Battery pack structure parameter determination method and device, battery pack and vehicle

Abstract

The invention discloses a battery pack structure parameter determination method and device, a battery pack and a vehicle, and the method comprises the steps: obtaining the mechanical characteristics and energy absorption characteristics of deformation of a battery pack shell corresponding to multiple groups of candidate structure parameters under a set collision working condition through a prediction model, and obtaining the structural parameters of the battery pack based on the mechanical characteristics and energy absorption characteristics; according to the method, target structure parameters enabling the mechanical and energy absorption characteristics of the battery pack shell to be optimal are efficiently determined, that is, the optimal thicknesses of the inner-layer material, the middle-layer material and the outer-layer material are rapidly determined, so that the battery pack shell has the good mechanical and energy absorption characteristics in the aspects of strength and energy absorption under the set collision working condition. And meanwhile, multi-directional demand balance is achieved in the aspects of mechanical property, energy absorption property, light weight and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to a method and device for determining battery pack structure parameters, a battery pack, and a vehicle. Background Art

[0002] With the rapid development of the new energy vehicle industry, as a core component of the vehicle body structure, the battery pack housing not only needs to bear the weight of the battery pack, but also must have excellent energy absorption characteristics to ensure safety in a collision accident.

[0003] With the progress of research technology, there are more and more types of battery pack housing materials. When designing the housing structure of the battery pack, in order to determine appropriate structure parameters to achieve a multi-faceted requirement balance in terms of strength, energy absorption, and lightweight, a large number of comparative experiments need to be designed. Therefore, the cost is high and the time consumption is long. Summary of the Invention

[0004] The present application provides a method and device for determining battery pack structure parameters, a battery pack, and a vehicle to solve the technical problem of high cost and long time consumption in the existing design of the battery pack housing structure.

[0005] In view of the above problems, the present application is proposed to provide a method and device for determining battery pack structure parameters, a battery pack, and a vehicle that overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect, a method for determining battery pack structure parameters is provided, including:

[0007] Obtain multiple groups of candidate structure parameters of the battery pack housing, where the battery pack housing includes an inner layer material, a middle layer material, and an outer layer material arranged in sequence, and the multiple groups of candidate structure parameters include multiple combinations of the candidate thickness of the inner layer material, the candidate thickness of the middle layer material, and the candidate thickness of the outer layer material;

[0008] For each group of candidate structure parameters, input the candidate structure parameters into a preset prediction model to obtain prediction data, where the prediction data is parameter data for indicating the mechanical characteristics and energy absorption characteristics of the battery pack housing corresponding to the candidate structure parameters under the set collision condition;

[0009] Based on the prediction data corresponding to each group of candidate structure parameters, determine the target structure parameters of the battery pack housing from the multiple groups of candidate structure parameters.

[0010] Optionally, based on the prediction data corresponding to each group of candidate structure parameters, determining the target structure parameters of the battery pack housing from the multiple groups of candidate structure parameters includes:

[0011] Input the prediction data corresponding to each group of candidate structural parameters into a preset multi-objective optimization model to obtain the objective function values corresponding to the prediction data, where the multi-objective optimization model includes an objective function and constraint conditions;

[0012] Use the candidate structural parameters corresponding to the prediction data with the smallest objective function value as the target structural parameters of the battery pack housing.

[0013] Optionally, the prediction data includes the stress prediction value, deformation prediction value, and energy absorption prediction value of the deformation of the battery pack housing corresponding to each group of candidate structural parameters under the set collision condition; the multi-objective optimization model includes an objective function and constraint conditions, and the objective function is expressed as:

[0014] f(S,D,E) = P(S) + P(D) - R(E);

[0015]

[0016] R(E) = γ×E;

[0017] The constraint conditions are

[0018] In the formula, f(S,D,E) is the objective function, P(S) is the first penalty term, α is the first penalty coefficient, S is the stress prediction value, and S max is the stress upper limit value; P(D) is the second penalty term, β is the second penalty coefficient, D is the deformation prediction value, and D max is the deformation upper limit value; R(E) is the first reward term, γ is the first reward coefficient, and E is the energy absorption prediction value.

