the standardized data as the criterion data. In one embodiment, the concatenation of the arbitrary matrix data may be performed by concatenating the arbitrary matrix data with other matrix data in a column direction. In one embodiment, the concatenation of the arbitrary matrix data may be performed by sequentially concatenating the arbitrary matrix data excluding the first column, the first column of the arbitrary matrix data, and the last column of the arbitrary matrix data. In one embodiment, the electronic device 101 may determine the first abnormal status and / or the second abnormal status based on the concatenated data (i.e., the criterion data).

[0075] In one embodiment, the electronic device 101 may acquire the criterion data by sequentially performing offset removal, interval averaging, variation acquisition, and concatenation on the standardized data. In one embodiment, the electronic device 101 may determine the first abnormal condition and / or the second abnormal condition based on the criterion data acquired by sequentially performing offset removal, interval averaging, variation acquisition, and concatenation on the standardized data. The order of the processes of offset removal, interval averaging, variation acquisition, and concatenation on the standardized data may be set differently depending on the embodiment.

[0076] 2 is a flowchart illustrating the operation of an electronic device according to an embodiment of the present disclosure. The operation of FIG. 2 may be performed by the electronic device 101 shown in FIG.

[0077] As shown in FIG. 2 , at operation 210, the electronic device 101 may acquire input data. In one embodiment, the input data may include status values ​​of each of one or more battery cells 111, 113, or 115 acquired at specified time periods during a specified time interval. In one embodiment, the input data may be represented as a matrix (e.g., an M×N matrix) consisting of N values ​​for each of the M battery cells 111, 113, or 115. For example, an entry of the input data may indicate a voltage value for each of the battery cells 111, 113, or 115. As another example, an entry of the input data may indicate a value for one of the resistance, state of charge, state of health, or temperature for each of the battery cells 111, 113, or 115. Here, M may be the number of battery cells 111, 113, or 115, and N may be the number of time periods for acquiring the status values ​​of the battery cells 111, 113, or 115.

[0078] In operation 220, the electronic device 101 may obtain the standardized data. In one embodiment, the standardized data may be data standardized between entries of each of the column vectors of the input data.

[0079] In operation 225, the electronic device 101 may acquire criteria data based on the standardized data. In one embodiment, the criteria data may be the standardized data itself. In one embodiment, the criteria data may be data that has undergone data processing (e.g., offset removal, interval averaging, variation acquisition, and / or concatenation) on the standardized data.

[0080] In operation 230, the electronic device 101 can determine a first abnormal state. In one embodiment, the electronic device 101 can obtain an output vector of the learning-based model based on the row vector of the criteria data. In one embodiment, the electronic device 101 can determine a first abnormal state of the battery cell based on the output vector of the learning-based model.

[0081] In one embodiment, the electronic device 101 can determine the first abnormal state of the battery cell based on the restoration error of the autoencoder. In one embodiment, the restoration error for an arbitrary row vector can be an RMS value of a vector obtained by subtracting the output vector for the arbitrary row vector from the arbitrary row vector.

[0082] In one embodiment, the electronic device 101 may identify row vectors in the criteria data whose restoration errors exceed a specified reference restoration error, and may determine that a battery cell associated with the row vectors whose restoration errors exceed the reference restoration error is in a first abnormal state.

[0083] At operation 240, the electronic device 101 may determine a second abnormal state. In one embodiment, the electronic device 101 may determine a second abnormal state of the battery cell 111, 113, or 115 based on the sum of the entries of each row vector of the determination criteria data. In one embodiment, the electronic device 101 may identify row vectors whose sum is less than or equal to a specified reference sum. In one embodiment, the electronic device 101 may determine that a battery cell associated with a row vector whose sum is less than or equal to a specified reference sum is in a second abnormal state.

[0084] 2 illustrates an example in which the electronic device 101 acquires standardized data of input data and determines a first status abnormality and / or a second status abnormality based on the criterion data of the standardized data, but this is merely an example. Depending on the embodiment, the electronic device 101 may perform a process for processing the input data and determine a first status abnormality and / or a second status abnormality based on the processed standardized data of the input data. Furthermore, the electronic device 101 may determine a first status abnormality and / or a second status abnormality based on the criterion data acquired by performing a process for processing the standardized data of the input data. Depending on the embodiment, processing of the input data and / or processing of the standardized data may be selectively performed.

[0085] In one embodiment, the method by which the electronic device 101 processes the input data may include removing an offset from the input data and smoothing the input data. In one embodiment, the method by which the electronic device 101 processes the standardized data to obtain the reference data may include removing an offset from the standardized data, averaging the standardized data over an interval, and obtaining a variation from the standardized data.

