Method and system for estimating SOHC of electric vehicle

Abstract

A method and system are provided for estimating a real-time SOHC by generating an SOHC estimation model using cell data obtained from a test battery and first field data in estimating the SOHC of a battery in use and inputting second field data obtained from the battery in use into the SOHC estimation model.

Description

Technical Field

[0001] The present invention relates to a method and system for estimating the SOHC of a battery of an electric vehicle (EV) using field data. Specifically, the present invention aims to provide a method and system for calculating an accurate SOHC value of a battery using a machine learning prediction model in a cloud BMS so as to calculate an accurate state of health capacity value of the battery. Background Art

[0002] Conventionally, when estimating the state of health capacity (SOHC) of an electric vehicle (EV) battery using field data, the battery capacity value calculated from the onboard battery management system (BMS) is used. However, since the battery capacity value calculated in this way cannot be regarded as the true value, the SOHC value of the battery estimated using this value contains a large error.

[0003] Therefore, a method for calculating SOHC directly from monomer data is needed.

[0004] Previous inventions related to this include Patent Document 1 which estimates the remaining life of a battery using an LSTM model and Patent Document 2 which estimates the dischargeable time of a secondary battery using a neural network.

[0005] However, these previous inventions do not propose a method for generating an accurate estimation model as in the present invention. In addition, the limitation of using only on-board calculated values ​​when generating the estimation model cannot be overcome.

[0006] The relevant prior art is as follows.

[0007] Patent Document 1: KR 2023-0003848 A (2023.01.06)

[0008] Patent document 2: JP 6250298 B2 (2017.12.01). Summary of the invention

[0009] Technical issues

[0010] Therefore, the present invention aims to solve the above-mentioned problems of the prior art and provide a method and system for estimating accurate SOHC of a battery in situ by generating an accurate SOHC estimation model using cell data acquired during a battery cell testing process and using the SOHC estimation model.

[0011] Technical Solution

[0012] Therefore, the present invention provides a SOHC estimation model generating device, which includes: a battery testing device, which acquires cell data from a plurality of battery cells and first field data from other battery cells or from different charge / discharge cycles during a cell testing process; and a SOHC estimation model generating unit, which calculates a first SOHC value based on the cell data, constructs a first training data set with the cell data as an input value and with the first SOHC value as a label value to generate a first SOHC estimation model that estimates the SOHC value based on the cell data, inputs the first field data into the first SOHC estimation model to calculate a second SOHC value, constructs a second training data set with the first field data and the second SOHC value as a label value, and uses the second training data set to retrain the first SOHC estimation model to generate a second SOHC estimation model.

[0013] In addition, the present invention provides an application BMS, which includes a SOHC estimation model unit including a SOHC estimation model, and receives field data from a field battery operating in the application, inputs the field data into the SOHC estimation model, and calculates a real-time SOHC value of the field battery.

[0014] At this time, the SOHC estimation model is generated by the following operations: acquiring cell data from multiple battery cells during a cell testing process and acquiring first field data from other battery cells or different charge / discharge cycles, calculating a first SOHC value based on the cell data, constructing a first training data set with the cell data and the first SOHC value as a label value to generate a first SOHC estimation model that estimates the SOHC value based on the cell data, inputting the first field data into the first SOHC estimation model to calculate a second SOHC value, constructing a second training data set with the first field data and the second SOHC value as a label value, and retraining the first SOHC estimation model using the second training data set to generate a second SOHC estimation model.

[0015] In addition, the present invention provides a SOHC estimation system for a field battery, which includes: a battery testing device, which acquires cell data from a plurality of battery cells and first field data from other battery cells or from different charge / discharge cycles during a cell testing process; a SOHC estimation model generation unit, which calculates a first SOHC value based on the cell data, constructs a first training data set with the cell data and the first SOHC value as a label value to generate a first SOHC estimation model that estimates the SOHC value based on the cell data, inputs the first field data into the first SOHC estimation model to calculate a second SOHC value, constructs a second training data set with the first field data and the second SOHC value as a label value, and retrains the first SOHC estimation model using the second training data set to generate a second SOHC estimation model; and an application BMS, which includes a SOHC estimation model unit that includes a second SOHC estimation model as a SOHC estimation model, and receives field data from a field battery operating in an application, inputs the field data into the SOHC estimation model, and calculates a real-time SOHC value of the field battery.

