Maximum temperature prediction device and method

Abstract

The maximum temperature prediction device may include a preprocessing device including a first processor and a first memory storing a plurality of programs, a second memory, and a temperature determination device including a temperature prediction learning device. The first processor may generate input data including cell design parameters for candidate battery cells constituting a candidate battery module and simulation interpretation conditions for a simulation predicting the maximum temperature of the candidate battery cells. The second memory stores the input data, and during a learning operation, the temperature prediction learning device may perform machine learning using training data from the input data stored in the second memory and determine a temperature calculation formula for predicting the maximum temperature of the candidate battery cells through the machine learning.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of priority based on Korean Patent Application No. 10-2023-0079003, filed June 20, 2023, the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to a maximum temperature prediction apparatus and method. [Background technology]

[0003] The maximum temperature of a battery is one of the main factors that determine its lifespan. Battery manufacturers can measure the maximum temperature of multiple candidate batteries that meet the required specifications. However, it is not possible to actually manufacture multiple candidate batteries to measure the maximum temperature due to cost and time constraints.

[0004] To overcome this problem, a performance test is performed on the battery cells constituting each of a plurality of candidate batteries, various conditions are set for interpreting the performance test results, and an interpretation simulation is performed to predict the maximum battery temperature based on the set conditions. Through this series of processes, it takes a considerable amount of time and money to predict the maximum temperature for each candidate battery. Since it is not possible to simultaneously predict the maximum temperatures for multiple candidate batteries, it takes even more time and money to predict the maximum temperatures for all of the multiple candidate batteries. During this process, there is a possibility that a maximum temperature prediction will be made for unnecessary candidate batteries. At the same time, it also takes a considerable amount of time to examine the performance of each candidate battery based on the interpretation simulation results. Summary of the Invention [Problem to be solved by the invention]

[0005] The object is to provide an apparatus and method for predicting the maximum battery temperature. [Means for solving the problem]

[0006] According to one aspect of the present invention, a maximum temperature prediction device may include a preprocessing device including a first processor and a first memory storing a plurality of programs, a second memory, and a temperature determination device including a temperature prediction learning device. The first processor may generate input data including cell design parameters for candidate battery cells constituting a candidate battery module and simulation interpretation conditions for a simulation predicting a maximum temperature for the candidate battery cells. The second memory stores the input data, and during a learning operation, the temperature prediction learning device may perform machine learning using training data from the input data stored in the second memory and determine a temperature calculation formula for predicting a maximum temperature of the candidate battery cell through the machine learning.

[0007] The temperature determination device may further include a second processor that controls the second memory to provide the training data to the temperature prediction learning device during the learning operation and controls the temperature prediction learning device to perform machine learning on the training data.

[0008] After the learning operation, the second processor may perform a normal operation of determining a maximum temperature of the candidate battery cell according to the updated temperature calculation formula.

[0009] The temperature prediction learning device may perform a learning operation to determine a plurality of first to nth parameters that affect the maximum temperature of the training data and a plurality of first to nth parameter coefficients corresponding to the plurality of first to nth parameters, respectively. The training data may include cell design parameters, the simulation interpretation conditions, and the maximum temperature for the candidate battery cells.

[0010] The simulation interpretation conditions of the training data may include a maximum duration of maximum current for the candidate battery cell.

[0011] The temperature calculation formula may be a regression formula for an item formed by the products of the plurality of first to n-th parameters and the plurality of first to n-th parameter coefficients.

[0012] The first memory may store an RC (Resistance*Capacitance) extraction program for deriving an RC value of the candidate battery cell. The first processor may apply hybrid pulse power characterization (HPPC) test data for the candidate battery cell to the RC extraction program to derive the RC value in an equivalent circuit corresponding to the candidate battery cell.

[0013] The first memory may store a maximum temperature interpretation program for determining a maximum temperature of the candidate battery cell, and the first processor may apply the cell design parameters, an RC value in an equivalent circuit corresponding to the candidate battery cell, and the simulation interpretation conditions to the maximum temperature interpretation program to determine the maximum temperature.

