Method for learning impact analysis model of battery module and method for predicting impact analysis result of battery module

Abstract

A method for learning an impact analysis model of a battery module according to one embodiment of the present invention includes the steps of sampling an initial state value of a battery module and a deformed state value of the battery module due to an impact value applied to the battery module, repeating the sampling step for a predetermined test period to obtain learning data, and receiving the initial state value of the battery module and the applied impact value the number of times sampled, and performing machine learning on an impact analysis model of the battery module to predict an analysis result of the battery module due to an impact.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of priority based on Korean Patent Application No. 10-2022-0174030, dated December 13, 2022, and all contents disclosed in the documents of this Korean patent application are incorporated herein by reference.

[0002] The present invention relates to a method for learning an impact analysis model for a battery module and a method for predicting the results of impact analysis for a battery module, and more particularly to a method for quickly predicting the stability of a battery module against impact by applying a machine learning technique. [Background technology]

[0003] When developing a battery module, it is essential to verify its structural safety under specific impact conditions. A commonly used method is to perform finite element analysis.

[0004] Although the impact analysis results obtained by finite element analysis are relatively accurate, it has the disadvantages of being time-consuming and laborious to model and calculate, and requiring the use of specialized structural analysis software.

[0005] However, frequent design changes occur during the initial development stage, and repeating this process for each change creates inefficiencies in operations.There is a need for a method for quickly predicting the stability of a battery module against shocks during the design and development process of a battery module, including the initial development stage of the battery module. Summary of the Invention [Problem to be solved by the invention]

[0006] The present invention provides a method for predicting the stability of a battery module, and in particular, an object of the present invention is to provide a method for quickly predicting the stability of a battery module against an impact by applying a machine learning technique.

[0007] However, the problems to be solved by the embodiments of the present invention are not limited to the above problems, and can be variously expanded within the scope of the technical ideas included in the present invention. [Means for solving the problem]

[0008] A method for predicting an analysis result of a battery module due to an impact in a battery module evaluation system including an impact analysis model for a battery module according to one embodiment of the present invention may include a step of inputting an initial state value of the battery module and an impact value to be applied to the battery module, and a step of predicting an analysis result of the battery module due to an impact from the impact analysis model for the battery module.

[0009] The battery module evaluation system may further include a step of learning an impact analysis model of the battery module applied thereto, wherein the step of learning the impact analysis model of the battery module may include a step of sampling an initial state value of the battery module and a deformed state value of the battery module due to an impact value applied to the battery module, a step of repeating the sampling step for a predetermined test period to obtain learning data, and a step of receiving the initial state value of the battery module and the applied impact value a number of times of sampling and performing machine learning on the impact analysis model of the battery module to predict an analysis result of the battery module due to an impact.

[0010] The sampling step may include measuring and storing an initial state value of the battery module, storing an impact value applied to the battery module, and measuring and storing a deformed state value of the battery module due to the impact.

[0011] The step of predicting the analysis result of the battery module may include predicting a state value of deformation of the battery module due to the impact.

[0012] The method may further include predicting a deformation rate of the battery module from the deformation state value of the battery module.

[0013] The initial state value of the battery module may be an initial state value of a predetermined portion of the battery module, and the deformed state value of the battery module may be a deformed state value of the predetermined portion of the battery module.

[0014] The deformation rate of the battery module may be a plastic strain of the battery module due to the impact.

[0015] The deformation rate of the battery module may be a deformation rate of a predetermined portion of the battery module.

[0016] The deformation rate of the battery module (

[0017]

number

[0018] ) is the total deformation rate (

[0019]

number

[0020]

number

[0021]

number

[0022]

number

[0023]

number

[0024] where:

[0025]

number

[0026] is the dimension of the battery module before deformation, L is the dimension of the battery module after deformation,

[0027]

number

[0028] is the stress value when the material is at its elastic limit state, and E may be the elastic modulus of the material.

[0029] The method may further include predicting a score indicating a risk level of the battery module based on the deformation rate of the battery module.

[0030] The score (SCORE) indicating the risk level of the battery module is calculated by the following Equation 9:

[0031]

number

[0032] The score may be a value between 0 and 1.

[0033] When the score (SCORE) is less than 0.4, the risk of impact on the battery module is determined to be "safe," when the score (SCORE) is more than 0.6, the risk of impact on the battery module is determined to be "dangerous," and when the score (SCORE) is between 0.4 and 0.6, the determination of the risk of impact on the battery module can be withheld.

