Information processing system, information processing method, and program

Abstract

To provide an information processing system that allows a user to more effectively estimate the degree of battery deterioration.SOLUTION: The information processing system includes a data acquisition step of acquiring a dataset including reference data indicating a relationship among an open-circuit voltage of a reference battery, a capacity of the reference battery, and results of impedance measurement for each frequency with respect to the reference battery; a frequency setting step of setting at least one specific frequency based on a predetermined score; and an output step of outputting a deterioration estimation model based on a partial dataset composed of at least one piece of reference data having results of impedance measurement at a frequency corresponding to the specific frequency among the dataset. The deterioration estimation model outputs information on a degree of deterioration of a target battery, which is a battery to be estimated, by inputting an open-circuit voltage of the target battery and results of impedance measurement at a frequency corresponding to the specific frequency.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a degradation level estimation device that evaluates the degradation level of an electricity storage device more efficiently while improving accuracy. The degradation determination device is a device that determines the degradation level of an electricity storage device, and includes a storage unit that stores an estimation model constructed based at least on the real part of the impedance of an electricity storage device whose degradation level is known and the open-circuit voltage of this electricity storage device, and a control unit that acquires the real part of the impedance and the open-circuit voltage of the electricity storage device to be determined, and determines the degradation level of this electricity storage device from the estimation model using the acquired real part of the impedance and the open-circuit voltage as explanatory variables. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-064054 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is still room for improvement in the process for estimating the degree of deterioration of a battery based on the results of measuring the impedance of the battery. [Means for solving the problem]

[0005] According to one aspect of the present invention, there is provided an information processing system. The information processing system includes at least one processor, and the processor is configured to execute a program to perform the following steps: In the data acquisition step, a dataset is acquired, including reference data indicating a correspondence between the open-circuit voltage of a reference battery, the capacity of the reference battery, and the results of impedance measurement for each frequency for the reference battery; In the frequency setting step, at least one specific frequency is set based on a predetermined score; In the output step, a degradation level estimation model is output based on a partial dataset constituted by at least one piece of reference data having the results of impedance measurement at a frequency corresponding to the specific frequency in the dataset; The degradation level estimation model is configured to output information regarding the degradation level of the target battery by inputting the open-circuit voltage of the target battery, which is a battery to be estimated, and the results of impedance measurement at a frequency corresponding to the specific frequency.

[0006] With this configuration, it is possible to provide an information processing system that allows the user to more effectively estimate the degree of battery deterioration. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a configuration diagram illustrating an information processing system 1. FIG. [Figure 2] FIG. 2 is a block diagram showing a hardware configuration of an information processing device 2. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a user terminal 3. [Figure 4] FIG. 2 is a diagram showing an example of the configuration of a test device 4. [Figure 5] FIG. 2 is a diagram showing an example of the data structure of a data set DS1. [Figure 6] 2 is a flowchart showing an example of an outline of information processing executed in the information processing system 1. [Figure 7] 10 is a flowchart illustrating an example of a frequency setting process. [Figure 8]10 is a flowchart showing the flow of an example of a method for calculating an evaluation index related to the robustness of a degradation level estimation model. DETAILED DESCRIPTION OF THE INVENTION

[0008] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

[0009] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0010] Furthermore, various information processing according to an embodiment may realize input and output corresponding to the input. Here, the form of information referenced in such information processing (hereinafter referred to as reference information) is not limited as long as an output is obtained as a result of the input. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression formula constructed using a statistical method), a trained model that has previously trained the correlation between input and output, or a large-scale language model that can output a desired result by inputting a prompt.

[0011] In one embodiment, a "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In one embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit set consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations can be performed on a circuit in the broad sense.

[0012] Furthermore, a circuit in the broad sense is a circuit realized by at least an appropriate combination of a circuit, circuitry, processor, memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0013] 1. Hardware Configuration This section explains the hardware configuration.

[0014] <Information Processing System 1> FIG. 1 is a configuration diagram showing an information processing system 1. The information processing system 1 includes an information processing device 2, a user terminal 3, and a database DB1. The information processing device 2, the user terminal 3, and the database DB1 are configured to be able to communicate with each other via a telecommunications line. In one embodiment, the information processing system 1 is made up of one or more devices or components. For example, if the information processing system 1 is made up of only the information processing device 2, the information processing system 1 can be the information processing device 2. These components will be described below.

[0015] <Database DB1> The database DB1 is configured to store various sets of data. For example, the database DB1 stores a data set DS1 including information on the capacity and deterioration state of the battery, such as battery deterioration tests, impedance measurements, etc. The data set DS1 will be described in detail later.

