Secondary battery state estimation system, secondary battery state estimation method, and recording medium

Abstract

The invention provides a state estimation system for a secondary battery, a state estimation method for a secondary battery, and a recording medium. The state estimation system for a secondary battery suppresses a reduction in estimation accuracy of an internal state of the secondary battery. A system including a secondary battery state estimation device includes an OCV estimation unit that acquires a machine learning model and estimates an open circuit voltage using the machine learning model. The OCV estimation unit acquires first data including time-series data of a current, a closed-circuit voltage, and an open-circuit voltage of the secondary battery in a predetermined state including at least one of charging and discharging. The OCV estimation unit acquires, on the basis of the first data, a machine learning model for outputting an overvoltage of the secondary battery at an arbitrary timing. The OCV estimation unit estimates an overvoltage of the secondary battery to be estimated at an arbitrary time by inputting second data having data of a current and a closed-circuit voltage at a predetermined time detected in the secondary battery to be estimated into the machine learning model.

Description

Technical Field

[0001] This invention relates to a state estimation system for secondary batteries, a state estimation method for secondary batteries, and a recording medium. Background Technology

[0002] In recent years, research and development have been conducted on secondary batteries that contribute to energy efficiency in order to ensure that more people can afford, rely on, and achieve sustainable and advanced energy pathways.

[0003] Conventionally, for example, there is a known device that filters historical data of a battery's closed-circuit voltage (CCV) to obtain an OCV curve representing the change in open-circuit voltage (OCV) corresponding to the discharge capacity (e.g., see International Publication No. 2023 / 054443). This device, for example, extracts data that can be considered as open-circuit voltage from the historical data of the closed-circuit voltage through filtering based on specified conditions related to the battery's current, voltage, and temperature. Summary of the Invention

[0004] In technologies related to secondary batteries, it is a challenge to suppress the decrease in the accuracy of estimating internal states, including the OCV curve, even when the secondary battery has deteriorated. For example, in the aforementioned prior art devices, when the overvoltage increases due to the increase in internal resistance caused by the deterioration of the secondary battery, there is a possibility that the accuracy of estimating the open-circuit voltage (OCV) will decrease.

[0005] Furthermore, even when the open-circuit voltage (OCV) is estimated based on an electrochemical model that estimates the internal resistance or the relationship between the open-circuit voltage (OCV) at the start of discharge and the discharge capacity, there is a possibility that the estimation accuracy of the open-circuit voltage (OCV) may decrease as the internal resistance increases due to the degradation of the secondary battery.

[0006] The purpose of this invention is to suppress the decrease in the accuracy of estimating the internal state of a secondary battery.

[0007] The first aspect of the present invention relates to a state estimation system for a secondary battery, comprising: a learning model constructed by acquiring first data having time-series data of the current, closed-circuit voltage, and open-circuit voltage of the secondary battery in a predetermined state including at least one of charging and discharging, and constructing, based on the first data, the learning model outputting the open-circuit voltage of the secondary battery at any given time or an overvoltage as the difference between the open-circuit voltage and the closed-circuit voltage; and a voltage estimation unit that inputs second data having data of the current and closed-circuit voltage detected in the secondary battery to be estimated at a predetermined time into the learning model, thereby estimating the open-circuit voltage or overvoltage of the secondary battery to be estimated at any given time.

[0008] The second approach, based on the secondary battery state estimation system described in the first approach, may also include data in which the second data comprises time-series data of the current and closed-circuit voltage detected in the secondary battery of the estimation object.

[0009] The third approach, based on the secondary battery state estimation system described in the second approach, may involve the voltage estimation unit inputting data from a predetermined time interval containing current and closed-circuit voltage detected in the secondary battery of the estimation target before a predetermined time, thereby estimating the open-circuit voltage or overvoltage of the secondary battery of the estimation target at the predetermined time.

[0010] The fourth approach, based on the secondary battery state estimation system described in the second or third approach above, may involve the voltage estimation unit inputting back interval data containing current and closed-circuit voltage data detected in the secondary battery of the estimation target within a specified time interval after the specified time, thereby estimating the open-circuit voltage or overvoltage of the secondary battery of the estimation target at the specified time.

[0011] The fifth option, based on the secondary battery state estimation system described in the first or second option above, may also be that the second data does not contain data related to the temperature of the secondary battery of the estimation object.