[0016] In addition, the present invention provides a SOHC estimation method for a field battery cell, which includes: a cell data acquisition process, which acquires cell data from a plurality of battery cells during a cell test process; a first SOHC value calculation process, which calculates a first SOHC value corresponding to the cell data; a first SOHC estimation model generation process, which uses the cell data as an input value and uses the first SOHC value as a first label value to train and generate a first SOHC estimation model that estimates the SOHC value based on the cell data; a first field data acquisition process, which acquires second cell data different from the first field data from a plurality of battery cells during the cell test process; a second SOHC estimation value calculation process, which generates a second SOHC estimation value corresponding to the first field data by inputting the first field data into the generated first SOHC estimation model; a second SOHC estimation model generation process, which generates a second SOHC estimation model by retraining the first SOHC estimation model using the generated second SOHC estimation value as a label value and using the first field data as an input value; and a SOHC value estimation process, which estimates the SOHC value during operation of a predetermined battery cell by inputting the field data generated when operating the predetermined battery cell into the second SOHC estimation model.

[0017] Beneficial Effects

[0018] According to the present invention, a first SOHC estimation model is generated using cell data obtained during a battery testing process, and then a second SOHC estimation model is generated by retraining the first SOHC estimation model using a calculated SOHC value as a label value, the calculated SOHC value being calculated by using the first SOHC estimation model, and the second SOHC estimation model is applied as a final SOHC estimation model, thereby providing an estimation model with increased accuracy compared to the prior art that uses only an on-board calculated capacity value. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The following drawings attached to this specification illustrate preferred embodiments of the present invention, and together with the detailed description of the above invention, are used to further understand the technical concept of the present invention. Therefore, the present invention should not be interpreted as being limited to the contents described in these drawings.

[0020] Figure 1 is a block diagram of a SOHC estimation system according to the present invention.

[0021] Figure 2 is a block diagram of a SOHC estimation system according to another embodiment of the present invention.

[0022] Figure 3 is a flowchart illustrating a SOHC estimation model generation process and a SOHC estimation method using the generated estimation model according to the present invention. DETAILED DESCRIPTION

[0023] The present invention provides a method and system for estimating real-time SOHC by generating a SOHC estimation model using cell data obtained from a test battery and first field data different from the cell data when estimating the SOHC of a battery in use, and inputting second field data obtained from the battery in use into the SOHC estimation model.

[0024] 1. Definition of terms

[0025] Unless otherwise defined, the terms used in the present invention follow the definitions of terms described below.

[0026] The present invention constructs a model for estimating the SOHC of a battery in use based on cell data and field data. In the present invention, the state of health capacity (SOHC) refers to the ratio of the capacity reduction due to degradation to the initial capacity of the battery. Generally, it is calculated as SOHC (%) = (current battery capacity / initial battery capacity) × 100. Here, the current battery capacity represents the actual capacity of the battery, which varies according to use and charge-discharge cycles, and the initial battery capacity represents the capacity when the battery was first manufactured. It can be judged that the closer the SOHC value is to 100%, the better the health of the battery. It can be considered that as the SOHC value decreases, the life of the battery is shortened and the performance deteriorates.

[0027] In the present invention, cell data means battery cell data acquired from a test battery or a reference battery during a cell test process. In the present invention, field data means battery data acquired from a battery in use, which is being used in an application such as a vehicle.

[0028] In the present invention, a cloud battery management system (BMS) means a system that performs battery management functions on a cloud server and allows users to monitor and manage battery status in real time through a web browser anytime and anywhere. The cloud BMS can centrally and efficiently monitor and control battery systems in various locations, and can collect and analyze data and perform estimation analysis. In addition, the cloud BMS has the effect of optimizing overall energy management by sharing and linking data between multiple systems.

[0029] 2. SOHC estimation system for on-site battery according to the present invention

[0030] The SOHC estimation system for an on-site battery according to the present invention is a system that performs a real-time SOHC estimation method for an on-site battery. Figure 1 and Figure 2 The SOHC estimation system of the present invention is described.

[0031] like Figure 1 As shown in , the system of the present invention includes a SOHC estimation model generation unit 200 and an application BMS 400 installed with the generated estimation model, the application BMS 400 receives second field data from a field battery being used in the application, and calculates a real-time SOHC estimation value of the field battery based on this, and the application BMS 400 can be configured as a cloud BMS. In addition, the SOHC estimation model generation unit 200 generates a SOHC estimation model based on the single cell data received from the battery testing device 100 and the first field data received from the application battery 300.

