Battery deterioration estimation method

Abstract

The battery deterioration estimation method according to the present disclosure is a battery deterioration estimation method for a battery installed in a vehicle and supplying power to a motor, and includes a process of performing weighting of deterioration degree performance data of the battery accumulated in advance by performing weighting in accordance with similarity to supplementary information about an estimation target battery, a process of performing machine learning by using the deterioration degree performance data weighted in the process as training data, generating a training model that inputs usage history information of the battery and outputs a deterioration degree of the battery, and estimating the deterioration degree of the estimation target battery using the training model based on the usage history information about the estimation target battery.

Description

Technical Field

[0001] This disclosure relates to a method for estimating battery degradation. Background Technology

[0002] Japanese Patent Application Publication No. 2013-089424 (JP 2013-089424 A) discloses a model for estimating the degree of degradation (state of health (SOH)) of a secondary battery based on the physical and chemical characteristics of battery degradation (such as the degradation behavior of electrodes according to the Arrhenius equation, the square root law of degradation over time, etc.). Summary of the Invention

[0003] The degradation estimation model for secondary batteries disclosed in JP 2013-089424 A takes information about the usage history of the secondary battery (such as elapsed time, current, and the battery's charge rate (state of charge (SOC))) as input and outputs the degradation level of the secondary battery. The inventors have found that the estimation accuracy of the degradation level estimation model can be improved by using additional parameters (such as the environment in which the battery (secondary battery) is exposed and the driving operations of the vehicle with the battery installed). However, when parameters are directly added to the degradation estimation model for secondary batteries disclosed in JP 2013-089424 A, there is a problem that the performance of the model, which estimates the degradation level based on physical and chemical degradation characteristics, cannot be guaranteed.

[0004] This disclosure takes into account the above circumstances and provides a battery degradation estimation method that can improve estimation accuracy while ensuring the performance of models based on physical and chemical degradation characteristics.

[0005] According to one aspect of this disclosure, a battery degradation estimation method is used for estimating the degradation of a battery installed in a vehicle and supplying power to an electric motor, and includes: The pre-accumulated degradation performance data of the battery is weighted by performing weighting based on the similarity with supplementary information about the battery being estimated; Machine learning is performed by using the degradation performance data weighted in the processing as training data to generate a trained model that takes the battery's usage history information as input and outputs the battery's degradation level; and Based on the usage history information about the battery being estimated, the trained model is used to estimate the degree of degradation of the battery being estimated.

[0006] According to this disclosure, a battery degradation estimation method can be provided that can improve estimation accuracy while ensuring the performance of models based on physical and chemical degradation characteristics. Attached Figure Description

[0007] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, wherein like symbols denote like elements, and wherein: Figure 1 This is a block diagram illustrating the configuration of a battery degradation estimation system according to an embodiment of the present disclosure; Figure 2A It is a graph showing the state of health (SOH) of a battery over time according to an embodiment of the present disclosure; Figure 2B These are time-series data of the State of Harm (SOH) of a battery according to embodiments of this disclosure; Figure 2C These are examples of supplementary information regarding the battery according to embodiments of this disclosure; Figure 2D These are examples of supplementary information regarding the battery according to embodiments of this disclosure; Figure 3A This is an input / output flowchart of the SOH estimation model according to an embodiment of the present disclosure; Figure 3B This is a comparison diagram of an SOH estimation model according to an embodiment of the present disclosure, an existing SOH estimation model, and an SOH estimation model obtained by complicating the existing model; Figure 4A It is a weighted graph based on dimensional compression corresponding to the similarity with supplementary information about the battery, according to embodiments of this disclosure; Figure 4B It is a rule-based weighted graph corresponding to the similarity with supplementary information about the battery according to embodiments of this disclosure; Figure 5 This is a flowchart of a battery degradation estimation method according to embodiments of the present disclosure; and Figure 6 This is a diagram illustrating a method for updating a degradation estimation model according to an embodiment of the present disclosure. Detailed Implementation

[0008] Specific embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. Note that the present disclosure is not limited to the following embodiments. Furthermore, for clarity, the following description and drawings have been appropriately simplified.

[0009] Configuration of battery degradation estimation system Figure 1 This is a block diagram illustrating the configuration of a battery degradation estimation system according to an embodiment of the present disclosure.

