Method and system for predicting SOHC for electric vehicle (EV)

By utilizing cell data to generate and retrain a prediction model for electric vehicle batteries, the method improves the accuracy of State of Health Capacity predictions, addressing the inaccuracies of existing on-board calculation methods and providing real-time SOHC estimation for field batteries.

WO2024248267A1PCT designated stage expired Publication Date: 2024-12-05LG ENERGY SOLUTION LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
PCT/KR2024/000589
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-01-08
Filing Date
2024-01-12
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Existing methods for predicting the State of Health Capacity (SOHC) of electric vehicle batteries rely on on-board calculated values, leading to inaccuracies in SOHC prediction, as they do not utilize direct cell data effectively.

Method used

A method and system that acquire cell data during testing, construct a learning dataset, and generate a prediction model using machine learning to calculate an accurate SOHC value, which is then retrained using field data to improve prediction accuracy, enabling real-time SOHC estimation in field batteries.

Benefits of technology

This approach provides a more accurate SOHC prediction model compared to prior methods by leveraging cell data and field data, overcoming the limitations of relying solely on on-board calculated values, resulting in enhanced prediction accuracy for field batteries.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure KR2024000589_05122024_PF_FP_ABST
    Figure KR2024000589_05122024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention provides, in predicting the SOHC of a battery in use, a method and a system for predicting SOHC in real-time by generating a SOHC prediction model by using cell data and first field data acquired from a test battery, and inputting second field data acquired from a battery in use into the SOHC prediction model.
Need to check novelty before this filing date? Find Prior Art

Description

SOHC prediction method and system for EV (electric vehicle)

[0001] The present invention relates to a method and system for predicting the state of health capacity (SOHC) of an electric vehicle (EV) battery using field data. In particular, in a cloud BMS, the present invention provides a method and system for calculating an accurate SOHC value of a battery using a machine learning prediction model.

[0002] Traditionally, when predicting the state of health capacity (SOHC) of electric vehicle (EV) batteries using field data, battery capacity values ​​calculated by the onboard Battery Management System (BMS) were used. However, these calculated battery capacities were often not true, and thus, predicted SOHC values ​​contained significant errors.

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

[0004] Prior art inventions related to this include Patent Document 1, which predicts the remaining life of a battery using an LSTM model, and Patent Document 2, which predicts the discharge time of a secondary battery using a neural network.

[0005] However, these prior inventions failed to provide a method for generating an accurate prediction model, as described in the present invention. Furthermore, they failed to overcome the limitation of using only onboard output values ​​when generating the prediction model.

[0006] Related 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)

[0009] Accordingly, the present invention aims to solve the problems of the above-described prior art, and to provide a method and system for generating an accurate SOHC prediction model using cell data acquired during a battery cell test process and using the model to predict the accurate SOHC of a field battery.

[0010] Accordingly, the present invention provides an SOHC prediction model generation device, including: a battery test device that acquires cell data from a plurality of battery cells during a cell test process and acquires first field data from other battery cells or other charge / discharge cycles; a SOHC prediction model generation unit that calculates a first SOHC value from the cell data, constructs a first learning data set with the cell data as an input value and the first SOHC value as a label value, and generates a first SOHC prediction model that predicts the SOHC value from the cell data; inputs the first field data into the first SOHC prediction model to calculate a second SOHC value, constructs a second learning data set with the second SOHC value as the first field data and the label value, and retrains the first SOHC prediction model with the second learning data set to generate a second SOHC prediction model;

[0011] In addition, the present invention provides an application BMS that includes an SOHC prediction model unit including an SOHC prediction model, receives field data from a field battery being operated in an application, inputs the data into the SOHC prediction model, and calculates a real-time SOHC value of the field battery.

[0012] At this time, the SOHC prediction model is generated by acquiring cell data from a plurality of battery cells during a cell test process, acquiring first field data from other battery cells or other charge / discharge cycles, calculating a first SOHC value from the cell data, constructing a first learning dataset with the first SOHC value using the cell data and a label value, and generating a first SOHC prediction model that predicts the SOHC value from the cell data, inputting the first field data into the first SOHC prediction model to calculate a second SOHC value, constructing a second learning dataset with the second SOHC value using the first field data and a label value, and retraining the first SOHC prediction model with the second learning dataset.