[0032] In another embodiment, Figure 2As shown in , in the system of the present invention, the SOHC estimation model unit 420 and the SOHC estimation unit 430 may be configured as a separate SOHC estimation device 500 instead of being installed on the application BMS 400 .

[0033] Hereinafter, each configuration will be described.

[0034] (1) Battery testing equipment 100

[0035] The battery testing device 100 is a device that performs various tests on a battery after manufacturing the battery. The present invention uses cell data including various state information of a test battery generated during a battery test from the known battery testing device 100 as data for generating a SOHC estimation model.

[0036] The battery testing device 100 acquires cell data from a test battery and transmits the cell data to the SOHC estimation model generating unit 200 .

[0037] The types and characteristics of monomer data are described later.

[0038] (2) SOHC estimation model generation unit 200

[0039] The SOHC estimation model generation unit 200 is a configuration that generates a SOHC estimation model using not only the above-mentioned single body data but also the first field data, and includes a computer algorithm that performs a corresponding process. The present invention uses a known neural network as a neural network that is the basis of the SOHC estimation model, and is characterized by data and a training method for training the SOHC estimation model.

[0040] The SOHC estimation model generator 200 generates a SOHC estimation model by executing S10 to S60 processes described later, and provides the generated estimation model, ie, a computer-implemented algorithm for calculating a SOHC prediction value of a battery, to the SOHC estimation model unit 420 online or offline.

[0041] The SOHC estimation model generation unit 420 obtains cell data and a first SOHC value as a first label value from a battery test device or a reference data set previously managed to obtain, the first SOHC value being a SOHC value corresponding to the cell data, constructs a first training data set with the cell data and the first SOHC value (which is the first label value), and generates a first SOHC estimation model that estimates the SOHC value based on the cell data. The first SOHC value is a SOHC value calculated based on the cell data from the onboard BMS of the test battery, a predetermined artificial neural network model configured to estimate the SOHC value based on the cell data can be used as the first SOHC estimation model, and in one embodiment, a support vector regression (SVR) model is applied thereto, and the first SOHC estimation model is obtained by performing machine learning to obtain a first parameter set using a first training data set with the cell data as input and the first SOHC value as a label value, the first parameter set including coefficients, intercepts, and model parameters of a regression function that determines the SVR model. The first training data set is {cell data, first SOHC}.

[0042] Afterwards, the SOHC estimation model generation unit 420 acquires first field data from a predetermined field battery, and inputs the first field data into the first SOHC estimation model to calculate a second SOHC value as a second label value, and constructs a second training data set {first field data, second SOHC value} with the first field data as an input value and the second SOHC value as a label value. The second SOHC value is a SOHC value calculated by inputting the first field data into the first SOHC estimation model.

[0043] In another embodiment, the first field data may be obtained from the battery testing device 100. In this case, the battery testing device 100 obtains, as the first field data, single cell data obtained from a test battery other than the test battery from which the single cell data is obtained, or single cell data obtained from a charge / discharge cycle different from the charge / discharge cycle when the single cell data is obtained. In this case, the second training data set is also set to {first field data, second SOHC value}.

[0044] Afterwards, a second SOHC estimation model is generated by retraining the first SOHC estimation model using the second training data set to obtain a second parameter set, and the second SOHC estimation model is provided as a final SOHC estimation model. The provided second SOHC estimation model is installed on the SOHC estimation model unit 420 of the application BMS 400, which will be described later.

[0045] (3) Application of BMS400

[0046] The application BMS 400 of the present invention is a battery management device that manages the application battery 300 , and may be configured to include a field data collection unit 410 , a SOHC estimation model unit 420 , a SOHC estimation unit 430 , and a monitoring unit 440 in addition to typical BMS components.

[0047] The application BMS 400 of the present invention collects field data such as battery status information from the application battery 300 in operation, and may be configured as an on-site battery management system (on-Site BMS) configured in the same location or facility as the application battery, or may be configured as a cloud BMS.

[0048] When the application BMS 400 is configured as a cloud BMS, the application BMS 400 is connected to a plurality of vehicle-mounted BMSs through a predetermined wired / wireless communication network, and receives cell data and field data from the vehicle-mounted BMSs.