[0016] <Information processing device 2> 2 is a block diagram showing the hardware configuration of the information processing device 2. The information processing device 2 includes a communication unit 21, a storage unit 22, and at least one processor 23, and these components are electrically connected via a communication bus 20 inside the information processing device 2. Each component will be further described below.

[0017] The communication unit 21 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G / LTE / 5G, BLUETOOTH (registered trademark) communication, etc. as needed. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the information processing device 2 may communicate various information from the outside via the communication unit 21 and the network.

[0018] The storage unit 22 stores various pieces of information defined above. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the information processing device 2 executed by the processor 23, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program operations. The storage unit 22 stores various programs, variables, etc. related to the information processing device 2 executed by the processor 23.

[0019] The processor 23 processes and controls the overall operations related to the information processing device 2. The processor 23 is, for example, a central processing unit (CPU) not shown. The processor 23 realizes various functions related to the information processing device 2 by reading out predetermined programs stored in the storage unit 22. In other words, information processing by software stored in the storage unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23. These will be described in more detail in the next section. Note that the processor 23 is not limited to being single, and multiple processors 23 may be provided for each function. A combination of these may also be used.

[0020] The processor 23 is configured to be able to acquire information from the user terminal 3 or other devices. The processor 23 is configured to be able to acquire various pieces of information by reading out various pieces of information stored in a storage area that is at least a part of the memory unit 22 and writing the read out information in a working area that is at least a part of the memory unit 22. The storage area is, for example, an area of ​​the memory unit 22 that is implemented as a storage device such as an SSD. The working area is, for example, an area that is implemented as a memory such as a RAM. Note that acquisition by the processor 23 includes acquiring output results from each functional unit included in the processor 23.

[0021] The processor 23 is configured to be able to display various types of information. The information can be presented to the user via the display unit 34 of the user terminal 3 or another device. In such a case, for example, the processor 23 controls the display unit 34 of the user terminal 3 to display visual information such as a screen, an image including a still image or a video, an icon, or a message. The processor 23 may generate only rendering information for displaying the visual information on the user terminal 3. Note that the processor 23 may present the output information to the user without going through the user terminal 3 or another device user.

[0022] The processor 23 is configured to be able to execute learning of a trained model using the acquired dataset DS1. Note that the processor 23 may transmit a command to start learning of a trained model using the dataset DS1 and information necessary for the learning, such as learning conditions such as hyperparameters and the number of times of learning, in order to cause a device other than the processor 23 to perform learning.

[0023] <User terminal 3> 3 is a block diagram showing the hardware configuration of the user terminal 3. The user terminal 3 includes a communication unit 31, a storage unit 32, at least one processor 33, a display unit 34, and an HMI device 35, and these components are electrically connected via a communication bus 30 inside the user terminal 3. The description of the communication unit 31, the storage unit 32, and the processor 33 is omitted because they are the same as the description of each unit in the information processing device 2.

[0024] The display unit 34 may be included in the housing of the user terminal 3 or may be externally attached. The display unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. This is preferably implemented by selectively using display devices such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display depending on the type of user terminal 3.

[0025] The HMI device 35 is a human-machine interface device. The HMI device 35 may be included in the housing of the user terminal 3 or may be externally attached. For example, the HMI device 35 may be integrated with the display unit 34 as a touch panel. The touch panel allows the user to input operations such as tapping and swiping. Of course, instead of a touch panel, switch buttons, a mouse, a QWERTY keyboard, a voice recognition device, a gesture detection device, a gaze detection device, a biosignal detection device, an imaging device, or the like may be used. That is, the HMI device 35 accepts an operation input made by the user. In response, the HMI device 35 transfers a signal corresponding to the operation input to the processor 33 via the communication bus 30. The processor 33 may execute predetermined control or calculations as necessary. The HMI device 35 can also be said to include an input unit configured to accept input from the user.

[0026] <Test equipment 4> 4 is a diagram showing an example of the configuration of the test device 4. The test device 4 includes a thermostatic chamber 41 and an impedance measuring device 43.

[0027] The thermostatic bath 41 is configured to be able to house the target battery 42. The thermostatic bath 41 is configured to adjust the temperature around the target battery 42. The target battery 42 is configured to be rechargeable and dischargeable, such as a lead-acid battery, nickel-cadmium battery, lithium-ion battery, or air battery. Note that the target battery 42 may also be a non-rechargeable battery such as a primary battery, as long as its impedance can be measured.

[0028] The impedance measuring device 43 is configured to be able to measure the impedance and open circuit voltage (OCV) of the target battery 42 in accordance with the measurement conditions for measuring the impedance of the target battery, for input into a degradation estimation model described below. The impedance measuring device 43 is configured to measure the impedance of the target battery 42, for example, by measuring the amplitude of a current that flows when an AC voltage characterized by a certain frequency is applied to the target battery 42 and the phase difference between the AC voltage and the current.