[0086] 2 shows that both operations 230 and 240 are performed, but this is merely an example. Depending on the embodiment, operations 230 and 240 may be selectively performed. In some embodiments, either operation 230 or operation 240 may not be performed. For example, to determine only a first abnormal status, the electronic device 101 may perform operation 230 but not perform operation 240. As another example, to determine only a second abnormal status, the electronic device 101 may perform operation 240 but not perform operation 230.

[0087] FIG. 3 is a flowchart illustrating the operation of an electronic device according to an embodiment of the present disclosure. FIG. 4a is a diagram illustrating input data. FIG. 4b is a diagram illustrating smoothed input data. FIG. 4c is a diagram illustrating input data with offset removed. FIG. 4d is a diagram illustrating standardized data of the input data with offset removed. FIG. 4e is a diagram illustrating standardized data with offset removed. FIG. 4f is a diagram illustrating section average data of the standardized data. FIG. 4g is a diagram illustrating variation data of the section average data. Operations 310, 320, and 330 of FIG. 3 may be included in operation 220 of FIG. 2. Operations 340, 350, and 360 of FIG. 3 may be included in operation 225 of FIG. 2. The operations of FIG. 3 may be performed by the electronic device 101 shown in FIG. 1. In one embodiment, the variation data of FIG. 4g may be understood as criterion data obtained by the operations of FIG. 3.

[0088] As shown in FIG. 3, in operation 310, the electronic device 101 may perform smoothing on the input data.

[0089] In one embodiment, the input data may include status values ​​for each of one or more battery cells 111, 113, or 115 obtained at specified time periods during a specified time interval. In one embodiment, the input data may be represented as a matrix (e.g., an M×N matrix) of N values ​​for each of M battery cells 111, 113, or 115. In one embodiment, the status values ​​may be one or more values ​​related to voltage, current, resistance, state of charge, state of health, or temperature.

[0090] 4a, the graph 401 may show input data 410. The input data 410 may be voltage values ​​of each of the M battery cells 111, 113 or 115 acquired during a time interval of 180 seconds.

[0091] In one embodiment, smoothing of the input data 410 may be performed between entries of each row vector of the input data. For example, smoothing of the input data 410 may be performed based on Equation 3.

[0092] 4b, graph 402 can show smoothed input data 420. Compared to graph 401, graph 402 shows that smoothing has reduced noise in input data 420.

[0093] At operation 320, the electronic device 101 may remove the offset of the smoothed input data 420. In one embodiment, the offset of the smoothed input data 420 may be set for each row vector of the smoothed input data 420. In one embodiment, the offset for the smoothed input data 420 may be the value of the first entry of each row vector of the smoothed input data 420. In one embodiment, removing the offset for the smoothed input data 420 may be by subtracting the offset of each row vector from the entry of each row vector of the smoothed input data 420.

[0094] 4c, graph 403 can show the offset-removed input data 430. Compared to graph 402, graph 403 shows that the first value of input data 430 starts from 0.

[0095] In operation 330, the electronic device 101 may perform standardization on the offset-removed input data 430. In one embodiment, the standardized data for the input data 430 may be obtained based on standardization between entries of each column vector of the input data 430. In one embodiment, the standardization may be converting values ​​into standardized scores (or Z scores). For example, the standardization may be based on Equation 2 above.

[0096] As shown in FIG. 4 d , the graph 404 may show normalized data 440 of the input data 430 .

[0097] In operation 340 , the electronic device 101 may remove the offset of the standardized data 440 .

[0098] In one embodiment, the offset of the standardized data 440 may be set for each row vector of the standardized data 440. In one embodiment, the offset for the standardized data 440 may be the value of the first entry of each row vector of the standardized data 440. In one embodiment, removing the offset for the standardized data 440 may be subtracting the offset of each row vector from the entry of each row vector of the standardized data 440.

[0099] As shown in FIG. 4e, the graph 405 can show normalized data 450 with the offset removed.

[0100] In operation 350, the electronic device 101 may perform interval averaging of the offset-removed standardized data 450. In one embodiment, the interval averaging may be the average of each entry in the row vector of the standardized data 450 over a specified time interval (e.g., 18 seconds). For example, if the specified time interval is 18 seconds, the specified time interval is 180 seconds, and the specified time period is 0.1 seconds, the number of columns of the interval average data may be 10, and the columns of the interval average data may represent the average of the 180 columns of the standardized data.

[0101] As shown in Figure 4f, graph 406 can show interval average data 460. Compared to graph 405 in Figure 4e, graph 406 shows 10 intervals.

