BATTERY DECLINE ESTIMATE METHOD

Abstract

A 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 an engine, and comprises a process for performing a weighting of deterioration-degree performance data of the battery, which is collected in advance, by performing a weighting in accordance with the similarity of additional information regarding an estimation object battery, generating a trained model that takes usage history information of the battery as input and outputs the deterioration degree of the battery by performing machine learning on the deterioration-degree performance data weighted during processing as training data, and estimating the deterioration degree of the estimation object battery using the trained model.based on the usage history information regarding the estimated object battery.

Description

BACKGROUND OF THE INVENTION 1. Field of the invention

[0001] The present disclosure relates to a battery deterioration estimation method. 2. Description of the related prior art

[0002] Japanese patent application No. 2013-089424 (JP 2013-089424 A) discloses an estimation model for the degree of deterioration (state of health (SOH)) of secondary batteries based on physical and chemical characteristics of battery deterioration, such as the deterioration behavior of electrodes according to the Arrhenius equation, the square root law of deterioration over time, and so on. BRIEF SUMMARY OF THE INVENTION

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

[0004] The present disclosure was made in light of the circumstances described above and provides a battery deterioration estimation method that can improve the estimation accuracy while ensuring the performance of a model based on physical and chemical characteristics.

[0005] A battery deterioration estimation method according to one aspect of the present disclosure is a battery deterioration estimation method for a battery installed in a vehicle and supplying power to an engine, and comprises a processing of performing a weighting of deterioration-degree performance data of the battery, which are collected in advance, by performing a weighting according to a similarity with additional information regarding an estimated object battery; a trained model that takes battery usage history information as input and outputs a battery degradation level, by performing machine learning on the degradation level performance data, which are weighted during processing as training data; and an estimation of the deterioration level of the estimation object battery using the trained model, based on usage history information regarding the estimation object battery.

[0006] According to the present disclosure, a battery deterioration estimation method can be provided that can improve the estimation accuracy while ensuring the performance of a model based on physical and chemical deterioration characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Features, advantages and technical and industrial significance of embodiments of the invention are described below with reference to the accompanying drawings, in which the same symbols denote the same elements and in which: Fig. Figure 1 is a block diagram representing a configuration of a battery deterioration estimation system according to an embodiment of the present disclosure; Fig. 2A is a graph of the state of health (SOH) over time for a battery according to the embodiment of the present disclosure; Fig. 2B are time series data of the SOH of the battery according to the embodiment of the present disclosure; Fig. 2C is an example of additional information regarding the battery according to the embodiment of the present disclosure; Fig. 2D is an example of additional information about the battery according to the embodiment of the present disclosure; Fig. 3A is an input / output flowchart of a SOH estimation model according to the embodiment of the present disclosure; Fig. Figure 3B is a diagram comparing the SOH estimation model according to the embodiment of the present disclosure, an existing SOH estimation model and an SOH estimation model obtained by complicating the existing model; Fig. 4A is a diagram of weighting based on dimensional compression according to the similarity of additional information about the battery according to the embodiment of the present disclosure; Fig. 4B is a diagram of the rule-based weighting according to the similarity of the additional information about the battery according to the embodiment of the present disclosure; Fig. Figure 5 is a flowchart of a battery deterioration estimation method according to the embodiment of the present disclosure; and Fig. Figure 6 is a diagram showing a method for updating an estimation model for deterioration according to the embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EXECUTION EXAMPLES

[0008] A specific embodiment of the present disclosure is described in detail below with reference to the drawings. It should be noted that the present disclosure is not limited to the following embodiment. Furthermore, the following description and the drawings have been simplified for the sake of clarity. Configuration of the battery deterioration estimation system

[0009] Fig. Figure 1 is a block diagram representing a configuration of a battery deterioration estimation system according to an embodiment of the present disclosure.

[0010] The battery deterioration estimation system S comprises a vehicle C and a battery deterioration estimation device 5. The vehicle C includes a battery 1, a battery sensor 2, an operations unit 3, and an operating history acquisition unit 4. The battery sensor 2 includes a usage history acquisition unit 21, a usage history recording unit 22, an additional information acquisition unit 23, and an additional information recording unit 24. The battery deterioration estimation device 5 includes a performance data collection unit 51, a model generation unit 52, and a deterioration estimation unit 53. It should be noted that battery 1 is an estimation object battery.