[0029] The measurement conditions include the measurement frequency, measurement time, temperature of the thermostatic chamber 41 (in other words, the temperature of the target battery 42), current rate of the target battery 42, average SOC (State of Charge), SOC range, etc. The measurement conditions may also include the temperature control speed and temperature control time of the thermostatic chamber 41, etc., and the waiting time when the target SOC is reached. In this embodiment, the measurement conditions include information about a frequency corresponding to a specific frequency in impedance measurement of the target battery 42. The frequency corresponds to the measurement frequency.

[0030] <Dataset DS1> Next, an example of the dataset DS1 stored in the database DB1 will be described. FIG. 5 is a diagram showing an example of the data structure of the dataset DS1. As shown in FIG. 5, the database DB1 stores the dataset DS1, which includes a plurality of reference data D1. The reference data D1 includes information on battery degradation test conditions, capacity, etc., which can serve as training data when generating a degradation level estimation model for estimating the degradation level of a battery. Hereinafter, for convenience of explanation, a battery corresponding to the reference data D1 will be referred to as a reference battery. In this embodiment, the reference battery is a battery that has been degraded under specified degradation test conditions. The specified degradation test conditions include, for example, a condition of being in a new state (in other words, not exposed to degradation conditions), a condition of storing the battery at 60°C for 20 days to 2 years while maintaining an SOC of 100%, a condition of repeating 3 to 63 cycles of 2C charge / discharge at 20°C, etc. Here, as an example, the degradation level of a battery indicates the degradation level of the battery capacity, but the degradation level of a battery may also be the degradation level based on the internal resistance.

[0031] Each of the reference data D1 is configured to indicate a correspondence relationship between the open-circuit voltages V1 to V4 of the reference batteries, the capacities Q1 to Q4 of the reference batteries, and the impedance measurement results R11 to R44 for each frequency of the reference batteries. The reference data D1 can be obtained, for example, by measuring the capacity of a reference battery stored under the conditions of the deterioration test described above by discharging it at a constant current and constant voltage (CCCV) of 0.1 C and measuring its impedance. Each of the reference data D1 may be obtained by performing corresponding deterioration tests on different reference batteries, or by sequentially performing different deterioration tests on the same reference battery. The reference data D1 includes real parts R11 to R14, R31 to R34, and imaginary parts R21 to R24, R41 to R44 of the impedance for each frequency, which are the results of the impedance measurement for each frequency of the reference batteries. The reference data D1 also includes a real part R' and an imaginary part R'' of the impedance for each discrete frequency, such as 10,000 Hz and 8,254 Hz. Hereinafter, for convenience of explanation, the frequency at which the impedance measurement is performed is referred to as the “impedance frequency.” The impedance frequency values ​​included in the data set DS1 are arbitrary, but specifically, for example, they are values ​​selected from 12 points per digit at equal intervals on a logarithmic scale in the range of 0.01 Hz to 10,000 Hz.

[0032] The reference data D1 may include a measurement temperature, which is the temperature at which the impedance measurement was performed on the reference battery. The reference data D1 may also include information regarding the conditions of a degradation test performed on the reference battery. The degradation test conditions are, for example, the conditions of the degradation test performed on the reference battery described above.

[0033] 3. Information Processing In this section, the information processing executed in the information processing system 1 described above will be described.

[0034] 3.1. Overview of information processing 6 is a flowchart showing an example of an outline of information processing executed in the information processing system 1. Note that the information processing may include any exception processing not shown. Exception processing includes interruption of the information processing or omission of each process. Selection or input performed in the information processing may be based on a user operation or may be performed automatically without relying on a user operation.

[0035] <Step S1> In step S1, the processor 23 acquires the data set DS1 from the database DB1.

[0036] <Step S2> Next, in step S2, the processor 23 executes a frequency setting process to set at least one specific frequency based on a predetermined score.

[0037] <Step S3> Next, in step S3, the processor 23 executes a model output process to output a degradation estimation model based on a partial data set including at least one piece of reference data having an impedance measurement result at a frequency corresponding to a specific frequency in the data set DS1. The model output process will be described in detail later.