[0019] Optionally, the prediction model is obtained by the following operations:

[0020] Construct an initialized support vector regression model as the initial prediction model;

[0021] Obtain sample data, which includes: multiple groups of sample structural parameters of the battery pack housing samples, and the mechanical properties and energy absorption properties of the deformation of the battery pack housing samples corresponding to each group of sample structural parameters. Among them, the battery pack housing samples include an inner layer material, a middle layer material, and an outer layer material arranged in sequence. The multiple groups of sample structural parameters include multiple combinations of the thickness of the inner layer material of the battery pack housing sample, the thickness of the middle layer material of the battery pack housing sample, and the thickness of the outer layer material of the battery pack housing sample;

[0022] Train the initial prediction model based on the sample data to obtain the prediction model.

[0023] Optionally, the mechanical properties and energy absorption properties of the battery pack housing samples corresponding to each set of sample structure parameters during deformation under the set collision condition are obtained by the following operations:

[0024] Based on each set of sample structure parameters, a finite element model of the battery pack housing sample is constructed, and collision simulation is performed based on the finite element model to determine the mechanical properties and energy absorption properties of the battery pack housing sample corresponding to the sample structure parameters during deformation under the set collision condition.

[0025] Optionally, the target structure parameters of the battery pack housing include the optimized thickness of the inner layer material, the optimized thickness of the middle layer material, and the optimized thickness of the outer layer material; wherein, the inner layer material is glass fiber reinforced plastic or carbon fiber reinforced composite material, and the value range of the optimized thickness of the inner layer material is [1 mm, 2 mm]; the middle layer material is aluminum foam, and the value range of the optimized thickness of the middle layer material is [3 mm, 5 mm]; the outer layer material is pure aluminum alloy, and the value range of the optimized thickness of the outer layer material is [1 mm, 2.5 mm].

[0026] In a second aspect, the present application provides a device for determining battery pack structure parameters, including:

[0027] An acquisition unit, configured to acquire multiple sets of candidate structure parameters of the battery pack housing, the battery pack housing includes an inner layer material, a middle layer material, and an outer layer material arranged in sequence, and the multiple sets of candidate structure parameters include multiple combinations of the candidate thickness of the inner layer material, the candidate thickness of the middle layer material, and the candidate thickness of the outer layer material;

[0028] A prediction unit, configured to input the candidate structure parameters into a preset prediction model for each set of candidate structure parameters to obtain prediction data, and the prediction data is used to indicate the mechanical properties and energy absorption properties of the battery pack housing corresponding to the candidate structure parameters during deformation under the set collision condition;

[0029] A determination unit, configured to determine the target structure parameters of the battery pack housing from the multiple sets of candidate structure parameters based on the prediction data corresponding to each set of candidate structure parameters.

[0030] Optionally, the determination unit includes:

[0031] A multi-objective optimization unit, configured to input the prediction data corresponding to each set of candidate structure parameters into a preset multi-objective optimization model to obtain the objective function value corresponding to the prediction data, wherein the multi-objective optimization model includes an objective function and constraint conditions;

[0032] A value-taking unit, configured to use the candidate structure parameters corresponding to the prediction data with the minimum objective function value as the target structure parameters of the battery pack housing.

[0033] In a third aspect, a battery pack is provided, including a battery pack housing, and the structural parameters of the battery pack housing are obtained by using the method of the first aspect.

[0034] In a fourth aspect, a vehicle is provided, including the battery pack of the third aspect.

[0035] In a fifth aspect, the present application further provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the server is caused to execute the method provided in the first aspect.

[0036] In a sixth aspect, the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the computer is caused to execute the method provided in the first aspect.

[0037] In a seventh aspect, the present application further provides a computer program product, including a computer program. When the computer program is run on a computer, the computer is caused to execute the method provided in the first aspect.