[0010] The battery degradation estimation system S consists of a vehicle C and a battery degradation estimation device 5. Vehicle C includes a battery 1, a battery sensor 2, an operation unit 3, and an operation history acquisition unit 4. Battery sensor 2 includes a usage history acquisition unit 21, a usage history recording unit 22, a supplementary information acquisition unit 23, and a supplementary information recording unit 24. Battery degradation estimation device 5 includes a performance data accumulation unit 51, a model generation unit 52, and a degradation estimation unit 53. Note that battery 1 is the battery being estimated.

[0011] Vehicle C is a car capable of operating by driving the electric motor (not shown) of operating unit 3 with electricity supplied from battery 1 to operating unit 3. Vehicle C may be, for example, a pure electric vehicle, but may also be a hybrid electric vehicle with external charging capability, etc.

[0012] Battery 1 is connected to usage history acquisition unit 21 and supplementary information acquisition unit 23. Battery 1 is an electrical storage device installed in vehicle C and has the function of supplying power to the drive unit that drives vehicle C. Battery 1 is a secondary battery, such as a lithium-ion battery, lead-acid battery, nickel-metal hydride battery, etc., and is configured by accommodating a positive electrode active material layer, a negative electrode active material layer, a current collector, a separator, an electrolyte, etc., within a sealed member. Battery 1 is connected to the electric motor that drives vehicle C, thereby supplying power to the electric motor. The size of battery 1 and the type of secondary battery used for battery 1 are appropriately determined according to the size and purpose of vehicle C in which battery 1 is to be installed.

[0013] Battery sensor 2 is connected to battery 1, operation history acquisition unit 4, and model generation unit 52. For example, as... Figure 2A As shown, battery sensor 2 acquires the SOH (State of Health) value of battery 1 at predetermined intervals and sends the acquired result to model generation unit 52. Here, SOH is the ratio of the full charge capacity of battery 1 at degradation to the full charge capacity of battery 1 in the initial period, and is defined as... .

[0014] In this disclosure, the SOH obtained by equation (1) is used as an indicator of the degree of degradation of battery 1. The smaller the SOH value, the more advanced the degradation of battery 1 has been and the greater the degree of degradation of battery 1.

[0015] The usage history acquisition unit 21 is connected to the battery 1 and the usage history recording unit 22. The usage history acquisition unit 21 acquires the SOH value of the battery 1 at predetermined time intervals and sends the acquired data to the usage history recording unit 22. For example, the usage history acquisition unit 21 includes sensors such as a current sensor and a voltage sensor, and acquires current or voltage values ​​at predetermined time intervals. The usage history acquisition unit 21 calculates the SOH value of the battery 1 by, for example, determining the amount of current flowing from when the battery 1 is in a depleted state to when it is fully charged based on the acquired current or voltage values. To calculate the SOH value of the battery 1, the usage history acquisition unit 21 may consist of a central processing unit (CPU), a microprocessor unit (MPU), working memory, a non-volatile storage device storing the control program, etc.

[0016] The historical record unit 22 is connected to the usage history acquisition unit 21 and the degradation estimation unit 53. The historical record unit 22 records the SOH value of battery 1 received from the usage history acquisition unit 21 and sends the recorded SOH value of battery 1 to the degradation estimation unit 53. However, note that the historical record unit 22 can also record information about parameters used to determine the SOH of battery 1, such as the duration and amount of current flowing through battery 1. In other words, the usage history information about battery 1 includes parameters used to determine the SOH of battery 1, such as the SOH value of battery 1 at a predetermined time, the duration of current flow, and the amount of current flow.

[0017] In the historical record unit 22, the SOH value of battery 1 is recorded in the form of time series data, for example, as shown in the example. Figure 2B As shown, each battery is assigned a battery ID, the date the SOH was recorded, and the recorded SOH value. The usage history unit 22 includes a storage device capable of storing various types of data, and is not necessarily part of the battery sensor 2; it can be an external storage device or cloud storage connected to the usage history acquisition unit 21 via a network. The usage history unit 22 also includes a communication interface that can communicate with the degradation estimation unit 53 via a wired communication device, a wireless communication device, or the like.

[0018] The supplementary information acquisition unit 23 is connected to the battery 1 and the supplementary information recording unit 24. The supplementary information acquisition unit 23 acquires supplementary information about the battery 1 and sends the acquired supplementary information about the battery 1 to the supplementary information recording unit 24.