[0013] In addition, the present invention provides a SOHC prediction system of a field battery, including a battery test device that acquires cell data from a plurality of battery cells during a cell test process and acquires first field data from other battery cells or other charge / discharge cycles; a SOHC prediction model generation unit that calculates a first SOHC value from the cell data, constructs a first learning dataset with the first SOHC value using the cell data and a label value, and generates a first SOHC prediction model that predicts the SOHC value from the cell data, inputs the first field data into the first SOHC prediction model to calculate a second SOHC value, constructs a second learning dataset with the second SOHC value using the first field data and a label value, and retrains the first SOHC prediction model with the second learning dataset to generate a second SOHC prediction model; and a SOHC prediction model unit that includes the second SOHC prediction model as a SOHC prediction model, and an application BMS that receives field data from a field battery being operated in an application, inputs the field data into the SOHC prediction model, and calculates a real-time SOHC value of the field battery.

[0014] In addition, the present invention provides a cell data acquisition process for acquiring cell data from a plurality of battery cells during a cell test process; a first SOHC value calculation process for calculating a first SOHC value corresponding to the cell data; a first SOHC prediction model generation process for generating a first SOHC prediction model by learning the cell data as an input value and the first SOHC value as a first label value to predict a SOHC value from the cell data; a first field data acquisition process for acquiring second cell data different from the first field data during the cell test process from a plurality of battery cells; a second SOHC prediction value calculation process for generating a second SOHC prediction value corresponding to the first field data by inputting the first field data into the generated first SOHC prediction model; a second SOHC prediction model generation process for generating a second SOHC prediction model by relearning the first SOHC prediction model by using the generated second SOHC prediction value as a label value and the first field data as an input value. A method for predicting SOHC of a field battery cell is provided, including a SOHC value prediction process for predicting SOHC values ​​during operation of the predetermined battery cells by inputting field data generated while operating predetermined battery cells into the second SOHC prediction model.

[0015] According to the present invention, a first SOHC prediction model is generated using cell data acquired during a battery test process, and then the first SOHC prediction model is retrained using the SOHC value calculated using the first SOHC prediction model as a label value to generate a second SOHC prediction model, which is then applied as a final SOHC prediction model, thereby providing a prediction model with higher accuracy than the prior art that uses only onboard calculated capacity values.

[0016] The following drawings attached to this specification illustrate preferred embodiments of the present invention and, together with the detailed description of the invention described above, serve to further understand the technical idea of ​​the present invention, and therefore, the present invention should not be construed as being limited to matters described in such drawings.

[0017] Figure 1 is a block diagram of an SOHC prediction system according to the present invention.

[0018] Figure 2 is a block diagram of an SOHC prediction system according to another embodiment of the present invention.

[0019] Figure 3 is a flowchart showing the procedure for creating a SOHC prediction model according to the present invention and the sequence of a SOHC prediction method using the created prediction model.

[0020] The present invention provides a method and system for predicting SOHC of a battery in use, wherein an SOHC prediction model is created using cell data acquired from a test battery and first field data different from the cell data, and second field data acquired from the battery in use is input into the SOHC prediction model to predict real-time SOHC.

[0021] 1. Definition of Terms

[0022] Unless otherwise defined, the terms used in the present invention follow the definitions of terms described below.

[0023] The present invention constructs a model for predicting the State of Health Capacity (SOHC) of a battery in use from cell data and field data. In the present invention, SOHC (State of Health Capacity) refers to the rate of capacity reduction due to degradation compared to the initial capacity of the battery. Generally, it is calculated as SOHC (%) = (current battery capacity / initial battery capacity) × 100, where the current battery capacity represents the actual capacity of the battery that changes according to use and charge-discharge cycles, and the initial battery capacity represents the capacity when the battery is first manufactured. The closer the SOHC value is to 100%, the better the battery's health can be determined, and the lower the SOHC value, the shorter the battery's lifespan and the lower its performance can be determined.

[0024] In the present invention, cell data refers to battery cell data acquired from a test battery or a reference battery during a cell testing process. In the present invention, field data refers to battery data acquired from an in-use battery in use in an application such as a vehicle.

[0025] In the present invention, a cloud BMS (Cloud Battery Management System) refers to a system that executes battery management functions on a cloud server and allows users to monitor and manage battery status in real time via a web browser anytime, anywhere. A cloud BMS can centrally and efficiently monitor and control battery systems from various locations, collect and analyze data, and perform predictive analysis. Furthermore, it can optimize overall energy management by sharing and linking data across multiple systems.