[0038] The degradation level estimation model is configured to output information regarding the degradation level of the target battery 42, which is the battery to be estimated, by inputting the open-circuit voltage of the target battery 42, which is the battery to be estimated, and the results of impedance measurement at a frequency corresponding to a specific frequency. In this embodiment, the frequency corresponding to the specific frequency coincides with the specific frequency, but this is not limited to this. The degradation level estimation model may be defined as a function optimized based on the above-mentioned score, defined as a calibration table such as a look-up table, or a trained model trained based on a predetermined algorithm. When the degradation level estimation model is implemented as a trained model, the learning mode of the trained model is appropriately set depending on the type of reference data D1, the task performed by the trained model, etc. The specific learning algorithm for the trained model may be any, such as supervised learning, unsupervised learning, or reinforcement learning. In the case of supervised learning, linear regression, logistic regression, random forest, boosting, support vector machine, neural network, etc. can be used as the learning algorithm for the trained model. The learning may be performed by the processor 23 itself or by a device other than the processor 23.

[0039] The processor 23 may then perform impedance measurement on the target battery 42 under measurement conditions suitable for the degradation estimation model. In this case, the processor 23 may present to the user, based on the learning dataset, measurement conditions for the impedance measurement on the target battery to be input into the degradation estimation model. Presentation is an example of output. For example, the processor 23 may present a specific frequency as the frequency for the impedance measurement on the target battery 42. Furthermore, if the reference data D1 includes a measurement temperature, which is the temperature at which the impedance measurement was performed on the reference battery, the processor 23 may further present, based on the partial dataset, information regarding the temperature at which the impedance measurement was performed on the target battery as a measurement condition. This configuration enables impedance measurement that is more suitable for the degradation estimation model. Furthermore, this configuration may provide, through information processing described below, a degradation estimation model that can estimate the degradation level while taking into account the temperature environment to which the target battery is exposed. The user performs impedance measurement based on the presentation by the processor 23, thereby obtaining impedance measurement results for the target battery 42 to be input into the degradation estimation model.

[0040] <Step S4> Next, in step S4, the processor 23 acquires the results of the impedance measurement of the target battery 42. The results of the impedance measurement of the target battery 42 can be obtained, for example, as a result of performing impedance measurement using the test device 4. In this case, the processor 23 may acquire the results of the impedance measurement of the target battery 42 from the test device 4. Alternatively, the processor 23 may acquire the results of the impedance measurement of the target battery 42 stored in the memory unit 22, an external memory device, or the like.

[0041] <Step S5> Next, in step S5, the processor 23 estimates and outputs the degradation level of the target battery 42 based on the acquired results of the impedance measurement of the target battery 42. The output degradation level may be presented to the user via the display unit 34, for example, or may be used to change the control mode of an external device driven by the target battery 42. Thereafter, the processor 23 ends this information processing.

[0042] With the above configuration, the capacity of a battery can be estimated by inputting the results of impedance measurement at a frequency corresponding to a specific frequency for the battery. Here, the specific frequency is determined based on a predetermined score, and a relatively preferable value is set in consideration of various evaluation items included in the score. Therefore, by incorporating various evaluation items, such as time efficiency of impedance measurement and estimation accuracy, into the score, it is possible to provide an information processing system 1 that allows the user to more effectively estimate the degree of battery degradation.

[0043] 3.2. Example of frequency setting process (step S2) Next, an example of the frequency setting process (step S2) described in the previous section will be described. Fig. 7 is a flowchart showing an example of the frequency setting process.

[0044] <Step S21> As shown in FIG. 7, first, in step S21, the processor 23 acquires designations regarding the evaluation items to be included in the score and the number of specific frequencies to be used in measuring the impedance of the target battery 42.

[0045] The score is a value for identifying an optimal specific frequency and can be defined based on various evaluation indices. For example, the score is a scalar value output using the specific frequency (or a combination of specific frequencies) as a variable. A higher score for a specific frequency indicates that the specific frequency is more suitable for the user to estimate the deterioration level of the target battery 42. For example, the score can be defined based on at least one of an evaluation index related to the accuracy of the estimation result of the deterioration level of the battery, an evaluation index related to the robustness of the deterioration level estimation model, and an evaluation index related to the measurement time required to measure the impedance of the target battery 42.

[0046] An evaluation index for the accuracy of the degradation level estimation result can be defined, for example, by the reciprocal of the Root Mean Squared Error (RMSE) of the battery estimation result. The higher the accuracy, the smaller the RMSE value, and therefore the larger the reciprocal.

[0047] The evaluation index for the robustness of the degradation level estimation model is configured to be larger as the variation in the estimation results for the results of impedance measurements of target batteries 42 showing the same degradation state decreases.

[0048] The evaluation index relating to the measurement time required to measure the impedance of the target battery 42 is configured to be larger, for example, as the time required to measure the impedance when a specific frequency is used is shorter.

[0049] The designation of each evaluation item may be performed automatically, manually by the user, or a combination of these.

