Battery internal temperature estimation method and device

Abstract

Embodiments of the present specification relate to a method and apparatus for estimating an internal temperature of a battery using impedance of a specific frequency band. A battery management device according to an embodiment of the present specification may include: an impedance measurement unit for measuring an impedance of a battery for each frequency band; and a controller for controlling the impedance measuring unit to apply a signal of a set frequency band to the battery, receiving a set impedance corresponding to the set frequency band from the impedance measuring unit, and estimating an internal temperature of the battery by inputting the set impedance into a learning model, the set frequency band is determined by a correlation between an impedance and a state of charge (SOC) for each frequency band.

Description

Technical Field

[0001] Embodiments of the present specification relate to a method and apparatus for estimating an internal temperature of a battery using impedance in a specific frequency band. Background Art

[0002] Today, batteries are designed to have high energy density, making fire extinguishing much more difficult than normal. First, if the battery overheats (such as runaway), the energy released in the feedback loop may be high, burning the electrolyte in the cell and generating more heat, burning more electrolyte. In addition, during the fire extinguishing process, the battery cell is sealed by the battery pack, making it difficult for the fire extinguishing agent to reach the fire area.

[0003] Therefore, it is very important to continuously monitor the battery status to predict the possibility of fire in advance. Therefore, as an electronic system that maintains battery cells, modules, racks or battery packs, the battery management system (BMS) manages the battery system so that it can be used safely while performing optimal performance (such as calculating the battery charge status, providing battery surface temperature status and usage history information, preventing overcharge / overdischarge, and communicating with external devices).

[0004] This type of BMS is used in a variety of fields from small battery products to large battery products such as automobiles and ESS.

[0005] The above-mentioned background technology is technical information mastered by the inventor in order to derive the present invention or obtained in the process of deriving the present invention, and is not necessarily technology that has been disclosed to the public before submitting the present invention. Summary of the invention

[0006] Technical issues

[0007] Various embodiments proposed in this specification to solve the above problems provide a method and apparatus for estimating the internal temperature of a battery.

[0008] Workaround

[0009] A battery management device according to an embodiment of the present specification may include: an impedance measurement unit for measuring a band-specific impedance of a battery; and a controller for controlling the impedance measurement unit to apply a signal of a set band to the battery, receive a set impedance corresponding to the set band from the impedance measurement unit, and estimate the internal temperature of the battery by inputting the set impedance into a learning model, wherein the set band is determined by a correlation between the band-specific impedance and a state of charge (SOC).

[0010] The learning model may be generated based on a data set including a set impedance and an internal temperature of the battery.

[0011] The learning model may be a polynomial regression model between the internal temperature of the battery and the set impedance.

[0012] When the estimated internal temperature of the battery is equal to or greater than a first threshold, the controller may transmit a fire risk message.

[0013] When the estimated internal temperature of the battery is equal to or greater than a second threshold, the controller may perform fire diagnosis.

[0014] When the phase change amount of the set impedance over time is equal to or greater than a third threshold, the controller may perform fire management.

[0015] A battery management method according to an embodiment of the present specification may include: acquiring a set impedance corresponding to a set frequency band from an impedance measurement unit; and estimating an internal temperature of a battery by inputting the set impedance into a learning model, wherein the set frequency band is determined by a correlation between a frequency band-specific impedance and a state of charge (SOC).

[0016] The set frequency band may be a frequency band that minimizes the correlation between the frequency band specific impedance and the charging state.

[0017] The battery management method according to one embodiment may further include: transmitting a fire risk message when the estimated internal temperature of the battery is equal to or greater than a first threshold.

[0018] The battery management method according to one embodiment may further include performing fire diagnosis when the estimated internal temperature of the battery is equal to or greater than a second threshold value.

[0019] The performing of the fire diagnosis may include performing fire management when the amount of phase change of the set impedance over time is equal to or greater than a third threshold value.

[0020] According to an embodiment of the present specification, a method for estimating the internal temperature of a battery may include: setting the internal temperature of the battery; obtaining a band-specific impedance of the battery corresponding to the internal temperature of the battery from an impedance measurement unit; obtaining a state of charge (SOC) of the battery; determining a set frequency band based on a correlation between the band-specific impedance and the state of charge; determining a set impedance corresponding to the set frequency band among the band-specific impedances and the set internal temperature of the battery as a data set; and using the data set to generate a learning model for estimating the internal temperature of the battery based on the set impedance.

[0021] The learning model may be a polynomial regression model between the internal temperature of the battery and the set impedance.

[0022] Beneficial Effects

[0023] According to an embodiment of the present invention, it is possible to estimate the internal temperature of a battery and perform battery fire management.

[0024] The effects of the present invention are not limited to the above-mentioned effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A diagram for explaining the process of a battery fire.

[0026] Figure 2 is a view schematically showing a management system according to an embodiment of the present invention.

[0027] Figure 3 is a view schematically showing a configuration of a battery management device according to an embodiment of the present invention.

[0028] Figure 4 is a flowchart illustrating a fire estimation operation of a battery management device according to an embodiment of the present invention.

[0029] Figure 5 is a flowchart illustrating an operation of generating a learning model of a battery management device according to an embodiment of the present invention.

[0030] Figures 6a to 6d 3 and 4 are Bode diagrams showing a first correlation between the frequency band specific impedance and the charging state according to an embodiment of the present invention, respectively.

[0031] Figure 7 is a RMSE graph according to frequency bands illustrating a second correlation between frequency band specific impedance and the state of charge according to an embodiment of the present invention.

[0032] Figure 8 is a RMSE graph according to frequency bands in which the correlation between the frequency band specific impedance and the state of charge is low according to an embodiment of the present invention.

[0033] Fig. 9 is a view schematically showing a battery pack according to an embodiment of the present invention.

[0034] Fig.10 is a view schematically showing a battery module according to an embodiment of the present invention.

[0035] Fig.11 is a flowchart illustrating a fire estimation operation of a battery management device according to an embodiment of the present invention.

[0036] Fig.12 is a flowchart illustrating an operation of generating a learning model of a battery management device for each module according to an embodiment of the present invention.

[0037] Figures 13a to 13c 3 are diagrams showing the dependency of frequency band specific impedances of individual channels of a specific module, respectively.

[0038] Fig.14is a flowchart illustrating an operation of generating a learning model of a battery management device for each channel according to an embodiment of the present invention.

[0039] Figures 15a to 15c 4 and 5 are graphs showing the dependency of the frequency band specific impedance of each module of a specific channel. DETAILED DESCRIPTION

[0040] The present invention can be modified in many ways and has many embodiments, so specific embodiments are shown in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods for achieving them will become clear through the embodiments described in detail below in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below and can be implemented in many forms.

[0041] Each logic block can represent a part of a module, segment or code, which includes one or more executable instructions for performing a specific logic function. It should be noted that, in one embodiment, the functions mentioned for each block can be performed in an order different from the order described. For example, even if two blocks are shown in succession, the functions described for each block can also be performed substantially simultaneously, or can be performed in reverse order according to different execution conditions or environments. In the following embodiments, unless the context clearly states otherwise, singular expressions include plural expressions.