[0049] In the present invention, the on-board BMS means a BMS of the application battery 300 or the test battery from which the first SOHC value is calculated, and the field BMS means an application BMS 400 that receives field data from the on-board BMSs of a plurality of application batteries 300 and is physically the same as or adjacent to the application battery 300 to form one system. When the application BMS 400 is separated from the application battery 300 and is configured to receive field data through a wired / wireless network, it is referred to as a cloud BMS.

[0050] Such an application BMS 400 includes the following configuration in addition to a data path connected to the plurality of application batteries 300 or a communication device (not shown) connected to a wired / wireless network.

[0051] A. Field Data Collection Unit 410

[0052] The field data collection unit 410 collects field data from the battery used in the application and transmits the field data to the SOHC estimation unit 430. The field data collected by the field data collection unit 410 is stored in Figure 1 and Figure 2 The field data is indicated as the second field data in order to distinguish the field data from the first field data used for retraining the SOHC estimation model.

[0053] B. SOHC Estimation Model Unit 420

[0054] The SOHC estimation model unit 420 is configured with a memory device on which a SOHC estimation model generated according to the SOHC estimation model generation method of the present invention is installed, which will be described later. The SOHC estimation model is a computer-implemented algorithm for constructing an artificial neural network model that receives field data in real time and is trained to calculate a real-time SOHC estimation value of the application battery 300 corresponding to the real-time field data.

[0055] C. SOHC estimation unit 430

[0056] The SOHC estimation unit 430 reads a computer-implemented algorithm for constructing a SOHC estimation model, inputs field data into the SOHC estimation model, and outputs a SOHC estimation value corresponding to the field data. It may be configured with a processor of a computer device or a computing device including a predetermined processor.

[0057] D. Monitoring unit 440

[0058] The monitoring unit 440 monitors the state of the application battery 300 based on the real-time SOHC estimation value calculated by the SOHC estimation unit 430 .

[0059] As described above, the application BMS 400 of the present invention may be installed on an application device such as a vehicle, or may be configured as a cloud battery management system BMS. When configured as a cloud BMS, the cloud BMS may include a communication module that receives field data from the application battery 300 from a remote location.

[0060] At the same time, if Figure 2 As shown in , the SOHC estimation system according to another embodiment of the present invention may be configured as a separate SOHC estimation device 500 without configuring the SOHC estimation model unit 420 , the SOHC estimation unit 430 , and the monitoring unit 440 within the application BMS 400 .

[0061] 3. The method of the present invention for estimating the SOHC of a single unit in use

[0062] The present invention estimates and calculates the SOHC of the monomer in use through the following process.

[0063] (1) Monomer data acquisition process (S10)

[0064] This is a process of acquiring cell data from a plurality of battery cells during a cell testing process after cell manufacturing. The cell data may include at least one of the cumulative charge capacity during a charge cycle of the battery cell, the cumulative discharge capacity during a discharge cycle, the cumulative charge energy (which is the energy required for charging during a charge cycle), the cumulative discharge energy (which is the discharge energy during a discharge cycle), and the average temperature data of the battery cell.

[0065] Preferably, the single-cell data may be limited to single-cell data obtained in a standard charging section, which has similar characteristics to the field data and is a relatively standardized section. For standard charging, the charging speed may be set to 0.33 C rate. The reason for limiting the single-cell data to data obtained in the standard charging section is to try to obtain single-cell data obtained in a test environment in a section similar to the field data, which is data in an actual use environment.

[0066] More preferably, the monomer data may be limited to the monomer data obtained in a predetermined partial charge section. In this case, the partial charge section may be a section of 3.6 to 3.9V. The reason for limiting the monomer data to the predetermined partial charge section is that, since there is a difference in the charge start voltage of each monomer in each cycle, during the battery test process, a common voltage section is extracted and a voltage section with a high correlation with SOHC is extracted. Since the correlation between SOHC and the monomer voltage was checked in units of 0.1V by experiment, the inventors of the present invention confirmed that the correlation between SOHC and the monomer voltage is high in the section of 3.6 to 3.8V.

[0067] (2) First SOHC label value calculation process (S20)

[0068] This is a process of calculating a cell SOHC value corresponding to cell data during a cell testing process after cell manufacturing.

[0069] The first SOHC value calculated by the BMS during the test process after manufacturing the cell is a value calculated by the vehicle-mounted BMS. The BMS at this time may be the vehicle-mounted BMS used in the cell test process. A known method is used as a method of calculating the first SOHC using the cell data in the vehicle-mounted BMS.