[0011] Vehicle C is a car that can move by being driven by a motor (not shown) of the operating unit 3, with power supplied to the operating unit 3 from battery 1. Vehicle C is, for example, a battery-powered electric vehicle, but could also be a hybrid electric vehicle with an external charging function or the like.

[0012] Battery 1 is connected to the usage history acquisition unit 21 and the additional information acquisition unit 23. Battery 1 is a power storage device installed in vehicle C and serves to supply power to a drive unit that propels vehicle C. Battery 1 is a secondary battery, such as a lithium-ion battery, a lead-acid battery, a nickel-metal hydride battery, or similar, and is configured to contain a layer of active cathode material, a layer of active anode material, a current collector, a separator, an electrolyte solution, etc., within a sealing element. Battery 1 is connected to and supplies power to a motor that propels vehicle C.The size of battery 1 and the type of secondary battery used for battery 1 are determined depending on the size and use of the vehicle C into which battery 1 is to be installed.

[0013] The battery sensor 2 is connected to the battery 1, the operating history recording unit 4, and the model generation unit 52. For example, in Fig. As shown in Figure 2A, the battery sensor 2 obtains a state of health (SOH) value of battery 1 at a predetermined time and transmits the obtained results to the model generation unit 52. The SOH is a ratio of the full charge capacity of battery 1 when deteriorated to the full charge capacity of battery 1 in an initial period and is defined as SOH(%)=(full charge capacity of battery 1 when deteriorated)(full charge capacity of battery 1 in initial period)×100

[0014] In the present disclosure, the SOH value determined by expression (1) is used as an index indicating the degree of deterioration of battery 1. The smaller the SOH value, the more advanced the deterioration of battery 1 is, and the greater the degree of deterioration of battery 1.

[0015] The usage history acquisition unit 21 is connected to battery 1 and the usage history recording unit 22. Usage history acquisition unit 21 acquires the state of health (SOH) value of battery 1 at a predetermined time and transmits the acquired data to usage history recording unit 22. Usage history acquisition unit 21 includes, for example, sensors such as a current sensor, a voltage sensor, or similar, and acquires a current or voltage value at a predetermined time. Usage history acquisition unit 21 calculates the SOH value of battery 1 by, for example, determining the amount of current flowing from a discharged state to a fully charged state, based on the acquired current or voltage value.To calculate the SOH value of battery 1, the usage history procurement unit 21 can consist of a central processing unit (CPU), a microprocessor unit (MPU), a working memory, a non-volatile device that stores control programs, etc.

[0016] The usage history recording unit 22 is connected to the usage history acquisition unit 21 and the deterioration estimation unit 53. The usage history recording unit 22 records the state of health (SOH) value of battery 1 received from the usage history acquisition unit 21 and transmits the recorded SOH value of battery 1 to the deterioration estimation unit 53. It should be noted, however, that the usage history recording unit 22 can also record information about parameters used to determine the SOH value of battery 1, such as the duration of current flow and the amount of current flowing through battery 1. That is, the usage history information relating to battery 1 consists of the parameters used to determine the SOH value of battery 1, such as the SOH value of battery 1 at a predetermined time, the duration of current flow, the amount of current flowing, and so on.

[0017] In the usage history recording unit 22, the SOH value of battery 1 is recorded in the form of time series data, such as in Fig. Figure 2B shows the battery ID assigned to each battery, the date the SOH value was recorded, and the recorded SOH value. The usage history recording unit 22 includes a storage device that can store various types of data and does not necessarily have to be part of the battery sensor 2, but can also be an external storage device or cloud storage connected to the usage history acquisition unit 21 via a network. The usage history recording unit 22 also includes a communication interface that can communicate with the deterioration estimation unit 53 via wired communication devices, wireless communication devices, or similar means.

[0018] The supplementary information retrieval unit 23 is connected to battery 1 and the supplementary information recording unit 24. The supplementary information retrieval unit 23 retrieves supplementary information via battery 1 and transmits the retrieved supplementary information via battery 1 to the supplementary information recording unit 24.