[0042] In the following embodiments, terms such as including or having mean that the features or components described in the present specification are present, and do not exclude the possibility that one or more other features or components may be added.

[0043] Instructions executed by a processor of a computer or other programmable data processing device may generate means for performing the functions described with reference to the flowchart or block diagram. Instructions may be installed on a computer or other device and may generate a process executed on the computer or other device to complete a series of operation steps.

[0044] At this time, the term "... unit" used in this embodiment refers to a component that performs a specific function performed by software or hardware, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). However, the "... unit" is not limited to being performed by software or hardware. The "... unit" may exist in the form of data stored in an addressable storage medium, or may be configured to cause one or more processors to perform a specific function.

[0045] In the accompanying drawings, for ease of explanation, the size of the components may be exaggerated or reduced. For example, for ease of explanation, the size and thickness of each configuration shown in the accompanying drawings are arbitrarily shown, so the present invention is not necessarily limited to the content shown. In addition, in the present disclosure, the expressions "greater than" and "less than" are used to determine whether a specific condition is satisfied or achieved, but they are only descriptions of the expression examples and do not exclude the description of "equal to or greater than" or "equal to or less than". The condition described as "equal to or greater than" can be replaced with "greater than", and the condition described as "equal to or less than" and the condition described as "equal to or greater than and less than" can be replaced with "greater than and equal to or less than". Terms such as "first", "second" and the like can be used to describe various components, but these components should not be limited by these terms. These terms are only used to distinguish one component from another component. Software can include computer programs, codes, instructions, or a combination of one or more thereof, and can configure processing devices to run as needed or command processing devices independently or in clusters. Software and / or data may be embodied permanently or temporarily in any type of machine, component, physical device, virtual device, computer storage medium or device or transmission signal wave for parsing by a processing device or providing instructions or data to a processing device. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0046] The battery according to the present disclosure is not limited to a specific battery, and may represent a single battery or even a plurality of batteries. In addition, the battery according to the present disclosure may be a concept including a battery cell, a battery module, a battery rack, and a battery pack. Therefore, the battery management device according to the present disclosure may perform internal temperature estimation on the battery cell, the battery module, the battery rack, and the battery pack.

[0047] The learning model according to the present disclosure is a model for estimating the internal temperature of the battery, which can be a machine learning model or a neural network model. At this time, the neural network model is a representative example of an artificial neural network model that simulates brain nerves and is not specified by any algorithm.

[0048] The battery internal temperature according to the present disclosure refers to the internal temperature of the battery, for example, for a lithium ion battery, it may refer to the temperature of the internal electrolyte.

[0049] Figure 1 A diagram for explaining the process of a battery fire.

[0050] Reference Figure 1 , showing the process of a typical battery fire. The fire process generally goes through the process of battery aging 110, single cell (cell) overcharging 120, internal temperature increase 130, impedance phase change 140 and thermal runaway 150. The battery fire according to the present disclosure may specifically refer to a battery fire caused by overcharging.

[0051] Battery aging 110 is based on chemical and mechanical factors and refers to the process by which the battery life is shortened due to the battery structure. For example, in the case of lithium-ion batteries, when the battery is used repeatedly, the structure of the negative electrode material changes due to chemical and mechanical reasons, and the energy density of the battery decreases. If this process is repeated, it will cause slight changes in the graphite structure of the negative electrode material, thereby shortening the battery life.

[0052] Cell overcharge 120 may be caused by battery aging 110, battery state of charge (SOC) estimation error or ripple voltage. When the battery undergoes the overcharge 120 process, micro short circuits or electrolyte redox may occur due to overcharge of the electrode plates.

[0053] The internal temperature increase 130 process is a gradual increase in the internal temperature of the battery due to a micro short circuit caused by overcharging of the battery or an electrolyte redox process.

[0054] Then, the battery impedance phase undergoes an impedance phase change 140 process, in which the battery impedance phase changes rapidly for about 2 to 10 minutes, and then thermal runaway 150 occurs.

[0055] Subsequently, the electrochemical reaction inside the battery generates gas in the electrolyte, and the internal pressure increases due to the gas, resulting in pressure release, which leads to the thermal runaway 150 process.

[0056] In this process, if the data of the internal temperature increase process 130 is used to predict the fire, effective battery fire management can be performed, but it is difficult to measure the internal temperature of the battery, that is, the temperature of the internal electrolyte, with a general sensor because it only measures the battery surface temperature.

[0057] According to an embodiment of the present invention, a system for predicting fire based on a model for estimating the internal temperature of a battery is disclosed below.

[0058] Figure 2 is a diagram schematically showing a management system 200 according to an embodiment of the present invention.

[0059] Reference Figure 2 , the management system 200 may include a battery management system (BMS) 210 , a charge / discharge execution unit 220 , and a plurality of batteries 230 .

[0060] The plurality of batteries 230 are devices as internal temperature and fire prediction targets, and may be connected to the charge / discharge execution unit 220 to be charged or discharged, and may be connected to the battery management unit 210 to be managed.

[0061] The charge / discharge execution unit 220 may be controlled by the battery management unit 210 to charge or discharge the connected battery 230 .

[0062] The battery management unit 210 is a device that controls battery charging / discharging, and can perform battery state of charge (SOC), battery state monitoring, etc. Specifically, the battery management device 210 can perform current, single cell voltage, surface temperature, SOC, single cell balancing, relay or FET control, fault diagnosis, fire prediction, etc. of the battery 230 installed on the ESS energy storage system, electric vehicle BEV, etc.

[0063] The battery management device 210 according to an embodiment of the present invention can estimate the internal temperature of the battery 230 and perform fire diagnosis and fire management. Such a battery management device 210 can perform operations according to an embodiment of the present invention. Figure 3 The battery management device 210 is described in detail.

[0064] The management system 200 according to an embodiment of the present invention may include a separate server (not shown). For example, the server may include a learning model, and the battery management device 210 may send information about the impedance of the battery cell 230 to the server and receive information about the internal temperature of the battery from the server to manage the battery cell 230.

[0065] Figure 3 is a view schematically showing a configuration 300 of a battery management device 210 according to an embodiment of the present invention.

[0066] See also Figure 3 The battery management device 210 is shown as being composed of a controller 310, a memory 320, a battery state measurement unit 330, an impedance measurement unit 340, and a communication unit 350, but is not necessarily limited thereto. For example, the controller 310, the memory 320, the battery state measurement unit 330, the impedance measurement unit 340, and the communication unit 350 may each exist as a physically independent component.

[0067] The memory 320 may store various data for the overall operation of the battery management device 210, such as a program for processing or controlling the controller 310 in the battery management device 210. The memory 320 may store a plurality of application programs being driven, data for the operation of the battery management device 210, and commands. The memory 320 may be implemented as an internal memory (such as a ROM or RAM) included in the controller 310, or as a memory separate from the controller 310.