[0034] The initial state value of the battery module may include an initial value of the dimension of the battery module, and the deformed state value of the battery module may include a value of the dimension of the battery module after deformation.

[0035] The dimensional values ​​of the battery module may include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module.

[0036] The initial state value of the battery module may include at least one of the density of the battery cells included in the battery module and the mass of the battery cells.

[0037] The value of the shock applied to the battery module may include at least one of the magnitude of the shock and the duration for which the shock is applied.

[0038] A battery module evaluation system for performing a method for predicting an analysis result due to an impact on a battery module according to one embodiment of the present invention may include a data input unit to which an initial state value of the battery module and an impact value applied to the battery module are input, a data processing unit to execute an impact analysis model for the battery module, and a data output unit to output an analysis result of the battery module.

[0039] The battery module may further include a data storage unit for storing an impact analysis model of the battery module.

[0040] A method for learning an impact analysis model of a battery module according to one embodiment of the present invention may include the steps of sampling an initial state value of a battery module and a deformed state value of the battery module due to an impact value applied to the battery module, repeating the sampling step for a predetermined test period to obtain learning data, and receiving the initial state value of the battery module and the applied impact value the number of times sampled, and performing machine learning on the impact analysis model of the battery module to predict an analysis result of the battery module due to an impact.

[0041] The sampling step may include measuring and storing an initial state value of the battery module, storing an impact value applied to the battery module, and measuring and storing a deformed state value of the battery module due to the impact.

[0042] The initial state value of the battery module may be an initial state value of a predetermined portion of the battery module, and the deformed state value of the battery module may be a deformed state value of the predetermined portion of the battery module.

[0043] The machine learning step may include calculating and storing a deformation rate of the battery module from a deformation state value of the battery module.

[0044] The deformation rate of the battery module may be a plastic strain of the battery module due to the impact.

[0045] The deformation rate of the battery module may be a deformation rate of a predetermined portion of the battery module.

[0046] The deformation rate of the battery module (

[0047]

number

[0048] ) is the total deformation rate (

[0049]

number

[0050] ) to the elastic strain (elastic strain,

[0051]

number

[0052] ) is subtracted from the value, and according to the following formulas 13 to 15,

[0053]

number

[0054]

number

[0055]

number

[0056] where:

[0057]

number

[0058] is the dimension of the battery module before deformation, L is the dimension of the battery module after deformation,

[0059]

number

[0060] may be a stress value when the material of the battery module is in an elastic limit state, and E may be an elastic modulus of the material of the battery module.

[0061] The machine learning step may further include calculating and storing a score indicating a risk level of the battery module based on the deformation rate of the battery module.

[0062] The score (SCORE) indicating the risk level of the battery module is calculated by the following Equation 18:

[0063]

number

[0064] The score may be a value between 0 and 1.

[0065] When the score (SCORE) is less than 0.4, the risk of impact on the battery module is determined to be "safe," when the score (SCORE) is more than 0.6, the risk of impact on the battery module is determined to be "dangerous," and when the score (SCORE) is between 0.4 and 0.6, the determination of the risk of impact on the battery module can be withheld.

[0066] The initial state value of the battery module may include an initial value of a dimension of the battery module, and the deformed state value of the battery module may include a value of the dimension of the battery module after the deformation.

[0067] The dimensional values ​​of the battery module may include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module.

[0068] The initial state value of the battery module may include at least one of the density of the battery cells included in the battery module and the mass of the battery cells.

[0069] The value of the shock applied to the battery module may include at least one of the magnitude of the shock and the duration for which the shock is applied.

[0070] The magnitude of the impact may be expressed as an acceleration of an object that applies the impact to the battery module.

[0071] The method may further include a step of verifying the validity of the impact analysis of the battery module, wherein the step of verifying the validity may include a step of generating, as verification data, an initial state value of the battery module and a deformed state value of the battery module due to an impact value applied to the battery module during a predetermined verification period; a step of calculating an analysis result of the battery module from an impact analysis model of the battery module using the verification data; a step of calculating, by finite element analysis, the analysis result of the battery module due to the initial state value of the battery module and the impact value applied to the battery module using the verification data; and a step of determining that the impact analysis model of the battery module is valid when a difference between the analysis result of the battery module predicted from the impact analysis model of the battery module and the analysis result of the battery module calculated by the finite element analysis is within a predetermined reference value range. [Effects of the Invention]

[0072] According to the present invention, it is possible to quickly predict the stability of a battery module against impact, and as a result, it is possible to efficiently proceed with the design and development of electrode modules.

