Battery diagnostic apparatus and method

Abstract

A battery diagnosis apparatus according to an embodiment of the present document comprises: a memory in which one or more instructions are stored; and a processor for executing the one or more instructions. While operating a first battery in a first state up to the at least one state including a second state according to at least one designated condition, the processor may acquire data sets related to the first battery in each of the first state and the at least one state, and may predict the lifespan of a second battery different from the first battery by using a neural network model trained by the data sets.

Description

Battery diagnostic device and method

[0001] Cross-citation with related applications

[0002] The present application claims the benefit of priority based on Korean Patent Application No. 10-2024-0158826 filed November 11, 2024, Korean Patent Application No. 10-2024-0158827 filed November 11, 2024, and Korean Patent Application No. 10-2025-0165364 filed November 05, 2025, and incorporates all contents disclosed in the documents of said patent applications as part of this specification.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a battery diagnostic device and a method thereof.

[0005] Recently, active research and development on secondary batteries has been underway. Here, secondary batteries are rechargeable batteries that can be interpreted to encompass conventional Ni / Cd and Ni / MH batteries, as well as recent lithium-ion batteries. With their scope of application expanding to include power sources for electric vehicles, they are garnering attention as a next-generation energy storage medium.

[0006] Calculating battery life using data obtained from actual charging and discharging operations is problematic due to the significant time and cost involved; therefore, various studies are being conducted to reduce these factors. In particular, numerous studies are underway to predict battery life using neural network models.

[0007] In particular, battery life can vary depending on the operating environment (or conditions); however, calculating battery life under all conditions is excessively costly and time-consuming, so various studies are currently underway to address this issue.

[0008] According to the embodiments disclosed in this document, a battery diagnostic device and a method for predicting the lifespan of a second battery using a neural network model learned from data sets acquired while operating a first battery are provided.

[0009] According to the embodiments disclosed in this document, a battery diagnostic device and a method are provided for training a neural network model using data sets obtained by operating a first battery under a first condition, and for predicting the lifespan of a second battery when operating a second battery under a second condition different from the first condition.

[0010] The technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below.

[0011] A battery diagnostic device according to one embodiment of the present document includes a memory in which one or more instructions are stored, and a processor that executes said one or more instructions. The processor, while operating a first battery in a first state up to at least one state including a second state according to at least one specified condition, acquires data sets related to the first battery in each of the first state and said at least one state, and can predict the life of a second battery different from the first battery using a neural network model learned from said data sets.

[0012] In one embodiment, the data sets may include at least one of the state of health (SOH) of the first battery, the resistance increase rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

[0013] In one embodiment, the at least one specified condition may include the temperature of the first battery, a C-rate related to the charging and discharging of the first battery, a range of the state of charge (SOC) when charging and discharging the first battery, or at least one combination thereof.

[0014] In one embodiment, the neural network model may include at least one of a machine learning model, a deep learning model, or any combination thereof.

[0015] In one embodiment, the first state may include a state in which the SOH of the first battery exceeds the SOH of the first battery in the second state.

[0016] In one embodiment, the processor can predict the lifespan of the second battery when operating the second battery according to at least one specified condition.

[0017] In one embodiment, the at least one designated condition may include a first designated condition and a second designated condition.

[0018] In one embodiment, the first designated condition comprises at least one of a first temperature of the first battery, a first C-rate associated with charging and discharging the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof, and the second designated condition may comprise at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range different from the first range of SOC, or any combination thereof.

[0019] In one embodiment, the data sets may include at least one of the state of health (SOH) of the first battery, a plurality of resistance increase rates of the first battery, a positive capacity loss of the first battery, or any combination thereof.

[0020] In one embodiment, the plurality of resistance increase rates may include at least one of the ratio of the CV (current voltage) charge amount to the total charge amount of the first battery, the DC-IR (direct current internal resistance), the resistance obtained by the hysteresis voltage of the first battery, or any combination thereof.

[0021] In one embodiment, the processor may obtain the hysteresis voltage based on a charging profile obtained during the process of charging the first battery and a discharge profile obtained during the process of discharging the first battery, and obtain the resistance based on the hysteresis voltage.

[0022] A battery diagnostic method according to one embodiment of the present document comprises: an operation of acquiring data sets related to a first battery in each of the first state and the at least one state while operating a first battery in a first state up to at least one state including a second state according to at least one specified condition by a processor; and an operation of predicting the life of a second battery different from the first battery by using a neural network model learned by the data sets by the processor.

[0023] In one embodiment, the data sets may include at least one of the state of health (SOH) of the first battery, the resistance increase rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

[0024] In one embodiment, the at least one specified condition may include the temperature of the first battery, a C-rate related to the charging and discharging of the first battery, a range of the state of charge (SOC) when charging and discharging the first battery, or at least one combination thereof.

[0025] In one embodiment, the neural network model may include at least one of a machine learning model, a deep learning model, or any combination thereof.

[0026] In one embodiment, the first state may include a state in which the SOH of the first battery exceeds the SOH of the first battery in the second state.

[0027] The battery diagnostic method according to one embodiment may include an operation of predicting the lifespan of the second battery when the second battery is operated by the processor according to at least one specified condition.