[0019] Here, examples of supplementary information regarding battery 1 may include: Information about the characteristics of battery 1, such as the full charge capacity of battery 1 in the initial period, positive electrode material, negative electrode material, materials constituting the electrolyte, manufacturer, etc. Information about the characteristics of vehicle C equipped with battery 1, such as vehicle C's model, driving performance, vehicle weight, etc. Historical information about the driving environment or vehicle status of vehicle C, which is equipped with battery 1, such as the driving area of ​​vehicle C, the SOC of battery 1 during driving, battery temperature, ambient temperature, etc. Historical information about the driving and charging operations of the vehicle C equipped with battery 1, such as the number of sudden accelerations and decelerations, and the ratio of fast charging to normal charging. And so on. Here, the characteristic information about vehicle C is also the vehicle information about vehicle C. The driving environment of vehicle C, the historical information about vehicle status, and the historical information about driving operation and charging operation of vehicle C are also the driving history information about vehicle C. The supplementary information acquisition unit 23 acquires information that can be directly obtained from battery 1, such as the SOC of battery 1 during driving, battery temperature, and the ratio of fast charging to normal charging, as supplementary information about battery 1.

[0020] For example, the supplementary information acquisition unit 23 includes sensors such as current sensors and temperature sensors. Furthermore, in order to acquire supplementary information about the battery 1 based on data such as current values ​​and temperature acquired by the sensors, the supplementary information acquisition unit 23 may consist of a CPU, an MPU, working memory, and a non-volatile storage device for storing control programs.

[0021] The supplementary information recording unit 24 is connected to the supplementary information acquisition unit 23, the operation history acquisition unit 4, and the model generation unit 52. The supplementary information recording unit 24 records the supplementary information about battery 1 sent from the supplementary information acquisition unit 23 and the operation history acquisition unit 4, and sends the recorded supplementary information about battery 1 to the model generation unit 52.

[0022] The supplementary information recording unit 24 is a storage device capable of storing various types of data, and it does not necessarily have to be part of the battery sensor 2. Instead, it can be an external storage device or cloud storage connected to the usage history acquisition unit 21 via a network. The supplementary information recording unit 24 also includes a communication interface capable of communicating with the degradation estimation unit 53 via a wired communication device, a wireless communication device, or the like. Note that the usage history unit 22 and the supplementary information recording unit 24 can be the same storage device. Furthermore, supplementary information about the battery 1 (such as characteristic information about the battery 1 and characteristic information about the vehicle C on which the battery 1 is installed) can be pre-recorded in the supplementary information recording unit 24, or it can be recorded by sending data from the supplementary information acquisition unit 23 and the operation history acquisition unit 4.

[0023] Operation unit 3 is connected to operation history acquisition unit 4. Operation unit 3 is a device used to operate vehicle C as a vehicle, such as an electric motor, brake, steering wheel, safety device, car navigation system, etc.

[0024] The operation history acquisition unit 4 is connected to the operation unit 3 and the supplementary information recording unit 24. The operation history acquisition unit 4 acquires the operation history of the operation unit 3 and sends the acquired data as supplementary information about the battery 1 to the supplementary information recording unit 24. The operation history acquisition unit 4 is equipped with sensors, such as a speed sensor, a rotation speed sensor for the electric motor, a global positioning system (GPS) receiver, etc., and acquires information that can be directly obtained from the operation unit 3, such as the area where the vehicle C is traveling, the number of sudden accelerations and decelerations, etc., as supplementary information about the battery 1.

[0025] The battery degradation estimation device 5 is connected to the usage history unit 22 and the supplementary information recording unit 24. The battery degradation estimation device 5 estimates the state of harm (SOH) based on usage history information and supplementary information about battery 1, as well as performance value data and test data accumulated in the performance data accumulation unit 51 for a large number of batteries. Here, an SOH estimation model is used to estimate SOH, which can estimate SOH based on the physical and chemical characteristics of battery degradation. The SOH estimation model will be described later.

[0026] The performance data accumulation unit 51 is connected to the model generation unit 52. The performance data accumulation unit 51 accumulates performance value data from previously used batteries and test data from tested batteries as degradation performance data. Here, the degradation performance data includes battery usage history information and supplementary information. The degradation performance data is the necessary training data for the model generation unit 52 to generate the SOH estimation model and is sent to the model generation unit 52 as needed. The performance data accumulation unit 51 includes a storage device capable of storing various types of data and does not necessarily have to be part of the battery degradation estimation device 5; it can be an external storage device or cloud storage connected to the model generation unit 52 via a network.