[0038] The technical solutions provided by the present application have at least the following technical effects or advantages:

[0039] The method, device, battery pack, and vehicle for determining the structural parameters of the battery pack housing provided by the present application utilize a prediction model to obtain the mechanical properties and energy absorption properties of the deformation of the battery pack housing corresponding to multiple sets of candidate structural parameters under set collision condition. Based on the mechanical properties and energy absorption properties, the target structural parameters that optimize the mechanical and energy absorption properties of the battery pack housing are efficiently determined, that is, the optimal thicknesses of the inner layer material, the middle layer material, and the outer layer material are quickly determined, so that the battery pack housing has good mechanical and energy absorption properties in terms of strength under the set collision condition, and at the same time achieves a multi-faceted requirement balance in terms of mechanical properties, energy absorption properties, and lightweight. Description of the Drawings

[0040] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0041] Figure 1 is a flowchart of the method for determining the structural parameters of the battery pack housing in an embodiment of the present application;

[0042] Figure 2 is a flowchart of the construction of the prediction model in an embodiment of the present application;

[0043] Figure 3Schematic diagram of the multi-layer material structure of the battery pack housing in the embodiment of the present application;

[0044] Figure 4 Schematic diagram of the stress distribution after the simulated collision analysis of the aluminum alloy battery pack housing in the embodiment of the present application;

[0045] Figure 5 Schematic diagram of the thickness optimization process of the three-layer material of the battery pack housing in the embodiment of the present application;

[0046] Figure 6 Block diagram of the device for determining the structural parameters of the battery pack in the embodiment of the present application;

[0047] Figure 7 Block diagram of the determination unit of the device for determining the structural parameters of the battery pack in the embodiment of the present application;

[0048] Figure 8 Schematic diagram of the server in the embodiment of the present application. Detailed implementation manners

[0049] Hereinafter, the exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings.

[0050] In the accompanying drawings, various structural schematic diagrams according to the embodiments of the present application are shown. These figures are not drawn to scale, in which for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary, and in practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0051] In order to facilitate a clear description of the technical solutions in the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. For example, the first value and the second value are only used to distinguish different values, and do not limit their order. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and terms such as "first" and "second" do not necessarily limit being different.

[0052] It should be noted that in the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific manner.

[0053] In this application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the relationship between associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or a similar expression refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0054] To better understand the above technical solutions, the above technical solutions will be described in detail below in combination with specific implementation manners. It should be understood that the embodiments of the present disclosure and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. Without conflict, the technical features in the embodiments of this application and the embodiments can be combined with each other.

[0055] With the rapid development of the new energy vehicle industry, as a core component of the vehicle body structure, the battery pack housing must not only bear the weight of the battery pack but also have excellent energy absorption characteristics to ensure safety in collision accidents. Most of the designs of traditional electric vehicle battery pack housings adopt single-material solutions, such as aluminum alloys and steels. However, it is often difficult for a single material to achieve a balance among strength, energy absorption, and lightweight. Especially when facing high impact loads and collisions, the performance of the material often fails to meet multi-faceted requirements. Therefore, how to achieve comprehensive optimization of the battery pack housing in terms of strength, energy absorption, and weight has become a hot topic in current technical research.

[0056] Taking the aluminum alloy battery pack as an example, the main technical challenges faced by the current design of pure aluminum alloy battery pack housings are as follows:

[0057] (1) The energy absorption characteristics of aluminum alloy are limited: Although aluminum alloy has good lightweight characteristics, its energy absorption ability under high-strength collision conditions is relatively weak, and it cannot effectively disperse collision energy, which may lead to structural damage.

[0058] (2) The impact resistance of aluminum foam is relatively low: Aluminum foam performs excellently in terms of energy absorption characteristics, but its impact resistance is relatively low, and it is difficult to withstand high-strength collision loads when used alone.

[0059] (3) It is difficult to design the thickness of multi-material layers: How to scientifically design the thickness of each layer of material on the premise of meeting the requirements of strength, energy absorption, and lightweight to ensure the best balance of various performances is a difficult point in the current technical solutions.

[0060] In view of this, the present application provides a method for determining the structural parameters of a battery pack. Please refer to Figure 1 , Figure 1 which is the flow chart of the method for determining the structural parameters of the battery pack in the embodiments of the present application, and includes:

[0061] S101. Obtain multiple groups of candidate structural parameters of the battery pack housing. The battery pack housing includes an inner layer material, a middle layer material, and an outer layer material arranged in sequence. The multiple groups of candidate structural parameters include multiple combinations of the candidate thickness of the inner layer material, the candidate thickness of the middle layer material, and the candidate thickness of the outer layer material.

[0062] S102. For each group of candidate structural parameters, input the candidate structural parameters into a preset prediction model to obtain prediction data. The prediction data is the parameter data of the mechanical characteristics and energy absorption characteristics of the deformation of the battery pack housing corresponding to the candidate structural parameters under the set collision condition.