[0028] In one embodiment, the at least one designated condition comprises a first designated condition and a second designated condition, wherein the first designated condition comprises at least one of a first temperature of the first battery, a first C-rate associated with charging and discharging the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof, and the second designated condition may comprise at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range different from the first range of SOC, or any combination thereof.

[0029] The present technology can predict the lifespan of the second battery by using a neural network model learned from data sets acquired while operating the first battery.

[0030] In addition, the present technology can predict the lifespan of a second battery by training a neural network model using data sets obtained by operating a first battery under first conditions and operating a second battery under second conditions different from the first conditions.

[0031] In addition, various effects that can be identified directly or indirectly through this document may be provided.

[0032] FIG. 1 is a block diagram showing a battery pack in a battery diagnostic device and battery diagnostic method according to one embodiment of the present document.

[0033] FIG. 2 illustrates an example of a block diagram showing the configuration of a battery diagnostic device according to one embodiment of the present document.

[0034] FIG. 3 illustrates an example related to a change in the state of a battery in one embodiment of the present document.

[0035] FIG. 4 illustrates an example of acquiring data sets according to conditions in one embodiment of the present document.

[0036] FIG. 5 illustrates an example of a flowchart related to a battery diagnostic method according to one embodiment of the present invention.

[0037] FIG. 6a illustrates an example in which a battery diagnostic device according to one embodiment of the present document predicts the lifespan of a battery.

[0038] FIG. 6b illustrates an example in which a battery diagnostic device according to one embodiment of the present document predicts the lifespan of a battery.

[0039] FIG. 7 is a block diagram showing the hardware configuration of a computing system for performing a battery diagnosis method in a battery diagnosis device and a battery diagnosis method according to one embodiment of the present document.

[0040] Some embodiments disclosed herein are described below with reference to the various embodiments of the accompanying drawings. However, this is not intended to limit the technology to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives to embodiments of the technology.

[0041] It should be noted that when assigning reference numerals to the components of each drawing, the same components are assigned the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the various embodiments disclosed in this document, if it is determined that a detailed description of related known configurations or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted. The singular form of a noun corresponding to an item may include one or more items unless the relevant context clearly indicates otherwise.

[0042] In describing the components of the embodiments of this document, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components and do not limit the essence, order, or sequence of the components. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments disclosed in this document pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning 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 in this application.

[0043] Additionally, in this disclosure, expressions of "greater than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" may be replaced with "less than," and conditions described as "greater than and less than" may be replaced with "greater than and less than." Furthermore, "A" to "B" below refer to at least one of the elements from A (including A) to B (including B).

[0044] In this document, each of the phrases 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 in the corresponding phrase, or all possible combinations thereof.

[0045] In this document, where any component (e.g., 1) is referred to as being “connected,” “coupled,” or “joined” to another component (e.g., 2), with or without the terms “functionally” or “communicationally,” or where it is referred to as “coupled” or “connected,” it means that the component may be connected to the other component directly (e.g., via a wire), wirelessly, or through a third component.

[0046] According to one embodiment, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) 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 temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0047] According to various embodiments, each component (e.g., module or program) of the described components may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the aforementioned components or operations may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or 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 they were performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically; one or more of the operations may be executed in a different order; may be omitted; or one or more other operations may be added.

[0048] Hereinafter, embodiments of the present document will be described in detail with reference to FIGS. 1 to 7.

[0049] FIG. 1 is a block diagram showing a battery pack in a battery diagnostic device and battery diagnostic method according to one embodiment of the present document.

[0050] Referring to FIG. 1, the battery pack (1) may include a battery unit (12), a sensor unit (14), a switching unit (16), and a battery management system (BMS) (20). At this time, the battery pack (1) may be equipped with a plurality of battery units (12), sensor units (14), switching units (16), and battery management systems (20).

[0051] According to one embodiment, the battery unit (12) can supply power to a target device (not shown). To this end, the battery unit (12) may be electrically connected to the target device. Here, the target device may include an electrical, electronic, or mechanical device that operates by receiving power from the battery pack (1). For example, the target device may be an electric vehicle (EV), but is not limited thereto.

[0052] According to one embodiment, the battery unit (12) may include at least one rechargeable battery cell (10). Here, the battery cell (10) may be a basic unit of a battery cell capable of charging and discharging electrical energy. For example, the battery cell (10) may be a lithium-ion (Li-ion) battery, a lithium-ion polymer (Li-ion polymer) battery, a nickel-cadmium (Ni-Cd) battery, a nickel-hydrogen (Ni-MH) battery, etc., but is not limited thereto.

[0053] According to one embodiment, a plurality of battery units (12) may be connected in series or in parallel. For example, a battery unit (12) may be a battery module, a battery bank, or a set of battery cells (cell-to-pack structure).

[0054] According to one embodiment, the sensor unit (14) can obtain information related to the battery unit (12). According to one embodiment, the sensor unit (14) can obtain values ​​(or information) related to the state of each of the battery unit (12) or battery cells (10). In one embodiment, the values ​​related to the state may include 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.

[0055] According to one embodiment, the sensor unit (14) can provide information of each of the plurality of battery units (12) to the battery management system (20).