[0073] Furthermore, conditions and predicted results for the stability of battery modules against impacts can be standardized, thereby ensuring reliability in the quality of the produced battery modules.

[0074] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims. [Brief explanation of the drawings]

[0075] [Figure 1] 1 is a block diagram showing a battery module evaluation system 100 according to an embodiment of the present invention. [Figure 2] 1 is a flowchart showing a learning method for a battery module impact analysis model performed in a battery module evaluation system 100 according to an embodiment of the present invention. [Figure 3] 1 is a flowchart showing a method for predicting an analysis result due to a shock to a battery module, which is performed in a battery module evaluation system 100 including an impact analysis model for a battery module according to an embodiment of the present invention. [Figure 4] 10 shows a graph of a score calculated based on the deformation rate of a battery module as a result of an analysis of an impact on the battery module according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0076] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, in which the same or similar components are designated by the same or similar drawing numbers, and redundant descriptions thereof will be omitted.

[0077] The suffixes "module" and / or "unit" for components used in the following description are given or used interchangeably solely for the convenience of writing the specification, and do not have any meanings or roles that are distinct from each other. Furthermore, terms such as "unit," "device," and "module" used in the specification refer to a unit that processes at least one function or operation, and may be realized by hardware, software, or a combination of hardware and software.

[0078] Furthermore, when describing the embodiments disclosed herein, if it is determined that a detailed description of such known technology may obscure the gist of the embodiments disclosed herein, the detailed description will be omitted. Furthermore, the attached drawings are merely provided to facilitate understanding of the embodiments disclosed herein, and it should be understood that the attached drawings do not limit the technical ideas disclosed herein, and all modifications, equivalents, or alternatives within the spirit and technical scope of the present invention are included.

[0079] In this application, the term "comprises" and the like are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but are to be understood as not precluding the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0080] 1 is a block diagram showing a battery module evaluation system 100 according to an embodiment of the present invention. The battery module evaluation system 100 according to the embodiment of the present invention includes a data input unit 110, a data processing unit 120, and a data output unit .

[0081] The data input unit 110 may be, for example, an input device for a mobile device, an input device for a computer, various keyboards, a mouse, an electronic pen, a microphone, or any other unit that can input data.

[0082] The data processing unit 120 receives learning data and performs machine learning on the battery module shock analysis model according to one embodiment of the present invention, while in predicting the battery module shock analysis result, it receives the initial state value of the battery module and the shock value applied to the module and predicts the analysis result of the battery module shock using the battery module shock analysis model. The data processing unit 120 may be, for example, a processor of a mobile device or a computer processor, or any other device capable of performing the battery module shock analysis model learning method and the battery module shock analysis result prediction method according to one embodiment of the present invention.

[0083] The data output unit 130 outputs the results of processing by the data processing unit 120. For example, it may be an output device of a mobile device, an output device of a computer, various display devices, various speaker units, or any other unit capable of outputting data.

[0084] The data storage unit 140 stores an impact analysis model of a battery module according to one embodiment of the present invention, and can store learning data, data input to the data input unit 110, processing results in the data processing unit 120, and various other data.

[0085] The data input unit 110, the data processing unit 120, the data output unit 130, and the data storage unit 140 may all be integrated into a single device, and in some cases, at least one of the data input unit 110, the data processing unit 120, the data output unit 130, and the data storage unit 140 may be connected to and controlled remotely from the other components.

[0086] The impact analysis model of the battery module according to one embodiment of the present invention can be obtained by machine learning.

[0087] First, a method for training the battery module impact analysis model will be described.

[0088] FIG. 2 is a flowchart showing a learning method for a battery module impact analysis model performed in the battery module evaluation system 100 according to an embodiment of the present invention.

[0089] First, the data processing unit 120 performs step S110 of sampling an initial state value of the battery module and a deformed state value of the battery module according to an impact value applied to the battery module. In step S110, the data processing unit 120 receives the initial state value of the battery module and the impact value applied to the battery module from the data input unit 110 and performs step S110.