[0012] The sixth option, based on the state estimation system of the secondary battery described in the first or second option above, may also involve the learning model outputting the overvoltage of the secondary battery.

[0013] The seventh option, based on the state estimation system of the secondary battery described in the first or second option above, may also involve the learning model outputting the open-circuit voltage of the secondary battery.

[0014] The eighth scheme, based on the state estimation system of the secondary battery described in the first or second scheme above, may also include the first data having time series data of the current, closed-circuit voltage and open-circuit voltage of the secondary battery that has deteriorated.

[0015] The ninth aspect of the present invention relates to a state estimation method for a secondary battery, which is a state estimation method for a secondary battery executed by an electronic device. The electronic device includes a processing unit for estimating the open-circuit voltage or overvoltage of the secondary battery to be estimated. The state estimation method for the secondary battery includes: a model acquisition step, which acquires first data having time series data of the current, closed-circuit voltage, and open-circuit voltage of the secondary battery in a predetermined state including at least one of charging and discharging, and acquires a learning model based on the first data to output the open-circuit voltage of the secondary battery at any time or an overvoltage as the difference between the open-circuit voltage and the closed-circuit voltage; and a voltage estimation step, which inputs second data having data of the current and closed-circuit voltage detected in the secondary battery to be estimated at a predetermined time into the learning model acquired by the model acquisition step, thereby estimating the open-circuit voltage or overvoltage of the secondary battery to be estimated at any time.

[0016] The tenth aspect of the present invention relates to a recording medium having a recording program in which an electronic device includes a processing unit for estimating the open-circuit voltage or overvoltage of a secondary battery of a presumed object. The program causes a computer of the electronic device to execute: a model acquisition step, acquiring first data having time-series data of the current, closed-circuit voltage, and open-circuit voltage of the secondary battery in a predetermined state including at least one of charging and discharging, and acquiring, based on the first data, a learning model for outputting the open-circuit voltage of the secondary battery at any given time or an overvoltage as the difference between the open-circuit voltage and the closed-circuit voltage; and a voltage estimation step, inputting second data having data of the current and closed-circuit voltage detected in the secondary battery of the presumed object at a predetermined time into the learning model acquired by the model acquisition step, thereby estimating the open-circuit voltage or overvoltage of the secondary battery of the presumed object at any given time.

[0017] According to the first scheme mentioned above, by using a learning model that outputs open-circuit voltage or overvoltage based on input current and closed-circuit voltage data, the reduction in the estimation accuracy of the internal state of the secondary battery can be suppressed.

[0018] In the second scheme described above, the accuracy of the learning model in estimating the open-circuit voltage can be improved by using the second data, which has time-series data.

[0019] In the third scheme described above, the open-circuit voltage can be estimated using past data at the time of comparison, which can improve the versatility of the learning model.

[0020] In the fourth scheme described above, the open-circuit voltage can be estimated from future data using the ratio as the objective, which can improve the versatility of the learning model.

[0021] In the fifth scheme described above, the open-circuit voltage can be estimated without temperature data. For example, even when the learning model is obtained solely based on data from the secondary battery before its degradation, the estimation accuracy of the open-circuit voltage can be improved for the degraded secondary battery.

[0022] In the case of the sixth or seventh scheme described above, the open-circuit voltage of the secondary battery can be easily and accurately estimated.

[0023] According to the eighth or ninth scheme mentioned above, by using a learning model that outputs open-circuit voltage or overvoltage based on input current and closed-circuit voltage data, it is possible to suppress the decrease in the estimation accuracy of the internal state of the secondary battery. Attached Figure Description

[0024] Figure 1 This is a block diagram illustrating the functional structure of a system equipped with the state estimation device for a secondary battery according to an embodiment of the present invention.

[0025] Figure 2 This diagram illustrates an example of the flow of information processed by the estimation unit of the secondary battery state estimation device in an embodiment of the present invention.

[0026] Figure 3 This is a diagram illustrating an example of the correspondence between the open-circuit voltage (OCV) and the closed-circuit voltage (CCV) obtained by the estimation unit of the secondary battery state estimation device in an embodiment of the present invention.

[0027] Figure 4 This is a diagram showing an example of an OCV curve obtained by the estimation unit of the secondary battery state estimation device in an embodiment of the present invention based on the OCP curves of the positive and negative electrodes respectively.