[0027] In the performance data accumulation unit 51, supplementary information about the battery included in the degradation performance data is recorded in association with characteristic information about the battery and vehicle C (such as battery ID, manufacturer, positive electrode material, negative electrode material, and the vehicle in which the battery is installed). For example, such as... Figure 2C As shown. Furthermore, supplementary information about the battery included in the degradation performance data is recorded in association with the battery ID and historical information about the vehicle (such as the number of sudden accelerations and the rate of fast charging), for example, as... Figure 2D As shown.

[0028] The model generation unit 52 is connected to the supplementary information recording unit 24, the performance data accumulation unit 51, and the degradation estimation unit 53. Based on the supplementary information and degradation performance data of battery 1, the model generation unit 52 generates a State of Health (SOH) estimation model and sends the generated model to the degradation estimation unit 53. The model generation unit 52 consists of, for example, a CPU, an MPU, working memory, and a non-volatile storage device for storing control programs. Furthermore, the model generation unit 52 does not necessarily have to be part of the battery degradation estimation device 5 and can be configured with an external cloud computing environment.

[0029] Here, the SOH estimation model f generated by the model generation unit 52 is, for example, an estimation model based on the square root law model related to the capacity retention rate y of battery 1.

[0030] Where k is the degradation rate constant and t is time. Furthermore, the capacity retention rate y is the same as the SOH value, not expressed as a percentage. The value of k in equation (2) is determined based on, for example, the Arrhenius equation.

[0031] Where A is the frequency factor, E a R is the activation energy of the reaction, R is the gas constant, and T is the temperature. A and E are estimated using equation (3). a The value of k at a specific temperature T can be estimated, and therefore the SOH can be estimated. The parameters k, A, and E in equations (2) and (3) are... a This refers to parameter θ in the SOH estimation model f. In other words, calculating parameter θ allows SOH to be estimated using the SOH estimation model f. Note that the SOH estimation model f can estimate SOH using formulas based on physical and chemical characteristics of battery degradation other than those mentioned above, and therefore, parameter θ can include parameters other than k, A, and E mentioned above. a Other parameters.

[0032] Figure 3AThis is an input / output flowchart of an SOH estimation model according to an embodiment of the present disclosure. In the SOH estimation model f, the parameter θ is estimated by using degradation performance data z as training data and performing a parameter learning process g for learning the parameter θ. The SOH estimation model f generated by estimating the parameter θ is a training model that takes the usage history information x_t of battery 1 as input and outputs the SOH value y_t of battery 1. Here, the inventors have discovered that by applying weights W to the performance data of each battery included in the degradation performance data according to the similarity with the supplementary information x_history of battery 1, degradation performance data z' consistent with the supplementary information x_history of battery 1 can be generated. Using degradation performance data z' as training data when performing machine learning makes it possible to improve the estimation accuracy of parameter θ and improve the performance of the SOH estimation model f.

[0033] Figure 3B This is a comparison of the SOH estimation model according to embodiments of the present disclosure, existing SOH estimation models, and SOH estimation models obtained by complicating existing models. In the SOH estimation model f according to embodiments of the present disclosure, instead of changing the model structure or parameter learning process g, the following improvement is made: the degradation performance data used as training data in the parameter learning process g is adopted as z'. Therefore, the accuracy of SOH estimation can be improved while ensuring the performance of the SOH estimation model f itself based on the physical and chemical characteristics of battery degradation.

[0034] The weighted W of the degradation performance data z is performed, for example, by adding weights to the performance data of batteries with supplementary information that has a high degree of similarity to the supplementary information about battery 1. Figure 4A This is a weighted graph based on dimensional compression corresponding to the similarity of supplementary information about the battery, according to embodiments of this disclosure. For example, weighting of degradation performance data z is performed by performing dimensional compression on a set of supplementary information and calculating feature vectors between batteries for supplementary information about battery 1, which is the object of estimation, and supplementary information about the battery included in degradation performance data. The similarity between batteries is calculated based on the length of the feature vectors, and weighting is performed based on the similarity to generate degradation performance data z', wherein batteries with supplementary information similar to that about battery 1 are weighted more heavily.

