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

Abstract

A method for learning a battery module impact analysis model according to one embodiment of the present disclosure comprises the steps of: sampling a deformation state value of a battery module according to an initial state value of the battery module and an impact value applied to the battery module; repeating the sampling step during a predetermined test period to obtain learning data; and receiving inputs of an initial state value of the battery module and an impact value applied to the battery module through multiple sampling and performing machine learning on the battery module impact analysis model to predict an analysis result of the battery module due to the impact.

Description

Technical Field

[0001] Cross - Reference to Related Applications

[0002] This application claims the benefit of Korean Patent Application No. 10-2022-0174030, filed with the Korean Intellectual Property Office on December 13, 2022, the disclosure of which is incorporated herein by reference in its entirety.

[0003] The present disclosure relates to a method for learning a battery module impact analysis model and a method for predicting an analysis result of an impact on a battery module, and more particularly, to a method for quickly predicting the impact stability of a battery module by applying machine learning technology. Background Art

[0004] In the development process of a battery module, it is basically necessary to verify the structural safety under specific impact conditions. The method commonly used at present is to perform finite element analysis.

[0005] Although the impact analysis results obtained by finite element analysis are relatively accurate, however, its disadvantages are that modeling and calculation are laborious and time-consuming, and specialized structural analysis software must be used.

[0006] Meanwhile, in the early stage of development, design changes are frequent, and this process has to be repeated every time a change is made, resulting in low operational efficiency. In the process of designing and developing a battery module, including the early stage of the development of the battery module, a method capable of predicting the impact stability of the battery module in a short time is needed. Summary of the Invention

[0007] Technical Problem

[0008] An object of the present disclosure is to provide a method for predicting the stability of a battery module, particularly a method for quickly predicting the impact stability of a battery module by applying machine learning technology.

[0009] However, the technical problems to be solved by the embodiments of the present disclosure are not limited to the above problems, and various extensions can be made within the scope of the technical idea included in the present disclosure.

[0010] Technical Solution

[0011] According to an embodiment of the present disclosure, there is provided a method for predicting an analysis result of an impact on a battery module of a battery module evaluation system, the battery module evaluation system including a battery module impact analysis model, the method including the steps of: receiving an input of an initial state value of the battery module and an impact value applied to the battery module; and predicting an analysis result of the battery module due to the impact according to the battery module impact analysis model.

[0012] The method for predicting the analysis result of an impact on a battery module further includes learning a battery module impact analysis model applied to a battery module evaluation system, wherein learning the battery module impact analysis model may include: sampling the deformation state value of the battery module according to the initial state value of the battery module and the impact value applied to the battery module; repeating the sampling step during a predetermined test period to obtain learning data; and receiving the input of the initial state value of the battery module and the impact value applied to the battery module through multiple samplings and performing machine learning on the battery module impact analysis model to predict the analysis result of the battery module due to the impact.

[0013] The sampling step may include: measuring the initial state value of the battery module and storing the initial state value of the battery module; storing the impact value applied to the battery module; and measuring the deformation state value of the battery module due to the impact and storing the deformation state value of the battery module.

[0014] The step of predicting the analysis result of the battery module may include predicting the deformation state value of the battery module due to the impact.

[0015] The method for predicting the analysis result of an impact on a battery module may include predicting the strain of the battery module based on the deformation state value of the battery module.

[0016] The initial state value of the battery module may be the initial state value of a predetermined part of the battery module, and the deformation state value of the battery module may be the deformation state value of a predetermined part of the battery module.

[0017] The strain of the battery module may be the plastic strain of the battery module due to the impact.

[0018] The strain of the battery module may be the strain of a predetermined part of the battery module.

[0019] The strain of the battery module ( ) is the value obtained by subtracting the elastic strain ( ) from the total strain ( ) at the time of the impact on the battery module, and follows the following mathematical equations 1 to 3,

[0020] [Mathematical Equation 1]

[0021] [Mathematical Equation 2]

[0022] [Mathematical Equation 3]

[0023] Wherein, is the size of the battery module before deformation, is the size of the battery module after deformation, is the stress value when the material is at its elastic limit state, and is the elastic modulus of the material.

[0024] The method for predicting the analysis result of the impact on the battery module may further include predicting a score indicating the degree of danger of the battery module based on the strain of the battery module.

[0025] The score indicating the degree of danger of the battery module follows the following mathematical equation 4,

[0026] [Mathematical Equation 4] Score

[0027] where the score can be a value between 0 and 1.