[0068] The memory 320 according to one embodiment may store a learning model, a current of the battery 230 , a cell voltage, a surface temperature, an SOC, and the like.

[0069] The battery state measurement unit 330 may measure the voltage of the battery cell, the cell balance, and the surface temperature of the battery cell. The battery state measurement unit 330 may transmit data of the sensed battery state to the controller 310.

[0070] The impedance measurement unit 340 can measure the frequency band specific impedance of the battery. The impedance measurement unit 340 can be implemented by a frequency perturbation unit 341, an impedance voltage measurement unit 343, and an impedance current measurement unit 345. The impedance measurement unit 340 can measure the impedance of the battery using electrical impedance spectroscopy (EIS: Electrical Impedance Spectroscopy). Specifically, the impedance measurement unit 340 can analyze the impedance by measuring the size and phase changes of the impedance voltage and impedance current signals that respond within the range of the electrical equilibrium state and thermal equilibrium state of the battery by applying a small sinusoidal current and voltage signal from the high frequency range to the low frequency range. The impedance measurement unit 340 can analyze the impedance by applying the frequency band indicated by the controller 310 to the battery 230, and sending at least one of the impedance voltage, impedance current, and impedance to the controller 310. The measurement unit can extract the necessary signals through passive and active filters for the impedance voltage and current. The filtering function of the measurement unit can be configured by IC, OPAMP, RLC elements, or can also be implemented by MCU, RLC elements. After passing through the filter, it can be sent to the controller's analog-to-digital converter (ADC).

[0071] The frequency perturbation unit 341 may apply a frequency signal to the battery to measure a frequency band specific impedance of the battery. The frequency perturbation unit 341 may apply a sinusoidal current and voltage signal for a frequency band instructed by the controller 310 .

[0072] The impedance voltage measuring unit 343 may measure the impedance voltage of the battery disturbed by the frequency perturbation unit 341. The impedance voltage measuring unit 343 may measure the voltage applied to the battery through the signal applied by the frequency perturbation unit 341.

[0073] The impedance current measuring unit 345 may measure the impedance current of the battery disturbed by the frequency perturbation unit 341. The impedance current measuring unit 345 may measure the current flowing through the battery through the signal applied by the frequency perturbation unit 341.

[0074] The communication unit 350 performs a function of transmitting and receiving signals through a network.

[0075] All or part of the communication unit 350 may be referred to as a sending unit, a receiving unit, or a transceiver unit. The communication unit 350 may provide a function for the battery management device 210 to communicate with at least one other node through a communication network. According to an embodiment of the present disclosure, when a request signal is generated according to a program code stored in a recording device such as a memory 320 of the battery management device 210, the request signal may be sent to at least one other node through the communication network under the control of the communication unit 350. Conversely, a control signal, command, content, file, etc. provided under the control of a processor of at least one other node may be received by the battery management device 210 through the communication unit 350. According to one embodiment, the communication unit 350 may send impedance information to a server and receive internal temperature information of the battery from the server.

[0076] The controller 310 may be a configuration that generally controls the battery management device 210. For example, the controller 310 may control the battery management device 210 to perform Figure 4 and Figure 5 operation.

[0077] Specifically, the controller 310 may control the operation of the battery management device 210 using various programs stored in the memory 320 of the battery management device 210. The controller 310 may include a CPU, a RAM, a ROM, a system bus, etc. The controller 310 may be implemented as a single CPU or multiple CPUs (or DSP, SOC). In one embodiment, the controller 310 may be implemented as a digital signal processor (DSP: digital signal processor), a microprocessor, or a timing controller (TCON: time controller) that processes digital signals. However, the controller 310 is not limited thereto, but may include one or more of a central processing unit (CPU: central processing unit), a microcontroller unit (MCU: micro controller unit), a microprocessing unit (MPU: micro processing unit), a controller, an application processor (AP: application processor), a communication processor (CP: communication processor), or an ARM processor, or may be defined by corresponding terms. In addition, the controller 310 may be implemented as a system on chip (SOC: system on chip), a large scale integration LSI (1arge scale integration) with a built-in processing algorithm, or may be implemented in the form of a field programmable gate array (FPGA: field programmable gate array).

[0078] According to one embodiment, the controller 310 may estimate the state of charge SOC of the battery. For example, the controller 310 may estimate the state of charge SOC of the battery based on the cell voltage, cell balance, and surface temperature of the battery received from the battery state measurement unit 330. For example, the controller 310 may estimate the state of charge SOC of the battery by a current integration method (Coulomb counting), or estimate various states of the battery by using an extended Kalman filter.

[0079] The controller 310 according to one embodiment may control the impedance measurement unit 340 to apply a frequency band signal to the battery. The controller 310 may receive an impedance voltage and an impedance current from the impedance measurement unit 340, and calculate the impedance using the digital lock-in amplifier principle. In addition, the controller 310 may receive an impedance from the impedance measurement unit 340. The impedance may be represented by a real part and an imaginary part, and the controller 310 may calculate the magnitude and phase of the impedance. In addition, the controller 310 may send an impedance voltage and an impedance current value to an external server or cloud through the communication unit 350, and receive the impedance voltage and impedance current value from the external server or cloud, and calculate the impedance using the digital lock-in amplifier principle in the external server and cloud.

[0080] According to one embodiment, the controller 310 may control the impedance measurement unit 340 to apply a signal of a set frequency band to the battery, and receive a measured impedance corresponding to the set frequency band from the impedance measurement unit. At this time, the set frequency band may be determined by the correlation between the frequency band specific impedance and the state of charge (SOC). Specifically, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the state of charge.

[0081] The set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the state of charge. In other words, it may represent a frequency band where the frequency band specific impedance value remains unchanged regardless of the SOC. For example, the controller 310 may generate a learning model that estimates the internal temperature using the SOC and the impedance corresponding to the frequency range, check the model performance evaluation score for each SOC using the estimated internal temperature and the actual internal temperature in the process of evaluating the learning model, and set the frequency band with the smallest correlation with the SOC as the set frequency band. The model performance evaluation may be performed according to the machine learning model or the neural network model through the mean square error (MSE), the root mean square error (RMSE), R 2 For example, the controller 310 may determine the frequency band in which the average value of the RMSE of the internal temperature of each SOC is the smallest as the set frequency band.

[0082] Furthermore, the controller 310 may determine the frequency band having the smallest correlation with the SOC as the set frequency band using the impedance Bode diagram of the battery for each SOC.

[0083] The controller 310 as described above may also specify frequency bands for multiple modules and multiple channels.

[0084] The controller 310 according to another embodiment may control the impedance measurement unit 340 to apply a signal corresponding to a set frequency band of a specific module to the battery, and may receive a measured impedance corresponding to the set frequency band from the impedance measurement unit. At this time, the set frequency band corresponding to the specific module may be determined by the correlation between the frequency band specific impedance and the channel. Specifically, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the channel.