[0050] <Step S22> Next, in step S22, processor 23 acquires the designation regarding the priority of each evaluation item designated in step S21 and sets a score based on the designation. The priority of the evaluation items may be defined, for example, using a numerical value for each evaluation item. For example, processor 23 defines the priorities of the "evaluation index related to the accuracy of the estimation result of the battery degradation level," the "evaluation index related to the robustness of the degradation level estimation model," and the "evaluation index related to the measurement time required to measure the impedance of target battery 42" as "2:2:1" based on user input. These ratios correspond to the weights of each evaluation index when calculating the score, which will be described later.

[0051] <Step S23> Next, in step S23, the processor 23 identifies candidates for specific frequencies based on the designation of the number of specific frequencies acquired in step S21. If the number of specific frequencies is two or more, the processor 23 identifies candidate combinations of specific frequencies of that number. For example, the processor 23 identifies combinations of a designated number of measurement frequencies from among the values ​​of the measurement frequencies of the reference data D1 included in the data set DS1 as candidates for combinations of specific frequencies. In this embodiment, the processor 23 identifies all possible combinations of the values ​​of the measurement frequencies of the reference data D1 as candidates for combinations of specific frequencies. For convenience of explanation, hereinafter, when the number of designated specific frequencies is two or more, they will simply be referred to as "candidates for specific frequencies," just as when the number is one.

[0052] <Step S24> Next, in step S24, the processor 23 calculates the value of each evaluation item for each candidate specific frequency. For example, if an evaluation index related to the accuracy of the degradation level estimation is specified, the processor 23 calculates the value of the evaluation index by performing 10-fold cross-validation on the dataset DS1. If an evaluation index related to the robustness of the degradation level estimation model is specified, the processor 23 calculates the value of the evaluation index, for example, according to a method for calculating an evaluation index related to the robustness of the degradation level estimation model, which will be described later. If an evaluation index related to the measurement time required for impedance measurement of the target battery 42 is specified, the processor 23 calculates an index related to the measurement time required for impedance measurement of the target battery 42, for example, based on the frequency used for the impedance measurement. Specifically, the processor 23 calculates the reciprocal of the frequency (or, if multiple specific frequencies are set, the sum of the reciprocals of the frequencies) as the value of the evaluation index. With this configuration, it is possible to generate a degradation level estimation model while taking into account the time efficiency for obtaining impedance measurement results necessary to estimate the degradation level of the target battery 42.

[0053] <Step S25> Next, in step S25, processor 23 standardizes the value of each evaluation item calculated in step S24. For example, processor 23 converts each population so that the mean value of the population of values ​​of each evaluation item calculated for each specific frequency candidate is 0 and the variance is 1.

[0054] <Step S26> Next, in step S26, processor 23 calculates the score set in step S22 for each of the specific frequency candidates based on the values ​​of the evaluation items standardized in step S26. Here, processor 23 calculates the score as a weighted linear sum of the values ​​of each evaluation item based on priority.

[0055] <Step S27> Next, in step S27, processor 23 identifies the specific frequency with the highest score among the candidate specific frequencies as the optimal specific frequency. This configuration allows a degradation estimation model to be generated for estimating the degree of degradation of the capacity of the target battery based on the results of impedance measurements at multiple frequencies. Using multiple frequencies allows for more accurate estimation of the degree of degradation of the capacity.

[0056] In this way, the processor 23 can identify the optimal frequency from among the candidate specific frequencies according to the priority of various evaluation items, and thereby estimate the degree of deterioration of the target battery 42 in a manner appropriate for the evaluation items from the results of the impedance measurement of the target battery 42.

[0057] 3.3. Example of a method for calculating evaluation indices related to the robustness of the degradation estimation model Next, an example of a method for calculating an evaluation index relating to the robustness of a degradation level estimation model, which is one of the evaluation items, will be described. Fig. 8 is a flowchart showing the flow of an example of a method for calculating an evaluation index relating to the robustness of a degradation level estimation model. The following process is executed for all specific frequency candidates.

[0058] <Step S31> 8, first, in step S31, the processor 23 identifies a combination of reference batteries having the same state of degradation from among the reference batteries indicated by the reference data D1 included in the acquired data set DS1. While any method of identification is possible, for example, if the relationship between the two pieces of reference data D1 satisfies a predetermined specific condition, the processor 23 identifies the two pieces of reference data D1 as representing reference batteries having the same state of degradation, and if the relationship does not satisfy the specific condition, the processor 23 identifies the two pieces of reference data D1 as representing reference batteries having different states of degradation. While any method of defining the specific condition is possible, for example, the specific condition may include a condition regarding the same type of degradation, a condition regarding the same capacity, and a condition regarding the same results of impedance measurement.