[0028] If the score is less than 0.4, it is determined that the degree of danger of the battery module due to the impact is "safe", if the score is greater than 0.6, it is determined that the degree of danger of the battery module due to the impact is "dangerous", and if the score is 0.4 or more and less than 0.6, the determination of the degree of danger of the battery module due to the impact can be postponed.

[0029] The initial state value of the battery module includes the initial value of the size of the battery module, and the deformed state value of the battery module may include the size value of the deformed battery module.

[0030] The size value of the battery module may include at least one of the length, width, height, upper thickness, lower thickness, and side thickness of a predetermined part of the battery module.

[0031] 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.

[0032] The impact value applied to the battery module may include at least one of the impact magnitude and the duration of the applied impact.

[0033] According to another embodiment of the present disclosure, there is provided a battery module evaluation system that executes a method for predicting the analysis result of the impact on the battery module. The battery module evaluation system includes: a data input unit that receives the input of the initial state value of the battery module and the impact value applied to the battery module; a data processing unit that executes a battery module impact analysis model; and a data output unit that outputs the analysis result of the battery module.

[0034] The battery module evaluation system may further include a data storage unit that stores the battery module impact analysis model.

[0035] According to another embodiment of the present disclosure, a method for learning a battery module shock analysis model is provided, the method comprising the steps of: sampling a deformation state value of a battery module according to an initial state value of the battery module and a shock value applied to the battery module; repeating the sampling step during a predetermined test period to obtain learning data; and receiving an input of the initial state value of the battery module and the shock value applied to the battery module sampled multiple times and performing machine learning on the battery module shock analysis model to predict an analysis result of the battery module due to the shock.

[0036] The sampling step may include: measuring an initial state value of the battery module and storing the initial state value of the battery module; storing a shock value applied to the battery module; and measuring a deformation state value of the battery module due to the shock and storing the deformation state value of the battery module.

[0037] The initial state value of the battery module may be an initial state value of a predetermined part of the battery module, and the deformation state value of the battery module may be a deformation state value of a predetermined part of the battery module.

[0038] The machine learning step may include calculating a strain of the battery module according to the deformation state value of the battery module and storing the strain of the battery module.

[0039] The strain of the battery module may be a plastic strain of the battery module due to the shock.

[0040] The strain of the battery module may be a strain of a predetermined part of the battery module.

[0041] The strain of the battery module ( ) is a value obtained by subtracting an elastic strain ( ) from a total strain ( ) at the time of the shock of the battery module, and follows the following mathematical equations 1 to 3,

[0042] [Mathematical Equation 1]

[0043] [Mathematical Equation 2]

[0044] [Mathematical Equation 3]

[0045] Wherein, is the size of the battery module before deformation, is the size of the battery module after deformation, is the stress value when the material of the battery module is in its elastic limit state, and is the elastic modulus of the material.

[0046] The machine learning step may also include calculating a score indicating the degree of danger of the battery module based on the strain of the battery module and storing the score.

[0047] The score indicating the degree of danger of the battery module follows the following mathematical equation 4,

[0048] [Mathematical equation 4] Score

[0049] wherein, the score may be a value between 0 and 1.

[0050] If the score is less than 0.4, it is determined that the degree of danger of the battery module due to the impact is "safe"; if the score is greater than 0.6, it is determined that the degree of danger of the battery module due to the impact is "dangerous"; and if the score is above 0.4 and below 0.6, the determination of the degree of danger of the battery module due to the impact may be postponed.

[0051] The initial state value of the battery module may include the initial value of the size of the battery module, and the deformed state value of the battery module may include the size value of the deformed battery module.

[0052] The size value of the battery module may include at least one of the length, width, height, upper thickness, lower thickness, and side thickness of a predetermined part of the battery module.

[0053] 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.

[0054] The impact value applied to the battery module may include at least one of the impact magnitude and the duration of the applied impact.

[0055] The impact magnitude may be represented by the acceleration of the object applying the impact to the battery module.

[0056] The method for learning the battery module impact analysis model may also include verifying the effectiveness of the impact analysis of the battery module. Among them, verifying the effectiveness includes: generating the initial state value of the battery module and the deformed state value of the battery module according to the impact value applied to the battery module as verification data during a predetermined verification period; using the verification data to calculate the analysis result of the battery module according to the battery module impact analysis model; through finite element analysis, using the verification data to calculate the analysis result of the battery module according to the initial state value of the battery module and the impact value applied to the battery module; and when the difference between the analysis result of the battery module predicted according to the battery module impact analysis model and the analysis result of the battery module calculated by finite element analysis is within a predetermined reference value range, determining that the battery module impact analysis model is effective.