[0090] The data sampled in step S110 is stored in the data storage unit 140. More specifically, the method includes step S111 of measuring an initial state value of the battery module and storing the value in the data storage unit 140, step S112 of applying an impact to the battery module and storing the value of the impact applied to the battery module in the data storage unit 140, and step S113 of measuring a state value of the battery module deformed by the impact and storing the value in the data storage unit 140.

[0091] Here, the initial state value of the battery module refers to the initial state value of a predetermined portion of the battery module. The predetermined portion of the battery module may be a portion of the battery module that is specified (predetermined) in advance by an operator depending on the process, environment, etc. This is because, when an impact is applied to the battery module, the battery module may be deformed in terms of dimensions, etc., around the portion to which the impact is applied. However, the present invention is not limited to the above, and the predetermined portion of the battery module may be the entire battery module. Furthermore, the initial state value of the battery module includes the initial dimension value of the battery module. The deformed state value of the battery module due to an impact refers to the deformed state value of a predetermined portion of the battery module. Furthermore, the deformed state of a predetermined portion of the battery module includes the dimensional value of the initial dimension deformed due to the impact applied to the battery module.

[0092] The dimension values ​​of the battery module refer to the dimension values ​​of a predetermined portion of the battery module. The dimension values ​​of the battery module (i.e., the dimension values ​​of a predetermined portion of the battery module) include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of the predetermined portion of the battery module. The detailed factors included in the dimension values ​​of the battery module are not limited to those described above, and can be set in various ways according to the environment in which the present invention is implemented and the conditions required by the worker.

[0093] For example, the overall length, width, and height of the battery module may be set to the dimensional values ​​of the battery module, but if the battery module consists of a U-frame and a top plate that covers it, the length, width, and height of the U-frame alone may be set to the dimensional values ​​of the battery module, or the length, width, and height of the top plate alone may be set to the dimensional values ​​of the battery module, etc. Various modifications and variations are possible. Also, it is possible to focus on the part of the frame or plate that is subject to impact and only consider the dimensional values ​​of that part.

[0094] The initial state value of the battery module also includes at least one of the density of the battery cells and the mass of the battery cells included in the battery module.

[0095] The impact value applied to the battery module includes at least one of the magnitude of the impact and the duration of the impact. Factors (physical quantities) indicating the magnitude of the impact include, for example, the acceleration of the object that applies the impact to the battery module. However, the present invention is not limited to the above, and various physical quantities indicating the magnitude of the impact can be selected to analyze the impact on the battery module according to the environment in which the present invention is implemented and the conditions required by the operator.

[0096] The state value of the deformation of the battery module due to the impact may be information on the state of the battery module, such as temperature change, fire, explosion, etc., in some cases.

[0097] The data processing unit 120 repeats the sampling step S110 for a predetermined test period to acquire learning data in step S120. In step S120, the data processing unit 120 similarly receives the initial state value of the battery module and the shock value to be applied to the battery module from the data input unit 110, and performs step S120. The learning data acquired in step S120 is stored in the data storage unit 140.

[0098] The data processing unit 120 receives the initial state value of the battery module and the impact value applied to the battery module for the number of samplings, and performs step S130 of machine learning an impact analysis model of the battery module to predict the analysis result of the battery module due to impact.

[0099] Step S130 includes step S131 in which the data processing unit 120 calculates the deformation rate of the battery module from the deformation state value of the battery module and stores the calculated rate in the data storage unit 140.

[0100] In this case, the deformation rate of the battery module refers to the deformation rate of a predetermined portion of the battery module, and the predetermined portion of the battery module refers to the above-mentioned portion.

[0101] The deformation rate of the battery module is the plastic strain of the battery module due to the impact (

[0102]

number

[0103] ) means the deformation rate (

[0104]

number

[0105] ) is the total deformation rate of the battery module at the time of impact (

[0106]

number

[0107] ) to the elastic strain (elastic strain,

[0108]

number

[0109] ) and is calculated by the following formulas 23 to 25.

[0110]

number

[0111]

number

[0112]

number

[0113] where:

[0114]

number

[0115] is the dimension of the battery module before deformation (i.e., the dimension of a predetermined portion of the battery module before deformation), and L is the dimension of the battery module after deformation (i.e., the dimension of a predetermined portion of the battery module after deformation).