[0085] That is, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band-specific impedance and the channel. In other words, it may represent a frequency band in which the frequency band-specific impedance value remains constant because the frequency response characteristics are similar regardless of the channel. For example, the controller 310 may generate a learning model that estimates the internal temperature using the impedance corresponding to the channel and the frequency range, check the channel-specific model performance evaluation score using the estimated internal temperature and the actual internal temperature in the process of evaluating the learning model, and set the frequency band with the least correlation with the channel as the set frequency band. The model performance evaluation may be performed according to the machine learning model or the neural network model through the mean square error (MSE), root mean square error (RMSE), R 2 For example, the controller 310 may determine the frequency band in which the average value of the channel-specific RMSE of the internal temperature is the smallest as the set frequency band.

[0086] In addition, the controller 310 may determine, as the set frequency band, a frequency band having the least correlation with the channel using a channel-specific impedance Bode plot of the battery.

[0087] According to another embodiment, the controller 310 may control the impedance measurement unit 340 to apply a signal of a set frequency band corresponding to a specific channel to the battery, and may receive a measured impedance corresponding to the set frequency band from the impedance measurement unit. At this time, the set frequency band corresponding to the specific channel may be determined by the correlation between the frequency band specific impedance and the module. Specifically, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the module.

[0088] That is, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the module. In other words, it may represent a frequency band in which the frequency band specific impedance value remains constant because the frequency response characteristics are similar regardless of the module. For example, the controller 310 may generate a learning model that estimates the internal temperature using the impedance corresponding to the module and the frequency range, check the module-specific model performance evaluation score using the estimated internal temperature and the actual internal temperature in the process of evaluating the learning model, and set the frequency band with the least correlation with the module as the set frequency band. The model performance evaluation may be performed according to the machine learning model or the neural network model through the mean square error (MSE), root mean square error (RMSE), R 2 For example, the controller 310 may determine the frequency band in which the average value of the module-specific RMSE of the internal temperature is the smallest as the set frequency band.

[0089] Furthermore, the controller 310 may determine a frequency band having the least correlation with the module as the set frequency band using a module-specific impedance Bode diagram of the battery.

[0090] Will be in Figures 5 to 8 as well as Figure 12 to Figure 15c The operation of setting the set frequency band is described in detail in.

[0091] The controller 310 according to one embodiment may estimate the internal temperature of the battery by inputting the set impedance into the learning model. The operation of generating such a learning model will be Figure 5 , Fig.12 and Fig.14 Described in detail in.

[0092] The learning model is a model that estimates the internal temperature of a battery, for example, the temperature of an electrolyte of the battery, from a set impedance, and may be a model based on a GPR or polynomial regression algorithm.

[0093] The controller 310 according to one embodiment may control the battery management device 210 to perform fire diagnosis based on the estimated internal temperature of the battery. If the internal temperature is equal to or greater than a first threshold, the controller 310 may issue a warning notification for a fire risk. For example, if the estimated internal temperature is equal to or greater than the first threshold, the controller 310 may send a risk signal through the communication unit 350.

[0094] If the internal temperature is equal to or greater than the second threshold, the controller 310 may perform fire diagnosis.

[0095] That is, when the internal temperature is equal to or greater than the second threshold, the controller 310 may determine that there is a possibility of fire in the battery and control the battery management device 210 to enter the fire diagnosis mode. For example, when the estimated internal temperature is equal to or greater than the second threshold, the controller 310 may shorten the monitoring cycle of the battery state measurement unit 330, shorten the SOC estimation cycle, or shorten the battery cooling system cooling cycle. In addition, when the internal temperature is equal to or greater than the second threshold, the controller 310 may increase the charging margin of the battery through charging / discharging control.

[0096] The controller 310 according to one embodiment may control the battery management device 210 to perform battery management in a normal mode when the internal temperature is less than a first threshold.

[0097] The controller 310 according to one embodiment may control the battery management device 210 to perform fire management based on the phase change of the set impedance. As previously described, before thermal runaway, there may be a rapid change in the impedance phase, where, for example, if the change in the set impedance phase is equal to or greater than the third threshold, the controller 310 may determine that the probability of a fire is high and control the battery management device 210 to enter the fire management mode. For example, if the change in the set impedance phase is equal to or greater than the third threshold, the controller 310 may use a fire extinguishing device to extinguish a battery fire. The controller 310 may use a fire extinguishing water supply device to extinguish a battery fire, or may use another fire extinguishing water supply device to isolate the battery.

[0098] According to one embodiment, if the set impedance variation is less than the third threshold, the controller 310 may control the battery management device 210 to perform battery management in a normal mode.

[0099] The fire management mode described above may be executed independently and in parallel with the fire risk and diagnosis mode, or may be executed dependent on the fire diagnosis mode. For example, the controller 310 according to one embodiment may control to enter the fire risk mode when the internal temperature is equal to or greater than a first threshold, to enter the fire diagnosis mode when the internal temperature is equal to or greater than a second threshold in the fire risk mode, and to enter the fire management mode when the phase change amount of the impedance is equal to or greater than a third threshold in the fire diagnosis mode.

[0100] The controller 310 according to one embodiment may control the system to enter the general mode when the internal temperature is less than the first threshold value, and not enter the fire diagnosis mode even when the phase change amount of the impedance is equal to or greater than the third threshold value in the fire management mode. This is to perform fire prediction based on two variables, the battery internal temperature and the phase change amount of the battery impedance, to perform more reliable prediction.

[0101] The controller 310 according to one embodiment may generate a learning model. The controller 310 may determine a set impedance corresponding to a set frequency band and a set internal temperature of the battery as a data set, and use the data set to generate a learning model that estimates the internal temperature of the battery according to the set impedance. However, such a learning model may be generated by a separate computing device including at least one of a GPU, a CPU, and a TPU, and may be stored in the memory 320 or in a separate server.

[0102] Figure 4 is a flowchart of a fire estimation operation of a battery management device according to an embodiment of the present invention.

[0103] Reference Figure 4 The battery management device can measure the set impedance corresponding to the set frequency band from the impedance measurement unit in step S410. The set frequency band and the specific frequency can be determined by Figure 5 The set frequency band may be determined by the correlation between the frequency band specific impedance and the state of charge (SOC).

[0104] According to one embodiment, the set frequency band may represent a frequency band that minimizes the correlation between the frequency band specific impedance and the state of charge. For example, the battery management device may generate a learning model that estimates the internal temperature using the impedance corresponding to the SOC and the frequency band, and in the process of evaluating the learning model, the model performance evaluation score for each SOC is checked with the estimated internal temperature and the actual internal temperature, and the frequency band with the smallest correlation with the SOC is set as the set frequency band. The model performance evaluation can be performed according to the machine learning model or the neural network model through the mean square error (MSE), root mean square error (RMSE), R 2 For example, the battery management device may determine the set frequency band as the frequency band in which the average value of the RMSE of the internal temperature for each SOC is the smallest.

[0105] In addition, the battery management device may use the impedance Bode diagram of the battery for each SOC to determine the frequency band with the smallest correlation between SOC and impedance as the set frequency band. In this case, the Bode diagram may be at least one of a magnitude Bode diagram and a phase Bode diagram of impedance.