[0057] Beneficial effects

[0058] According to the present disclosure, the impact stability of a battery module can be predicted quickly, and thus, the design and development of an electrode module can be efficiently performed.

[0059] In addition, the conditions and prediction results of the impact stability of the battery module can also be standardized. Thus, the reliability of the quality of the manufactured battery module can be ensured.

[0060] The effects obtainable from the present disclosure are not limited to the above effects, and other additional effects not mentioned herein will be clearly understood by those skilled in the art from the description of the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a block diagram showing a battery module evaluation system 100 according to an embodiment of the present disclosure.

[0062] Figure 2 is a flowchart of a method of learning a battery module impact analysis model executed in a battery module evaluation system 100 according to an embodiment of the present disclosure.

[0063] Figure 3 is a flowchart showing a method of predicting an impact analysis result of a battery module performed by a battery module evaluation system 100 including a battery module impact analysis model according to an embodiment of the present disclosure.

[0064] Figure 4 is an analysis result of an impact on a battery module according to an embodiment of the present disclosure, and graphically shows a score calculated based on the strain of the battery module. DETAILED DESCRIPTION

[0065] Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the drawings. However, regardless of the reference numerals, the same or similar elements are assigned the same reference numerals, and redundant descriptions thereof will be omitted.

[0066] The suffixes “module” and / or “part” of the elements used in the following description are assigned or used only for the convenience of description of the specification, and the suffixes themselves do not have a meaning or function for distinguishing each other. In addition, terms such as “... part”, “... unit” and “module” described in the specification mean a unit for performing at least one function or operation, which can be embodied by hardware, by software, or by a combination of hardware and software.

[0067] In the following description of the present disclosure, when the detailed description of known functions and configurations incorporated herein may obscure the subject matter of the present disclosure, the detailed description will be omitted. In addition, the drawings are only for easy understanding of the embodiments disclosed in this specification. However, the technical ideas disclosed herein are not limited by the drawings and should be construed to include all changes, equivalents, and alternatives within the spirit and scope of the present disclosure.

[0068] In this specification, terms such as "including" or "having" are intended to indicate the presence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. However, it should be understood that this does not exclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0069] Figure 1 is a block diagram showing a battery module evaluation system 100 according to an embodiment of the present disclosure. The battery module evaluation system 100 according to an embodiment of the present disclosure includes a data input unit 110, a data processing unit 120, and a data output unit 130.

[0070] For example, the data input unit 110 may be an input device of a mobile device, an input device of a computer, various keyboards, mice, electronic pens, microphones, etc., and as long as it is a unit capable of receiving the input of other data.

[0071] The data processing unit 120 receives the input of learning data and performs machine learning on the battery module shock analysis model according to an embodiment of the present disclosure. When predicting the analysis result of the shock to the battery module, it can receive the input of the initial state value of the battery module and the shock value applied to the module, and use the battery module shock analysis model to predict the analysis result of the shock to the battery module. For example, the data processing unit 120 may be a processor of a mobile device, a processor of a computer, etc., and as long as it is a device capable of executing the method for learning the battery module shock analysis model according to an embodiment of the present disclosure and the method for predicting the analysis result of the shock to the battery module.

[0072] The data output unit 130 outputs the result processed 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, etc., and as long as it is a unit capable of outputting other data.

[0073] The data storage unit 140 can store the battery module shock analysis model according to an embodiment of the present disclosure, and can also store learning data, data input to the data input unit 110, processing results in the data processing unit 120, various other data, etc.

[0074] 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 one 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 remotely connected to other components and controlled by other components.

[0075] The battery module shock analysis model according to an embodiment of the present disclosure can be obtained through machine learning.

[0076] First, a method for learning the battery module shock analysis model will be described.

[0077] Figure 2 It is a flowchart of a method for learning a battery module shock analysis model executed in the battery module evaluation system 100 according to an embodiment of the present disclosure.

[0078] First, the data processing unit 120 executes step S110, which samples the deformation state value of the battery module according to the initial state value of the battery module and the shock value applied to the battery module. In step S110, the data input unit 110 receives the input of the initial state value of the battery module and the shock value applied to the battery module, and the data processing unit 120 executes step S110.