[0014] The first memory may store a candidate derivation program that determines the cell design parameters based on cell design data related to required specifications and derives candidate battery modules based on the cell design parameters. The first processor may apply the cell design data to the candidate derivation program to derive the candidate battery modules.

[0015] According to another aspect of the present invention, a maximum temperature prediction method may include the steps of: deriving an RC (Resistance*Capacitance) value in an equivalent circuit corresponding to a candidate battery cell constituting a candidate battery module; determining a maximum temperature for the candidate battery cell using cell design parameters for the candidate battery cell, the RC value, and simulation interpretation conditions for a simulation predicting a maximum temperature; and performing machine learning using training data including the cell design parameters, the RC value, and the simulation interpretation conditions to determine a temperature calculation formula for predicting a maximum temperature of the candidate battery cell.

[0016] The maximum temperature prediction method may further include determining a maximum temperature of the candidate battery cell according to the temperature calculation formula updated after the learning operation.

[0017] The step of determining the temperature calculation formula may include a step of determining, from the training data, a plurality of 1st to nth parameters that affect the maximum temperature and a plurality of 1st to nth parameter coefficients corresponding to each of the plurality of 1st to nth parameters.

[0018] The temperature calculation formula may be a regression formula for items formed by products of the plurality of first to n-th parameters and the plurality of first to n-th parameter coefficients.

[0019] The training data may include a maximum sustained time of maximum current for the candidate battery cell.

[0020] The step of deriving the RC value may include applying hybrid pulse power characterization (HPPC) test data for the candidate battery cell to an RC extraction program to derive the RC value.

[0021] The maximum temperature prediction method may further include a step of determining the cell design parameters based on cell design data relating to required specifications. [Effects of the Invention]

[0022] It is possible to provide a maximum temperature prediction apparatus and method based on cell design parameters and interpretation conditions required to predict the maximum temperature. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram illustrating a maximum temperature prediction device according to an embodiment. [Figure 2] 10 is a flowchart illustrating a preprocessing method for temperature predictive learning according to an embodiment. [Figure 3] 1 is a flowchart illustrating a temperature predictive learning method according to an embodiment. [Figure 4] 10 is a graph showing the predicted maximum temperature according to the number of stacks in the pretreatment device. DETAILED DESCRIPTION OF THE INVENTION

[0024] In describing the embodiments disclosed herein, if it is determined that a detailed description of related publicly known technology may obscure the gist of the embodiments disclosed herein, the detailed description will be omitted. In addition, the attached drawings are provided to facilitate understanding of the embodiments disclosed herein, and the technical ideas disclosed herein should not be limited by the attached drawings, and should be understood to include all modifications, equivalents, or alternatives within the spirit and technical scope of the present invention.

[0025] Terms including ordinal numbers such as first, second, etc. may be used to describe various components, but the components are not limited by the terms. These terms are used only to distinguish one component from another.

[0026] When a component is described as being "coupled" or "connected" to another component, it should be understood that the component is or may be directly connected to the other component, but that there may be other components in between. On the other hand, when a component is described as being "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0027] In this application, the terms "comprise" or "have" and the like are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are to be understood as not precluding the possible presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0028] FIG. 1 is a diagram illustrating a maximum temperature prediction device according to an embodiment.

[0029] As shown in FIG. 1, the maximum temperature prediction device 1 may include a preprocessing device 10 and a temperature determination device 20. The preprocessing device 10 may preprocess at least a portion of the input data provided to the temperature determination device 20. For example, the input data may include cell design parameters and interpretation conditions (hereinafter, simulation interpretation conditions) applied to an interpretation simulation that determines the maximum temperature. The cell design parameters may include cell size (length, width, thickness), number of cell stacks, positive electrode material loading amount, cell capacity, cathode / anode foil width / thickness ratio, cathode / anode tab thickness / length, cathode / anode lead width / thickness, and SiO content. The simulation interpretation conditions may include initial temperature, ambient temperature, coolant temperature, quick charge SOC (State of Charge) range, initial SOC, heat transfer coefficient (based on the battery module), internal busbar thickness, maximum current, fast charge target time, maximum maximum current maintenance time, etc. Fast charging may refer to charging at a high current above a predetermined value.