[0035] However, as Figure 4B As shown, the deterioration level performance data z can be weighted using rule-based weighting. Figure 4BFor example, vehicles equipped with batteries (i.e., vehicles with batteries installed) are compared, and batteries equipped in vehicles of the same model as vehicle C equipped with battery 1 are given a greater weight. The same kind of weighting is performed based on each piece of supplementary information, and, for example, the weight values ​​obtained for each battery are summed to generate degradation performance data z', wherein batteries with supplementary information similar to that for battery 1 are given a greater weight.

[0036] The degradation estimation unit 53 is connected to the usage history unit 22 and the model generation unit 52. The degradation estimation unit 53 uses the SOH estimation model generated by the model generation unit 52 to estimate the SOH of battery 1 based on usage history information about battery 1. The degradation estimation unit 53 is composed, for example, of a CPU, MPU, working memory, and a non-volatile storage device for storing control programs. Furthermore, the degradation estimation unit 53 does not necessarily have to be part of the battery degradation estimation device 5 and can be configured with an external cloud computing environment. Additionally, the model generation unit 52 and the degradation estimation unit 53 can be configured using the same CPU, MPU, working memory, non-volatile storage device for storing control programs, etc.

[0037] As described above, the battery degradation estimation system according to embodiments of this disclosure generates new degradation performance data, wherein, based on the accumulated degradation performance data, increased weights are applied to batteries that have a high level of similarity to supplementary information about the target battery. Furthermore, using the generated degradation performance data as training data to perform machine learning enables the generation of a SOH estimation model that is more consistent with the target battery. This makes it possible to provide a battery degradation estimation method that improves estimation accuracy while ensuring the performance of models based on physical and chemical degradation characteristics.

[0038] Battery degradation estimation method Next, we will refer to Figure 5 A battery degradation estimation method according to embodiments of the present disclosure is described. Figure 5 This is a flowchart of a battery degradation estimation method according to an embodiment of the present disclosure.

[0039] First, the model generation unit 52 acquires supplementary information and degradation performance data of battery 1, which is the battery to be estimated, and the degradation estimation unit 53 acquires usage history information about battery 1 (step S1). However, note that it is sufficient for the degradation estimation unit 53 to acquire usage history information about battery 1 before the degradation estimation unit 53 performs step S5, which will be described later.

[0040] Next, a decision is made on whether to apply weights to the degradation performance data z (step S2). In step S2, for example, if the number of degradation performance data z is too large relative to the performance of model generation unit 52, model generation unit 52 does not perform weighting. However, it should be noted that, depending on the performance of model generation unit 52, weighting may be performed only on a portion of the degradation performance data z. Based on the performance of model generation unit 52, a threshold for the number of degradation performance data z that should be weighted is appropriately determined.

[0041] Furthermore, when comparing the supplementary information about battery 1 with the supplementary information about batteries included in the degradation performance data z indicates that only a few batteries have supplementary information similar to that about battery 1, weighting based on supplementary information is not performed in rule-based weighting. For example, when the number of data items related to batteries installed in vehicles similar to vehicle C that has battery 1 installed is very small, weighting based on the vehicle with the installed battery is not performed. However, it should be noted that the threshold for the number of batteries with supplementary information similar to that of battery 1 is appropriately determined based on the number of battery data included in the degradation performance data z.

[0042] When weighting the degradation performance data z (Yes in step S2), the model generation unit 52 performs weighting of the degradation performance data z (step S3). Weighting is performed as described above, and for batteries with supplementary information similar to that of battery 1, degradation performance data z' is generated with a higher weight. On the other hand, if the degradation performance data z is not weighted (No in step S2), step S3 is not performed, and the degradation performance data z is used as unchanged training data.

[0043] Next, machine learning is performed using degradation performance data z' or z as training data to generate a trained model as a degradation estimation model (SOH estimation model), which takes battery usage history information as input and outputs the battery degradation degree (step S4). Here, when degradation performance data z' consistent with supplementary information about battery 1 is used as training data, an SOH estimation model that is more suitable for estimating the SOH of battery 1 is generated.

[0044] In step S4, machine learning is performed to reduce the error between the SOH value output by the SOH estimation model f and the SOH performance value contained in the degradation performance data z', and an SOH estimation model f is generated. Here, least squares and the like can be used, for example, as optimization techniques to optimize parameters θ to generate the SOH estimation model f. Furthermore, for example, parameters θ can be optimized using artificial intelligence (AI). When optimizing parameters θ, the weight values ​​assigned to each degradation performance data point in step S3 are used unchanged as the weights at each degradation performance data point.