[0079] In addition, the data sampled in step S110 is stored in the data storage unit 140. More specifically, it includes the following steps: the step of measuring the initial state value of the battery module and storing it in the data storage unit 140 (S111); the step of applying a shock to the battery module and storing the shock value applied to the battery module in the data storage unit 140 (S112); and the step of measuring the deformation state value of the battery module due to the shock and storing it in the data storage unit 140 (S113).

[0080] Here, the initial state value of the battery module means the initial state value of a predetermined part of the battery module. The predetermined part of the battery module may be a battery module part that is pre-specified (preset) by an operator according to needs such as the process and environment. This is because when a shock is applied to the battery module, the size and other conditions of the battery module may mainly deform in the area where the shock is applied. However, the present disclosure is not limited to the above, and the predetermined part of the battery module may be the entire battery module. In addition, the initial state value of the battery module includes the initial size value of the battery module. The deformation state value of the battery module due to the shock means the deformation state value of a predetermined part of the battery module. In addition, the deformation state of the predetermined part of the battery module includes the size value in which the initial size has been deformed due to the shock applied to the battery module.

[0081] The dimensional value of the battery module means the dimensional value of a predetermined part of the battery module. The dimensional value of the battery module (i.e., the dimensional value of a predetermined part of the battery module) includes at least one of the length, width, height, upper thickness, lower thickness, and side thickness of the predetermined part of the battery module. Regarding the detailed factors included in the dimensional value of the battery module, the present disclosure is not limited to the above, and these factors can be set in various ways according to the environment in which the present invention is embodied or the conditions required by the operator.

[0082] For example, the total length, width, and height of the battery module can be set as the dimensional value of the battery module. However, if the battery module is composed of a U-shaped frame and a top plate covering it, various variations and changes can be made. For example, the length, width, and height of the U-shaped frame can be individually set as the dimensional value of the battery module, and the length, width, and height of the top plate can be individually set as the dimensional value of the battery module. In addition, the dimensional values of only the frame or the plate can be considered, focusing on the part where the impact is applied.

[0083] In addition, 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.

[0084] The impact value applied to the battery module includes at least one of the impact magnitude and the duration of the applied impact. Examples of the factors (physical quantities) representing the impact magnitude include the acceleration of the object that impacts the battery module. However, the present disclosure is not limited to the above, and the impact on the battery module can be analyzed by selecting various physical quantities indicating the impact magnitude to match the environment in which the present invention is embodied or the conditions required by the operator.

[0085] The deformation state value of the battery module due to the impact can be state information such as a temperature change, fire, or explosion of the battery module depending on the situation.

[0086] The data processing unit 120 repeats the sampling step S110 within a predetermined test period to obtain learning data S120. In step S120, similarly, the data input unit 11 receives the input of the initial state value of the battery module and the impact value applied to the battery module, and the data processing unit 120 executes step S120. In addition, the learning data obtained in step S120 is stored in the data storage unit 140.

[0087] The data processing unit 120 executes step S130, which receives the input of the initial state value of the battery module and the impact value applied to the battery module through multiple samplings and performs machine learning on the battery module impact analysis model to predict the analysis result of the battery module due to the impact.

[0088] Step S130 includes step S131, which is used to calculate the strain of the battery module according to the deformation state value of the battery module by the data processing unit 120 and store the strain in the data storage unit 140.

[0089] At this time, the strain of the battery module means the strain of a predetermined part of the battery module. For the predetermined part of the battery module, refer to the above part.

[0090] In addition, the strain of the battery module means the plastic strain of the battery module generated due to impact ( ). The strain of the battery module ( ) is the value obtained by subtracting the elastic strain ( ) from the total strain ( ) at the time of impact of the battery module, and follows the following mathematical equations 1 to 3,

[0091] [Mathematical Equation 1]

[0092] [Mathematical Equation 2]

[0093] [Mathematical Equation 3]

[0094] Among them, is the size of the battery module before deformation (i.e., the size of the predetermined part of the battery module before deformation), is the size of the battery module after deformation (i.e., the size of the predetermined part of the battery module after deformation). In addition, is the stress value when the material (the material of the battery module, i.e., the material of the predetermined part of the battery module) is in its elastic limit state, and is the elastic modulus of the material. When the material (the material of the battery module, i.e., the material of the predetermined part of the battery module) is deformed within its elastic limit, stress and strain have a linear relationship with each other, and the slope is called the elastic modulus. and each of which is a unique value for the battery module to be inspected (i.e., the material of the battery module) and is input as a preset value. Alternatively, the elastic strain ( ) derived from Mathematical Equation 3 is also a unique value for the battery module to be inspected (i.e., the material of the battery module), so the elastic strain ( ) is input as a preset value. As described above, the size of the battery module includes at least one of the length, width, height, upper thickness, lower thickness, and side thickness of the predetermined part of the battery module.