[0030] The pre-processing device 10 includes a processor 11 and a memory 12, and the memory 12 may include a candidate derivation program 121, an RC extraction program 122, and a maximum temperature interpretation program 123. The processor 11 applies cell design data provided to the pre-processing device 10 to the candidate derivation program 121 to determine candidate battery cells that constitute a candidate battery module, applies hybrid pulse power characterization (HPPC) test data for the candidate battery cells to the RC extraction program 122 to derive RC (Resistance*Capacitance) values ​​of the candidate battery cells, and applies simulation interpretation conditions and the RC values ​​to the maximum temperature interpretation program 123 to determine the maximum temperature of the candidate battery cells. The cell design data is data related to required specifications and may include the maximum current during charging, the time during which fast charging can be performed (hereinafter referred to as the fast charging target time), battery pack size, etc.

[0031] The maximum temperature prediction device 1 can acquire HPPC test data from an external simulator 2. The processor 11 can determine candidate battery cells and provide cell design parameters for the candidate battery cells to the simulator 2. The simulator 2 can acquire HPPC test data by performing a physics-model-based simulation based on chemical information among the cell design parameters for the candidate battery cells. For example, the simulator 2 can derive the voltage behavior of the candidate battery cell by performing a physics-model-based simulation based on chemical information on the cathode material, anode material, etc. that constitute the candidate battery cell. The HPPC test data can include data on the voltage behavior of the cell.

[0032] First, the processor 11 may load the candidate derivation program 121 from the memory 12, input cell design data into the candidate derivation program 121, and execute the candidate derivation program 121. The candidate derivation program 121 may generate cell design parameters for cells constituting a battery module based on the cell design data. For example, the candidate derivation program 121 may determine the size of a cell constituting a battery module and the number of cells to be stacked to form the battery module (hereinafter, the number of cell stacks). A battery module refers to a unit energy storage system realized by electrically connecting at least two battery cells. The candidate derivation program 121 may determine the cell size based on the cell design data and determine the number of cell stacks that can be realized with the determined cell size. The cell size may be defined by the cell length, cell width, and cell thickness. A battery pack may be realized by electrically connecting multiple battery modules. A cell may include a cathode material loading, an anode material loading, and foils attached to each of the cathode material loading and the anode material loading. The candidate derivation program 121 can determine the number of stacks that constitute a battery module, taking into consideration the thickness of the positive electrode material loading and the negative electrode material loading.

[0033] The candidate derivation program 121 derives all of a plurality of cell sizes and the number of cell stacks for each of the plurality of cell sizes that satisfy required specifications, and can derive candidate battery modules by considering the producibility of each of a plurality of battery modules implemented with the derived plurality of cell sizes and the number of cell stacks for each of the plurality of cell sizes. Factors for determining producibility and criteria for the factors may be set in the candidate derivation program 121.

[0034] 1 and the description referring to it, the memory 12 includes the candidate derivation program 121 and the processor 11 executes the candidate derivation program 121, but the present invention is not limited thereto. The memory 12 does not store the candidate derivation program 121, and the processor 11 can receive information about candidate battery modules from an external source.

[0035] The processor 11 can load the RC extraction program 122 from the memory 12, input HPPC test data for a cell of a candidate battery module (a candidate battery cell) into the RC extraction program 122, and execute the RC extraction program 122. The RC extraction program 122 can realize an equivalent circuit representing the electrical characteristics of the cell based on the input HPPC test data for the candidate battery cell, and estimate the RC value of the candidate battery cell based on the equivalent circuit. The RC extraction program 122 can realize an equivalent circuit based on the voltage behavior of the cell according to the HPPC test data for the candidate battery cell, and determine the RC value of the candidate battery cell by multiplying the resistance and capacitance values ​​of the realized equivalent circuit.