[0106] The battery management device according to one embodiment may estimate the internal temperature of the battery by inputting the set impedance into the learning model in step S420. For example, the battery management device may estimate the internal temperature of the battery by inputting the phase value of the set impedance. The internal temperature of the battery may represent the temperature of the electrolyte inside the battery.

[0107] A learning model according to one embodiment may be generated based on a data set including a set impedance and an internal temperature of a battery.

[0108] The battery management device according to one embodiment may perform a battery fire risk notification function in step S430 . For example, if the estimated battery internal temperature is equal to or greater than the first threshold, the battery management device may send a fire risk notification message through the communication unit 350 .

[0109] The battery management device according to one embodiment may perform battery fire diagnosis in step S440. For example, if the estimated internal temperature of the battery is equal to or greater than the second threshold, the battery management device may perform fire diagnosis. That is, if the internal temperature is equal to or greater than the second threshold, the battery management device may determine that there is a possibility of fire in the battery and enter a fire diagnosis mode. For example, if the estimated internal temperature is equal to or greater than the second threshold, the battery management device may shorten the monitoring cycle of the battery state measurement unit 330, shorten the SOC estimation cycle, or shorten the battery cooling system cooling cycle. In addition, if the internal temperature is equal to or greater than the second threshold, the battery management device may increase the charging margin of the battery through charge / discharge control. In addition, if the internal temperature is less than the first threshold, the battery management device according to one embodiment may perform battery management in normal mode.

[0110] The battery management device according to one embodiment may perform battery fire management in step S450. For example, if the phase change amount of the set impedance is equal to or greater than the third threshold, the battery management device may determine that the probability of a fire is high and enter a fire management mode. In one embodiment, if the change amount of the set impedance is equal to or greater than the third threshold, the battery management device may use a fire extinguishing device to extinguish the battery fire. The battery management device may use a fire extinguishing water supply device to extinguish the battery fire, or may use another fire extinguishing water supply device to isolate the battery.

[0111] When the set impedance change amount is less than the third threshold, the battery management device may perform battery management in a normal mode.

[0112] The fire management mode can be executed independently and in parallel with the fire risk and diagnosis mode, or can be executed dependent on the fire diagnosis mode. For example, a battery management device according to one embodiment can be controlled to enter the fire risk mode when the internal temperature is equal to or greater than a first threshold; enter the management mode when the internal temperature is equal to or greater than a second threshold; and enter the fire management mode when the phase change of the impedance in the fire management mode is equal to or greater than a third threshold.

[0113] The battery management device according to one embodiment may enter the normal mode when the internal temperature is less than the first threshold value, and may not enter the fire diagnosis mode when the phase change amount of the impedance is equal to or greater than the third threshold value in the fire management mode. This is to perform fire prediction based on two variables, the internal temperature of the battery and the phase change amount of the battery impedance, so as to perform more reliable prediction.

[0114] Figure 5 is a flowchart illustrating an operation of generating a learning model of a battery management device according to an embodiment of the present invention.

[0115] See also Figure 5 , the battery management device may set the internal temperature of the battery in step S510. For example, the battery management device may use a separate temperature chamber to set the internal temperature of the battery so that the battery is in thermal equilibrium with the chamber temperature.

[0116] The battery management device may acquire the frequency band specific impedance of the battery corresponding to the internal temperature of the battery from the impedance measurement unit in step S520. The battery management device may acquire the impedance for the full frequency range from the impedance measurement unit and store the data.

[0117] According to one embodiment, the battery management device may obtain the state of charge (SOC) of the battery in step S530. The battery management device may obtain the state of charge of the battery from the battery state measurement unit, or calculate the state of charge of the battery based on the received battery current, single cell voltage, and battery surface temperature. That is, the battery management device may obtain the band-specific impedance of the battery for each state of charge (SOC) of the battery in steps S510 and S520.

[0118] In one embodiment, the battery management device may determine the set frequency band based on the correlation between the frequency band specific impedance and the state of charge in step S540. In one embodiment, the battery management device may use the impedance Bode diagram for each SOC to determine the frequency band with the smallest correlation with the SOC as the set frequency band.

[0119] In one embodiment, the battery management device may determine the set impedance corresponding to the set frequency band among the frequency band specific impedances and the set internal temperature of the battery as a data set in step S550. Specifically, the battery management device may determine a data set characterized by the impedance data corresponding to the set frequency band among the impedance data about the entire frequency range and labeled with the internal temperature data of the battery. For example, the battery management device may determine a data set characterized by at least one of the real part, imaginary part, magnitude, or phase of the impedance and labeled with the internal temperature data.

[0120] In one embodiment, the battery management device may generate a learning model for estimating the internal temperature of the battery according to the set impedance using the data set in step S560. The learning model may be a model based on GPR or polynomial regression algorithm for estimating the internal temperature of the battery according to the set impedance.

[0121] The battery management apparatus according to one embodiment may evaluate a learning model for estimating the internal temperature of the battery according to the set impedance and determine the learning model in step S570 .

[0122] The battery management device according to another embodiment may generate a learning model for estimating the internal temperature of the battery according to the frequency band specific impedance in step S560. That is, the battery management device may generate a learning model for estimating the internal temperature using the state of charge and the impedance throughout the frequency.

[0123] The battery management device according to another embodiment may evaluate the learning model for estimating the internal temperature using the state of charge and the impedance over frequency in step S570. The learning model performance evaluation may be performed by using the mean square error (MSE), the root mean square error (RMSE), R 2 Specifically, the battery management device may confirm a root mean square error (RMSE) for each SOC using the estimated internal temperature and the actual internal temperature.

[0124] Thereafter, the battery management device may proceed to step S540 again to determine the frequency band in which the correlation between the frequency band specific impedance and the state of charge is the smallest as the set frequency band. For example, the battery management device may determine the frequency band in which the average RMSE of the internal temperature by the state of charge (SOC) is the smallest as the set frequency band. By repeating this process, the set frequency band may be determined, and a learning model for estimating the internal temperature of the battery using the set impedance corresponding to the set frequency band may be generated.

[0125] Figures 6a to 6d 3 are Bode diagrams showing a first correlation between the frequency band specific impedance and the charging state according to an embodiment of the present invention, respectively.

[0126] As described above, the set frequency band may indicate a frequency band where the correlation between the frequency band specific impedance and the state of charge is minimal. The battery management device may determine the frequency band with the least correlation with the state of charge (SOC) as the set frequency band using the impedance Bode diagram for each state of charge (SOC).

[0127] Reference Figure 6a , showing a first Bode diagram 610 of impedance phase correlation according to the internal temperature of the battery when the state of charge (SOC) is 95%; referring to Figure 6b , showing a second Bode diagram 620 of impedance phase correlation according to the internal temperature of the battery when the state of charge (SOC) is 70%; referring to Figure 6c , showing a third Bode diagram 630 of impedance phase correlation according to the internal temperature of the battery when the state of charge (SOC) is 50%: and referring to Figure 6d, a fourth Bode diagram 640 showing the impedance phase correlation according to the battery internal temperature when the state of charge (SOC) is 25%.