[0056] According to one embodiment, the switching unit (16) may include an element for controlling the current flow for charging or discharging the battery unit (12). For example, the switching unit (16) may include at least one relay and / or magnetic contactor, etc., depending on the specifications of the battery pack (1).

[0057] According to one embodiment, a battery management system (BMS) (20) can monitor the voltage, current, temperature, etc. of a battery pack (1) and control or manage the battery pack (1) to prevent overcharging and over-discharging. For example, the battery management system (20) may include a plurality of terminals as an interface for receiving values ​​of the various parameters described above, and a circuit connected to these terminals to perform processing of the received values. Additionally, the battery management system (20) may control a sensor unit (14) and / or a switching unit (16). For example, the battery management system (20) may be connected to a plurality of battery units (12) to monitor the status of each of the plurality of battery units (12) and control the ON / OFF of relays or contactors.

[0058] According to one embodiment, the operation of the battery management system (20) can be performed by a battery management system (BMS) in the vehicle, as well as by various devices such as a server, cloud, charger, or charger / discharger.

[0059] The upper controller (2) can transmit control signals for a plurality of battery units (12) to the battery management system (20). Accordingly, the operation of the battery management system (20) can be controlled based on the signals applied from the upper controller (2).

[0060] According to one embodiment, the battery management system (20) may include the battery diagnostic device (200) of FIG. 2. According to another embodiment, the battery management system (20) may be a different system from the battery diagnostic device (200) of FIG. 2. That is, the battery diagnostic device (200) of FIG. 2 may be included in the battery pack (1) or may be configured as another device outside the battery pack (1). For convenience of explanation, the following description assumes that the battery diagnostic device (200) is configured as another device outside the battery pack (1). Furthermore, the operation of the battery diagnostic device (200) below may be performed by a battery management system (BMS) within the vehicle, as well as by various devices such as a server, cloud, charger, or charger / discharger.

[0061] FIG. 2 illustrates an example of a block diagram showing the configuration of a battery diagnostic device according to one embodiment of the present document.

[0062] Referring to FIG. 2, a battery diagnostic device (200) according to one embodiment may include a processor (210) and a memory (220). The processor (210) and the memory (220) may be electrically and / or operably coupled with each other by an electronic device including a communication bus.

[0063] In the following, the hardware being operatively coupled may include direct and / or indirect connections between the hardware being established via wired and / or wireless connections so that the second hardware is controlled by the first hardware among the hardware.

[0064] Although the hardware is illustrated in different blocks, the embodiment is not limited thereto. For example, some of the hardware in FIG. 2 may be included in a single integrated circuit including a system-on-a-chip (SoC). The type and / or number of hardware included in the battery diagnostic device (200) is not limited to that illustrated in FIG. 2. For example, the battery diagnostic device (200) may include only some of the hardware illustrated in FIG. 2.

[0065] A battery diagnostic device (200) according to one embodiment may include hardware for processing data based on one or more instructions. The hardware for processing data may include a processor (210).

[0066] For example, hardware for processing data may include an arithmetic and logic unit (ALU), a floating point unit (FPU), a field programmable gate array (FPGA), a central processing unit (CPU), and / or an application processor (AP). The processor (210) may have the structure of a single-core processor or the structure of a multi-core processor including a dual core, a quad core, a hexa core, or an octa core.

[0067] A memory (220) of a battery diagnostic device (200) according to one embodiment may include a hardware component for storing data and / or instructions that are input and / or output to a processor (210) of the battery diagnostic device (200).

[0068] For example, the memory (220) may include volatile memory including random-access memory (RAM) and / or non-volatile memory including read-only memory (ROM).

[0069] For example, volatile memory may include at least one of DRAM (dynamic RAM), SRAM (static RAM), Cache RAM, PSRAM (pseudo SRAM), or any combination thereof.

[0070] For example, non-volatile memory may include at least one of PROM (programmable ROM), EPROM (erasable PROM), EEPROM (electrically erasable PROM), flash memory, hard disk, compact disk, SSD (solid state drive), eMMC (embedded multi-media card), or any combination thereof.

[0071] For example, within the memory (220) of the battery diagnostic device (200), one or more instructions (or commands) representing operations and / or actions to be performed on data by the processor (210) of the battery diagnostic device (200) may be stored. A set of one or more instructions may be referred to as a program, firmware, operating system, process, routine, sub-routine, and / or application. Hereinafter, the statement that an application is installed within the battery diagnostic device (200) may mean that one or more instructions provided in the form of an application are stored within the memory (220), and that one or more applications are stored in an executable format (e.g., a file having an extension specified by the operating system of the battery diagnostic device (200)) by the processor (210) of the battery diagnostic device (200).

[0072] A processor (210) of a battery diagnostic device (200) according to one embodiment can operate a first battery in a first state according to at least one specified condition. For example, the processor (210) can operate the first battery in a first state up to at least one state including a second state according to at least one specified condition.

[0073] For example, at least one specified condition may include the temperature of the first battery, the C-rate associated with the charging and discharging of the first battery, the range of the state of charge (SOC) when charging and discharging the first battery, or at least one combination thereof.