[0028] Figure 5 This is a flowchart illustrating the process performed by the secondary battery state estimation device in an embodiment of the present invention. Detailed Implementation

[0029] Hereinafter, the secondary battery state estimation system, secondary battery state estimation method and recording medium involved in the embodiments of the present invention will be described with reference to the accompanying drawings.

[0030] The secondary batteries involved in the implementation are, for example, detachable or fixedly configured in various electrical devices.

[0031] Various electrical devices include electric vehicles, electric mobile bodies, electric machinery, and power supply units. Electric vehicles include, for example, electric motor vehicles powered by a rotary electric motor driven by a secondary battery, motorcycles and scooters, hybrid vehicles based on a combination of a rotary electric motor and an internal combustion engine, and fuel cell vehicles based on a combination of a secondary battery and a fuel cell. Electric mobile bodies include, for example, robots, mobile work machines, flying vehicles, and water-based or underwater mobile bodies. Electric machinery includes, for example, construction machinery powered by a rotary electric motor. Power supply units include, for example, fixed or mobile power supply units for discharging and charging secondary batteries, or exchange devices for supplying and receiving secondary batteries to users through so-called battery sharing services.

[0032] It should be noted that various electrical devices, such as those in PHVs (Plug-in Hybrid Vehicles) or PHEVs (Plug-in Hybrid Electric Vehicles), can also have external charging capabilities, allowing them to be charged by an external power source (external DC power and external AC power). These electrical devices can also supply power to external sources using electricity from a secondary battery. Furthermore, the rotary motor mounted in an electric vehicle can, in addition to traction, exchange power with the secondary battery through regenerative braking based on rotational power input from the wheel side or through power generation based on power input from the internal combustion engine.

[0033] Figure 1 This is a block diagram showing the functional structure of system 1, which includes a secondary battery state estimation device 10 with an implementation method.

[0034] like Figure 1 As shown, System 1 (secondary battery state estimation system, electronic device) of the embodiment includes, for example, a vehicle 2 and a server 3. Vehicle 2 and server 3 are connected, for example, via a wired or wireless communication network (network) 4. Network 4 is, for example, the Internet, a mobile communication network, a LAN (Local Area Network), and a WAN (Wide Area Network). For example, the LAN is a wired LAN (Local Area Network) of a specified standard such as Ethernet, or a wireless LAN of various standards such as Wi-Fi and Bluetooth (registered trademark).

[0035] The secondary battery state estimation device 10 in the embodiment is, for example, composed of a server 3.

[0036] Vehicle 2 includes, for example, a secondary battery 11, a battery sensor 12, a battery control unit 13, an electric control unit 14, a rotary motor 15, a drive mechanism 16, and an overall processing unit 17.

[0037] The secondary battery 11 is, for example, a type of battery that is repeatedly charged and discharged, such as a lithium-ion battery, a sodium-ion battery, or a nickel-metal hydride battery. The electrolyte of the secondary battery 11 is, for example, a non-aqueous electrolyte such as a liquid, a solid, or a polymer.

[0038] The positive electrode active material constituting the positive electrode of the secondary battery 11 is, for example, a metal oxide containing lithium ions in the case of a lithium-ion battery.

[0039] Metal oxides containing lithium ions include, for example, monomers or mixtures of multiple different composite oxides formed from lithium with metals such as nickel, cobalt, manganese, and aluminum. Composite oxides are classified, for example, from a crystal structure perspective, into layered rock salt type, spinel type, and olivine type. Examples of layered rock salt type composite oxides include lithium cobalt oxide (LCO: LiCoO2) and nickel-cobalt-manganese oxide (NCM: Li(Ni)O2). x Co y Mn z O2), nickel-cobalt-aluminum oxide (NCA:LiNi) x Co y Al x O2), etc. Spinel-type composite oxides include lithium manganese oxide (LMO:LiMn2O4) and lithium nickel manganese oxide (LNMO:LiNi). x Mn y Olivine-type composite oxides include lithium iron phosphate (LFP: LiFePO4) and lithium manganese iron phosphate (LMFP: LiMn). x Fe （1-x） PO4, etc.

[0040] In the case of a lithium-ion battery, the negative electrode active material constituting the negative electrode of the secondary battery 11 is formed from carbon materials, oxide-based materials, or a mixture of materials. Examples of carbon materials include graphite and hard carbon (difficult-to-graphitize carbon). Examples of oxide-based materials include lithium titanate (LTO: Li4Ti5O). 12 ), etc. Hybrid materials include, for example, graphite and silicon oxide (SiO₂). x Mixed materials, such as those containing metals like Si and Sn mixed with carbon materials.