[0036] The processor 11 can load the maximum temperature interpretation program 123 from the memory 12 and execute the maximum temperature interpretation program 123 by inputting the cell design parameters, simulation interpretation conditions, and RC value of the candidate battery cell into the maximum temperature interpretation program 123. The maximum temperature interpretation program 123 can derive data necessary for temperature interpretation from the cell design parameters and determine the maximum temperature by solving a governing equation related to the maximum temperature using the derived data (e.g., cell size, coolant temperature, heat transfer coefficient, etc.) and the RC value. The governing equation is pre-installed in the maximum temperature interpretation program 123, and the cell design parameters and RC value can be independent variables and the maximum temperature can be a dependent variable in the governing equation. The maximum temperature interpretation program 123 can determine the maximum temperature by performing a calculation operation to solve the governing equation.

[0037] According to one embodiment, the temperature determining device 20 receives input data from the pre-processing device 10, stores the input data, performs a learning operation using the stored input data, and after the learning operation, performs a normal operation of predicting the maximum temperature based on the input data provided from the pre-processing device 10.

[0038] Temperature determination device 20 can include processor 201, memory 202, and temperature prediction learning device 203. Processor 201 determines which operation to perform, normal operation or learning operation, controls the operation of temperature prediction learning device 203 when the determined operation mode is learning operation, and can perform temperature calculations when the determined operation mode is normal operation.

[0039] The processor 201 can determine the operation mode according to an external command, or can determine the operation mode according to a preset specific control condition and an operation mode corresponding to the specific control condition. For example, the processor 201 can determine the operation mode as the learning operation at regular intervals or whenever the accumulated new training data reaches a predetermined reference amount.

[0040] In the learning operation, the processor 201 can instruct the temperature prediction learning device 203 to perform machine learning. The processor 201 can determine training data from the input data stored in the memory 202 and control the memory 202 and the temperature prediction learning device 203 to cause the temperature prediction learning device 203 to read the training data from the memory 202. The processor 201 can determine data added since the most recent learning operation from the input data stored in the memory 202 as the training data. In the learning operation, the temperature prediction learning device 203 can perform machine learning to output a temperature formula for determining the maximum temperature during cell charging using the read training data. The temperature prediction learning device 203 can determine the temperature formula through the learning operation and update it to the processor 201. In the learning operation, the processor 201 can control the maximum temperature to be included in the training data. That is, the temperature prediction learning device 203 can perform machine learning to receive information on cell design parameters, information on maximum temperature simulation interpretation conditions, and the predicted maximum temperature and output a temperature formula for determining the maximum temperature.

[0041] The temperature prediction learning device 203 can perform a learning operation to determine a plurality of 1st to nth parameters that affect the maximum temperature among the training data and a plurality of 1st to nth parameter coefficients corresponding to each of the plurality of 1st to nth parameters. The training data during the learning operation includes cell design parameters, simulation interpretation conditions, and the maximum temperature for a candidate battery cell. During the learning operation, the temperature prediction learning device 203 can determine parameters that affect the maximum temperature among the cell design parameters and simulation interpretation conditions, i.e., parameters that have a significant level of correlation with the maximum temperature, as the plurality of 1st to nth parameters. The temperature prediction learning device 203 can learn the degree of correlation between the plurality of 1st to nth parameters and the maximum temperature through the learning operation and determine a plurality of 1st to nth parameter coefficients that indicate the degree of correlation. The temperature prediction learning device 203 can output the plurality of 1st to nth parameters and the plurality of 1st to nth parameter coefficients as output data through a learning operation using input data.