[0095] The strain of each battery module is derived by applying Mathematical Equation 1 to Mathematical Equation 3 to each factor of the length, width, height, upper surface thickness, lower surface thickness, and side thickness of a predetermined part of the battery module ( ), and then the average value of the strain of each battery module derived for each factor of the length, width, height, upper surface thickness, lower surface thickness, and side thickness of a predetermined part of the battery module can be determined, or alternatively, the maximum value among the strains of each battery module ( ). ) can be determined.

[0096] Alternatively, in some cases, only some factors suitable for the environment are selected from the length, width, height, upper surface thickness, lower surface thickness, and side thickness of a predetermined part of the battery module to derive the strain of the battery module respectively ( ). Similarly, the average value of the strain of each battery module ( ) can be determined, or the maximum value can be determined.

[0097] In addition, step S130 further includes step S132 of calculating a score representing the degree of danger of the battery module based on the strain of the battery module calculated in step S131.

[0098] For example, the score indicating the degree of danger of the battery module follows the following Mathematical Equation 4.

[0099] [Mathematical Equation 4] Score

[0100] This is a value obtained by arbitrarily scaling the plastic strain of the battery module ( ), such that when 0 ≤ the plastic strain of the battery module ( ) ≤ 1, the score is a value between 0 and 1 (see Figure 4 ).

[0101] Mathematical Equation 4 is an example, and the present disclosure is not limited to the above. The score can be adjusted according to various environments embodying the present invention.

[0102] [Mathematical Equation 5] Score .

[0103] Wherein, C1, C2, C3, and C4 are coefficients.

[0104] In addition, this can also be classified into each grade according to the score calculated in step S132.

[0105] For example, if the score is less than 0.4, the determined risk level of the battery module due to the impact is "safe"; if the score is greater than 0.6, the determined risk level of the battery module due to the impact is "dangerous"; and if the score is 0.4 or more and 0.6 or less, the determination of the risk level of the battery module due to the impact can be postponed. This is an example, and the present disclosure is not limited to the above content.

[0106] For example, the levels of the risk level can be classified into different numbers of levels instead of the above three levels, and the range in which the score calculated according to the coefficient value set in Mathematical Equation 5 is scaled is also different. Therefore, various changes and modifications can be made. For example, the standard values for dividing the levels can be values other than the above 0.4 and 0.6.

[0107] In addition, the data processing unit 120 executes step S140 of verifying the effectiveness of the impact analysis of the battery module.

[0108] Step S140 includes the following steps: a step (S141) of generating an initial state value of the battery module and a deformed state value of the battery module according to the impact value applied to the battery module as verification data during a predetermined verification period; a step (S142) of using the verification data to calculate an analysis result of the battery module according to the battery module impact analysis model; a step (S143) of calculating an analysis result of the battery module by finite element analysis using the verification data according to the initial state value of the battery module and the impact value applied to the battery module; and a step (S144) of determining that the battery module impact analysis model is effective when the difference between the analysis result of the battery module predicted according to the battery module impact analysis model and the analysis result of the battery module calculated by finite element analysis is within a predetermined reference value range.

[0109] Figure 3 is a flowchart showing a method for predicting an analysis result of an impact on a battery module performed by a battery module evaluation system 100 including a battery module impact analysis model according to an embodiment of the present disclosure.

[0110] The battery module evaluation system 100 executes the method for learning the battery module impact analysis model described above with reference to Figure 2 The battery module impact analysis model can be obtained by machine learning in the data processing unit 120 and stored in the data storage unit 140. According to an embodiment of the present disclosure, the battery module evaluation system 100 predicts an analysis result of an impact on the battery module through the battery module impact analysis model learned by machine learning.

[0111] First, the data processing unit 120 executes step S210 of receiving an input of an initial state value of the battery module and an impact value applied to the battery module.