[0019] The additional information about battery 1 may include, for example, the following: characteristic information about battery 1, such as the full charging capacity of battery 1 in the initial phase, the cathode material, the anode material, the electrolyte material, the manufacturer, etc.; characteristic information about the vehicle C in which the battery 1 is installed, such as model, mileage, vehicle weight, etc. C;

[0020] Information relating to the driving environment or the vehicle condition of vehicle C in which battery 1 is installed, such as the driving region of vehicle C, the SOC of battery 1 during driving, the battery temperature, the ambient temperature, etc.;

[0021] History information about the operations and charging processes of vehicle C, in which battery 1 is installed, such as the number of sudden accelerations and decelerations, the ratio of fast charging to normal charging, etc.; and so on. Here is the characteristic information regarding vehicle C. Vehicle information regarding vehicle C also includes the driving environment of vehicle C, historical information regarding the vehicle's condition, and historical information regarding the driving and charging processes of vehicle C. The additional information acquisition unit 23 also obtains information that can be obtained directly from battery 1, such as the state of charge (SOC) of battery 1 during driving, the battery temperature, the ratio of fast charging to normal charging, and so on, as additional information regarding battery 1.

[0022] The additional information acquisition unit 23 includes, for example, sensors such as a current sensor, a temperature sensor, or similar devices. To acquire additional information about battery 1 based on data such as current values, temperatures, or similar information recorded by the sensors, the additional information acquisition unit 23 can also consist of a CPU, an MPU, main memory, non-volatile memory for storing control programs, and so on.

[0023] The supplementary information recording unit 24 is connected to the supplementary information acquisition unit 23, the operation acquisition unit 4, and the model generation unit 52. The supplementary information recording unit 24 records the supplementary information regarding battery 1 that is transmitted by the supplementary information acquisition unit 23 and the operation history acquisition unit 4, and transmits the recorded supplementary information regarding battery 1 to the model generation unit 52.

[0024] The Additional Information Recording Unit 24 is a storage device capable of storing various types of data. It does not necessarily have to be part of the Battery Sensor 2, but rather can be an external storage device or cloud storage connected to the Usage History Acquisition Unit 21 via a network. The Additional Information Recording Unit 24 also includes a communication interface that can communicate with the Deterioration Estimation Unit 53 via wired communication devices, wireless communication devices, or the like. It should be noted that the Usage History Recording Unit 22 and the Additional Information Recording Unit 24 can be the same storage device. Furthermore, additional information regarding Battery 1, such as...characteristic information relating to battery 1 and characteristic information relating to vehicle C in which battery 1 is installed may be recorded in advance in the supplementary information recording unit 24, or may be recorded by being transmitted from the supplementary information acquisition unit 23 and the operation history recording unit 4.

[0025] Operational Unit 3 is connected to Operational History Unit 4. Operational Unit 3 is a device for operating vehicle C as a vehicle, such as an engine, brakes, steering wheel, safety devices, a vehicle navigation system, and so on.

[0026] The operational history acquisition unit 4 is connected to the operational unit 3 and the supplementary information recording unit 24. The operational history acquisition unit 4 obtains the operational history from the operational unit 3 and transmits the acquired data to the supplementary information recording unit 24 as additional information about battery 1. The operational history acquisition unit 4 is equipped with sensors such as a speed sensor, an engine speed sensor, a GPS receiver, etc., and acquires information that can be obtained directly from the operational unit 3, such as the region in which vehicle C is moving, the number of sudden accelerations and decelerations, etc., as supplementary information regarding battery 1.

[0027] The battery deterioration estimator 5 is connected to the usage history recording unit 22 and the supplementary information recording unit 24. The battery deterioration estimator 5 estimates the state of health (SOH) based on the usage history information and supplementary information about the battery 1, as well as on performance and test data collected in the performance data collection unit 51 for a large number of batteries. Here, the SOH is estimated using an SOH estimation model that can estimate the SOH based on the physical and chemical characteristics of battery deterioration. The SOH estimation model is described later.

[0028] The performance data collection unit 51 is connected to the model generation unit 52. The performance data collection unit 51 collects performance value data from used batteries that have been used in the past and test data from batteries that have been tested, as deterioration-degree performance data. This deterioration-degree performance data includes usage history information and additional information. The deterioration-degree performance data is training data required by the model generation unit 52 to create a state-of-health (SOH) estimation model and is transmitted to the model generation unit 52 as needed.The performance data collection 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, but can also be an external storage device or cloud storage connected to the model generation unit 52 via a network.

[0029] In the performance data collection unit 51, the additional information relating to the battery, which includes the deterioration-degree performance data, is recorded in conjunction with characteristic information relating to the battery and the vehicle C, such as battery ID, manufacturer, cathode material, anode material and vehicle in which the battery is installed, as in Fig. 2C is shown. Furthermore, additional information about the battery, including degradation performance data, is recorded in conjunction with the battery ID and vehicle history information C, such as the number of sudden vehicle accelerations and the ratio of fast charging usage, as shown in Fig. Shown in 2D.