[0070] (3) First SOHC estimation model generation process (S30)

[0071] A first SOHC estimation model is generated by using the acquired single-unit data as input data and using a first SOHC value corresponding thereto as a label value to estimate the SOHC value according to the single-unit data. The first SOHC estimation model is generated by performing machine learning on a known neural network-based model using the single-unit data and the first SOHC label value corresponding thereto.

[0072] (4) First-site data acquisition process (S40)

[0073] At the same time, the present invention obtains first field data from an application battery 300 operating in actual application, which is different from the test battery from which the cell data is obtained during the cell test process. Like the cell data, the first field data also consists of data including at least one of the cumulative charging capacity during the charging cycle, the cumulative discharging capacity during the discharging cycle, the cumulative charging energy (which is the energy required for charging during the charging cycle), the cumulative discharging energy (which is the discharging energy during the charging cycle), and the average temperature data of the battery cell, but the difference is that the first field data is battery data obtained from a battery in operation in actual application.

[0074] Meanwhile, the first field data may be data acquired from a battery different from that used to acquire the second field data, which will be described later, or may be data acquired in a charge / discharge cycle different from that used to acquire the second field data.

[0075] (5) Second SOHC label value calculation process (S50)

[0076] This is a process of inputting the first field data into the first SOHC estimation model to calculate the second SOHC tag value corresponding to the first field data.

[0077] (6) Second SOHC estimation model generation process (S60)

[0078] This is a process of generating a second SOHC estimation model by retraining the first SOHC estimation model. The process of generating the second SOHC estimation model is a process of generating the second SOHC estimation model by retraining the first SOHC estimation model using {first field data, second SOHC calculated value} as training data, {first field data, second SOHC calculated value} obtained by using the first field data as input data of the first SOHC estimation model and using the calculated second SOHC calculated value calculated from the first SOHC estimation model as a label value.

[0079] (7) Second on-site data collection process (S70)

[0080] This is a process of collecting second field data from a field battery in operation in an application for which SOHC is intended to be estimated. Like the cell data, the second field data also includes at least one of the cumulative charge capacity during the charge cycle of the battery cell, the cumulative discharge capacity during the discharge cycle, the cumulative charge energy (which is the energy required for charging during the charge cycle), the cumulative discharge energy (which is the discharge energy during the discharge cycle), and the average temperature data of the battery cell.

[0081] (8) SOHC estimation process for on-site battery (S80)

[0082] This is a process of calculating a real-time SOHC value of a field battery (application battery) by inputting the collected field data (second field data) into a second SOHC estimation model.

[0083] As described above, the disclosed embodiments have been described with reference to the accompanying drawings. Those skilled in the art to which the present invention belongs will understand that the present invention can be practiced in a form different from the disclosed embodiments without changing the technical ideas or basic features of the present invention. The disclosed embodiments are illustrative and should not be interpreted as limiting.

[0084] The names of the components shown in the drawings of the present invention are as follows.

[0085] 100: Battery test equipment 200: SOHC estimation model generation unit

[0086] 300: Application battery 400: Application BMS

[0087] 410: Field data collection unit 420: SOHC estimation model unit

[0088] 430: SOHC estimation unit 440: monitoring unit

[0089] 500: SOHC estimated equipment

Claims

1. A SOHC estimation model generating device, comprising: a battery testing device that acquires cell data from a plurality of battery cells during a cell testing process; and A SOHC estimation model generation unit, wherein the SOHC estimation model generation unit: calculating a first SOHC value according to the monomer data, constructing a first training data set using the monomer data as an input value and the first SOHC value as a label value to generate a first SOHC estimation model estimating the SOHC value according to the monomer data, A first SOHC estimation model is generated by training a predetermined artificial neural network using {single-unit data, first SOHC value} as first training data, and a second SOHC estimation model is generated by retraining the first SOHC estimation model using {first field data, second SOHC value} as second training data, wherein The first field data is battery data acquired from an application battery in operation, or cell data acquired from a test battery cell other than the test battery cell from which the cell data is acquired, or cell data acquired from a test battery cell in a different charge / discharge cycle from which the cell data is acquired, The first SOHC value is calculated based on the monomer data, and The second SOHC value is a value calculated by inputting the first field data into the first SOHC estimation model.