[0112] Among them, the initial state value of the battery module includes the initial dimension value of the battery module. The initial dimension value of the battery module includes at least one of the length, width, height, upper thickness, lower thickness, and side thickness of a predetermined portion of the battery module. In addition, 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. The impact value applied to the battery module includes at least one of the impact magnitude and the duration of the applied impact.

[0113] Perform step S220 of analyzing the result of predicting the impact on the battery module according to the battery module impact analysis model.

[0114] Step S220 includes step S221 of predicting the deformation state value of the battery module due to the impact. Here, the deformation state value of the battery module due to the impact includes the dimension value in which the initial dimension is deformed due to the impact applied to the battery module. The deformed dimension value of the battery module, that is, the dimension of the deformed battery module, includes at least one of the length, width, height, upper thickness, lower thickness, and side thickness of a predetermined portion of the battery module. The deformation state value of the battery module due to the impact may be state information such as a temperature change, fire, or explosion of the battery module depending on the situation.

[0115] In addition, step S220 includes step S222 of predicting the strain of the battery module according to the deformation state value of the battery module predicted in step S221.

[0116] At this time, the strain of the battery module means the plastic strain of the battery module due to the impact ( ). The strain of the battery module ( ) is the value obtained by subtracting the elastic strain ( ) from the total strain ( ) at the time of the impact of the battery module, and follows the following mathematical equations 1 to 3,

[0117] [Mathematical Equation 1]

[0118] [Mathematical Equation 2]

[0119] [Mathematical Equation 3]

[0120] Among them, is the dimension of the battery module before deformation, and are the dimensions of the deformed battery module. The dimensions of the battery module include at least one of the length, width, height, upper thickness, lower thickness, and side thickness of the above-mentioned battery module. The dimensions of the battery module can be set by being deformed and changed in various ways. Refer to the above reference Figure 2 for content.

[0121] The strain of each battery module is derived by applying Mathematical Equations 1 to 3 to each factor of the length, width, height, upper thickness, lower thickness, and side thickness of the predetermined part of the battery module ( ), and then the average value of the strain of each battery module derived for each factor of the length, width, height, upper thickness, lower thickness, and side thickness of the predetermined part of the battery module can be obtained ( ), or alternatively, the maximum value among the strains of each battery module ( ) can be obtained.

[0122] Alternatively, in some cases, only some factors suitable for the environment are selected from the length, width, height, upper thickness, lower thickness, and side thickness of the predetermined part of the battery module to separately derive the strain of the battery module ( ). Similarly, the average value of the strain of each battery module can be determined ( ), or the maximum value can be determined.

[0123] In addition, step S220 further includes step S223 for calculating a score indicating the degree of danger of the battery module according to the strain of the battery module predicted in step S222.

[0124] For example, the score indicating the degree of danger of the battery module follows the following Mathematical Equation 4.

[0125] [Mathematical Equation 4] Score

[0126] This is a value obtained by arbitrarily scaling the plastic strain of the battery module ( ), such that when 0 ≤ the plastic strain of the battery module ( ) ≤ 1, the score is a value between 0 and 1 (see Figure 4 ).

[0127] Mathematical Formula 4 is an example, and the present disclosure is not limited to the above content. The score can be adjusted according to various environments embodying the present invention.

[0128] [Mathematical Equation 5] Score

[0129] where C1, C2, C3, and C4 are coefficients.

[0130] In addition, this can be classified into each grade according to the score calculated in step S132.

[0131] For example, if the score is less than 0.4, it is determined that the risk level of the battery module due to impact is "safe"; if the score is greater than 0.6, it is determined that the risk level of the battery module due to impact is "dangerous"; and if the score is 0.4 or more and 0.6 or less, the determination of the risk level of the battery module due to impact can be postponed. This is an example, and the present disclosure is not limited to the above content.

[0132] For example, the grades of the risk level can be classified into different numbers of grades instead of the above three grades, and the range in which the score calculated according to the coefficient value set in mathematical equation 5 is scaled is also different. Therefore, various changes and modifications can be made. For example, the standard values for dividing grades can be values other than 0.4 and 0.6 described above.

[0133] Compared with the conventional finite element analysis technology, the method for predicting the impact on the battery module using the battery module impact analysis model according to the present disclosure shows a matching rate of more than about 90%. On the other hand, compared with the conventional technology, the impact stability of the battery module can be predicted quickly, and therefore, the design and development of the electrode module can be carried out efficiently. In addition, it also enables the standardization of the conditions and prediction results of the impact stability of the battery module. Therefore, the reliability of the quality of the manufactured battery module can be ensured.