[0030] The model generation unit 52 is connected to the ancillary information recording unit 24, the performance data collection unit 51, and the deterioration estimation unit 53. The model generation unit 52 generates a state-of-health (SOH) estimation model based on the ancillary information and deterioration performance data from battery 1 and transmits the generated model to the deterioration estimation unit 53. The model generation unit 52 consists, for example, of a CPU, an MPU, main memory, non-volatile storage for control programs, and so on. Furthermore, the model generation unit 52 does not necessarily have to be part of the battery deterioration estimation unit 5, and an external cloud computing environment can be configured for this purpose.

[0031] Here is a SOH estimation model f generated by the model generation unit 52, for example an estimation model based on a square root law model regarding the capacity conservation rate y of battery 1. y=−kt+1 where k is a constant of the deterioration rate and t is time. The capacity conservation rate y corresponds to the value of SOH, which is not expressed as a percentage. The value of k in expression (2) is determined, for example, based on the Arrhenius equation. k=A×exp(−EaRT) where A is a frequency factor, E a The activation energy for the reaction, R a gas constant, and T the temperature. By estimating A and E a In expression (3), the value of k at a specific temperature T, and thus the SOH, can be estimated. The parameters k, A, and E aIn expressions (2) and (3), the parameters θ in the SOH estimation model f are given. That is, calculating the parameter θ allows the estimation of the SOH using the SOH estimation model f. It should be noted that the SOH estimation model f can estimate the SOH using an expression based on physical and chemical characteristics of battery degradation other than those described above, and as a result, the parameter θ can be other parameters than k, A, and E mentioned above. a include.

[0032] Fig. Figure 3A is an input / output flowchart of the SOH estimation model according to the embodiment of the present disclosure. In the SOH estimation model f, the parameter θ is estimated by using deterioration-degree performance data z as training data and by performing a parameter learning process g to learn the parameter θ. The SOH estimation model f generated by estimating the parameter θ is a trained model that takes usage history information x_t of battery 1 as input and outputs the SOH value y_t of battery 1. Here, the inventors have found that by applying a weight W to the performance data of each of the batteries included in the deterioration-degree performance data, according to the similarity with respect to the additional information x_history of battery 1, deterioration-degree performance data z' can be generated that correspond to the additional information x_history of battery 1.Using the deterioration-level performance data z' as training data when performing machine learning allows for an improvement in the estimation accuracy of the parameter θ and an improvement in the performance of the SOH estimation model f.

[0033] Fig. Figure 3B is a comparison of the SOH estimation model according to the embodiment of the present disclosure, an existing SOH estimation model, and an SOH estimation model obtained by complicating the existing model. In the SOH estimation model f according to the embodiment of the present disclosure, no change is made to the model structure or the parameter learning process g, but an improvement is achieved by adopting the deterioration-degree performance data used as training data by the parameter learning process g as z'. Accordingly, the accuracy of the SOH estimation can be improved while ensuring the performance of the SOH estimation model f itself, which is based on the physical and chemical characteristics of battery deterioration.

[0034] The weighting W of the deterioration performance data z is carried out, for example, by processing the increase in the weighting of the performance data of a battery with additional information that has a high degree of similarity to the additional information regarding battery 1. Fig. Figure 4A is a diagram of weighting based on dimensional compression according to the similarity of the ancillary information about the battery, as described in the embodiment of this disclosure. The weighting of the deterioration-degree performance data z is performed, for example, by dimensional compression on a set of ancillary information and computing feature vectors between batteries for ancillary information relating to battery 1, which is the object of the estimation, and the ancillary information relating to the battery included in the deterioration-degree performance data. The similarity between the batteries is calculated according to the length of the feature vector, and the weighting is performed according to the similarity, thereby generating the deterioration-degree performance data z' in which batteries with ancillary information similar to the ancillary information relating to battery 1 are weighted more heavily.

[0035] It should be noted that the weighting of the deterioration-degree performance data z can be done by rule-based weighting, as in Fig. 4B shown. Fig. For example, in section 4B, vehicles equipped with batteries (i.e., vehicles in which batteries are installed) are compared, and a battery installed in a vehicle of the same model as vehicle C, which is equipped with battery 1, is weighted more heavily. The same type of weighting is performed based on each piece of additional information, and the weighting values ​​obtained for each of the batteries are added together to generate, for example, deterioration-degree performance data z', in which the batteries with additional information similar to the additional information regarding battery 1 are weighted more heavily.