[0074] For example, at least one specified condition may include a first specified condition and a second specified condition.

[0075] For example, the first specified condition may include at least one of a first temperature of the first battery, a first C-rate related to the charging and discharging of the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof.

[0076] For example, the second specified condition may include at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range different from the first range, or any combination thereof.

[0077] For example, the first state may include a state in which the state of health (SOH) of the first battery exceeds the state of health (SOH) of the battery in the second state. For example, the first state may include a beginning of life (BOL) state. For example, the BOL state may include a state immediately before the battery is first discharged.

[0078] In one embodiment, the processor (210) can acquire data sets associated with the first battery in each of the first state and at least one state while operating the first battery in the first state up to at least one state including the second state according to at least one specified condition.

[0079] For example, data sets may include at least one of the SOH of the first battery, the resistance growth rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

[0080] In one embodiment, the processor (210) can predict the life of a second battery different from the first battery by using a neural network model learned from data sets.

[0081] For example, a neural network model may include at least one of a machine learning model, a deep learning model, or any combination thereof.

[0082] For example, neural network models may include deep neural network models. Neural network models include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network) model, DCN (Deep Convolutional Network), DN (Deconvolutional Network) model, DCIGN (Deep Convolutional Inverse Graphics Network) model, GAN (Generative Adversarial Network) model, and LSM (Liquid State It may include Machine), ELM (Extreme Learning Machine), ESN (Echo State Network) model, DRN (Deep Residual Network) model, DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network) model, KN (Kohonen Network) model, and / or AN (Attention Network) model.

[0083] For example, the neural network model may be stored in memory (220) or received from an external electronic device through a communication circuit (not shown). For example, the processor (210) may use the neural network model stored in memory (220) through the communication circuit. For example, when using the neural network model through the communication circuit, the processor (210) may transmit input values ​​to be input to the neural network model to an external electronic device including the neural network model, and receive output values ​​output from the external electronic device including the neural network model. For example, the external electronic device may include at least one of a vehicle, a cloud server, or any combination thereof. However, examples of external electronic devices are not limited to those described above.

[0084] For example, the processor (210) can input conditions for operating the second battery into a neural network model learned from data sets. For example, the processor (210) can predict the lifespan of the second battery by obtaining prediction data that predicts the lifespan of the second battery from the neural network model based on inputting conditions for operating the second battery into the neural network model learned from data sets.

[0085] For example, the processor (210) can predict the lifespan of the second battery when operating the second battery according to the second specified condition by using a neural network model learned from a data set acquired while operating the first battery according to the first specified condition.

[0086] According to the embodiment, the operation of the battery diagnostic device (200) can be performed by a Battery Management System (BMS) within the energy storage system (1) site, as well as by various devices such as a server, cloud, charger, or charger / discharger.

[0087] FIG. 3 illustrates an example related to a change in the state of a battery in one embodiment of the present document.

[0088] Referring to FIG. 3, a processor (210) of a battery diagnostic device (200) according to one embodiment may operate a battery in a first state (301) up to at least one state including a second state (302) according to at least one specified condition. For example, operating the battery may include charging and discharging the battery for a specified number of cycles according to at least one specified condition. For example, a cycle may mean that the actual power consumption of the battery reaches 100%.

[0089] For example, the processor (210) of the battery diagnostic device (200) can acquire a data set related to the first battery in the second state (302) by operating the first battery in the first state (301) according to the first specified condition (311).

[0090] For example, the processor (210) can operate the first battery in a second state (302) according to a second specified condition (312). For example, the processor (210) can operate the first battery in a second state (302) according to a second specified condition (312) to obtain a data set related to the first battery in a third state (303).

[0091] A processor (210) of a battery diagnostic device (200) according to one embodiment can train a neural network model using data sets related to a first battery. For example, the processor (210) can train a neural network model stored in the memory (220) of the battery diagnostic device (200) using data sets related to the first battery. For example, the processor (210) can cause an external electronic device to train a neural network model included in the external electronic device using data sets related to the first battery.

[0092] A processor (210) of a battery diagnostic device (200) according to one embodiment can predict the lifespan of a second battery different from the first battery by using a neural network model learned from data sets related to the first battery. For example, the second battery may include a battery of the same type as the first battery. For example, the second battery may include a battery of a different type from the first battery.

[0093] As described above, the processor (210) of the battery diagnostic device (200) according to one embodiment can acquire data sets related to the first battery corresponding to each of the first state (301) to the nth state (300) while operating the first battery in the first state (301) according to at least one specified condition. The processor (210) of the battery diagnostic device (200) can predict the lifespan of a second battery different from the first battery by using a neural network model learned from the data sets related to the first battery. The processor (210) can accurately predict the lifespan of the second battery by predicting the lifespan of the second battery using the neural network model described above.

[0094] FIG. 3b illustrates an example related to a change in the state of a battery in one embodiment of the present document.

[0095] Referring to FIG. 3b, the processor (210) of the battery diagnostic device (200) according to one embodiment can operate the battery in a first state (301) to a second-1 state (302-1), a second-2 state (302-2), a second-3 state (302-3), or at least one combination thereof, according to at least one specified condition.