[0128] When the phase change according to the state of charge (SOC) in the frequency domain of the Bode diagram is seen, it can be known that in the frequency band of 20 Hz to 1 kHz, the displayed phase value according to the temperature is similar regardless of the state of charge (SOC). Specifically, when comparing the impedance phase 611 in the first frequency band of the first Bode diagram 610, the impedance phase 621 in the first frequency band of the second Bode diagram 620, the impedance phase 631 in the first frequency band of the third Bode diagram 630, and the impedance phase 641 in the first frequency band of the fourth Bode diagram 640, it can be known that there is a correlation with the state of charge (SOC) in the relationship between impedance and temperature. However, when comparing the impedance phase 613 in the second frequency band of the first Bode diagram 610, the impedance phase 623 in the second frequency band of the second Bode diagram 620, the impedance phase 633 in the second frequency band of the third Bode diagram 630, and the impedance phase 643 in the second frequency band of the fourth Bode diagram 640, it can be known that the correlation between the impedance and temperature and the state of charge (SOC) is low. Therefore, the battery management device can determine the second frequency band in which the correlation between the impedance and temperature and the state of charge (SOC) is low as the set frequency band.

[0129] Figure 7 is a RMSE graph according to frequency bands showing a second correlation between frequency band specific impedance and state of charge according to an embodiment of the present invention, and Figure 8 is a RMSE graph according to frequency bands in which the correlation between the frequency band specific impedance and the state of charge is low according to an embodiment of the present invention.

[0130] As described above, the set frequency band may indicate a frequency band where the correlation between the frequency band specific impedance and the state of charge is minimal. The battery management device may determine the frequency band where the average value of the RMSE of the internal temperature for each state of charge (SOC) is minimal as the set frequency band.

[0131] The battery management device can generate a learning model that estimates the internal temperature using the state of charge (SOC) and the impedance corresponding to the frequency range, and use the estimated internal temperature and the actual internal temperature to check the RMSE for each state of charge (SOC) in the process of evaluating the learning model, and set the frequency band with the least correlation with the state of charge (SOC) as the set frequency band.

[0132] Reference Figure 7 and Figure 8, the RMSE value of the state of charge (SOC) of the internal temperature has a minimum value in the first part 710 and the second part 720. Therefore, the battery management device may determine one of the first part 710 and the second part 720 as the set frequency band. The battery management device may narrow or expand the set frequency band by repeatedly performing this process. For example, the set frequency band may be a frequency band of 40 Hz to 80 Hz, or the specific frequency may be 44 Hz.

[0133] Fig. 9 is a view schematically showing a battery pack according to an embodiment of the present invention. Fig. 9 The invention is a battery management system for a battery pack 900 having a plurality of battery modules and a plurality of channels, wherein the system may include a plurality of battery modules 910 , a battery management unit (BMU) 930 , and a cell management (monitoring) unit (CMU) 920 .

[0134] Fig. 9 Itself corresponds to Figure 2 For example, the battery module 910 may be composed of a plurality of batteries 230, and the reference Fig.10 The battery module 910 is described in detail. The plurality of CMUs 920 and the plurality of BMUs 930 may be combined to perform at least one operation of the battery management device 210 .

[0135] The CMU 920 can monitor and manage the battery cells. It can measure the voltage, temperature, and impedance of each battery cell and send the data to the BMU 930. The CMU 920 manages the battery modules, for example, a single CMU 920 can manage 2 to 4 to 8 battery modules 910.

[0136] The BMU 930 can monitor and manage the status of the entire battery system. Data can be received from each of the multiple CMUs 920, and based on this, the state of charge (SOC) and state of health (SOH: state of health) of the entire battery pack can be estimated. In addition, the BMU 930 can protect the battery in situations such as overcharge, over discharge, and overheating. The BMU 930 can specifically determine a set frequency band for each of the multiple modules and multiple channels, or measure a set impedance value in a set frequency band to perform battery internal temperature estimation.

[0137] Fig.10 Schematically illustrates a battery module according to an embodiment of the present invention. Fig.10, one battery module 910 may include a plurality of battery cells 1001. Specifically, the battery module 910 may have a plurality of battery cells 1001 connected in series and in parallel. For example, a battery module 910 in which the battery cells xP 1010 are connected in parallel and the battery cells xS 1020 are connected in series may be referred to as an xPxS battery module, and such a series connection unit of battery cells 100 1 may be referred to as a channel 1030. For example, a 2P6S battery module 910 may have a total of six channels. Likewise, the presence of a plurality of battery modules 910 may be referred to as a multi-module, multi-channel battery system.

[0138] Fig.11 is a flowchart illustrating a fire estimation operation of a battery management device according to an embodiment of the present invention.

[0139] Reference Fig.11 In step S1110, the battery management device can measure the corresponding first set impedance in the first set frequency band for the specific module from the impedance measurement unit, and can measure the corresponding second set impedance in the second set frequency band for the specific channel. For example, if the first set impedance frequency band is 20 Hz, the impedance of the corresponding frequency band can be measured, and if the second set impedance frequency band is 100 Hz, the impedance of the corresponding frequency band can be measured respectively.

[0140] The first impedance can be set by Fig.12 The second impedance setting can be determined by Fig.14 to determine the learning outcomes.

[0141] The first set frequency band may be calculated by the channel-specific frequency band-specific impedance for each battery module. For example, the first set frequency band may be determined by the correlation between the frequency band-specific impedance and the channel.

[0142] For example, the battery management device may generate a first learning model for estimating the internal temperature for each battery module using a channel-specific frequency band-specific impedance. In the process of evaluating the model, the channel-specific model performance evaluation score is checked using the estimated internal temperature and the actual internal condition, and the frequency band with the least correlation with the channel is set as the set frequency band. Alternatively, a channel-specific frequency band-specific impedance Bode plot or a Nyquist plot may be used to determine the frequency band that minimizes the correlation between the channel and the impedance as the set frequency band. At this time, the Bode plot may use at least one of a magnitude Bode plot and a phase Bode plot of the impedance. Model performance evaluation may be performed based on a machine learning model or a neural network model through mean square error (MSE), root mean square error (RMSE), R 2 Scores etc. to determine.

[0143] In addition, the second set frequency band can be calculated based on the module-specific frequency band specific impedance for each battery channel. For example, the second set frequency band can be determined by the correlation between the frequency band specific impedance and the module.

[0144] For example, the battery management device may generate a second learning model for estimating the internal temperature using a module-specific frequency band-specific impedance for each battery channel. In the process of evaluating the model, the channel-specific model performance evaluation score is checked using the estimated internal temperature and the actual internal condition, and the frequency band with the least correlation with the module is set as the set frequency band. Alternatively, a module-specific frequency band-specific impedance Bode plot or Nyquist plot may be used to determine the frequency band that minimizes the correlation between the module and the impedance as the set frequency band. At this time, the Bode plot may use at least one of a magnitude Bode plot and a phase Bode plot of the impedance. Model performance evaluation may be performed based on a machine learning model or a neural network model through mean square error (MSE), root mean square error (RMSE), R 2 Scores etc. to determine.