[0116]

number

[0117] is the stress value when the material (the material of the battery module, i.e., the material of a specific part of the battery module) is at its elastic limit, and E is the elastic modulus of the material. For reference, when the material (the material of the battery module, i.e., the material of a specific part of the battery module) is deformed without exceeding its elastic limit, the stress and deformation rate are linearly related, and the slope of this relationship is called the elastic modulus.

[0118]

number

[0119] and E are values ​​specific to the battery module to be inspected (i.e., the material of the battery module) and are input as preset values. Alternatively, these can be used to calculate the elastic deformation rate (

[0120]

number

[0121] ) is also a value specific to the battery module being inspected (i.e., the material of the battery module), so the elastic deformation rate (

[0122]

number

[0123] ) are input as preset values. As described above, the dimensions of the battery module include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module.

[0124] The deformation rate (

[0125]

number

[0126] ) are derived, and then the deformation rate (

[0127]

number

[0128] ) or the average value for the deformation rate (

[0129]

number

[0130] ) may be used to find the maximum value.

[0131] Alternatively, in some cases, only some factors suitable for the environment may be selected from the length, width, height, top surface thickness, bottom surface thickness, and side surface thickness of a predetermined part of the battery module to determine the deformation rate (

[0132]

number

[0133] ) is derived for each battery module, and similarly, the deformation rate (

[0134]

number

[0135] ) Alternatively, the average value or the maximum value may be calculated for each of the above.

[0136] Also, step S130 further includes step S132 of calculating and storing a score indicating a risk level of the battery module based on the deformation rate of the battery module calculated in step S131.

[0137] For example, the score (SCORE) indicating the risk level of the battery module is calculated using the following Equation 36.

[0138]

number

[0139] this is,

number

[0140] When the battery module is in a plastic deformation state, the score (SCORE) is adjusted to a value between 0 and 1.

[0141]

number

[0142] ) is an arbitrarily scaled value (see Figure 4).

[0143] The above formula 36 is merely an example, and the present invention is not limited to the above. The score can be adjusted to suit various environments in which the present invention is implemented.

[0144]

number

[0145] where C1, C2, C3, and C4 are coefficients.

[0146] Also, the score calculated in step S132 can be classified into grades.

[0147] For example, when the score is less than 0.4, the risk of impact on the battery module is determined to be "safe," when the score is over 0.6, the risk of impact on the battery module is determined to be "dangerous," and when the score is between 0.4 and 0.6, the determination of the risk of impact on the battery module can be withheld. This is just one example, and the present invention is not limited to the above.

[0148] For example, the risk level may be classified into other numbers of levels other than the three mentioned above, and since the range in which the score calculated by the coefficient value set in Equation 5 is scaled is also different, the standard values ​​for dividing the levels may be other values ​​other than the above-mentioned 0.4 and 0.6, and various modifications and variations are possible.

[0149] In addition, the data processing unit 120 performs step S140 of verifying the validity of the shock analysis of the battery module.

[0150] Step S140 includes step S141 of generating, as verification data, initial state values ​​of the battery module and deformed state values ​​of the battery module due to impact values ​​applied to the battery module during a predetermined verification period; step S142 of calculating an analysis result of the battery module from an impact analysis model of the battery module using the verification data; step S143 of calculating, by finite element analysis, the analysis result of the battery module depending on the initial state values ​​of the battery module and the impact values ​​applied to the battery module using the verification data; and step S144 of determining that the impact analysis model of the battery module is valid when the difference between the analysis result of the battery module predicted from the impact analysis model of the battery module and the analysis result of the battery module calculated by finite element analysis is within a predetermined reference value range.

[0151] FIG. 3 is a flowchart showing a method for predicting an analysis result due to a shock to a battery module, which is performed in a battery module evaluation system 100 including a shock analysis model for a battery module according to an embodiment of the present invention.

[0152] The battery module evaluation system 100 performs the learning method for the battery module impact analysis model described above in Fig. 2. The battery module impact analysis model may be acquired by machine learning in the data processing unit 120 and stored in the data storage unit 140. The battery module evaluation system 100 predicts the analysis result of the impact on the battery module using the machine-learned battery module impact analysis model according to one embodiment of the present invention.