[0026] 2. SOHC prediction system of a field battery according to the present invention

[0027] The SOHC prediction system of a field battery according to the present invention is a system that performs a real-time SOHC prediction method of a field battery. The SOHC prediction system of the present invention is described with reference to FIGS. 1 and 2.

[0028] The system of the present invention, as illustrated in FIG. 1, includes a SOHC prediction model generation unit (200), an application BMS (400) that is equipped with the generated prediction model, receives second field data from a field battery being used in an application, and calculates a real-time SOHC prediction value of the field battery therefrom, wherein the application BMS (400) may be configured as a cloud BMS. In addition, the SOHC prediction model generation unit (200) generates a SOHC prediction model from cell data received from a battery test device (100) and first field data received from an application battery (300).

[0029] In another embodiment, the system of the present invention may be configured as a separate SOHC prediction device (500) instead of the SOHC prediction model unit (420) and the SOHC prediction unit (430) being mounted on the application BMS (400), as shown in FIG. 2.

[0030] Below, each component is explained.

[0031] (1) Battery test device (100)

[0032] The battery test device (100) is a device that performs various tests on a battery after manufacturing the battery. The present invention uses cell data including various status information of test batteries generated during battery testing from the known battery test device (100) as data for generating a SOHC prediction model.

[0033] The battery test device (100) acquires cell data from test batteries and transmits it to the SOHC prediction model generation unit (200).

[0034] The types and characteristics of cell data are described later.

[0035] (2) SOHC prediction model generation unit (200)

[0036] The SOHC prediction model generation unit (200) is a component that generates an SOHC prediction model using not only the cell data described above but also the first field data, and includes a computer algorithm that performs the process. The present invention uses a known neural network as the basis for the SOHC prediction model, and is characterized by the data and learning method for learning the SOHC prediction model.

[0037] The SOHC prediction model generation unit (200) generates an SOHC prediction model by performing the S10 to S60 processes described below, and provides the generated prediction model, i.e., a computer-executable algorithm that calculates the SOHC prediction value of the battery, to the SOHC prediction model unit (420) online or offline.

[0038] The SOHC prediction model generation unit (420) obtains cell data and first SOHC data, which is an SOHC value corresponding to the cell data, as a first label value from a battery test device or a previously acquired reference data set, and configures a first learning data set with the cell data and the first SOHC value, which is the first label value, to generate a first SOHC prediction model that predicts the SOHC value from the cell data. The first SOHC value is a SOHC value calculated based on cell data from an onboard BMS of a test battery, and the first SOHC prediction model may use a predetermined artificial neural network model configured to predict the SOHC value from the cell data. In one embodiment, a Support Vector Regression (SVR) model is applied, and a first parameter set including coefficients, intercepts, and model parameters for determining a regression function of the SVR model is obtained by performing machine learning using the cell data as an input value and the first SOHC value as a label value as a first learning data set, thereby obtaining the first SOHC prediction model. The first learning data set is {cell data, first SOHC}.

[0039] Thereafter, the SOHC prediction model generation unit (420) obtains first field data from a predetermined field battery, inputs this into the first SOHC prediction model to calculate a second SOHC value as a second label value, and configures a second learning 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 prediction model.

[0040] In another embodiment, the first field data may be acquired from a battery test device (100). In this case, the battery test device (100) acquires cell data acquired from a test battery other than the test battery from which the cell data was acquired, or from a charge / discharge cycle other than the one from which the cell data was acquired, as the first field data. In this case as well, the second learning data set is set to {first field data, second SOHC value}.

[0041] Thereafter, the first SOHC prediction model is retrained using a second learning dataset to obtain a second parameter set, thereby generating a second SOHC prediction model, and the second SOHC prediction model is provided as the final SOHC prediction model. The provided second SOHC prediction model is loaded into the SOHC prediction model unit (420) of the application BMS (400) described below.

[0042] (3) Application BMS (400)

[0043] The application BMS (400) of the present invention is a battery management device that manages an application battery (300), and may be configured to include, in addition to conventional BMS components, a field data collection unit (410), an SOHC prediction model unit (420), an SOHC prediction unit (430), and a monitoring unit (440).

[0044] The application BMS (400) of the present invention collects field data such as battery status information from the operating application battery (300), 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 as a cloud BMS.