[0145] The battery management device according to one embodiment may estimate the internal temperature of the battery by inputting the first set impedance into the first learning model and the second set impedance into the second learning model in step S1120. The internal temperature of the battery may indicate the temperature of the electrolyte inside the battery.

[0146] For example, the battery management device may use the first internal temperature estimated by the first learning model and the second internal temperature estimated by the second learning model and perform internal temperature estimation with different weights.

[0147] [Equation 1]

[0148] T=aT1+(1-a)T2

[0149] T is the estimated internal temperature, T1 is the first internal temperature, T2 is the second internal temperature, and a is the weight.

[0150] For example, the battery management device can, in a battery pack consisting of thirty-two 2P6S modules, i) measure the impedance of battery module No. 8 using a first set frequency band corresponding to battery module No. 8 and input it into a first learning model, and ii) measure the impedance of channel 3 using a second set frequency band corresponding to channel 3 and input it into a second learning model, thereby estimating the internal temperature of channel 3 of battery module No. 8.

[0151] For the following steps S1130 to S1150, the Figure 4 Any repeated descriptions described in steps S430 to S450.

[0152] Fig.12 is a flowchart illustrating an operation of generating a learning model for each module battery management device according to an embodiment of the present invention.

[0153] Reference Fig.12 In step S1210, the battery management device may set the internal temperature of the battery. For example, the battery management device may use a separate temperature chamber to set the internal temperature of the battery so that the battery and chamber temperatures are in thermal equilibrium.

[0154] The battery management device may acquire the channel-specific frequency band-specific impedance for each battery module from the impedance measurement unit in step S1220. The battery management device may acquire the channel-specific frequency range impedance for each battery module from the impedance measurement unit and store the data.

[0155] In one embodiment, the battery management device may determine a set frequency band corresponding to a specific battery module based on the frequency band-specific impedance and the channel-specific correlation in step S1230. In one embodiment, the battery management device may use a channel-specific impedance Bode plot or a Nyquist plot to determine a frequency band with the smallest correlation with the channel as the set frequency band. In each battery module, a set frequency band with similar frequency response characteristics of all channels may be determined and used for internal temperature estimation.

[0156] For example, the battery management device may identify a Bode plot of a frequency band specific impedance magnitude with a channel specific legend for a specific battery module in the battery pack, such as Fig.13a At this time, it can be confirmed that in the frequency band of 2 Hz to 30 Hz, the correlation between the channel and the impedance is low. The battery management device can determine the set frequency band corresponding to the specific battery module in the frequency band where the correlation between the channel and the impedance is low.

[0157] The battery management device can identify the Bode plot of the phase of the band-specific impedance of a specific battery module in the battery pack with a channel-specific legend, such as Fig.13b At this time, it can be confirmed that the correlation between the channel and the impedance phase is low in the frequency band of 2 Hz to 30 Hz. The battery management device can determine the set frequency band corresponding to the specific battery module in the frequency band with low correlation between the channel and the impedance phase.

[0158] The battery management device can identify the Nyquist plot of the phase of the band-specific impedance with the channel-specific legend for a specific battery module in the battery pack, such as Fig.13c At this time, it can be confirmed that the correlation between the channel and the impedance is low in the frequency band of 2 Hz to 30 Hz. The battery management device can determine the set frequency band corresponding to the specific battery module in the frequency band with low correlation between the channel and the impedance.

[0159] In one embodiment, in step S1240, the battery management device may determine the set impedance corresponding to the set frequency band among the frequency band specific impedances and the set internal temperature of the battery as a data set. Specifically, the battery management device may determine a data set characterized by the impedance data corresponding to the set frequency band among the impedance data about the full frequency range and labeled with the internal temperature data of the battery. For example, the battery management device may determine a data set characterized by at least one of the real part, imaginary part, magnitude, or phase of the impedance and labeled with the internal temperature data.

[0160] In one embodiment, in step S1250, the battery management device may generate a learning model for estimating the internal temperature of the battery according to the set impedance using the data set. The learning model is a model for estimating the internal temperature of the battery according to the set impedance corresponding to a specific battery module, and may be a model based on a GPR or polynomial regression algorithm.

[0161] The battery management apparatus according to one embodiment may evaluate a learning model for estimating the internal temperature of the battery according to the set impedance and determine the learning model in step S1260 .

[0162] The battery management device according to another embodiment may generate a learning model for estimating the internal temperature of the battery according to the frequency band specific impedance in step S1250. That is, the battery management device may generate a learning model for estimating the internal temperature using impedance across frequencies and channels.

[0163] In another embodiment, the battery management device may evaluate the learning model for estimating the internal temperature using impedance across frequencies and channels in step S1260. The model performance evaluation may be performed based on the machine learning model or the neural network model by using mean square error (MSE), root mean square error (RMSE), R 2 Specifically, the battery management device may confirm a root mean square error (RMSE) for each channel using the estimated internal temperature and the actual internal temperature.

[0164] Thereafter, the battery management device may proceed to step S1230 again to determine the frequency band in which the correlation between the frequency band specific impedance and the channel is the smallest as the set frequency band. For example, the battery management device may determine the frequency band in which the RMSE average value of the internal temperature for each channel is the smallest as the set frequency band. By repeating this process, the set frequency band may be determined, and a learning model for estimating the internal temperature of the battery using the set impedance corresponding to the set frequency band may be generated.

[0165] Fig.14 is a flowchart illustrating an operation of generating a learning model of a battery management device for each channel according to an embodiment of the present invention.

[0166] Reference Fig.14 , the battery management device may set the internal temperature of the battery in step S1410. For example, the battery management device may use a separate temperature chamber to set the internal temperature of the battery so that the battery and chamber temperatures are in thermal equilibrium.

[0167] In one embodiment, the battery management device may obtain module-specific frequency band-specific impedance for each channel from the impedance measurement unit in step S1420. The battery management device may obtain impedance across frequencies for each module for each channel from the impedance measurement unit and store the data.

[0168] In one embodiment, the battery management device may determine a set frequency band corresponding to a specific channel based on the frequency band specific impedance and the module specific correlation in step S1430. In one embodiment, the battery management device may use a module specific impedance Bode diagram or a Nyquist diagram to determine a frequency band with the smallest correlation with the module as the set frequency band. In each battery channel, a set frequency band with similar frequency response characteristics of all modules may be determined and used for internal temperature estimation.

[0169] For example, the battery management device may identify a Bode plot of a frequency band specific impedance magnitude with a module specific legend for a specific channel in the battery pack, such as Fig.15a At this time, it can be confirmed that the correlation between the module and the impedance size is low in the frequency band of 100 Hz to 350 Hz. The battery management device can determine the set frequency band corresponding to the specific channel in the frequency band where the correlation between the module and the impedance size is low.