[0134] Although the present invention has been described in detail above with reference to the preferred embodiments of the present invention, those skilled in the art will recognize that the scope of the present disclosure is not limited thereto, and various modifications and improvements can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. For example, the method for learning the battery module impact analysis model and the method for predicting the analysis result of the impact on the battery module according to the present disclosure can be applied not only to battery modules but also to battery cells, battery cell stacks, or battery packs.

[0135] (Description of reference numerals)

[0136] 100: Battery module evaluation system

[0137] 110: Data input unit

[0138] 120: Data processing unit

[0139] 130: Data output unit

[0140] 140: Data storage unit

Claims

1. A method for predicting the analysis result of the impact on a battery module of a battery module evaluation system, the battery module evaluation system including a battery module impact analysis model, the method comprising the following steps: Receiving an input of the initial state value of the battery module and the impact value applied to the battery module; and Predicting the analysis result of the battery module due to the impact according to the battery module impact analysis model.

2. The method for predicting the analysis result of the impact on a battery module according to claim 1, further comprising learning the battery module impact analysis model applied to the battery module evaluation system, Among them, learning the battery module impact analysis model includes: Sampling the deformation state value of the battery module according to the initial state value of the battery module and the impact value applied to the battery module; Repeating the sampling step during a predetermined test period to obtain learning data; and Receiving an input of the initial state value of the battery module and the impact value applied to the battery module by multiple samplings and performing machine learning on the battery module impact analysis model to predict the analysis result of the battery module due to the impact.

3. The method for predicting the analysis result of the impact on a battery module according to claim 2, wherein: The sampling step includes: Measuring the initial state value of the battery module and storing the initial state value of the battery module; Storing the impact value applied to the battery module; and Measuring the deformation state value of the battery module due to the impact and storing the deformation state value of the battery module.

4. The method for predicting the analysis result of the impact on a battery module according to claim 1, wherein: Predicting the analysis result of the battery module includes predicting the deformation state value of the battery module due to the impact.

5. The method for predicting the analysis result of the impact on a battery module according to claim 4, including predicting the strain of the battery module according to the deformation state value of the battery module.

6. The method for predicting the analysis result of the impact on a battery module according to claim 1, wherein: The initial state value of the battery module is the initial state value of a predetermined part of the battery module, and the deformation state value of the battery module is the deformation state value of the predetermined part of the battery module.

7. The method for predicting the analysis result of the impact on a battery module according to claim 5, wherein: The strain of the battery module is the plastic strain of the battery module due to the impact.

8. The method for predicting the analysis result of the impact on a battery module according to claim 5, wherein: The strain of the battery module is the strain of a predetermined part of the battery module.

9. The method for predicting the analysis result of the impact on a battery module according to claim 7, wherein: The strain ( ) of the battery module is a value obtained by subtracting the elastic strain ( ) from the total strain ( ) at the time of the impact of the battery module, and follows the following mathematical equations 1 to 3, [Mathematical Equation 1] [Mathematical Equation 2] [Mathematical Equation 3] Among them, is the size of the battery module before deformation, is the size of the battery module after deformation, is the stress value when the material is at its elastic limit state, and is the elastic modulus of the material.

10. The method for predicting the analysis result of the impact on a battery module according to claim 5, It also includes predicting a score indicating the degree of danger of the battery module based on the strain of the battery module.

11. The method for predicting the analysis result of an impact on a battery module according to claim 10, wherein: The score indicating the degree of danger of the battery module follows the following mathematical equation 4, [Mathematical Equation 4] Fraction wherein the score is a value between 0 and 1.

12. The method for predicting the analysis result of an impact on a battery module according to claim 11, wherein: If the score is less than 0.4, it is determined that the degree of danger of the battery module due to the impact is "safe", If the score is greater than 0.6, it is determined that the degree of danger of the battery module due to the impact is "dangerous", and If the score is 0.4 or more and 0.6 or less, the determination of the degree of danger of the battery module due to the impact is postponed.

13. The method for predicting the analysis result of an impact on a battery module according to claim 1, wherein: The initial state value of the battery module includes the initial value of the size of the battery module, and The deformed state value of the battery module includes the size value of the deformed battery module.