[0036] The deterioration estimation unit 53 is connected to the usage history recording unit 22 and the model generation unit 52. The deterioration estimation unit 53 uses the SOH estimation model generated by the model generation unit 52 to estimate the SOH value of battery 1 based on the usage history information about battery 1. The deterioration estimation unit 53 consists, for example, of a CPU, an MPU, RAM, and non-volatile storage that stores control programs. Furthermore, the deterioration estimation unit 53 does not necessarily have to be part of the battery deterioration estimation unit 5, and an external cloud computing environment can be configured for it.Furthermore, the model generation unit 52 and the deterioration estimation unit 53 can be configured to use the same CPU, MPU, main memory, non-volatile storage device that stores control programs, etc.

[0037] As described above, the battery deterioration estimation system, according to the embodiment of the present disclosure, generates new deterioration-degree performance data in which increased weighting is applied to batteries that exhibit a high degree of similarity to the additional information regarding the target battery, based on collected deterioration-degree performance data. Furthermore, a state-of-health (SOH) estimation model that better matches the target battery can be generated by machine learning using the generated deterioration-degree performance data as training data. In this way, a battery deterioration estimation method can be provided that improves estimation accuracy while ensuring the performance of a model based on physical and chemical characteristics. Battery deterioration estimation methods

[0038] The battery deterioration estimation method according to the embodiment of the present disclosure is described below with reference to Fig. 5 described. Fig. Figure 5 is a flowchart of the battery deterioration estimation method according to the embodiment of the present disclosure.

[0039] First, the model generation unit 52 obtains the additional information and the deterioration performance data of battery 1, which is the battery used for estimation, and the deterioration estimation unit 53 obtains the usage history information regarding battery 1 (step S1). However, it should be noted that it is sufficient for the deterioration estimation unit 53 to obtain the history information about battery 1 before the deterioration estimation unit 53 performs step S5, which is described later.

[0040] Next, a decision is made as to whether weighting should be applied to the deterioration-degree performance data z (step S2). In step S2, for example, the model generation unit 52 does not perform weighting if the count, or number, of deterioration-degree performance data z is excessively large relative to the power of the model generation unit 52. However, it should be noted that, depending on the power of the model generation unit 52, weighting can only be performed on a portion of the deterioration-degree performance data z. A threshold value for the count of the deterioration-degree performance data z, used to determine whether weighting should be performed, is set as appropriate in accordance with the power of the model generation unit 52.

[0041] If a comparison of the additional information regarding battery 1 with the additional information regarding the batteries included in the deterioration-degree performance data z indicates that there are only a few batteries with additional information similar to that of battery 1, the weighting based on the additional information in the rule-based weighting is not performed. For example, if the number of data elements regarding batteries installed in vehicles similar to vehicle C, in which battery 1 is installed, is extremely small, the weighting based on the vehicle in which the battery is installed is not performed.However, it should be noted that a threshold for the number of batteries with additional information similar to the additional information of battery 1 is deemed appropriate, depending on the count value of the battery data included in the deterioration performance data z.

[0042] If weighting of the deterioration-degree performance data z is to be performed (Yes in step S2), the model generation unit 52 performs weighting of the deterioration-degree performance data z (step S3). The weighting is performed as described above, and the deterioration-degree performance data z' are generated with a higher weight for batteries that have additional information similar to the additional information of battery 1. If, on the other hand, no weighting of the deterioration-degree performance data z is to be performed (No in step S2), step S3 is not performed, and the deterioration-degree performance data z are used unchanged as training data.

[0043] Next, machine learning is performed using the deterioration-level performance data z' or z' as training data to generate a trained model as a deterioration-level estimation model (SOH estimation model) that takes historical battery usage information as input and outputs the battery's deterioration level (step S4). If deterioration-level performance data z' that matches the additional information regarding battery 1 is used as training data, an SOH estimation model is generated that is better suited for estimating the SOH of battery 1.

[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 values ​​included in the deterioration performance data z', and the SOH estimation model f is generated. Here, for example, the least squares method or a similar optimization technique can be used to optimize the parameter θ for generating the SOH estimation model f. Alternatively, the parameter θ can be optimized using artificial intelligence (AI). When optimizing the parameter θ, the weighting values ​​assigned to each deterioration performance data point in step S3 are used unchanged as the weight for each deterioration performance data point.

[0045] Subsequently, the deterioration estimation unit 53 estimates the SOH of battery 1 using the deterioration estimation model generated in step S4 (step S5).