[0059] The condition for the identity of the type of deterioration may be specified, for example, based on whether or not the difference in each parameter indicating the condition of the deterioration test is within a predetermined range. The parameters may be specified, for example, by temperature, time, the presence or absence of cycle deterioration, etc. For example, the condition for the identity of the type of deterioration may be specified so that it is satisfied when the difference in temperature of the deterioration test is within a predetermined range and the cycle deterioration is the same. Furthermore, if the deterioration test has not been performed, i.e., if the reference battery is new, the condition for the identity of the type of deterioration may be specified so that only the reference data D1 related to the reference battery are determined to be the same.

[0060] The condition regarding the same capacity is configured to be satisfied, for example, when the capacities of the reference batteries in two reference data D1 that satisfy the condition regarding the same type of degradation can be treated as being the same. For example, the condition regarding the same capacity can be specified so that it is satisfied if the capacity of the final reference battery relative to the rated capacity of the reference battery is within an acceptable range, and is not satisfied if it is outside the acceptable range.

[0061] The condition regarding the identity of the impedance measurement results is configured to be satisfied when, among the reference data D1 that satisfy the above two conditions, the impedance measurements of two reference batteries can be treated as identical. For example, the processor 23 treats the string of impedance measurement results for each measurement frequency included in the reference data D1 as a single vector and evaluates the similarity between the two vectors represented by the two reference data D1. Note that any method for evaluating the identity may be used. The processor 23 may evaluate the identity of the impedance measurement results of the two reference data D1 using any index, such as cosine similarity, Manhattan distance, or Euclidean distance. If the similarity is within an acceptable range, the processor 23 determines that the condition regarding the identity of the impedance measurement results of the two reference data D1 is satisfied.

[0062] The processor 23 identifies a combination of reference batteries having the same state of deterioration by determining whether the various conditions described above are satisfied. Note that, here, a combination of reference batteries is treated as representing a pair of two reference batteries, but the processor 23 may treat three or more reference batteries as a combination of reference batteries. A set of reference data D1 specifying a combination of reference batteries having the same state of deterioration is an example of a test data set composed of two or more test data, and each of the reference data D1 constituting the test data set corresponds to a reference battery having the same state of deterioration among the reference data included in the data set, and is an example of test data.

[0063] <Step S32> Next, in step S32, for each combination of reference batteries identified in step S31, the processor 23 generates a learning dataset for each combination by excluding the set of reference data D1 corresponding to that combination of reference batteries from the dataset DS1.

[0064] <Step S33> Next, in step S33, processor 23 generates a capacity estimation model for each combination based on each training data set generated in step S32. The capacity estimation model is configured to output an estimated value of the capacity of the battery by inputting the impedance measurement results of the reference battery. In other words, processor 23 generates the capacity estimation model based on the training data sets excluding the test data set composed of two or more test data. Specific aspects and implementation methods of the capacity estimation model may be similar to those of the degradation estimation model described above.

[0065] <Step S34> Next, in step S34, the processor 23 inputs the results of measuring the impedance of the reference batteries that make up the combination into a capacity estimation model, thereby obtaining an estimated value of the capacity of each of the reference batteries that make up the combination.

[0066] <Step S35> Next, in step S35, processor 23 calculates the difference between the estimated capacities of the reference batteries that make up the combination. The difference between the estimated capacities is an example of a comparison result of the estimated capacities output from the capacity estimation model. Note that the comparison is not limited to the difference, and can be realized in any manner, such as a ratio or rate of change. Note that the capacity can be calculated under all measurement conditions included in dataset DS1, such as the measurement temperature and SOC.

[0067] <Step S36> Next, in step S36, processor 23 calculates a robustness evaluation index based on the differences in the estimated values ​​calculated in step S35. For example, processor 23 calculates the reciprocal of the average value of the differences in the estimated values ​​of capacity between combinations of reference batteries having the same state of degradation, measured under various measurement conditions, as the robustness evaluation index corresponding to the combination. For example, if the differences in the estimated values ​​of capacity based on the results of impedance measurement of two reference batteries under six measurement conditions at a certain frequency are 3.4, 32.4, 17.5, 10.7, 20.4, and 28.7 (units: mAh), the average value of the differences in the measured values ​​is 18.85, and its reciprocal is approximately 0.053. In this case, the reciprocal of the average value of the differences in the measured values, "0.053," is the robustness evaluation index corresponding to the combination of the two reference batteries.

[0068] Thereafter, processor 23 performs the processes of steps S32 to S35 for all combinations identified as combinations of reference batteries having the same degradation state, and calculates robustness evaluation indices corresponding to all combinations. Processor 23 then calculates the average value of the robustness evaluation indices corresponding to all calculated combinations as an evaluation index related to the overall robustness. In other words, processor 23 inputs each piece of test data into a capacity estimation model, and calculates the robustness evaluation index based on the comparison results of the estimated capacity values ​​output from the capacity estimation model. This configuration allows a degradation estimation model to be generated so that the difference in estimation results due to the presence or absence of impedance measurement results performed under the same test conditions is minimized.