[0042] Furthermore, the temperature prediction learning device 203 can output a temperature calculation formula using a combination of a plurality of first to n-th parameters and a plurality of first to n-th parameter coefficients. For example, the temperature calculation formula can be embodied as a regression formula for items formed by the product of a plurality of first to n-th parameters and a plurality of first to n-th parameter coefficients corresponding to the plurality of first to n-th parameters.

[0043] In normal operation, processor 201 can apply input data to a temperature formula to determine the maximum temperature. That is, in the learning operation, temperature prediction learning device 203 updates processor 201's temperature formula through the learning operation, and in normal operation, processor 201 can extract information on a plurality of first to nth parameters that make up the temperature formula from the input data and substitute it into the temperature formula to determine the maximum temperature. When the operating mode is normal, preprocessing device 10 can only perform preprocessing on a plurality of first to nth parameters.

[0044] For example, the temperature calculation formula may include the number of stacks, the coolant temperature, the initial SOC, the fast charge time, the maximum current, and the maximum current maintenance time as the first to sixth parameters, and the first to sixth parameter coefficients may be positive or negative real numbers.

[0045] An operating method of the maximum temperature prediction device according to an embodiment, i.e., a maximum temperature prediction method, may include a pre-processing method and a temperature prediction learning method.

[0046] FIG. 2 is a flowchart showing a preprocessing method for temperature predictive learning according to one embodiment.

[0047] The processor 11 can determine the sizes of multiple types of cells that can constitute a battery module and the number of multiple cell stacks corresponding to the sizes of the multiple types of cells based on the cell design data (S1).

[0048] The processor 11 may derive candidate battery modules by considering the producibility of each of the battery modules implemented with the cell sizes and the cell stack counts derived in step S1 (S2).

[0049] The processor 11 can receive information on the candidate battery modules from the outside instead of steps S1 and S2.

[0050] The processor 11 may transmit information about the candidate battery cells to the simulator 2 and receive HPPC test data about the candidate battery cells from the simulator 2 (S3).

[0051] Based on the HPPC test data for the candidate battery cell obtained in step S3, the processor 11 can realize an equivalent circuit representing the electrical characteristics of the cell, and derive the RC value of the candidate battery cell based on the equivalent circuit (S4).

[0052] The processor 11 can determine the maximum temperature using the cell design parameters, simulation interpretation conditions, and RC values ​​of the candidate battery cells (S5).

[0053] FIG. 3 is a flowchart showing a temperature predictive learning method according to one embodiment.

[0054] The processor 201 can determine the operation mode between normal operation and learning operation according to an external command or control condition (S10).

[0055] When the operation mode determined in step S10 is the learning operation, temperature prediction learning device 203 can read training data from memory 202 (S11).

[0056] In the learning operation, the temperature prediction learning device 203 can perform machine learning using the read training data to output a temperature calculation formula for determining the maximum temperature during cell charging (S12).

[0057] The temperature prediction learning device 203 can determine a temperature calculation formula through a learning operation and update the formula in the processor 201 (S13).

[0058] When the operation mode determined in step S10 is normal operation, the processor 201 can apply the input data to a temperature calculation formula to determine the maximum temperature (S14).

[0059] The plurality of first to n-th parameters determined by the learning operation of the temperature determining device 20 include a parameter for a maximum current maximum application time. The maximum current maximum application time means the longest time during which a maximum current is applied to a candidate battery cell during charging. The current applied to a candidate battery cell during charging fluctuates, and there may be multiple intervals during which the fluctuating current is the maximum current. The longest time among the multiple intervals is the maximum current maximum application time.

[0060] Table 1 below shows the error and error rate between the predicted maximum temperature and the measured temperature during normal operation after the temperature determination device 20 performs a learning operation using a plurality of first to nth parameters that do not include the maximum current and maximum application time.

[0061]

Table 1

[0062] Table 2 below shows the error and error rate between the predicted maximum temperature and the measured temperature during normal operation after the temperature determination device 20 performs a learning operation using a plurality of first to nth parameters that include the maximum current and maximum application time.