[0045] When the application BMS (400) is configured as a cloud BMS, the application BMS (400) is connected to a plurality of on-board BMSs through a predetermined wired / wireless communication network, and receives cell data and field data from the on-board BMS.

[0046] In the present invention, the onboard BMS refers to the BMS of the application battery (300) or the test battery that calculates the first SOHC value, and the on-site battery management system (On-Site BMS) refers to an application BMS (400) that receives field data from the onboard BMS of a plurality of application batteries (300) and is physically identical to or adjacent to the application batteries (300) to form a single system. When the application BMS (400) is configured to receive field data through a wired / wireless network while being separated from the application batteries (300), it is called a cloud BMS.

[0047] Such an application BMS (400) includes the following components in addition to a data path connected to a plurality of application batteries (300) or a communication device (not shown) connected to a wired / wireless network.

[0048] A. Field data collection unit (410)

[0049] The field data collection unit (410) collects field data from the battery used in the application and transmits it to the SOHC prediction unit (430). The field data collected by the field data collection unit (410) is indicated as second field data in FIGS. 1 and 2 to distinguish it from the first field data for retraining the SOHC prediction model.

[0050] B. SOHC Prediction Model Section (420)

[0051] The SOHC prediction model unit (420) is configured with a memory device that loads an SOHC prediction model generated according to the SOHC prediction model generation method according to the present invention, which will be described later. The SOHC prediction model is a computer-executable algorithm that constructs an artificial neural network model trained to receive field data in real time and produce a real-time SOHC prediction value of an application battery (300) corresponding to the real-time field data.

[0052] C. SOHC prediction unit (430)

[0053] The SOHC prediction unit (430) reads a computer-executed algorithm that constitutes the SOHC prediction model, inputs the field data into the SOHC prediction model, and outputs a SOHC prediction value corresponding to the field data. It may be configured as a processing device including a predetermined processor or a processor of a computer device.

[0054] D. Monitoring Department (440)

[0055] The monitoring unit (440) monitors the state of the application battery (300) based on the real-time SOHC prediction value produced by the SOHC prediction unit (430).

[0056] As described above, the application BMS (400) of the present invention may be installed in an application device such as a vehicle, or may be configured as a cloud BMS (Cloud Battery Management System). When configured as a cloud BMS, the cloud BMS may include a communication module that receives field data remotely from the application battery (300).

[0057] Meanwhile, as illustrated in FIG. 2, the SOHC prediction system according to another embodiment of the present invention may be configured as a separate SOHC prediction device (500) without configuring the SOHC prediction model unit (420), SOHC prediction unit (430), and monitoring unit (440) within the application BMS (400).

[0058] 3. SOHC prediction method of a cell in use according to the present invention

[0059] The present invention predicts and calculates the SOHC of a cell in use through the following procedure.

[0060] (1) Cell data acquisition process (S10)

[0061] This is a process of acquiring cell data from multiple battery cells during a cell test process after cell manufacturing. The cell data may include at least one of: accumulated charge capacity during a charge cycle of the battery cell, accumulated discharge capacity during a discharge cycle, accumulated charge energy, which is energy required for charging during a charge cycle, accumulated discharge energy, which is discharge energy during a discharge cycle, and average temperature data of the battery cell.

[0062] Preferably, cell data can be limited to cell data acquired in slow charging sections, which are relatively standardized sections with similar characteristics to field data. Slow charging can have a charging rate set to 0.33 C-rate. The reason for limiting cell data to data acquired in slow charging sections is to ensure that cell data acquired in a test environment is similar to field data, which is data from actual usage environments.

[0063] More preferably, the cell data may be limited to cell data acquired in a predetermined partial charge section. In this case, the partial charge section may be a section of 3.6 to 3.9 V. The reason for limiting the cell data to a predetermined partial charge section is that, during the battery test process, there is a difference in the charge start voltage for each cell for each cycle, so a common voltage section is extracted and a voltage section with a high correlation with SOHC is extracted. The inventor of the present invention confirmed the correlation between SOHC and cell voltage in 0.1 V units through an experiment, and as a result, confirmed that the correlation between SOHC and cell voltage was high in the section of 3.6 to 3.8 V.

[0064] (2) 1st SOHC label value calculation process (S20)

[0065] After cell manufacturing, this is the process of calculating the cell SOHC value corresponding to the above cell data during the cell testing process.