[0069] [others] The above-described embodiment can be modified as appropriate as follows.

[0070] The processor 23 does not need to identify specific frequency candidates and then perform a full search of the candidates to identify the specific frequency. For example, the processor 23 may use any optimization algorithm with a score as an objective function from a specific frequency that is an initial value to identify the specific frequency that maximizes the score. Specific aspects of the optimization algorithm are arbitrary, and examples include a local search method, a successive improvement method, and a neighborhood search method. Furthermore, metaheuristic search methods such as a cuckoo search, a genetic algorithm, and a particle swarm optimization method may also be used as the optimization processing algorithm.

[0071] The process of generating a trained model does not need to be performed inside the information processing device 2. For example, the process may be performed using an information processing device that exists outside the information processing system 1.

[0072] The information processing device 2 may be an on-premise type or a cloud type. As the information processing device 2 in the cloud type, the above-mentioned functions and processes may be provided in the form of, for example, SaaS (Software as a Service) or cloud computing.

[0073] In the above embodiment, the information processing device 2 performs various storage and control operations, but multiple external devices may be used instead of the information processing device 2. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like.

[0074] The above embodiment is not limited to the information processing system 1, and may be an information processing method or an information processing program. The information processing method includes each step of the information processing system 1. The information processing program causes at least one computer to execute each step of the information processing system 1.

[0075] The information processing system 1 and the like may be provided in the following aspects.

[0076] (1) An information processing system comprising at least one processor, the processor configured to execute a program to perform the following steps: a data acquisition step to acquire a dataset including reference data indicating a correspondence between the open-circuit voltage of a reference battery, the capacity of the reference battery, and the results of impedance measurement for each frequency for the reference battery; a frequency setting step to set at least one specific frequency based on a predetermined score; and an output step to output a degradation level estimation model based on a partial dataset consisting of at least one of the reference data having the results of impedance measurement at a frequency corresponding to the specific frequency in the dataset, wherein the degradation level estimation model is configured to output information regarding the degradation level of a target battery, which is a battery to be estimated, by inputting the open-circuit voltage of the target battery, which is a battery to be estimated, and the results of impedance measurement at a frequency corresponding to the specific frequency.

[0077] With this configuration, the deterioration level of a battery can be estimated by inputting the results of impedance measurement at a frequency corresponding to a specific frequency for the battery. Here, the specific frequency is determined based on a predetermined score, and is a relatively preferable value taking into account various evaluation items included in the score. Therefore, by incorporating various evaluation items, such as time efficiency of impedance measurement and estimation accuracy, into the score, it is possible to provide an information processing system that allows users to more effectively estimate the deterioration level of the battery.

[0078] (2) In the information processing system described in (1) above, the score includes an evaluation index regarding the robustness of the deterioration level estimation model.

[0079] With this configuration, it is possible to reduce variations in the estimation results of the degree of battery degradation among batteries having similar degradation histories and capacities.

[0080] (3) In the information processing system described in (2) above, the generation step further generates a capacity estimation model based on a learning dataset obtained by excluding a test dataset consisting of two or more test data from the dataset, wherein the two or more test data are reference data corresponding to reference batteries having the same state of deterioration among the reference data included in the dataset, and the capacity estimation model is configured to output an estimated value of the capacity of the reference battery by inputting a result of impedance measurement of the reference battery, and further, in the robustness calculation step, calculates an evaluation index related to the robustness based on a comparison result of the estimated values ​​of capacity output from the capacity estimation model by inputting each of the test data into the capacity estimation model.

[0081] With this configuration, it is possible to generate a degradation level estimation model so that the difference in estimation results between the presence or absence of impedance measurement results performed under the same test conditions is small.

[0082] (4) In the information processing system described in (2) or (3) above, the score further includes an index relating to the measurement time required to measure the impedance of the target battery.

[0083] With this configuration, it is possible to generate a deterioration level estimation model while taking into consideration the time efficiency for obtaining the impedance measurement results necessary to estimate the deterioration level of the target battery.

[0084] (5) In the information processing system described in (4) above, the index relating to the measurement time is calculated based on the frequency used in the impedance measurement.

[0085] (6) In the information processing system described in any one of (1) to (5) above, the system further includes, in the specification acquisition step, acquiring a specification regarding the number of specific frequencies to be used for impedance measurement of the target battery, and in the frequency setting step, setting the specified number of combinations of specific frequencies based on the scores of each of the specific frequency candidates identified by the specified number of frequency combinations.