[0063]

Table 2

[0064] Between the values indicating the stack numbers in Table 1 and Table 2, the relationship St_n1 < St_n2 < St_n3 < St_n4 < St_n5 holds. In Table 1, the maximum error rate was 5.29%, but in Table 2, the maximum error rate decreased to 1.85%. That is, it can be seen that when learning using a plurality of first to nth parameters including the maximum current and maximum application time, the prediction accuracy of the maximum temperature increases.

[0065] Hereinafter, a method for determining training data for temperature prediction learning according to an embodiment will be described.

[0066] Figure 4 is a graph showing the maximum temperature predicted by the preprocessing device according to the stack number.

[0067] In Figure 4, the predicted maximum temperature graphs for each of the stack numbers N1, N2, N3, N4, N5, N6, and N7 are shown. The variables N1 to N7 indicating the stack numbers can be set as N1 < N2 < N3 < N4 < N5 < N6 < N7, and the difference between two adjacent stack numbers for the variables N1 to N7 is the same.

[0068] As shown in FIG. 4, if the dotted line 41 is a linear fitting line, the predicted maximum temperatures for stack numbers N2 and N4 have discrepancies with the linear fitting line. When the temperature prediction learning device 203 performs machine learning on the training data under the condition that data corresponding to stack numbers N2 and N4 is excluded from the training data, and derives a temperature calculation formula, a prediction discrepancy as shown in Table 3 below occurs. Table 3 shows the measured maximum temperature and predicted maximum temperature under the 15-minute fast charging condition. The predicted maximum temperature can be derived using the temperature calculation formula determined by the temperature prediction learning device 203 through learning. When the temperature prediction learning device 203 performs machine learning on all training data including data corresponding to stack numbers N2 and N4 to derive a temperature calculation formula, a prediction discrepancy as shown in Table 4 below occurs.

[0069] As can be seen in Tables 3 and 4, the accuracy of the maximum temperature prediction results for stack numbers N2 and N4 improves when the entire training data is used for machine learning.

[0070] [Table 3]

[0071] [Table 4]

[0072] Table 5 below shows the error and error rate between the measured maximum temperature and the predicted maximum temperature when the temperature prediction learning device 203 derives a temperature calculation formula by performing machine learning on training data under conditions in which data corresponding to stack numbers N2 and N4 is excluded and fast charging times for stack numbers N2 and N4 are 15 minutes, 18 minutes, 20 minutes, 25 minutes, and 30 minutes.

[0073] [Table 5]

[0074] Table 6 below shows the error and error rate between the measured maximum temperature and the predicted maximum temperature when the temperature prediction learning device 203 performs machine learning on the entire training data to derive a temperature calculation formula, and when the high-speed charging times for stack numbers N2 and N4 are 15 minutes, 18 minutes, 20 minutes, 25 minutes, and 30 minutes.

[0075] [Table 6]

[0076] The highest error rate in Table 5 is 1.33%, which is smaller than the highest error rate of 2.13% in Table 6. The results in Table 5 can be seen as an overfitting of the temperature calculation formula derived through learning.

[0077] In this way, the training data includes training data for all stack numbers that can be applied to the candidate battery module, thereby improving the accuracy of maximum temperature prediction.

[0078] Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims also fall within the scope of the present invention. [Explanation of symbols]

[0079] 1 Maximum temperature prediction device 2 Simulator 10 Pretreatment device 11 processors 12 Memory 20 Temperature determining device 121 Candidate Derivation Program 122 RC Extraction Program 123 Maximum Temperature Interpretation Program 201 processor 202 memory 203 Temperature Prediction Learning Device

Claims

1. a preprocessing unit including a first processor and a first memory having a plurality of programs stored therein; and a second memory and a temperature determination device including a temperature prediction learning device; The first processor generates input data including cell design parameters for candidate battery cells constituting a candidate battery module and simulation interpretation conditions for a simulation predicting a maximum temperature for the candidate battery cells; the second memory stores the input data; A maximum temperature prediction device in which, during a learning operation, the temperature prediction learning device performs machine learning using training data among the input data stored in the second memory, and determines a temperature calculation formula for predicting the maximum temperature of the candidate battery cell through the machine learning.