[0102] In operation 360, the electronic device 101 can obtain a change amount for the interval average data 460. In one embodiment, the change amount may be a difference value between adjacent entries in each row vector of the interval average data 460. For example, the change amount for a given entry may be the value of the given entry minus the value of the entry preceding the given entry.

[0103] As shown in Fig. 4g, graph 407 may show variation data 470. It can be seen that there are nine intervals in graph 407 compared to graph 407 in Fig. 4g. This may be because there is one entry (e.g., the last entry) for which no variation is obtained in graph 407.

[0104] Thereafter, the electronic device 101 can determine the first abnormal condition and / or the second abnormal condition of the battery cell 111 , 113 or 115 based on the variation data 470 .

[0105] 5 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure. The operation of FIG. 5 may be included in operation 230 of FIG. 2. The operation of FIG. 5 may be performed by the electronic device 101 shown in FIG. 1.

[0106] The operations of FIG. 5 may be performed for each row vector.

[0107] As shown in FIG. 5, in operation 510, the electronic device 101 may determine whether a row vector includes an entry with a value equal to or less than the reference critical normalized score. In one embodiment, the electronic device 101 may identify row vectors including entries with values ​​equal to or less than the reference critical normalized score among the entries of the row vectors of the criterion data. In some embodiments, the row vector may be the row vector of the variation data 470 shown in FIG. 4f. In some embodiments, the row vector may be a row vector of data obtained by concatenating the variation data 470. In one embodiment, the row vector may be a row vector of data obtained by sequentially concatenating the variation data 470 excluding the first column, the first column of the variation data 470, and the last column of the variation data 470.

[0108] At operation 520, the electronic device 101 can obtain an output vector of row vectors based on a learning-based model. In one embodiment, the learning-based model can be an autoencoder. In one embodiment, the autoencoder can be an artificial neural network trained to reconstruct reference data according to normal behavior. In one embodiment, the output vector has the same dimensions as the row vector and can include a reconstruction error (or reconstruction loss).

[0109] At operation 530, the electronic device 101 may determine whether the reconstruction error between the row vector and the output vector exceeds a reference reconstruction error. In one embodiment, the reconstruction error between the row vector and the output vector may be the RMS value of the row vector minus the output vector.

[0110] In one embodiment, if the reconstruction error exceeds the reference reconstruction error, the electronic device 101 may perform operation 540. In one embodiment, if the reconstruction error does not exceed the reference reconstruction error, the electronic device 101 may perform operation 550.

[0111] In operation 540, the electronic device 101 may determine that a first abnormal state exists. In one embodiment, the electronic device 101 may determine that a battery cell corresponding to the row vector exists in a first abnormal state.

[0112] In operation 550, the electronic device 101 may determine that the first abnormal condition does not exist. In one embodiment, the electronic device 101 may determine that the battery cell corresponding to the row vector does not exist in the first abnormal condition.

[0113] 6 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure. The operation of FIG. 6 may be included in operation 240 of FIG. 2. The operation of FIG. 6 may be performed by the electronic device 101 shown in FIG. 1.

[0114] The operations of FIG. 6 may be performed for each row vector.

[0115] 6, in operation 610, the electronic device 101 may identify the sum of the entries of the row vector. Depending on the embodiment, the row vector may be the row vector of the variance data 470 shown in FIG. 4f.

[0116] In operation 620, the electronic device 101 may determine whether the sum is less than or equal to a reference sum.

[0117] In one embodiment, if the sum is less than or equal to the reference sum, the electronic device 101 may perform operation 630. In one embodiment, if the sum is not less than or equal to the reference sum, the electronic device 101 may perform operation 640.

[0118] In operation 630, the electronic device 101 may determine that a second abnormal state exists. In one embodiment, the electronic device 101 may determine that a battery cell corresponding to the row vector exists in a second abnormal state.

[0119] In operation 640, the electronic device 101 may determine that the second abnormal state does not exist. In one embodiment, the electronic device 101 may determine that the battery cell corresponding to the row vector does not exist in the second abnormal state.

Claims

1. 1. An electronic device, comprising: a battery module including M battery cells, where M is an integer greater than or equal to 2; a sensing circuit for acquiring a status value associated with a status of each of the M battery cells; a processor, the processor comprising: acquiring input data through the sensing circuit, the input data being expressible as an M×N matrix, the M×N entries of the input data representing state values ​​of the M battery cells, where N represents a number of time periods for acquiring the state values ​​of the M battery cells; standardizing each column vector of the input data to obtain standardized data for the input data, each column vector consisting of entries obtained in the same unit time; obtaining reference data based on the standardized data; determining a first abnormal state and / or a second abnormal state of each of the M battery cells based on a value indicated by each entry of a row vector of the determination criterion data; The first abnormal condition is determined based on a learning-based model; The second abnormal condition is determined based on a method other than the learning-based model. electronic equipment.