14. The method for predicting the analysis result of an impact on a battery module according to claim 13, wherein: The size value of the battery module includes at least one of the length, width, height, upper thickness, lower thickness, and side thickness of a predetermined part of the battery module.

15. The method for predicting the analysis result of an impact on 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 for predicting the analysis result of an impact on a battery module according to claim 1, wherein: The impact value applied to the battery module includes at least one of the impact magnitude and the duration of applying the impact.

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

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

19. A method for learning a battery module impact analysis model, the method comprising the following steps: Sampling the deformed state value of the battery module according to the initial state value of the battery module and the impact value applied to the battery module; Repeating the sampling step during a predetermined test period to obtain learning data; And Receive the input of the initial state value of the battery module through multiple samplings and the shock value applied to the battery module, and perform machine learning on the battery module shock analysis model to predict the analysis result of the battery module due to the shock.

20. The method for learning a battery module shock analysis model according to claim 19, wherein: The sampling step includes: Measuring the initial state value of the battery module and storing the initial state value of the battery module; Storing the shock value applied to the battery module; and Measuring the deformation state value of the battery module due to the shock and storing the deformation state value of the battery module.

21. The method for learning a battery module shock analysis model according to claim 19, wherein: The machine learning step includes calculating the strain of the battery module based on the deformation state value of the battery module and storing the strain of the battery module.

22. The method for learning a battery module shock analysis model according to claim 19, wherein: The initial state value of the battery module is the initial state value of a predetermined part of the battery module, and the deformation state value of the battery module is the deformation state value of the predetermined part of the battery module.

23. The method for learning a battery module shock analysis model according to claim 21, wherein: The strain of the battery module is the plastic strain of the battery module due to the shock.

24. The method for learning a battery module shock analysis model according to claim 21, wherein: The strain of the battery module is the strain of a predetermined part of the battery module.

25. The method for learning a battery module shock analysis model according to claim 23, wherein: The strain ( ) of the battery module is a value obtained by subtracting the elastic strain ( ) from the total strain ( ) at the time of impact of the battery module, and follows the following mathematical equations 1 to 3, [Mathematical Equation 1] [Mathematical equation 2] [Mathematical Equation 3] Wherein, is the size of the battery module before deformation, is the size of the battery module after deformation, is the stress value when the material of the battery module is at its elastic limit state, and is the elastic modulus of the material.

26. The method for learning a battery module shock analysis model according to claim 21, wherein: The machine learning step further includes calculating a score indicating the degree of danger of the battery module based on the strain of the battery module and storing the score.

27. The method for learning a battery module shock analysis model according to claim 26, wherein: The score indicating the degree of danger of the battery module follows the following mathematical equation 4, [Mathematical Equation 4] Fraction wherein the score is a value between 0 and 1.

28. The method for learning a battery module shock analysis model according to claim 27, wherein: If the score is less than 0.4, it is determined that the degree of danger of the battery module due to the shock is "safe", If the score is greater than 0.6, it is determined that the degree of danger of the battery module due to the shock is "dangerous", and If the score is above 0.4 and below 0.6, the determination of the degree of danger of the battery module due to the shock is postponed.

29. The method for learning a battery module shock analysis model according to claim 19, wherein: The initial state value of the battery module includes an initial value of the size of the battery module, and the deformed state value of the battery module includes a size value of the deformed battery module.

30. The method for learning a shock analysis model of a battery module according to claim 29, wherein: the size value of the battery module includes at least one of a length, a width, a height, a top thickness, a bottom thickness, and a side thickness of a predetermined portion of the battery module.

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

32. The method for learning a shock analysis model of a battery module according to claim 19, wherein: the shock value applied to the battery module includes at least one of a shock magnitude and a duration of applying the shock.

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

34. The method for learning a shock analysis model of a battery module according to claim 19, further comprising verifying the validity of the shock analysis of the battery module, Among them, wherein verifying the validity includes: generating, during a predetermined verification period, the initial state value of the battery module and the deformed state value of the battery module according to the shock value applied to the battery module as verification data; using the verification data, calculating an analysis result of the battery module according to the battery module shock analysis model; through finite element analysis, using the verification data, calculating an analysis result of the battery module according to the initial state value of the battery module and the shock value applied to the battery module; and when a difference between the analysis result of the battery module predicted according to the battery module shock analysis model and the analysis result of the battery module calculated through the finite element analysis is within a predetermined reference value range, determining that the battery module shock analysis model is valid.

Images