[0066] After cell manufacturing, the first SOHC value calculated by the BMS during the testing process is the value produced by the onboard BMS. The BMS used in this case may be the onboard BMS used during the cell testing process. The method for producing the first SOHC using cell data in the onboard BMS uses a known method.

[0067] (3) 1st SOHC prediction model creation process (S30)

[0068] A first SOHC prediction model is created that predicts SOHC values ​​from cell data using the acquired cell data as input data and the corresponding first SOHC values ​​as label values. The first SOHC prediction model is created by machine learning a known neural network-based model using the cell data and the corresponding first SOHC label values.

[0069] (4) First field data acquisition process (S40)

[0070] Meanwhile, the present invention acquires first field data from an application battery (300) operating in an actual application, which is different from a test battery that acquires the cell data during a cell test process. The first field data, like the cell data, is composed of data including at least one or more of: accumulated charge capacity during a charge cycle of a battery cell, accumulated discharge capacity during a discharge cycle, accumulated charge energy as energy required for charging during a charge cycle, accumulated discharge energy as discharge energy during a discharge cycle, and average temperature data of the battery cell; however, the first field data is different in that it is battery data acquired from a battery operating in an actual application.

[0071] Meanwhile, the first field data may be data acquired from a battery different from the battery that acquires the second field data described below, or may be data acquired in a cycle different from the charge / discharge cycle that acquires the second field data.

[0072] (5) 2nd SOHC label value calculation process (S50)

[0073] This is a process of inputting the first field data into the first SOHC prediction model to produce second SOHC label values ​​corresponding to the first field data.

[0074] (6) 2nd SOHC prediction model creation process (S60)

[0075] This is a process of generating a second SOHC prediction model by retraining the first SOHC prediction model. The second SOHC prediction model is a process of generating a second SOHC prediction model by retraining the first SOHC prediction model using {first field data, second SOHC output value}, which has the first field data as input data and the second SOHC output value generated from the first SOHC prediction model as a label value, as learning data.

[0076] (7) Second field data collection process (S70)

[0077] This is a process of collecting second field data from a field battery in operation in an application for which SOHC is to be predicted. The second field data, like cell data, includes at least one of: accumulated charge capacity during a charge cycle of the battery cell, accumulated discharge capacity during a discharge cycle, accumulated charge energy, which is energy required for charging during a charge cycle, accumulated discharge energy, which is discharge energy during a discharge cycle, and average temperature data of the battery cell.

[0078] (8) SOHC prediction process for field batteries (S80)

[0079] This is a process of inputting the collected field data (second field data) into the second SOHC prediction model to calculate the real-time SOHC value of the field battery (application battery).

[0080] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present invention can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present invention. The disclosed embodiments are illustrative and should not be construed as limiting.

[0081] The names of each part shown in the drawings of the present invention are as follows.

[0082] 100 Battery Test Device 200 SOHC Prediction Model Generation Unit

[0083] 300 Application Battery 400 Application BMS

[0084] 410 Field Data Collection Department 420 SOHC Prediction Model Department

[0085] 430 SOHC prediction unit 440 monitoring unit

[0086] 500 SOHC predictor

Claims

1. A battery test device that acquires cell data from a plurality of test battery cells during a cell test process; A first SOHC value is calculated from the cell data, and a first learning dataset is formed using the cell data as an input value and the first SOHC value as a first label value, thereby generating a first SOHC prediction model that predicts the SOHC value from the cell data. A SOHC prediction model generation unit that trains a predetermined artificial neural network using {cell data, first SOHC value} as first learning data to generate a first SOHC prediction model, and retrains the first SOHC prediction model using {first field data, second SOHC value} as second learning data to generate a second SOHC prediction model; It consists of, including, The above first field data is battery data acquired from an operating application battery, cell data acquired from test battery cells other than the test battery from which the cell data was acquired, or cell data acquired from a charge / discharge cycle different from the cell data from the test battery cell from which the cell data was acquired. The above first SOHC value is calculated from the cell data, The above second SOHC value is a SOHC prediction model generation device that is a value calculated by inputting the first field data into the first SOHC prediction model.