2. The processor: Identifying row vectors having at least one value less than or equal to a criterion critical normalized score from the row vectors of the criterion data; obtaining an output vector for the identified row vector based on the learning-based model; determining the first abnormal state of the battery cell corresponding to the identified row vector based on the output vector; The electronic device of claim 1 .

3. The processor: removing the offset of the entries of each of the row vectors of the input data; obtaining the standardized data by standardizing each of the column vectors of the input data from which the offset has been removed; the offset is set for each of the row vectors of the input data; the offset is set to the value of the first entry of each of the row vectors of the input data; The electronic device of claim 1 .

4. The processor: flattening the entries of each of the row vectors of the input data; standardizing each of the column vectors of the flattened input data to obtain the standardized data; The electronic device of claim 1 .

5. The processor: The average value of each section of the row vector of the standardized data is obtained as the reference data; determining the first abnormal state and / or the second abnormal state of each of the M battery cells based on the section average values ​​of the row vectors of the determination reference data; the interval mean values ​​are mean values ​​of the entries of the row vectors of the standardized data included in different time intervals, the time intervals do not overlap one another; The electronic device of claim 1 .

6. The processor: The change amount of each entry of the row vector of the standardized data is obtained as the judgment reference data; determining the first abnormal state and / or the second abnormal state of each of the M battery cells based on the amount of change in the entry of each of the row vectors of the determination reference data; The electronic device of claim 1 .

7. The processor: identifying a sum of the entries of each of the row vectors of the criteria data; identifying row vectors of the criterion data having sum values ​​less than or equal to a critical sum value; determining that the battery cell corresponding to the identified row vector is in the second abnormal state; The electronic device of claim 1 .

8. the learning-based model is an autoencoder; The autoencoder is trained based on the state values ​​of normal battery cells. The electronic device of claim 1 .

9. 1. A method of operating an electronic device, comprising: acquiring input data through a sensing circuit of the electronic device, the input data being representable as an M×N matrix, the M×N entries of the input data representing status values ​​of M battery cells of the electronic device, and the N representing a number of time periods for acquiring the status values ​​of the M battery cells; an operation of obtaining standardized data for the input data by standardizing each column vector of the input data, the column vectors each consisting of entries obtained in the same unit time; obtaining criteria data based on the standardized data; and determining a first abnormal state and / or a second abnormal state of each of the M battery cells based on a value indicated by each entry of a row vector of the determination criterion data; The first abnormal condition is determined based on a learning-based model; The second abnormal condition is determined based on a method other than the learning-based model. method.

10. The operation of determining the first abnormal status and / or the second abnormal status includes: an operation of identifying a row vector having at least one value less than a reference critical normalized score among the row vectors of the judgment criterion data; obtaining an output vector for the identified row vector based on the learning-based model; and determining, based on the output vector, the first abnormal state of a battery cell corresponding to the identified row vector; 10. The method of claim 9.

11. The operation of obtaining the standardized data includes: removing the offset of the entries of each of the row vectors of the input data; and obtaining the standardized data by standardizing each of the column vectors of the input data from which the offset has been removed; the offset is set for each of the row vectors of the input data; the offset is set to the value of the first entry of each of the row vectors of the input data; 10. The method of claim 9.

12. The operation of obtaining the standardized data includes: flattening the entries of each of the row vectors of the input data; and standardizing each of the column vectors of the flattened input data to obtain the standardized data.

10. The method of claim 9.

13. The operation of acquiring the criteria data includes: and acquiring an interval mean value of each row vector of the standardized data as the judgment reference data; The operation of determining the first abnormal status and / or the second abnormal status includes: determining the first abnormal state and / or the second abnormal state of each of the M battery cells based on the section average values ​​of the row vectors of the determination reference data; the interval mean values ​​are mean values ​​of the entries of the row vectors of the standardized data included in different time intervals, the time intervals do not overlap one another; 10. The method of claim 9.

14. The operation of acquiring the criteria data includes: an operation of acquiring a change amount of each entry of a row vector of the standardized data as the judgment reference data; The operation of determining the first abnormal status and / or the second abnormal status includes: and determining the first abnormal state and / or the second abnormal state of each of the M battery cells based on the amount of change in the entry of each of the row vectors of the determination criteria data.

10. The method of claim 9.

15. The operation of determining the first abnormal status and / or the second abnormal status includes: identifying the sum of the entries of each of the row vectors of the criteria data; identifying row vectors among the row vectors of the reference data having a sum value less than or equal to a critical sum value; and determining that a battery cell corresponding to the identified row vector is in the second abnormal state; 10. The method of claim 9.

Images