[0096] For example, the processor (210) of the battery diagnostic device (200) can acquire a data set related to the first battery in the second-first state (302-1) by operating the first battery in the first state (301) according to the first specified condition (311).

[0097] For example, the processor (210) of the battery diagnostic device (200) can operate the first battery in the first state (301) according to the second specified condition (312) to obtain a data set related to the first battery in the second-2 state (302-2).

[0098] For example, the processor (210) of the battery diagnostic device (200) can operate the first battery in the first state (301) according to the third specified condition (313) to obtain a data set related to the first battery in the second-third state (302-3).

[0099] For example, the processor (210) of the battery diagnostic device (200) can operate the first battery in the second-1 state (302-1) according to the second specified condition (312) to obtain a data set related to the first battery in the third-1 state (303-1).

[0100] For example, the processor (210) of the battery diagnostic device (200) can operate the first battery in the second-2 state (302-2) according to the third specified condition (313) to obtain a data set related to the first battery in the third-2 state (303-2).

[0101] For example, the processor (210) of the battery diagnostic device (200) can operate the first battery in the second-third state (302-3) according to the first specified condition (311) to obtain a data set related to the first battery in the third-third state (303-3).

[0102] A processor (210) of a battery diagnostic device (200) according to one embodiment can train a neural network model using data sets related to a first battery. For example, the processor (210) can train a neural network model stored in the memory (220) of the battery diagnostic device (200) using data sets related to the first battery. For example, the processor (210) can cause an external electronic device to train a neural network model included in the external electronic device using data sets related to the first battery.

[0103] A processor (210) of a battery diagnostic device (200) according to one embodiment can predict the lifespan of a second battery different from the first battery by using a neural network model learned from data sets related to the first battery. For example, the second battery may include a battery of the same type as the first battery. For example, the second battery may include a battery of a different type from the first battery.

[0104] As described above, the processor (210) of the battery diagnostic device (200) according to one embodiment can acquire data sets related to the first battery in the process of operating the first battery in a first state (301) according to at least one specified condition. The processor (210) of the battery diagnostic device (200) can predict the lifespan of a second battery that is different from the first battery by using a neural network model learned from the data sets related to the first battery. By predicting the lifespan of the second battery using the neural network model described above, the processor (210) can accurately predict the lifespan of the second battery.

[0105] FIG. 4 illustrates an example of acquiring data sets according to conditions in one embodiment of the present document.

[0106] Referring to FIG. 4, the processor (210) of the battery diagnostic device (200) according to one embodiment can acquire data sets for training a neural network model.

[0107] The graph illustrated in FIG. 4 may include an example of representing data sets related to the first battery and / or the second battery on the graph. For example, the horizontal axis of the graph illustrated in FIG. 4 may represent the number of cycles of charging and discharging the first battery and / or the second battery. For example, the vertical axis of the graph illustrated in FIG. 4 may represent the conditions when charging and discharging the first battery and / or the second battery. The first through ninth conditions of FIG. 4 may be included in at least one designated condition described in FIG. 2 through 3.

[0108] The circles shown in FIG. 4 may represent information generated when each battery is charged and discharged under each condition. For example, the processor (210) of the battery diagnostic device (200) may charge and discharge the first battery and / or the second battery to obtain information and obtain data sets.

[0109] For example, the processor (210) may obtain a first data set based on charging and discharging the first battery by a specified number of cycles according to a first condition. For example, the processor (210) may obtain a second data set based on charging and discharging the first battery by a specified number of cycles according to a second condition. For example, the processor (210) may obtain a third data set based on charging and discharging the first battery by a specified number of cycles according to a third condition. For example, the processor (210) may obtain a fourth data set based on charging and discharging the first battery by a specified number of cycles according to a fourth condition. For example, the processor (210) may obtain a sixth data set based on charging and discharging the first battery by a specified number of cycles according to a sixth condition. For example, the processor (210) may obtain an eighth data set based on charging and discharging the first battery by a specified number of cycles according to an eighth condition. For example, the processor (210) can obtain a ninth data set based on charging and discharging the first battery for a specified number of cycles according to the ninth condition.

[0110] In one embodiment, the processor (210) can train a neural network model using data sets obtained based on charging and discharging the first battery as described above.

[0111] In one embodiment, the processor (210) may input information related to the fifth condition and the second battery into a learned neural network model. Based on the input of information related to the fifth condition and the second battery into the learned neural network model, the processor (210) may obtain a fifth data set. For example, the processor (210) may use the fifth data set to predict the lifespan of the second battery when operating the second battery according to the fifth condition. For example, the information related to the second battery may include the specifications of the second battery.

[0112] As another example, the processor (210) may input information related to the seventh condition and the second battery into a learned neural network model. Based on the input of information related to the seventh condition and the second battery into the learned neural network model, the processor (210) may obtain a seventh data set. For example, the processor (210) may use the seventh data set to predict the lifespan of the second battery when operating the second battery according to the seventh condition.

[0113] As described above, the processor (210) of the battery diagnostic device (200) according to one embodiment can accurately predict the lifespan of the second battery when the second battery is operated under conditions different from those when the first battery is operated, by using a neural network model.