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

3. In paragraph 2, The above SOHC prediction model is, A first SOHC prediction model is created through machine learning using {cell data, first SOHC value} as the first learning data, It is generated by retraining the first SOHC prediction model using {first field data, second SOHC value} as the second learning data. The above cell data is battery data obtained from a test battery. The above first field data is battery data acquired from an operating application battery. The above first SOHC value is calculated from the cell data, The above second SOHC value is a value calculated by inputting the first field data into the first SOHC prediction model, application BMS.

4. In paragraph 3, Includes a field data collection unit that receives first field data and second field data from the application battery through a predetermined communication network, The above SOHC prediction model is an application BMS that receives second field data from the application battery and calculates a real-time SOHC value of the application battery.

5. A battery test device that acquires cell data from multiple battery cells during a cell test process; An application BMS that receives field data from an application battery in operation in an application, inputs it into a SOHC prediction model, and calculates a real-time SOHC value of the application battery; It consists of, including, The above application BMS, A SOHC prediction model generation unit that generates a first SOHC value from the cell data, configures a first learning data set with the cell data as an input value and the first SOHC value as a first label value, generates a first SOHC prediction model that predicts the SOHC value from the cell data, trains a predetermined artificial neural network using {cell data, first SOHC value} as first learning data to generate the first SOHC prediction model, and retrains the first SOHC prediction model using {first field data, second SOHC value} as second learning data to generate a second SOHC prediction model; A SOHC prediction model unit including the second SOHC prediction model as a SOHC prediction model; The above first SOHC value is calculated from the cell data, The above second SOHC value is a SOHC prediction system of an application battery, which is a value calculated by inputting the first field data into the first SOHC prediction model.

6. In paragraph 5, The above cell data or first field data, An SOHC prediction system for an application battery, comprising at least one of data on the accumulated charge capacity (during a charge cycle), accumulated discharge capacity (during a discharge cycle), accumulated charge energy (energy required for charging / charge cycle), accumulated discharge energy (discharge energy / discharge cycle), and average temperature of the battery cell.

7. In paragraph 6, The above first field data is, Data obtained from slow charging sections and predetermined partial charging sections; SOHC prediction system for in-field batteries.

8. Cell data acquisition process for acquiring cell data from multiple battery cells during the cell test process; A first SOHC value calculation process for calculating a first SOHC value corresponding to the above cell data; A first SOHC prediction model generation process for generating a first SOHC prediction model that predicts a SOHC value from cell data by performing machine learning on a learning data set using the above cell data as input values ​​and the first SOHC value as a first label value; During a cell test process, a first field data acquisition process for acquiring second cell data different from the first field data from a plurality of battery cells; A second SOHC prediction value generation process for generating a second SOHC prediction value corresponding to the first field data by inputting the first field data into the generated first SOHC prediction model; A second SOHC prediction model generation process in which the second SOHC prediction value generated above is used as a label value and the first field data is used as an input value, thereby retraining the first SOHC prediction model to generate a second SOHC prediction model; A SOHC value prediction process for predicting SOHC values ​​during operation of the specified battery cells by inputting field data generated while operating the specified battery cells into the second SOHC prediction model; A method for predicting SOHC of an application battery cell including:

9. In paragraph 8, The above cell data or first field data, Contains at least one of the following data: accumulated charge capacity (during charge cycle), accumulated discharge capacity (during discharge cycle), accumulated charge energy (energy required for charge / charge cycle), accumulated discharge energy (discharge energy / discharge cycle), and average temperature of the battery cell; A method for predicting SOHC of battery cells for applications.

10. In paragraph 9, The above first field data is obtained from battery cells different from the cell data or is obtained in a charge / discharge cycle different from the cell data; A method for predicting SOHC of in-application battery cells.

11. In paragraph 10, The above first field data is, Data obtained from slow charging sections and predetermined partial charging sections; A method for predicting SOHC of in-application battery cells.

12. In paragraph 11, The above first SOHC prediction model and the second SOHC prediction model are regression models or artificial neural network models generated by supervised learning; A method for predicting SOHC of in-application battery cells.

Citation Information

Patent Citations

  • Secondary Battery Life Prediction System and Secondary Battery Characteristic Evaluation Device

    JP6250298B2

  • Tilt detection device and tilt detection method for mobile communication base station antenna

    KR102846462B1

  • Lithium battery SOH estimation method based on novel generative adversarial neural network

    CN114236410A

  • Infant integrated vehicle seat

    KR1020230173300A

  • Composite fiber capable of discoloration by various external stimuli and manufacturing method thereof

    KR1020240000064A