[0063] S103. Based on the prediction data corresponding to each group of candidate structural parameters, determine the target structural parameters of the battery pack housing from the multiple groups of candidate structural parameters.

[0064] In step S101, the inner layer material, the middle layer material, and the outer layer material of the battery pack housing respectively have preset thickness ranges. For the inner layer material, traverse the thickness range of the inner layer material at a set step size to obtain multiple thickness values of the inner layer material, which form a first set. For the middle layer material, traverse the thickness range of the middle layer material at a set step size to obtain multiple thickness values of the middle layer material, which form a second set. For the outer layer material, traverse the thickness range of the outer layer material at a set step size to obtain multiple thickness values of the outer layer material, which form a third set. Take one value from each of the first set, the second set, and the third set, which constitutes a group of candidate structural parameters of the battery pack housing.

[0065] Exemplarily, the inner layer material is glass fiber reinforced plastic or carbon fiber reinforced composite material, the value range of the candidate thickness of the inner layer material is set to [0.5 mm, 10.05 mm], the middle layer material is aluminum foam, and the value range of the candidate thickness of the middle layer material is set to [0.5 mm, 10.05 mm]. The outer layer material is pure aluminum alloy, and the value range of the candidate thickness of the outer layer material is set to [0.5 mm, 10.05 mm]. If traversing and taking values at a step size of 0.05 mm respectively, multiple candidate thicknesses of the inner layer material, multiple candidate thicknesses of the middle layer material, and multiple candidate thicknesses of the outer layer material can be obtained respectively. Taking any one candidate thickness value of each layer of material for traversal combination, more than 6 million combinations of the candidate thickness of the inner layer material, the candidate thickness of the middle layer material, and the candidate thickness of the outer layer material can be obtained, that is, more than 6 million groups of candidate structural parameters of the battery pack housing are formed.

[0066] When the candidate structural parameters of the battery pack housing are different, the mechanical and energy absorption characteristics of the battery pack housing are also different. Taking the more than 6 million groups of candidate structural parameters of the battery pack housing combined with the above examples as an example, if bench tests are used to verify the true performance of the battery pack housing corresponding to each candidate structural parameter one by one, it will require high human, material and time costs.

[0067] In step S102, the prediction model can quickly predict the mechanical and energy absorption characteristics of the deformation of the battery pack housing corresponding to each candidate structural parameter under the set collision condition, with high efficiency and low cost.

[0068] It can be understood that the prediction model has mastered the functional relationship between the candidate structural parameters and the mechanical and energy absorption characteristics of the deformation of the battery pack housing under the set collision condition. Therefore, the prediction model needs to be trained.

[0069] In some alternative embodiments, as Figure 2 shown, Figure 2 is the flowchart for constructing the prediction model in the embodiment of the present application. The prediction model is obtained by the following operations S201 to S203.

[0070] S201. Construct an initialized support vector regression model as the initial prediction model.

[0071] S202. Obtain sample data. The sample data includes: multiple groups of sample structural parameters of the battery pack housing samples, and the mechanical and energy absorption characteristics of the deformation of the battery pack housing samples corresponding to each group of sample structural parameters under the set collision condition. Among them, the battery pack housing samples include an inner layer material, a middle layer material, and an outer layer material arranged in sequence. The multiple groups of sample structural parameters include multiple combinations of the thickness of the inner layer material of the battery pack housing sample, the thickness of the middle layer material of the battery pack housing sample, and the thickness of the outer layer material of the battery pack housing sample.

[0072] S203. Train the initial prediction model based on the sample data to obtain the prediction model.

[0073] In step S202, the mechanical and energy absorption characteristics of the deformation of the battery pack housing samples corresponding to each group of sample structural parameters are obtained by the following operations:

[0074] Based on each group of sample structural parameters, construct a finite element model of the battery pack housing sample, and perform collision simulation on the finite element model to determine the mechanical and energy absorption characteristics of the deformation of the battery pack housing sample corresponding to the sample structural parameters under the set collision condition.