[0170] The battery management device can identify a Bode plot of the phase of the band-specific impedance with a module-specific legend for a specific channel in the battery pack, such as Fig.15b At this time, it can be confirmed that the correlation between the module and the impedance phase is low in the frequency band of 100 Hz to 350 Hz. The battery management device can determine the set frequency band corresponding to the specific channel in the frequency band where the correlation between the module and the impedance magnitude is low.

[0171] The battery management device can identify the Nyquist plot of the phase of the band-specific impedance with the module-specific legend for a specific channel in the battery pack, such as Fig.15c At this time, it can be confirmed that the correlation between the module and the impedance is low in the frequency band of 100 Hz to 350 Hz. The battery management device can determine the set frequency band corresponding to the specific channel in the frequency band where the correlation between the module and the impedance size is low.

[0172] In one embodiment, the battery management device may determine the set impedance corresponding to the set frequency band among the frequency band specific impedances and the set internal temperature of the battery as a data set in step S1440. Specifically, the battery management device may determine a data set characterized by the impedance data corresponding to the set frequency band among the impedance data of the entire frequency range and labeled with the internal temperature data of the battery. For example, the battery management device may determine a data set characterized by at least one of the real part, imaginary part, magnitude, or phase of the impedance and labeled with the internal temperature data.

[0173] In one embodiment, the battery management device may generate a learning model for estimating the internal temperature of the battery according to the set impedance using the data set in step S1450. The learning model is a model for estimating the internal temperature of the battery according to the set impedance corresponding to a specific channel, and may be a model based on a GPR or polynomial regression algorithm.

[0174] The battery management apparatus according to one embodiment may evaluate a learning model for estimating the internal temperature of the battery according to the set impedance and determine the learning model in step S1460 .

[0175] The battery management device according to another embodiment may generate a learning model for estimating the internal temperature of the battery according to the frequency band specific impedance in step S1450. That is, the battery management device may generate a learning model for estimating the internal temperature using impedance and modules throughout the frequency.

[0176] In another embodiment, the battery management device may evaluate the learning model that estimates the internal temperature using impedance and module throughout the frequency in step S1460. The model performance evaluation may be performed based on the machine learning model or the neural network model by using mean square error (MSE), root mean square error (RMSE), R 2 Specifically, the battery management device may confirm a root mean square error (RMSE) for each module through the estimated internal temperature and the actual internal temperature.

[0177] Thereafter, the battery management device may proceed to step S1430 again to determine the frequency band in which the correlation between the frequency band specific impedance and the module is the smallest as the set frequency band. For example, the battery management device may determine the frequency band in which the average value of the module-specific RMSE of the internal temperature is the smallest as the set frequency band. By repeating this process, the set frequency band may be determined, and a learning model for estimating the internal temperature of the battery using the set impedance corresponding to the set frequency band may be generated.

[0178] In the above embodiment, the battery management device can estimate the internal temperature of the battery. In addition, the battery management device can also estimate the internal temperature of the battery to perform fire prediction, diagnosis and management.

[0179] Although the embodiments have been described above through limited embodiments and drawings, those skilled in the art may make various modifications and variations based on the above description. For example, even if the described techniques are performed in an order different from the described methods, and / or the components of the described systems, structures, devices, circuits, etc. are mixed or combined in a form different from the described methods, or replaced or substituted by other components or equivalents, appropriate results can be achieved. In other embodiments consistent with the principles of the present invention, the order of these operations can be changed. In addition, unrelated operations can be performed in parallel.

[0180] For example, impedance measurement may be performed based on a set frequency band determined based on a correlation between a set frequency band corresponding to a specific module and SOC, and internal temperature estimation may be performed. Alternatively, impedance measurement may be performed based on a set frequency band determined based on a correlation between a set frequency band corresponding to a specific channel and SOC, and internal temperature estimation may be performed.

[0181] In addition, the learning model according to the present invention may be generated by a separate computing device including at least one of a GPU, a CPU, and a TPU, and may be stored in a memory of a battery management device or stored in a separate server and provided through communication.

[0182] Accordingly, other implementations, embodiments, and equivalents are within the scope of the appended claims.

Claims

1. A battery management device, comprising: an impedance measuring unit configured to measure the impedance of the battery for each frequency band; Controller, configured as: controlling the impedance measurement unit to apply a signal of a set frequency band to the battery, receiving a set impedance corresponding to the set frequency band from the impedance measurement unit, and inputting the set impedance into a learning model to estimate the internal temperature of the battery, The set frequency band is determined by the correlation between the impedance and the state of charge (SOC) for each frequency band.

2. The battery management device according to claim 1, wherein: The set frequency band is a frequency band that minimizes the correlation between the impedance for each frequency band and the state of charge (SOC).

3. The battery management device according to claim 1, wherein: The learning model is generated based on a data set including the set impedance and an internal temperature of the battery.

4. The battery management device according to claim 3, wherein: The learning model is a polynomial regression model between the internal temperature of the battery and the set impedance.

5. The battery management device according to claim 1, wherein: The controller is configured to send a fire risk message when the estimated internal temperature of the battery is equal to or greater than a first threshold.

6. The battery management device according to claim 1, wherein: The controller is configured to perform fire diagnosis when the estimated internal temperature of the battery is equal to or greater than a second threshold.

7. The battery management device according to claim 6, wherein: The controller is configured to execute fire management when the phase change amount of the set impedance over time is equal to or greater than a third threshold.

8. A battery management method comprising the following steps: The impedance measuring unit measures the set impedance corresponding to the set frequency band; estimating the internal temperature of the battery by inputting the set impedance into a learning model, The set frequency band is determined by the correlation between the impedance for each frequency band and the state of charge (SOC).

9. The battery management method according to claim 8, wherein: The set frequency band is a frequency band that minimizes the correlation between the impedance for each frequency band and the state of charge (SOC).

10. The battery management method according to claim 8, further comprising the following steps: A fire risk alarm is issued when the estimated battery internal temperature is equal to or greater than a first threshold.

11. The battery management method according to claim 8, further comprising the following steps: Fire diagnosis is performed when the estimated battery internal temperature is equal to or greater than a second threshold value.

12. The battery management method according to claim 11, wherein: The performing of fire diagnosis includes performing fire management when the phase change amount of the set impedance over time is equal to or greater than a third threshold value.

13. A method for estimating the internal temperature of a battery, comprising the steps of: Set the internal temperature of the battery; acquiring, from an impedance measurement unit, an impedance of the battery for each frequency band corresponding to an internal temperature of the battery; Obtaining a state of charge (SOC) of the battery; determining a set frequency band based on the correlation between the impedance for each frequency band and the charging state; determining a set impedance corresponding to the set frequency band among the impedances for each frequency band and the set internal temperature of the battery as a data set; A learning model for estimating an internal temperature of the battery based on the set impedance is generated using the data set.

14. The method for estimating the internal temperature of a battery according to claim 13, wherein: The learning model is a polynomial regression model between the internal temperature of the battery and the set impedance.

Images