[0114] FIG. 5 illustrates an example of obtaining resistance using hysteresis voltage in one embodiment of the present document.

[0115] Referring to FIG. 5, a battery diagnostic device (200) according to one embodiment can obtain data related to voltage according to the capacity of the first battery. The horizontal axis of the graph shown in FIG. 4 may represent the capacity of the first battery, and the vertical axis may represent the voltage of the first battery. For example, the capacity of the first battery may correspond to the SOC of the first battery.

[0116] In FIG. 5, the first line (401) represents the voltage relative to the capacity of the first battery during the charging process of the first battery, and the second line (402) represents the voltage relative to the capacity of the first battery during the discharging process of the first battery.

[0117] The resistance obtained by the hysteresis voltage may correspond to a region (410) within the graph. The region (410) may correspond to a shape formed by a first boundary line (411), a second boundary line (413), a first line (401), and a second line (402).

[0118] For example, the first boundary line (411) and / or the second boundary line (413) may be variable. For example, the first boundary line (411) and / or the second boundary line (413) may be changed according to the degradation state of the first battery. For example, the first boundary line (411) and / or the second boundary line (413) may be changed according to the composition of the positive material of the first battery. However, the embodiments of this document are not limited to those described above.

[0119] FIG. 6 illustrates an example of data predicting the lifespan of a second battery using a plurality of resistance increase rates in one embodiment of the present document.

[0120] FIG. 6 illustrates an example of data predicting the lifespan of a second battery using a plurality of resistance increase rates in one embodiment of the present document.

[0121] In Fig. 6, the horizontal axis of the graph represents the output of the battery, and the vertical axis of the graph represents the SOH of the battery. The output of the battery may represent the total amount of accumulated discharge energy.

[0122] Referring to FIG. 6, the first data (601) may include an example in which the SOH of the battery is obtained by actually charging and discharging the battery. The second data (602) may include an example in which the battery life is predicted using a single resistance increase rate. The third data (603) may include an example in which the battery life is predicted using multiple resistance increase rates.

[0123] FIG. 6 shows how the battery's SOH is measured or the battery's lifespan is predicted by operating the battery according to the first condition (611), the second condition (612), and the third condition (613). Each of the first condition (611), the second condition (612), and the third condition (613) may be the same, but may also be different. For example, the first condition (611) and the third condition (613) may be the same, and the second condition (612) may be different from the first condition (611) and the third condition (613).

[0124] Referring to the graph in Fig. 6, it can be seen that the third data (603), which predicts the battery life using multiple resistance increase rates, is closer to the first data (601) that actually operates the battery, compared to the second data (602), which predicts the battery life using a single resistance increase rate.

[0125] FIG. 7 illustrates an example of obtaining battery operating conditions using a neural network model in one embodiment of the present document.

[0126] In FIG. 7, the horizontal axis of the graph represents the output amount of the battery, and the vertical axis of the graph represents the SOH of the battery. The output amount of the battery may represent the total amount of accumulated discharge energy. FIG. 7 may include a graph showing an example of deriving conditions that improve the lifespan or durability of the battery.

[0127] For example, the processor (210) of the battery diagnostic device (200) can control the battery by determining that operating the battery according to the first optimal condition (711), the second optimal condition (712), and the third optimal condition (713) is more efficient than operating the battery according to the first general condition (721) and the second general condition (721).

[0128] As can be seen in the graph of FIG. 7, the first experimental data (701) shows that the battery's SOH (i.e., battery life) is lower than that of the second experimental data (702). Therefore, the processor (210) of the battery diagnostic device (200) can operate the battery according to the first optimal condition (711), the second optimal condition (712), and the third optimal condition (713).

[0129] In this document, the first optimal condition (711), the second optimal condition (712), and the third optimal condition (713) are described separately; however, each of the first optimal condition (711), the second optimal condition (712), and the third optimal condition (713) may be the same, but may also be different. For example, the first optimal condition (711) and the third optimal condition (713) may be the same, and the second optimal condition (712) may be different from the first optimal condition (711) and the third optimal condition (713).

[0130] FIG. 8 illustrates an example of a flowchart related to a battery diagnostic method according to one embodiment of the present document.

[0131] In the following, it is assumed that the battery diagnostic device (200) of FIG. 2 performs the process of FIG. 8. Also, in the description of FIG. 8, the operation described as being performed by the device can be understood as being controlled by the processor (210) of the battery diagnostic device (200).

[0132] At least one of the operations of FIG. 8 can be performed by the battery diagnostic device (200) of FIG. 2. At least one of the operations of FIG. 8 can be controlled by the processor (210) of FIG. 2. Each of the operations of FIG. 8 can be performed sequentially, but is not necessarily performed sequentially. For example, the order of each of the operations can be changed, and at least two operations can be performed in parallel.

[0133] Referring to FIG. 8, a battery diagnostic method according to one embodiment may include, in operation S501, acquiring data sets related to the first battery in each of the first state (301) and at least one state while operating the first battery in the first state (301) up to at least one state including the second state (302) according to at least one specified condition.

[0134] For example, at least one specified condition may include the temperature of the first battery, the C-rate associated with the charging and discharging of the first battery, the range of SOC when charging and discharging the first battery, or at least one combination thereof.