2. The temperature determining device The maximum temperature prediction device of claim 1, further comprising a second processor that controls the second memory to provide the training data to the temperature prediction learning device during the learning operation and controls the temperature prediction learning device to perform machine learning with the training data.

3. The second processor The maximum temperature prediction device of claim 2 , further comprising: a normal operation for determining the maximum temperature of the candidate battery cell according to the temperature calculation formula updated after the learning operation.

4. the temperature prediction learning device performs a learning operation to determine a plurality of first to n-th parameters that affect the maximum temperature among the training data and a plurality of first to n-th parameter coefficients corresponding to the plurality of first to n-th parameters, respectively; The maximum temperature prediction device of claim 2 , wherein the training data includes cell design parameters, the simulation interpretation conditions, and a maximum temperature for the candidate battery cells.

5. The simulation interpretation conditions are: The maximum temperature prediction device of claim 4 , further comprising a maximum sustained time of maximum current for the candidate battery cell.

6. 5. The maximum temperature prediction device according to claim 4, wherein the temperature calculation formula is a regression formula for items formed by products of the first to n-th parameters and the first to n-th parameter coefficients.

7. The first memory includes: storing an RC (Resistance*Capacitance) extraction program for deriving an RC value of the candidate battery cell; The first processor 2. The maximum temperature prediction device according to claim 1, wherein hybrid pulse power characterization (HPPC) test data for the candidate battery cell is applied to the RC extraction program to derive the RC value in an equivalent circuit corresponding to the candidate battery cell.

8. The first memory includes: storing a maximum temperature interpretation program for determining a maximum temperature of the candidate battery cells; The first processor The maximum temperature prediction device according to claim 1 , wherein the maximum temperature is determined by applying the cell design parameters, an RC value in an equivalent circuit corresponding to the candidate battery cell, and the simulation interpretation conditions to the maximum temperature interpretation program.

9. The first memory includes: determining the cell design parameters based on cell design data related to required specifications, and storing a candidate derivation program that derives candidate battery modules according to the cell design parameters; The maximum temperature prediction device according to claim 1 , wherein the first processor applies the cell design data to the candidate derivation program to derive the candidate battery module.

10. A step of deriving an RC (Resistance*Capacitance) value in an equivalent circuit corresponding to a candidate battery cell constituting a candidate battery module; determining a maximum temperature for the candidate battery cell using cell design parameters for the candidate battery cell, the RC value, and a simulation interpretation condition for a simulation predicting a maximum temperature; and A maximum temperature prediction method comprising: performing machine learning using training data including the cell design parameters, the RC value, and the simulation interpretation conditions to determine a temperature calculation formula for predicting a maximum temperature of the candidate battery cell.

11. The maximum temperature prediction method of claim 10 , further comprising: determining a maximum temperature of the candidate battery cell according to the temperature calculation formula updated after a learning operation.

12. The step of determining the temperature calculation formula includes:

11. The maximum temperature prediction method according to claim 10, further comprising a step of determining a plurality of first to nth parameters that affect the maximum temperature in the training data and a plurality of first to nth parameter coefficients corresponding to the plurality of first to nth parameters, respectively.

13. 13. The maximum temperature prediction method according to claim 12, wherein the temperature calculation formula is a regression formula for items formed by products of the first to n-th parameters and the first to n-th parameter coefficients.

14. The training data is The maximum temperature prediction method of claim 10 , further comprising a maximum sustained time of maximum current for the candidate battery cell.

15. The step of deriving the RC value comprises: The method of claim 10 , further comprising applying hybrid pulse power characterization (HPPC) test data for the candidate battery cell to an RC extraction program to derive the RC value.

16. The method for predicting a maximum temperature according to claim 10, further comprising the step of determining the cell design parameters based on cell design data relating to required specifications.

Images