[0045] Subsequently, the degradation estimation unit 53 uses the degradation estimation model generated in step S4 to estimate the SOH of battery 1 (step S5).

[0046] Finally, the actual SOH measurement of battery 1 is used to determine whether to update the degradation estimation model generated in step S4 (step S6). If the degradation estimation model is not updated (No in step S6), the process ends. Note that the actual SOH measurement data of battery 1 can be stored in the degradation performance data, and processing can be performed to increase the sample size of the degradation record data.

[0047] On the other hand, when it is necessary to update the degradation estimation model (Yes in step S6), the actual SOH measurement value of battery 1 is used, and the process returns to step S3 to perform the weighted and updated degradation estimation model again using the degradation performance data. Figure 6 This is a diagram illustrating a method for updating a degradation estimation model according to an embodiment of the present disclosure. For example, the degradation estimation model is updated by providing feedback to it, such that the absolute value of the error y(t)-s(t) between the estimated value y(t) and the accurate SOH measurement s(t) is reduced.

[0048] Currently, feedback to the degradation estimation model can be performed continuously, or only when the absolute value of the error y(t) - s(t) exceeds a threshold. Furthermore, when overestimating the estimate in estimating SOH is not desired, for example, a positive threshold can be set, and feedback can be performed when the value of the error y(t) - s(t) is greater than the positive threshold. On the other hand, when underestimating the estimate is not desired, a negative threshold can be set, and feedback can be performed when the value of the error y(t) - s(t) is less than the negative threshold. In addition to the SOH value itself, the threshold can also be other indicators, such as the ratio of error y(t) - s(t) to s(t).

[0049] As a method of execution feedback, steps S3 to S5 are repeated for s=[s(t_1), ..., s(t_n)] obtained as actual measurements at one or more times, for example, to reduce the error index (e.g., |ys| etc.) calculated from the estimated output y=[y(t_1), ..., y(t_n)] corresponding to each time to a predetermined value.

[0050] In the feedback process, in step S3, processing is performed, for example, by changing the similarity during weighting, or by changing the rule-based classification category during rule-based weighting. Furthermore, in step S4, for example, processing is performed to modify optimization techniques that change the parameter θ when generating the degraded estimation model, or to change the initial values ​​or random numbers given to the optimization techniques beforehand. Additionally, in step S5, for example, processing is performed such as reducing or adding input variables to the degraded estimation model or changing combinations of model architectures. Note that the efficiency of the feedback can be improved by having artificial intelligence perform these processing steps.

[0051] As described above, the battery degradation estimation method according to embodiments of this disclosure uses degradation performance data as training data to generate a SOH estimation model. For batteries with a high level of similarity to supplementary information about the target battery, the degradation performance data is given higher weight. Furthermore, the degradation estimation model is updated by comparing the estimated SOH value estimated using the generated SOH estimation model with the actual SOH measurement value and providing feedback. This enables the provision of a battery degradation estimation method that improves estimation accuracy while ensuring the performance of models based on physical and chemical degradation characteristics.

Claims

1. A battery degradation estimation method for a battery installed in a vehicle and supplying power to an electric motor, the battery degradation estimation method comprising: The pre-accumulated degradation performance data of the battery is weighted by performing weighting based on the similarity with supplementary information about the battery being estimated; Machine learning is performed by using the degradation performance data weighted in the processing as training data to generate a training model that takes the battery's usage history information as input and outputs the battery's degradation level. as well as Based on the usage history information about the battery being estimated, the trained model is used to estimate the degree of degradation of the battery being estimated.

2. The battery degradation estimation method according to claim 1, wherein the supplementary information about the battery being estimated includes either or both of vehicle information and driving history information about the vehicle.

3. The battery degradation estimation method according to claim 1 or 2, wherein, In the process, a process is performed to increase the weight of the degradation performance data that has a high similarity to the supplementary information about the estimated target battery.

4. The battery degradation estimation method according to claim 1 or 2, wherein, In the process, whether to perform weighting of the degradation performance data is determined based on the number of degradation performance data that have a high similarity to the supplementary information about the estimated target battery.

5. The battery degradation estimation method according to claim 1 further includes: Measure the degree of degradation of the estimated battery; as well as The training model is updated by adding the degradation performance data of the estimated object battery, measured in the measurement step, to the training data.

Images