[0041] The battery sensor 12 may include various sensors for detecting the state of the secondary battery 11. The battery sensor 12 may include, for example, a voltage sensor, a current sensor, and a temperature sensor. The battery sensor 12 may output signals containing various detected values ​​such as voltage, current, and temperature related to the state of the secondary battery 11.

[0042] The battery control unit 13, for example, is a so-called BMU (Battery Management Unit) that monitors and controls the state of the secondary battery 11. The battery control unit 13 is, for example, a software function unit that performs its functions by executing a predetermined program by a processor such as a CPU (Central Processing Unit). This software function unit is a type of ECU (Electronic Control Unit), which includes a processor such as a CPU, ROM (Read Only Memory) for storing the program, RAM (Random Access Memory) for temporarily storing data, and electronic circuits such as timers. It should be noted that at least a portion of the battery control unit 13 may also be an integrated circuit such as an LSI (Large Scale Integration).

[0043] The battery control unit 13 stores, for example, information related to the secondary battery 11 and prescribed procedures. The information related to the secondary battery 11 includes, for example, identification information such as an ID (IDentifier) ​​exclusively assigned to the secondary battery 11, manufacturing date, initial capacity, and information related to the state of the secondary battery 11 obtained based on the output of the battery sensor 12. The information related to the state of the secondary battery 11 includes, for example, charging status such as charge rate, remaining capacity (SOC) or power, charging and discharging history such as number of charging cycles, voltage and temperature, and other information related to the current state; information related to the current degradation state such as the degree of degradation; and information related to the presence or absence of abnormalities.

[0044] The power control unit 14 is connected to the secondary battery 11 and the rotary motor 15. The power control unit 14 includes, for example, a transformer such as a DC-DC converter that converts voltage under direct current; and a power converter such as a DC-AC converter that converts power between direct current and alternating current. The power control unit 14 controls the power transfer between the secondary battery 11 and the rotary motor 15, for example, based on control signals obtained from the overall processing unit 17.

[0045] The rotary motor 15 is, for example, a three-phase AC brushless DC motor. The rotary motor 15 generates rotational power by using electricity supplied from the power control unit 14 to perform a traction operation. For example, when connected to the wheels of the vehicle 2, the rotary motor 15 generates driving force by using electricity supplied from the power control unit 14 to perform a traction operation. The rotary motor 15 can also generate electricity by using rotational power input from the wheel side of the vehicle 2 for regenerative operation. When connected to the internal combustion engine of the vehicle 2, the rotary motor 15 can also generate electricity using the power of the internal combustion engine.

[0046] The drive mechanism 16 is a power transmission mechanism connected to the rotor of the rotary motor 15. The drive mechanism 16 may include, for example, components such as gears, belts, and chains. The drive mechanism 16 transmits power between the rotary motor 15 and the wheels of the vehicle 2. The drive mechanism 16 may also include limiting mechanisms that restrict power transmission, such as electric parking brakes and parking locking mechanisms that stop the rotation of the wheels or drive shaft.

[0047] The overall processing unit 17 comprehensively controls the operation of the vehicle 2. The overall processing unit 17 may include, for example, a software function unit. At least a portion of the overall processing unit 17 may also include an integrated circuit.

[0048] The overall processing unit 17 includes, for example, an input / output unit and a communication unit.

[0049] The input / output section includes, for example, various operating devices such as keyboards, touch panels, mice, and buttons; display devices such as liquid crystal displays or organic EL (electro-luminescence) displays; and various input / output devices such as microphones for sound input and speakers for sound output. The input / output section accepts operations performed by users or other operators, or input operations as sound input, and outputs signals corresponding to the input operations.

[0050] The communication unit and server 3 exchange various information via network 4. For example, the communication unit sends information to server 3 by combining information such as date and time, identification information of vehicle 2 or secondary battery 11, and information related to secondary battery 11 obtained from battery control unit 13.

[0051] Server 3 may include a software function unit. At least a portion of the overall processing unit 17 may also include an integrated circuit. Server 3 may include, for example, a storage unit 21, an acquisition unit 22, a preprocessing unit 23, an OCV estimation unit 24 (voltage estimation unit, processing unit), an optimization unit 25, and a diagnostic unit 26.