[0153] First, the data processing unit 120 performs step S210 in which an initial state value of the battery module and an impact value to be applied to the battery module are input.

[0154] Here, the initial state value of the battery module includes an initial dimension value of the battery module. The initial dimension value of the battery module includes at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module. Also, the initial state value of the battery module includes at least one of the density and mass of the battery cells included in the battery module. The impact value applied to the battery module includes at least one of the magnitude of the impact and the duration for which the impact is applied.

[0155] A step S220 of predicting the analysis result of the battery module due to the impact is performed based on the impact analysis model of the battery module.

[0156] Step S220 includes step S221 of predicting a state value of the battery module deformed by an impact. Here, the state value of the battery module deformed by an impact includes a dimensional value of the battery module deformed from its initial dimension due to the impact applied to the battery module. The deformed dimensional value of the battery module, i.e., the dimensions of the battery module after deformation, includes at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module. The state value of the battery module deformed by an impact may be state information such as a temperature change, fire, explosion, etc. of the battery module in some cases.

[0157] Step S220 also includes step S222 of predicting a deformation rate of the battery module from the deformation state value of the battery module predicted in step S221.

[0158] At this time, the deformation rate of the battery module is the plastic strain of the battery module due to the impact (

[0159]

number

[0160] ) means the deformation rate (

[0161]

number

[0162] ) is the total deformation rate of the battery module at the time of impact (

[0163]

number

[0164] ) to the elastic strain (elastic strain,

[0165]

number

[0166] ) is calculated by the following formulas 44 to 46.

[0167]

number

[0168]

number

[0169]

number

[0170] where:

[0171]

number

[0172] where λ is the dimension of the battery module before deformation, and L is the dimension of the battery module after deformation. As described above, the dimensions of the battery module include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module. The dimensions of the battery module can be modified and changed in various ways, and refer to the above-described dimensions in FIG. 2.

[0173] The deformation rate (

[0174]

number

[0175] ) are derived, and then the deformation rate (

[0176]

number

[0177] ) or the average value for the deformation rate (

[0178]

number

[0179] ) may be used to find the maximum value.

[0180] Alternatively, in some cases, only some factors suitable for the environment may be selected from the length, width, height, top surface thickness, bottom surface thickness, and side surface thickness of a predetermined part of the battery module to determine the deformation rate (

[0181]

number

[0182] ) is derived for each battery module, and similarly, the deformation rate (

[0183]

number

[0184] ) may be averaged or the maximum value may be found.

[0185] Step S220 also includes step S223 of predicting a score indicating a risk level of the battery module from the deformation rate of the battery module predicted in step S222.

[0186] For example, the score (SCORE) indicating the risk level of the battery module is calculated using the following formula 53.

number

[0187] this is,

[0188]

number

[0189] When the battery module is in a plastic deformation state, the score (SCORE) is adjusted to a value between 0 and 1.

[0190]

number

[0191] ) is an arbitrarily scaled value (see Figure 4).

[0192] The above formula 53 is merely an example, and the present invention is not limited to the above. The score can be adjusted to suit various environments in which the present invention is implemented.

number

[0193] where C1, C2, C3, and C4 are coefficients.

[0194] Also, the score calculated in step S132 can be classified into grades.

[0195] For example, when the score is less than 0.4, the risk of impact on the battery module is determined to be "safe," when the score is over 0.6, the risk of impact on the battery module is determined to be "dangerous," and when the score is between 0.4 and 0.6, the determination of the risk of impact on the battery module can be withheld. This is just one example, and the present invention is not limited to the above.

[0196] For example, the risk level may be classified into other numbers of levels other than the three mentioned above, and since the range in which the score calculated by the coefficient value set in Equation 5 is scaled is also different, the standard values ​​for dividing the levels may be other values ​​other than the above-mentioned 0.4 and 0.6, and various modifications and variations are possible.

[0197] The method of predicting the analysis results of a battery module impact using the battery module impact analysis model according to the present invention shows a consistency rate of about 90% or more compared to conventional finite element analysis methods. Meanwhile, the present invention allows for faster prediction of the stability of a battery module against impact compared to conventional techniques, thereby facilitating efficient design and development of electrode modules. Furthermore, the present invention also allows for standardization of the conditions and prediction results for the stability of a battery module against impact, thereby ensuring the reliability of the quality of the manufactured battery modules.