[0046] Finally, the actual SOH measurement of battery 1 is used to decide whether to update the SOH estimation model generated in step S4 (step S6). If the deterioration estimation model should not be updated (No in step S6), the process terminates. It should be noted that the actual SOH measurement data of battery 1 can be stored in the deterioration performance data, and processing can be performed to increase the number of samples in the deterioration performance data.

[0047] On the other hand, if the deterioration estimation model is to be updated (Yes in step S6), the actual SOH measurement of battery 1 is used, and the processing returns to step S3 to perform a weighting of the deterioration degree performance data and a re-update of the deterioration estimation model. Fig. Figure 6 is a diagram showing a method for updating the deterioration estimation model according to the embodiment of the present disclosure. The update of the deterioration estimation model is performed, for example, by providing feedback to the deterioration estimation model such that an absolute error value y(t) - s(t) between the estimated value y(t) and the exact SOH measurement s(t) becomes smaller.

[0048] The feedback loop to the deterioration estimation model can now be performed at any time or only when the absolute value of the error y(t) - s(t) exceeds a threshold. For example, if an overestimation of the estimated value is undesirable when estimating the SOH, a positive threshold can be set, and feedback can occur when the value of the error y(t) - s(t) is greater than the positive threshold.

[0049] If, on the other hand, an underestimation of the estimate is undesirable, a negative threshold can be set and feedback performed when the value of the error y(t) - s(t) is less than the negative threshold. Besides the SOH value itself, the threshold can also be another indicator, e.g., the ratio of the error y(t) - s(t) to s(t) or something similar.

[0050] As a procedure for carrying out the feedback, steps S3 to S5 are repeatedly executed for s = [s(t_1), ..., s(t_n)], which are obtained as actual measured values ​​at one or more time points, so that, for example, an error index (e.g. |y - s| or the like), which is calculated from the estimated output y = [y(t_1), ..., y(t_n)] according to each time point, is reduced to a predetermined value.

[0051] In the feedback loop, processing is performed in step S3, for example, by changing the similarity during weighting, by changing the rule-based classification category during rule-based weighting, or similar actions. Furthermore, in step S4, processing is performed, for example, to modify an optimization procedure for the parameter θ when the deterioration estimation model is created, or to change initial values ​​or random numbers pre-defined to the optimization procedure, or similar actions. Additionally, in step S5, processing is performed, for example, to reduce or add input variables to the deterioration estimation model, or to change the model's architecture combination, or similar actions.It should be noted that the efficiency of the feedback process can be improved by using artificial intelligence to perform the processing of these steps.

[0052] As described above, the battery deterioration estimation method according to the embodiment of the present disclosure generates a SOH estimation model using deterioration-degree performance data as training data. This data is heavily weighted for batteries that exhibit a high degree of similarity to the additional information regarding the battery being estimated. Furthermore, the SOH estimation model is updated by comparing the estimated SOH value, calculated using the generated SOH estimation model, with the actual SOH measurement and providing feedback. In this way, a battery deterioration estimation method can be provided that improves estimation accuracy while ensuring the performance of a model based on the physical and chemical characteristics of deterioration. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] JP 2013-089424

[0002] JP 2013-089424 A [0002, 0003]

Claims

A battery deterioration estimation method for a battery installed in a vehicle and supplying power to an engine, wherein the battery deterioration estimation method comprises: processing the weighting of pre-collected battery deterioration performance data by weighting according to similarity with additional information regarding an estimation object battery; generating a trained model that takes battery usage history information as input and outputs a battery deterioration level by performing machine learning on the deterioration performance data, weighted during processing, as training data; and estimating the deterioration level of the estimation object battery using the trained model, based on the usage history information regarding the estimation object battery. Battery deterioration estimation method according to claim 1, wherein the additional information relating to the estimation object battery includes both vehicle information and driving history information relating to the vehicle or one thereof. Battery deterioration estimation method according to claim 1 or 2, wherein the processing involves a process in which the weighting is increased for the deterioration degree performance data whose similarity to the additional information relating to the estimation object battery is high. Battery deterioration estimation method according to claim 1 or 2, wherein during processing a decision is made as to whether a weighting of the deterioration degree performance data is carried out according to a count value of the deterioration degree performance data whose similarity to the additional information relating to the estimation object battery is high. Battery deterioration estimation method according to claim 1, further comprising: measuring the degree of deterioration of the estimation object battery; and updating the trained model by adding the deterioration performance data of the estimation object battery, measured in the measurement step, to the training data.

Images