[0052] Storage unit 21 stores, for example, various information related to secondary battery 11 obtained in advance by server 3 or obtained by server 3 from vehicle 2 at appropriate times, as well as information generated by server 3, and prescribed procedures.

[0053] The acquisition unit 22 acquires, for example, time-series data of the voltage, current, and temperature of the secondary battery 11 from the vehicle 2. The voltage of the secondary battery 11 is, for example, the closed-circuit voltage (CCV). The acquisition unit 22 acquires the discharge capacity (discharge amount) by accumulating the time-series data of the current.

[0054] The preprocessing unit 23 performs processes such as cleaning and filtering of the time series data acquired by the acquisition unit 22. For example, the preprocessing unit 23 excludes data that has been missing or is abnormal from the time series data.

[0055] The OCV estimation unit 24, for example, performs the acquisition of a machine learning model and the estimation of the open-circuit voltage (OCV) using the machine learning model. The OCV estimation unit 24 acquires the machine learning model, for example, based on experiments performed on the secondary battery 11 with a known deterioration state or simulations performed on a predetermined model of the secondary battery 11. The OCV estimation unit 24 acquires time-series data (first data) of the current, closed-circuit voltage (CCV), and open-circuit voltage (OCV) of the secondary battery 11 under a predetermined state, including at least one of charging and discharging, through experiments or simulations. The OCV estimation unit 24, for example, based on the acquired time-series data, acquires input data (second data) of the current and closed-circuit voltage (CCV) at appropriate times and outputs a machine learning model of the overvoltage (i.e., the difference between the open-circuit voltage and the closed-circuit voltage) of the secondary battery 11 at any given time, using this input as an example. The machine learning model is, for example, a regression model such as a random forest, support vector machine, or neural network.

[0056] Figure 2 This diagram illustrates an example of the flow of information processed by the OCV estimation unit 24 of the secondary battery state estimation device 10 according to the embodiment.

[0057] like Figure 2 As shown, the OCV estimation unit 24 includes, for example, an overvoltage output unit 31 and an open-circuit voltage (OCV) calculation unit 32.

[0058] The overvoltage output unit 31, for example, uses a pre-acquired machine learning model to output the overvoltage at a predetermined time t as the target variable, based on input data of current and closed-circuit voltage (CCV) at appropriate times as explanatory variables. For example, the current and closed-circuit voltage (CCV) data include data at the predetermined time t as the target, and data at at least one of a predetermined first time interval (pre-determined time interval) preceding the predetermined time t and a predetermined second time interval (post-determined time interval) following the predetermined time t (at least one of the pre-interval data and the post-interval data). The predetermined first time interval is, for example, the time interval from time (tn) to the predetermined time t at any given time n. The predetermined second time interval is, for example, the time interval from the predetermined time t to time (t+k) after any given time k. The overvoltage at the predetermined time t is, for example, the difference between the open-circuit voltage (OCV(t)) and the closed-circuit voltage (CCV(t)) at the predetermined time t (= (OCV(t) - CCV(t))).

[0059] For example, the open-circuit voltage (OCV) calculation unit 32 adds the overvoltage at a predetermined time t output from the overvoltage output unit 31 to the closed-circuit voltage (CCV(t)) at a predetermined time t, which is used as an explanatory variable, thereby outputting the open-circuit voltage (OCV(t)) at the predetermined time t.

[0060] Figure 3 This is a diagram illustrating an example of the correspondence between the open-circuit voltage (OCV) and closed-circuit voltage (CCV) obtained by the OCV estimation unit 24 of the secondary battery state estimation device 10 in the embodiment.

[0061] like Figure 3 As shown, for example, based on the current and closed-circuit voltage (CCV) data in the time interval from time (tn) to time (t+k) including a specified time t, the open-circuit voltage (OCV(t)) at the specified time t can be obtained.

[0062] Figure 4 This is a diagram showing an example of an OCV curve obtained by the optimization unit 25 of the secondary battery state estimation device 10 in the embodiment based on the OCP curves of the positive and negative electrodes respectively.

[0063] like Figure 4As shown, the optimization unit 25 obtains, for example, an OCP curve representing the change in open circuit potential (OCP) corresponding to the discharge capacity x (Ah) of the positive and negative electrodes of the secondary battery 11 based on multiple parameters related to the state of the secondary battery 11. The optimization unit 25 applies multiple parameters to the OCP curve (reference OCP curve) pre-stored in the storage unit 21, thereby obtaining the positive electrode OCP curve (=fca(x)) and the negative electrode OCP curve (=fan(x)).