[0086] With this configuration, a degradation level estimation model for estimating the degradation level of a target battery can be generated based on the results of impedance measurements at multiple frequencies. By using multiple frequencies, the degradation level of the battery can be estimated with higher accuracy.

[0087] (7) In the information processing system described in any one of (1) to (6) above, the output step further outputs measurement conditions for impedance measurement of the target battery based on the partial data set to be input into the deterioration level estimation model, and the measurement conditions include information about a frequency corresponding to the specific frequency.

[0088] This configuration reduces the effort required to obtain impedance measurement results for the target battery that are optimized to obtain a good score and are suitable for input into a deterioration level estimation model.

[0089] (8) In the information processing system described in (7) above, the reference data includes a measurement temperature, which is the temperature at which impedance measurement was performed on the reference battery, and in the output step, information regarding the temperature at which impedance measurement was performed on the target battery is further output as the measurement condition based on the partial data set.

[0090] With this configuration, it is possible to perform impedance measurement that is more suited to the degradation level estimation model.

[0091] (9) An information processing method, comprising the steps of the information processing system according to any one of (1) to (8) above.

[0092] (10) A program that causes at least one computer to execute each step of the information processing system according to any one of (1) to (8) above. Of course, this is not the case.

[0093] Finally, while various embodiments of the present disclosure have been described, they are presented as examples and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. Such embodiments and modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the claims. [Explanation of symbols]

[0094] 1: Information processing system 2: Information processing equipment 3: User terminal 4: Test equipment 20: Communication bus 21: Communications Department 22: Storage section 23: Processor 30: Communication bus 31: Communications Department 32: Storage section 33: Processor 34:Display section 35: HMI device 41: Constant temperature bath 42: Target battery 43: Impedance measuring device D1: Reference data DB1 : Database DS1: Dataset

Claims

1. An information processing system, at least one processor configured to execute a program to perform the following steps: In the data acquisition step, a data set is acquired, the data set including reference data indicating a correspondence relationship between an open circuit voltage of a reference battery, a capacity of the reference battery, and a result of impedance measurement for each frequency of the reference battery; In the frequency setting step, at least one specific frequency is set based on a predetermined score; The output step is configured to output a degradation estimation model based on a partial data set configured of at least one of the reference data having a result of impedance measurement at a frequency corresponding to the specific frequency in the data set, wherein: The deterioration level estimation model is configured to output information regarding the deterioration level of a target battery by inputting the open circuit voltage of the target battery, which is the battery to be estimated, and the results of impedance measurement at a frequency corresponding to the specific frequency.

2. 2. The information processing system according to claim 1, The system, wherein the score includes an evaluation index related to the robustness of the degradation estimation model.

3. 3. The information processing system according to claim 2, Furthermore, in the generation step, a capacity estimation model is generated based on a training data set obtained by excluding a test data set configured of two or more test data from the data set, wherein: the two or more test data are reference data corresponding to reference batteries having the same deterioration state among the reference data included in the data set, the capacity estimation model is configured to output an estimated value of the capacity of the reference battery by inputting a result of impedance measurement of the reference battery; Furthermore, in the robustness calculation step, the system calculates an evaluation index related to the robustness based on a comparison result of the estimated capacity value output from the capacity estimation model by inputting each of the test data into the capacity estimation model.

4. 3. The information processing system according to claim 2, The system, wherein the score further includes an indicator related to the measurement time required to measure the impedance of the target battery.

5. 5. The information processing system according to claim 4, A system in which the index related to the measurement time is calculated based on a frequency used for the impedance measurement.

6. 2. The information processing system according to claim 1, Furthermore, in the specification acquisition step, a specification regarding the number of specific frequencies to be used in impedance measurement for the target battery is acquired, In the frequency setting step, a specified number of combinations of specific frequencies are set based on the scores of each of the specific frequency candidates identified by the specified number of frequency combinations.

7. 2. The information processing system according to claim 1, The output step further includes outputting measurement conditions for impedance measurement of the target battery based on the partial data set to be input into the deterioration level estimation model, the measurement conditions including information about a frequency corresponding to the specific frequency.

8. 8. The information processing system according to claim 7, the reference data includes a measurement temperature, which is a temperature at which an impedance measurement was performed on the reference battery; In the output step, the system further outputs, as the measurement condition, information regarding the temperature at which impedance measurement is performed on the target battery based on the partial data set.

9. An information processing method, comprising: A method comprising the steps of the information processing system according to any one of claims 1 to 8.

10. A program, A program that causes at least one computer to execute each step of the information processing system according to any one of claims 1 to 8.

Images