[0198] Although the preferred 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 concepts of the present invention defined in the following claims also fall within the scope of the present invention. For example, the method for learning an impact analysis model of a battery module and the method for predicting the impact analysis results of a battery module of the present invention can be applied not only to battery modules, but also to battery cells, battery cell stacks, or battery packs. [Explanation of symbols]

[0199] 100: Battery module evaluation system 110: Data entry section 120: Data processing unit 130: Data output unit 140: Data storage unit

Claims

1. 1. A method for predicting an analysis result of an impact on a battery module in a battery module evaluation system including an impact analysis model of the battery module, comprising: inputting an initial state value of the battery module and an impact value to be applied to the battery module; and predicting an analysis result of the battery module due to an impact from an impact analysis model of the battery module.

2. The battery module evaluation system further includes learning an impact analysis model of the battery module applied to the battery module evaluation system, The step of learning an impact analysis model of the battery module includes: sampling an initial state value of a battery module and a deformed state value of the battery module according to an impact value applied to the battery module; repeating the sampling step for a predetermined test period to obtain training data; 2. The method of claim 1, further comprising: receiving the initial state value and the applied shock value of the battery module for the number of samplings, and machine learning an impact analysis model for the battery module to predict an analysis result of the battery module due to an impact.

3. The sampling step includes: measuring and storing an initial state value of the battery module; storing an impact value applied to the battery module; 3. The method of claim 2, further comprising measuring and storing a state value of deformation of the battery module due to the impact.

4. The method of claim 1 , wherein predicting the analysis result of the battery module comprises predicting a state value of deformation of the battery module due to the impact.

5. The method of claim 4 , further comprising predicting a deformation rate of the battery module from the deformation state value of the battery module.

6. 2. The method for predicting the impact analysis result of a battery module according to claim 1, wherein the initial state value of the battery module is an initial state value of a predetermined portion of the battery module, and the deformed state value of the battery module is a deformed state value of a predetermined portion of the battery module.

7. The method of claim 5 , wherein the deformation rate of the battery module is a plastic strain of the battery module due to the impact.

8. The method for predicting the impact analysis result of a battery module according to claim 5 , wherein the deformation rate of the battery module is a deformation rate of a predetermined portion of the battery module.

9. The deformation rate of the battery module ( [Equation 1] ) is the total deformation rate ( [Equation 2] ) to obtain the elastic strain [Equation 3] ) is subtracted from the value, and is expressed by the following formulas 4 to 6. [Equation 4] [Equation 5] [Equation 6] where: [Equation 7] is the dimension of the battery module before deformation, L is the dimension of the battery module after deformation, [Equation 8] 8. The method for predicting the impact analysis result of a battery module according to claim 7, wherein σ is the stress value when the material is in its elastic limit state, and E is the elastic modulus of the material.

10. The method of claim 5 , further comprising predicting a score indicating a risk level of the battery module from the deformation rate of the battery module.

11. The score (SCORE) indicating the risk level of the battery module is calculated by the following Equation 9: [Equation 9] The method of claim 10, wherein the score is a value between 0 and 1.

12. If the score is less than 0.4, the battery module is judged to be "safe" in terms of the risk of impact; If the score exceeds 0.6, the risk of impact to the battery module is judged to be "dangerous"; The method of claim 11, further comprising suspending a determination of a risk level due to an impact on the battery module when the score is between 0.4 and 0.

6.

13. the initial state values ​​of the battery module include initial values ​​of the dimensions of the battery module; The method of claim 1 , wherein the deformed state value of the battery module includes a value of a dimension of the battery module after deformation.

14. 14. The method for predicting the impact analysis result of a battery module according to claim 13, wherein the dimensional values ​​of the battery module include at least one of the length, width, height, top thickness, bottom thickness, and side thickness of a predetermined portion of the battery module.

15. The method for predicting a shock analysis result of a battery module according to claim 1 , wherein the initial state value of the battery module includes at least one of the density of the battery cells included in the battery module and the mass of the battery cells.

16. The method of claim 1 , wherein the value of the shock applied to the battery module includes at least one of a magnitude of the shock and a duration for which the shock is applied.

17. 2. A battery module evaluation system for performing the method for predicting the analysis result of a battery module impact according to claim 1, a data input unit for inputting an initial state value of the battery module and an impact value applied to the battery module; a data processing unit that executes an impact analysis model of the battery module; a data output unit that outputs the analysis results of the battery module.