[0064] The reference OCP curve stored in the storage unit 21 is obtained in advance, for example, through experiments or simulations based on appropriate models. The reference OCP curve is, for example, the OCP curve of each active material cell constituting the positive and negative electrodes of the secondary battery 11. The optimization unit 25 estimates, for example, the OCV curve (=fca(x)-fan(x)) representing the change in open-circuit voltage (OCV) corresponding to the discharge capacity x (Ah) based on the difference between the positive electrode OCP curve (=fca(x)) and the negative electrode OCP curve (=fan(x)).

[0065] The optimization unit 25 optimizes (resets) multiple parameters related to the state of the secondary battery 11, for example, based on the historical data of the open-circuit voltage (OCV(t)) at a specified time t obtained by the OCV estimation unit 24 and the OCV curve estimated based on the OCP curve.

[0066] The optimization unit 25 performs a prescribed optimization process, for example, based on an error function representing the error between the estimated OCV curve and the historical data of the secondary battery 11. The error function may be, for example, the weighted root mean square error (RMSE) or the weighted average absolute error (MAE). The prescribed optimization process may be, for example, a local optimization algorithm such as the BFGS method, the conjugate gradient method, and the COBYLA method, or a global optimization algorithm such as a genetic algorithm, differential evolution method, the SHGO method, and the annealing method. In a series of processes including the prescribed optimization process, for example, the resetting of multiple parameters based on the optimization unit 25, the acquisition of the positive and negative OCP curves, and the estimation of the OCV curve are repeatedly performed to make the value of the error function below a predetermined value.

[0067] It should be noted that the open-circuit voltage (OCV(t)) history data is obtained, for example, data obtained during an appropriate period, and is not limited to a series of data such as time series data.

[0068] The diagnostic unit 26 obtains a diagnostic value associated with the degradation state of the secondary battery 11, for example, based on an OCV curve estimated from the OCP curve after optimization of multiple parameters performed by the optimization unit 25. The diagnostic unit 26 sets the initial fully charged capacity of the secondary battery 11 to 100% and the percentage of the fully charged capacity at degradation to the SOH (State of Health) diagnostic value. The fully charged capacity at degradation is, for example, the difference between the discharge capacity at the fully charged voltage and the discharge capacity at the fully discharged voltage, obtained based on the OCV curve.

[0069] For example, the diagnostic unit 26 establishes a correspondence between the obtained SOH diagnostic value and the date and time of the OCV curve obtained by the optimization unit 25, thereby saving the history data of the SOH diagnostic value in the storage unit 21.

[0070] (The operation of the secondary battery state estimation device)

[0071] The operation of the secondary battery state estimation device 10 in the following embodiment will be explained, especially the process performed by the OCV estimation unit 24 to obtain the open circuit voltage (OCV(t)) at a predetermined time t.

[0072] Figure 5 This is a flowchart illustrating the process performed by the secondary battery state estimation device 10 in the embodiment.

[0073] like Figure 5 As shown, firstly, the OCV estimation unit 24, for example, as learning data for obtaining a machine learning model, obtains time series data of the current, closed-circuit voltage (CCV), and open-circuit voltage (OCV) of the secondary battery 11 (step S01, model acquisition step).

[0074] Next, the OCV estimation unit 24, for example, obtains the input of current and closed-circuit voltage (CCV) data for appropriate times based on the acquired time series data, and outputs a machine learning model of the overvoltage of the secondary battery 11 at any time (step S02, model acquisition step).

[0075] Next, the OCV estimation unit 24 obtains, for example, data on the current and closed-circuit voltage (CCV) at appropriate times, which are input to the machine learning model as explanatory variables (step S03, voltage estimation step).

[0076] Next, the OCV estimation unit 24 obtains the overvoltage at a specified time t as the target variable by, for example, by inputting the explanatory variables for the machine learning model (step S04, voltage estimation step).

[0077] Next, the OCV estimation unit 24 adds, for example, the overvoltage at a predetermined time t output from the machine learning model to the closed-circuit voltage (CCV(t)) at the predetermined time t, which is used as an explanatory variable, thereby obtaining the open-circuit voltage (OCV(t)) at the predetermined time t (step S05, voltage estimation step). Then, the OCV estimation unit 24 advances the process to the end.