2. An application BMS, comprising a SOHC estimation model unit including a SOHC estimation model, and receiving field data from an application battery in operation in an application, inputting the field data into the SOHC estimation model, and calculating a real-time SOHC value of the application battery.

3. The application BMS according to claim 2, wherein The SOHC estimation model is generated by the following operations: generating a first SOHC estimation model by machine learning performed using {single-unit data, first SOHC value} as first training data, and Retraining the first SOHC estimation model using {first field data, second SOHC value} as second training data, The single cell data is battery data obtained from a test battery, The first field data is battery data obtained from an application battery in operation, The first SOHC value is calculated based on the monomer data, and The second SOHC value is a value calculated by inputting the first field data into the first SOHC estimation model.

4. The application BMS according to claim 3, further comprising: A field data collection unit receives first field data and second field data from the application battery via a predetermined communication network, wherein The SOHC estimation model receives the second field data from the application battery and calculates the real-time SOHC value of the application battery.

5. A SOHC estimation system for an application battery, comprising: a battery testing device that acquires cell data from a plurality of battery cells during a cell testing process; as well as an application BMS that receives field data from an application battery in operation in an application and inputs the field data into the SOHC estimation model and calculates a real-time SOHC value of the application battery, wherein The application BMS includes: a SOHC estimation model generating unit that calculates a first SOHC value based on the single-body data, constructs a first training data set with the single-body data as an input value and the first SOHC value as a label value to generate a first SOHC estimation model that estimates the SOHC value based on the single-body data, generates a first SOHC estimation model by training a predetermined artificial neural network using {single-body data, first SOHC value} as first training data, and generates a second SOHC estimation model by retraining the first SOHC estimation model using {first field data, second SOHC value} as second training data, and a SOHC estimation model unit, the SOHC estimation model unit including the second SOHC estimation model as a SOHC estimation model, The first SOHC value is calculated based on the monomer data, and The second SOHC value is a value calculated by inputting the first field data into the first SOHC estimation model.

6. The SOHC estimation system according to claim 5, wherein The monomer data or the first field data includes at least one of the following: Cumulative charge capacity (during charge cycles), cumulative discharge capacity (during discharge cycles), cumulative charge energy (energy required to charge / charge cycle), cumulative discharge energy (discharge energy / discharge cycle), and average temperature data for the battery cells.

7. The SOHC estimation system according to claim 6, wherein The first on-site data is data obtained in a standard charging section and a predetermined partial charging section.

8. A method for estimating SOHC of a battery cell in situ, comprising: a cell data acquisition process that acquires cell data from a plurality of battery cells during a cell testing process; a first SOHC value calculation process, wherein the first SOHC value calculation process calculates a first SOHC value corresponding to the monomer data; a first SOHC estimation model generating process that generates a first SOHC estimation model that estimates a SOHC value based on the single-unit data by performing machine learning using a training data set that has the single-unit data as an input value and has the first SOHC value as a first label value; a first field data acquisition process, wherein the first field data acquisition process acquires second cell data different from the first field data from a plurality of battery cells during the cell testing process; a second SOHC estimated value calculation process that generates a second SOHC estimated value corresponding to the first field data by inputting the first field data into the generated first SOHC estimation model; a second SOHC estimation model generating process that generates a second SOHC estimation model by retraining the first SOHC estimation model using the generated second SOHC estimation value as a label value and using the first field data as an input value; and A SOHC value estimation process estimates a SOHC value during operation of a predetermined battery cell by inputting field data generated when the predetermined battery cell is operated into the second SOHC estimation model.

9. The SOHC estimation method according to claim 8, wherein The monomer data or the first field data includes at least one of the following: Cumulative charge capacity (during charge cycles), cumulative discharge capacity (during discharge cycles), cumulative charge energy (energy required to charge / charge cycle), cumulative discharge energy (discharge energy / discharge cycle), and average temperature data for the battery cells.

10. The SOHC estimation method according to claim 9, wherein The first field data is acquired from a battery cell different from the cell data, or is acquired from a charge / discharge cycle different from the cell data.

11. The SOHC estimation method according to claim 10, wherein The first on-site data is data obtained in a standard charging section and a predetermined partial charging section.

12. The SOHC estimation method according to claim 11, wherein The first SOHC estimation model and the second SOHC estimation model are regression models or artificial neural network models generated by supervised learning.

Images