[0135] For example, the first state (301) may include a state in which the SOH of the first battery exceeds the SOH of the first battery in the second state (302).

[0136] For example, data sets may include at least one of the SOH of the first battery, the resistance growth rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

[0137] In operation S503, the battery diagnostic method according to one embodiment may include an operation of predicting the life of a second battery different from a first battery using a neural network model learned from data sets.

[0138] For example, a neural network model may include at least one of a machine learning model, a deep learning model, or any combination thereof.

[0139] For example, the battery diagnostic method may include an operation to predict the lifespan of the second battery when the second battery is operated according to at least one specified condition.

[0140] For example, at least one specified condition may include a first specified condition and a second specified condition.

[0141] For example, the first specified condition may include at least one of a first temperature of the first battery, a first C-rate related to the charging and discharging of the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof.

[0142] For example, the second specified condition may include at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range of SOC different from the first range, or any combination thereof.

[0143] For example, the battery diagnostic method may include an operation to predict the lifespan of the second battery when operating the second battery according to a second specified condition, using a neural network model learned from a data set acquired while operating the first battery according to a first specified condition.

[0144] As described above, a battery diagnostic method according to one embodiment can accurately predict the lifespan of a second battery by using a neural network model learned from data sets related to a first battery to predict the lifespan of the battery.

[0145] FIG. 9a illustrates an example in which a battery diagnostic device according to one embodiment of the present document predicts the lifespan of a battery.

[0146] Referring to FIG. 9a, the processor (210) of the battery diagnostic device (200) according to one embodiment can predict the lifespan of the battery. For example, the lifespan of the battery may include retention. For example, the horizontal axis of the graph may represent the number of cycles. For example, the vertical axis of the graph may represent retention.

[0147] In the graph of FIG. 9a, the first line (901) may be the battery life calculated using data obtained by actually charging and discharging the battery. The second line (903) may be the battery life predicted using a neural network model.

[0148] In the graph of FIG. 9a, it can be seen that the difference between the first line (901) and the second line (903) is about 0.4%.

[0149] FIG. 9b illustrates an example in which a battery diagnostic device according to one embodiment of the present document predicts the lifespan of a battery.

[0150] Referring to FIG. 9b, the processor (210) of the battery diagnostic device (200) according to one embodiment can predict the lifespan of the battery. For example, the horizontal axis of the graph may represent the number of cycles. For example, the vertical axis of the graph may represent retention.

[0151] In the graph of FIG. 9b, the first line (911) may be the battery life calculated using data obtained by actually charging and discharging the battery. The second line (913) may be the battery life predicted using a neural network model.

[0152] In the graph of Fig. 9b, it can be seen that the difference between the first line (911) and the second line (913) is about 0.3%.

[0153] As described above, with reference to FIGS. 9a and FIGS. 9b, the battery diagnostic device (200) can accurately predict the lifespan of the battery using a neural network model.

[0154] FIG. 10 is a block diagram showing the hardware configuration of a computing system for performing a battery diagnostic method in a battery diagnostic device and a battery diagnostic method according to one embodiment of the present document.

[0155] Referring to FIG. 10, a computing system (1100) according to one embodiment disclosed in this document may include an MCU (1110), memory (1120), an input / output I / F (1130), and a communication I / F (1140).

[0156] The MCU (1110) may be a processor that executes various programs stored in memory (1120) (e.g., battery cell data collection program, graph generation program, data analysis program, data decomposition algorithm, normalization program, battery cell diagnosis program, etc.), processes various information including characteristic data and potential variables of the battery cell through these programs, and performs the functions of the battery diagnosis device (200) shown in FIGS. 1 to 9b above.

[0157] The memory (1120) can store various programs such as a battery cell data collection program, a graph generation program, a data analysis program, a data decomposition algorithm, a normalization program, and a battery cell diagnosis program.

[0158] These memories (1120) may be provided in multiple quantities as needed. The memories (1120) may be volatile memories or non-volatile memories. As volatile memories, the memory (1120) may use RAM, DRAM, SRAM, etc. As non-volatile memories, the memory (1120) may use ROM, PROM, EAROM, EPROM, EEPROM, flash memory, etc. The examples of the listed memories (1120) are merely examples and are not limited to these examples.

[0159] The input / output I / F (1130) can provide an interface that enables data transmission and reception between an input device (not shown), such as a keyboard, mouse, or touch panel, an output device (not shown), and an MCU (1110).

[0160] The communication I / F (1140) is configured to transmit and receive various data with a server and may be various devices capable of supporting wired or wireless communication. For example, the battery diagnostic device (200) can transmit and receive various information, including the shape model of a battery cell, from a separately provided external server via the communication I / F (1140).

[0161] In this way, a computer program according to one embodiment disclosed in this document may be implemented as a module that performs, for example, the functions illustrated in FIG. 2, by being recorded in memory (1120) and processed by an MCU (1110).

[0162] As described above, even though all components constituting the embodiments disclosed in this document have been described as being combined or operating in combination, the embodiments disclosed in this document are not necessarily limited to such embodiments. That is, within the scope of the purposes of the embodiments disclosed in this document, all components may be selectively combined in one or more ways to operate.