[0078] As described above, the system 1 of the secondary battery state estimation device 10 according to the embodiment uses a machine learning model that outputs overvoltage based on input current and closed-circuit voltage (CCV) data. Therefore, even when the overvoltage increases due to an increase in internal resistance caused by, for example, degradation of the secondary battery 11, it is possible to suppress the decrease in the estimation accuracy of the internal state of the secondary battery 11. The shape change of the OCV curve resulting from the degradation of the secondary battery 11 is reflected in the closed-circuit voltage (CCV) detected in the secondary battery 11. Therefore, for example, not limited to a specific degradation mode, the estimation accuracy of the open-circuit voltage (OCV) can be improved for various degradation modes.

[0079] By using time-series data as the explanatory variables, the estimation accuracy of open-circuit voltage (OCV) by machine learning models can be improved.

[0080] The ability to estimate open-circuit voltage (OCV) using a given time t as a target, based on past or future data, can improve the versatility of machine learning models.

[0081] It is possible to estimate the open circuit voltage (OCV) without requiring temperature data in the description variables. For example, even when a machine learning model is obtained based solely on data from the secondary battery 11 before its degradation, the estimation accuracy of the open circuit voltage (OCV) can be improved for the degraded secondary battery 11.

[0082] (Modified example)

[0083] The following describes variations of the embodiments. It should be noted that the same reference numerals are used for the parts that are the same as those in the embodiments described above, and the descriptions are omitted or simplified.

[0084] In the above embodiment, the secondary battery state estimation device 10 is configured with server 3, but is not limited thereto. For example, at least one of the processes performed by server 3 may also be performed by battery control unit 13 of vehicle 2. That is, the secondary battery state estimation device 10 may be configured with server 3 and battery control unit 13 or with only battery control unit 13.

[0085] In the above-described embodiment, the machine learning model of the OCV estimation unit 24 outputs the overvoltage at a predetermined time t as the target variable, based on the input of current and closed-circuit voltage (CCV) data at an appropriate time as explanatory variables, but is not limited thereto. For example, the machine learning model may also output the open-circuit voltage (OCV(t)) at the predetermined time t as the target variable.

[0086] In the above embodiment, the machine learning model of the OCV estimation unit 24 uses current and closed-circuit voltage (CCV) data as explanatory variables, but is not limited to this. For example, the machine learning model may also use the temperature data of the secondary battery 11 as explanatory variables in addition to current and closed-circuit voltage (CCV).

[0087] In the above implementation, the multiple explanatory variables of the machine learning model can also be data from different time intervals.

[0088] In the above-described embodiment, the machine learning model is obtained by the OCV estimation unit 24, but it is not limited thereto. For example, the machine learning model may also be obtained by a device other than the OCV estimation unit 24 or the server 3 and then stored in the storage unit 21 of the server 3 or the OCV estimation unit 24.

[0089] In the above embodiments, the OCP curve and OCV curve are the changes in open-circuit potential (OCP) or open-circuit voltage (OCV) corresponding to the discharge capacity x (Ah), but are not limited to this. For example, instead of the discharge capacity (Ah), capacity-related parameters such as remaining capacity (SOC: State Of Charge) or depth of discharge (DOD) can be used.

[0090] It should be noted that alternatively, a program for implementing all or part of the functions of the system 1, which includes the state estimation device 10 for a secondary battery according to the present invention, can be recorded on a computer-readable recording medium. The computer system then reads and executes the program recorded on the recording medium, thereby performing all or part of the processing performed by the system 1. It should be noted that the term "computer system" here includes hardware such as an operating system and peripheral devices. Furthermore, "computer system" also includes a WWW system with a homepage providing environment (or display environment). Additionally, "computer-readable recording medium" refers to removable media such as floppy disks, optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into a computer system. Moreover, "computer-readable recording medium" also includes recording media that, when receiving program transmissions via a network such as the Internet or a communication line such as a telephone line, serve as volatile memory (RAM) within a computer system acting as a server or client, storing the program for a certain period of time.

[0091] Furthermore, the aforementioned program can also be transmitted from a computer system that has stored the program in a storage device or similar device to other computer systems via a transmission medium or by transmission waves within the transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium capable of transmitting information, such as a network (communication network) like the Internet or a communication line (communication line) like a telephone line. Additionally, the aforementioned program can also be used to implement a portion of the aforementioned functions. Moreover, the aforementioned program can also be a program that can be implemented by combining it with a program that has already recorded the aforementioned functions in a computer system; this is known as a differential file (differential program).