[0075] The basic idea of Support Vector Machine Regression (SVR) is to construct a classifier that maps the input data into a high-dimensional space, making the data more linearly separable in the high-dimensional space, so as to obtain an optimal regression model. It is applicable to datasets with a large number of features and can handle high-dimensional data. Therefore, once the simulation data corresponding to different thickness combinations are obtained through the finite element model, a non-linear relationship between the thickness combination and the performance can be established through the Support Vector Regression (SVR) model.

[0076] The thickness combinations of the battery pack housing samples input to the finite element model of the battery pack housing and the mechanical and energy absorption characteristic data in the simulation data output by the finite element model of the battery pack housing samples are used to train the SVR model to obtain a prediction model. The trained prediction model can capture the complex non-linear relationship between the thicknesses of the multi-layer materials of the battery pack housing, that is, the thicknesses of the inner layer material, the middle layer material, and the outer layer material, and the mechanical and energy absorption characteristics, that is, stress, deformation, and energy absorption. Therefore, the trained prediction model can predict the stress, deformation, and energy absorption under any given thickness combination. The core advantage of this process is the ability to predict thickness configurations that have not been simulated before, improving the calculation efficiency.

[0077] It can be understood that by constructing an automatically running computer program, the computer program automatically inputs the candidate structural parameters of the battery pack housing traversed into the trained prediction model to predict the mechanical characteristics and energy absorption characteristics of the deformation of the battery pack housing corresponding to each group of candidate structural parameters under the set collision condition.

[0078] In the operation of S203, the prediction data corresponding to each group of candidate structural parameters can be input into a preset multi-objective optimization model to obtain the objective function value corresponding to the prediction data. Among them, the multi-objective optimization model includes an objective function and constraint conditions; the candidate structural parameters corresponding to the prediction data with the smallest objective function value are used as the target structural parameters of the battery pack housing.

[0079] In some optional embodiments, the prediction data includes the stress prediction value, deformation prediction value, and energy absorption prediction value of the deformation of the battery pack housing corresponding to each group of candidate structural parameters under the set collision condition; the multi-objective optimization model includes an objective function and constraint conditions, and the objective function is expressed as:

[0080] f(S,D,E)=P(S)+P(D)-R(E);

[0081]

[0082] R(E)=γ×E;

[0083] The constraint conditions are

[0084] In the formula, f(S, D, E) is the objective function, P(S) is the first penalty term, α is the first penalty coefficient, S is the predicted stress value, and S max is the upper stress limit value; P(D) is the second penalty term, β is the second penalty coefficient, D is the predicted deformation value, and D max is the upper deformation limit value; R(E) is the first reward term, γ is the first reward coefficient, and E is the predicted energy absorption value.

[0085] The operation of S102 is based on the simulation data of the battery pack housing sample. Through the SVR model, a non-linear relationship is established between the thickness of the multi-layer materials of the battery pack housing and the mechanical properties and energy absorption properties of the battery pack housing. The operation of S103 uses the objective function to optimize the thickness of the multi-layer materials. As shown in the above formula, the objective function includes penalty terms for stress and deformation (the greater the penalty, the higher the penalty) and a reward term for energy absorption (the greater the reward, the higher the reward). By calculating the objective function values of each combination, the optimal thickness combination is found.

[0086] It can be understood that by constructing an automatically running computer program, the operation of inputting the mechanical properties and energy absorption properties of the battery pack housing corresponding to the candidate structural parameters of the battery pack housing traversed into the objective function when the battery pack housing deforms under the set collision condition is automatically performed by the computer program. If the obtained objective function value is smaller than the previously output objective function value, the thickness combination of the three-layer materials of the battery pack housing corresponding to the current objective function value is used as the optimal thickness combination, and the corresponding mechanical properties and energy absorption properties of the battery pack housing are used as the data to be preliminarily output.

[0087] The first penalty coefficient α is the stress penalty coefficient, the second penalty coefficient β is the deformation penalty coefficient, and the first reward coefficient γ is the energy absorption reward coefficient. These three coefficients are obtained through the following operations:

[0088] Design an initial comprehensive objective function that can impose penalties on stress and deformation and give rewards for energy absorption. Use a preset data set to train this objective function. The data set can use the sample structural parameters obtained by the operation of S202 and the corresponding mechanical properties and energy absorption properties of the battery pack housing sample. It can be understood that the mechanical properties refer to the predicted stress and predicted deformation output by the finite element model of the battery pack housing sample, and the energy absorption properties refer to the predicted energy absorption output by the finite element model of the battery pack housing sample.