[0163] Furthermore, terms such as "include," "compose," or "have" as described above, unless specifically stated otherwise, mean that the relevant component may be inherent; thus, they should be interpreted as allowing for the inclusion of additional components rather than excluding them. All terms, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments disclosed in this document pertain, unless otherwise defined. Commonly used terms, such as those defined in advance, should be interpreted in accordance with their contextual meanings in the relevant technology and, unless explicitly defined in this document, should not be interpreted in an ideal or overly formal sense.

[0164] The foregoing disclosure outlines the features of several embodiments to enable those skilled in the art to better understand the aspects of the present disclosure. Those skilled in the art will understand that the present disclosure can be readily used as a basis for designing or modifying other structures to perform the same purpose or achieve the same advantages as the embodiments introduced herein. Furthermore, those skilled in the art will recognize that such equivalent configurations do not depart from the scope of the present disclosure and that various changes, substitutions, and modifications may be made in the present specification without departing from the scope of the present disclosure.

Claims

1. Memory in which one or more instructions are stored; and It includes a processor that executes one or more of the above instructions, The above processor is, According to at least one specified condition, while operating a first battery in a first state up to at least one state including a second state, data sets related to the first battery are obtained in each of the first state and the at least one state, and A battery diagnostic device configured to predict the life of a second battery different from the first battery using a neural network model learned from the above data sets.

2. In Paragraph 1, The above data sets are, A battery diagnostic device comprising at least one of the state of health (SOH) of the first battery, the resistance increase rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

3. In Paragraph 1, The above at least one specified condition is, A battery diagnostic device comprising at least one of the temperature of the first battery, a C-rate related to the charging and discharging of the first battery, a range of the state of charge (SOC) when charging and discharging the first battery, or any combination thereof.

4. In Paragraph 1, The above neural network model is, A battery diagnostic device comprising at least one of a machine learning model, a deep learning model, or any combination thereof.

5. In Paragraph 1, The above first state is, A battery diagnostic device comprising a state in which the SOH of the first battery exceeds the SOH of the first battery in the second state.

6. In Paragraph 1, The above processor is, A battery diagnostic device configured to predict the lifespan of the second battery when the second battery is operated according to at least one specified condition.

7. In Paragraph 1, The above at least one specified condition is, A battery diagnostic device comprising a first specified condition and a second specified condition.

8. In Paragraph 7, The above-mentioned first designated condition is, It includes at least one of a first temperature of the first battery, a first C-rate related to the charging and discharging of the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof. The above second designated condition is, A battery diagnostic device comprising at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range different from the first range of SOC, or any combination thereof.

9. In Paragraph 1, The above data sets are, A battery diagnostic device comprising at least one of the state of health (SOH) of the first battery, a plurality of resistance increase rates of the first battery, a positive capacity loss of the first battery, or any combination thereof.

10. In Paragraph 9, The above plurality of resistance increase rates are, A battery diagnostic device comprising at least one of the ratio of the CV (current voltage) charge amount to the total charge amount of the first battery, the DC-IR (direct current internal resistance), the resistance obtained by the hysteresis voltage of the first battery, or any combination thereof.

11. In Paragraph 10, The above processor is, Based on the charging profile obtained during the process of charging the first battery and the discharge profile obtained during the process of discharging the first battery, the hysteresis voltage is obtained, and A battery diagnostic device configured to obtain the resistance based on the hysteresis voltage.

12. An operation of acquiring data sets associated with the first battery in each of the first state and the at least one state while operating the first battery in the first state up to at least one state including the second state, according to at least one specified condition by a processor; and A battery diagnosis method comprising the operation of predicting the life of a second battery different from the first battery using a neural network model learned by the above data sets by the above processor.

13. In Paragraph 12, The above data sets are, A battery diagnostic method comprising at least one of the state of health (SOH) of the first battery, the resistance increase rate of the first battery, the positive capacity loss of the first battery, or any combination thereof.

14. In Paragraph 12, The above at least one specified condition is, A battery diagnostic method comprising at least one of the temperature of the first battery, the C-rate related to the charging and discharging of the first battery, the range of the state of charge (SOC) when charging and discharging the first battery, or any combination thereof.

15. In Paragraph 12, The above neural network model is, A battery diagnostic method comprising at least one of a machine learning model, a deep learning model, or any combination thereof.

16. In Paragraph 12, The above first state is, A battery diagnostic method comprising a state in which the SOH of the first battery exceeds the SOH of the first battery in the second state.

17. In Paragraph 12, The above battery diagnostic method is, A battery diagnostic method comprising an operation to predict the lifespan of the second battery when the second battery is operated according to at least one specified condition by the processor.

18. In Paragraph 12, The above at least one specified condition is, Includes the first designated condition and the second designated condition, The above-mentioned first designated condition is, It includes at least one of a first temperature of the first battery, a first C-rate related to the charging and discharging of the first battery, a first range of SOC when charging and discharging the first battery, or any combination thereof. The above second designated condition is, A battery diagnostic method comprising at least one of a second temperature different from the first temperature, a second C-rate different from the first C-rate, a second range different from the first range of SOC, or any combination thereof.

Images