[0092] The embodiments described herein are illustrative examples and are not intended to limit the scope of the invention. These embodiments can be implemented in a variety of other ways, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included within the scope and spirit of the invention as well as within the scope of the invention described herein and its equivalents.

Claims

1. A state estimation system of a secondary battery, wherein the state estimation system of the secondary battery comprises: a learning model constructed by obtaining first data having data in a time series of a current, a closed-circuit voltage, and an open-circuit voltage of the secondary battery in a prescribed state including at least either of charging and discharging, and constructing the learning model outputting an open-circuit voltage or an overvoltage, which is a difference between the open-circuit voltage and the closed-circuit voltage, of the secondary battery at an arbitrary time based on the first data; and a voltage estimation unit inputting second data having data of a current and a closed-circuit voltage at a prescribed time detected in a secondary battery of an estimation target to the learning model, thereby estimating an open-circuit voltage or an overvoltage of the secondary battery of the estimation target at an arbitrary time.

2. The state estimation system of the secondary battery according to claim 1, wherein the second data has data in a time series of a current and a closed-circuit voltage detected in the secondary battery of the estimation target.

3. The state estimation system of the secondary battery according to claim 2, wherein the voltage estimation unit inputs front interval data having data of a current and a closed-circuit voltage in a prescribed front time interval earlier than a prescribed time detected in the secondary battery of the estimation target to the learning model, thereby estimating an open-circuit voltage or an overvoltage of the secondary battery of the estimation target at the prescribed time.

4. The state estimation system of the secondary battery according to claim 2 or 3, wherein the voltage estimation unit inputs rear interval data having data of a current and a closed-circuit voltage in a prescribed rear time interval later than a prescribed time detected in the secondary battery of the estimation target to the learning model, thereby estimating an open-circuit voltage or an overvoltage of the secondary battery of the estimation target at the prescribed time.

5. The state estimation system of the secondary battery according to claim 1 or 2, wherein the second data does not have data related to a temperature of the secondary battery of the estimation target.

6. The state estimation system of the secondary battery according to claim 1 or 2, wherein the learning model outputs an overvoltage of the secondary battery.

7. The state estimation system of the secondary battery according to claim 1 or 2, wherein the learning model outputs an open-circuit voltage of the secondary battery.

8. The state estimation system of the secondary battery according to claim 1 or 2, wherein the first data has data in a time series of a current, a closed-circuit voltage, and an open-circuit voltage of the secondary battery deteriorated.

9. A state estimation method of a secondary battery, which is a state estimation method of a secondary battery executed by an electronic device comprising a processing unit estimating an open-circuit voltage or an overvoltage of a secondary battery of an estimation target, wherein the state estimation method of the secondary battery comprises: ​ The model acquisition step acquires first data having data in time series of a current, a closed-circuit voltage, and an open-circuit voltage of a secondary battery in a prescribed state including at least one of charging and discharging, and acquires a learning model that outputs an open-circuit voltage or an overvoltage that is a difference between an open-circuit voltage and a closed-circuit voltage of the secondary battery at an arbitrary time based on the first data; and The voltage estimation step inputs second data having data of a current and a closed-circuit voltage at a prescribed time detected in the estimation target secondary battery to the learning model acquired by the model acquisition step, and thereby estimates an open-circuit voltage or an overvoltage of the estimation target secondary battery at an arbitrary time.

10. A recording medium recording a program, wherein An electronic device has a processing unit that estimates an open-circuit voltage or an overvoltage of an estimation target secondary battery, The program causes a computer of the electronic device to execute: a model acquisition step that acquires first data having data in time series of a current, a closed-circuit voltage, and an open-circuit voltage of a secondary battery in a prescribed state including at least one of charging and discharging, and acquires a learning model that outputs an open-circuit voltage or an overvoltage that is a difference between an open-circuit voltage and a closed-circuit voltage of the secondary battery at an arbitrary time based on the first data; and a voltage estimation step that inputs second data having data of a current and a closed-circuit voltage at a prescribed time detected in the estimation target secondary battery to the learning model acquired by the model acquisition step, and thereby estimates an open-circuit voltage or an overvoltage of the estimation target secondary battery at an arbitrary time. ​

Images