18. The battery module evaluation system according to claim 17 , further comprising a data storage unit that stores an impact analysis model of the battery module.

19. In the learning method for the impact analysis model of the battery module, sampling an initial state value of a battery module and a deformed state value of the battery module according to an impact value applied to the battery module; repeating the sampling step for a predetermined test period to obtain training data; receiving the initial state value and the applied shock value of the battery module for the number of samplings, and machine learning an impact analysis model of the battery module to predict an analysis result of the battery module due to an impact.

20. The sampling step includes: measuring and storing an initial state value of the battery module; storing an impact value applied to the battery module; 20. The method of claim 19, further comprising measuring and storing a state value of deformation of the battery module due to the impact.

21. The method of claim 19 , wherein the machine learning step comprises calculating and storing a deformation rate of the battery module from a deformation state value of the battery module.

22. 20. The method for learning an impact analysis model of a battery module according to claim 19, wherein the initial state value of the battery module is an initial state value of a predetermined portion of the battery module, and the deformed state value of the battery module is a deformed state value of a predetermined portion of the battery module.

23. The method of claim 21 , wherein the deformation rate of the battery module is a plastic strain of the battery module due to the impact.

24. The method for learning an impact analysis model of a battery module according to claim 21 , wherein the deformation rate of the battery module is a deformation rate of a predetermined portion of the battery module.

25. The deformation rate of the battery module ( [Equation 10] ) is the total deformation rate ( [0011] ) to obtain the elastic strain [0012] ) is subtracted from the value, and is expressed by the following formulas 13 to 15: [0013] [0014] [Equation 15] where: [0016] is the dimension of the battery module before deformation, L is the dimension of the battery module after deformation, [Equation 17] 24. The method for learning an impact analysis model of a battery module according to claim 23, wherein σ is the stress value when the material of the battery module is in an elastic limit state, and E is the elastic modulus of the material of the battery module.

26. The method of claim 21 , wherein the machine learning step further comprises calculating and storing a score indicating a risk level of the battery module from a deformation rate of the battery module.

27. The score (SCORE) indicating the risk level of the battery module is calculated by the following Equation 18: [Equation 18] The method for training an impact analysis model for a battery module according to claim 26, wherein the score is a value between 0 and 1.

28. If the score is less than 0.4, the battery module is judged to be "safe" in terms of the risk of impact; If the score exceeds 0.6, the risk of impact to the battery module is judged to be "dangerous"; The method for learning an impact analysis model for a battery module according to claim 27, wherein when the score is between 0.4 and 0.6, a determination of the risk of impact to the battery module is suspended.

29. The initial state value of the battery module includes an initial value of a dimension of the battery module; The method for training an impact analysis model of a battery module according to claim 19 , wherein the deformed state value of the battery module includes a value of a dimension of the battery module after deformation.

30. 30. The method for training an impact analysis model of a battery module as described in claim 29, wherein the dimensional values ​​of the battery module include at least one of the length, width, height, top surface thickness, bottom surface thickness, and side surface thickness of a predetermined portion of the battery module.

31. 30. The method for learning an impact analysis model of a battery module according to claim 29, wherein the initial state value of the battery module includes at least one of the density of the battery cells included in the battery module and the mass of the battery cells.

32. 20. The method of claim 19, wherein the value of the shock applied to the battery module includes at least one of a magnitude of the shock and a duration for which the shock is applied.

33. The method for learning an impact analysis model for a battery module according to claim 32 , wherein the magnitude of the impact is expressed by the acceleration of an object that applies the impact to the battery module.

34. further comprising verifying the validity of the impact analysis of the battery module; The step of verifying the validity includes: generating verification data based on an initial state value of the battery module and a deformed state value of the battery module due to an impact value applied to the battery module during a predetermined verification period; calculating an analysis result of the battery module from an impact analysis model of the battery module using the verification data; calculating an analysis result of the battery module according to an initial state value of the battery module and an impact value applied to the battery module by finite element analysis using the verification data; 20. The method of claim 19, further comprising determining that the impact analysis model of the battery module is valid when a difference between the analysis result of the battery module predicted from the impact analysis model of the battery module and the analysis result of the battery module calculated by the finite element analysis is within a predetermined reference value range.

Images