[0089] Objective function = stress_penalty + deformation_penalty + energy_reward;

[0090]

[0091] energy_reward = -γ × predicted_energy.

[0092] Among them, stress_penalty is the stress penalty term, deformation_penalty is the deformation penalty term, energy_reward is the energy absorption reward term, predicted_stress is the predicted stress, stress_limit is the upper limit stress, predicted_deformation is the predicted deformation, deformation_limit is the upper limit deformation, and predicted_energy is the predicted energy absorption.

[0093] The predicted stress, predicted deformation, and predicted energy absorption used to train the objective function are the performance data corresponding to different thickness combinations obtained through the above step S202 operation using the finite element model.

[0094] The purpose of training the objective function is to obtain the determined stress penalty coefficient, deformation penalty coefficient, and energy absorption reward coefficient. The specific operation is to substitute the stress, deformation, and energy absorption during the deformation of a battery pack housing sample corresponding to a set of sample structure parameters in a preset dataset under the set collision condition into the initial comprehensive objective function. For the stress penalty term, when the predicted stress exceeds the upper limit stress, this term is weighted and penalized according to the exceeding ratio; if the predicted stress does not exceed the upper limit stress, this term is 0. For the deformation penalty term, when the predicted deformation exceeds the upper limit deformation, this term is weighted and penalized according to the exceeding ratio; if the predicted deformation does not exceed the upper limit deformation, this term is 0. For the energy absorption reward term, a reward is given according to the predicted energy absorption value, and the larger the value, the smaller the objective function value.

[0095] The stress penalty coefficient, deformation penalty coefficient, and energy absorption reward coefficient determined through the above operations are used to be set as the first penalty coefficient, the second penalty coefficient, and the first reward coefficient of the objective function of the above multi-objective optimization model respectively. It can be understood that the purpose of optimization is to obtain the optimal material size with stress and deformation within the limit range when the battery pack housing experiences a collision event. Therefore, the upper limits of stress and deformation need to be restricted. The value of the upper limit stress in the above operation is the same as the stress upper limit value S max in the constraint conditions of the multi-objective optimization model, and the value of the upper limit deformation in the above operation is the same as the deformation upper limit value D maxThe values are the same. Quickly determine the optimal thickness of the lightweight material and the heavyweight material, ensure excellent mechanical and energy absorption characteristics of the battery pack housing, while reducing the thickness of the material layer to reduce the weight of the battery pack, so as to achieve a multi-faceted requirement balance in terms of strength, energy absorption and lightweighting.

[0096] In some alternative embodiments, the target structural parameters of the battery pack housing include the optimized thickness of the inner layer material, the optimized thickness of the middle layer material, and the optimized thickness of the outer layer material; wherein, the inner layer material is glass fiber reinforced plastic or carbon fiber reinforced composite material, and the value range of the optimized thickness of the inner layer material is [1mm, 2mm]; the middle layer material is aluminum foam, and the value range of the optimized thickness of the middle layer material is [3mm, 5mm]; the outer layer material is pure aluminum alloy, and the value range of the optimized thickness of the outer layer material is [1mm, 2.5mm].

[0097] When the battery pack housing adopts a multi-layer structure composed of laminated lightweight materials such as glass fiber, carbon fiber, and aluminum foam and heavyweight materials such as aluminum alloy, one-to-one combinations are made of multiple candidate thicknesses of the lightweight material in a higher value range and multiple candidate thicknesses of the heavyweight material in a lower value range to obtain multiple groups of candidate structural parameters. Through the prediction model, the mechanical characteristics and energy absorption characteristics corresponding to each group of candidate structural parameters are obtained. Based on these prediction data, quickly determine the optimal thickness of the lightweight material and the heavyweight material, ensure excellent mechanical and energy absorption characteristics of the battery pack housing, while reducing the weight of the battery pack, so as to achieve a multi-faceted requirement balance in terms of strength, energy absorption and lightweighting.

[0098] In summary, the solution provided by the embodiments of the present application, through the design of multi-layer composite materials, overcomes the limitations of the single material solution, can provide more excellent comprehensive performance, and has unique advantages especially in the balance between lightweighting, strength and energy absorption. Through the optimized combination of the thicknesses of different material layers, the performance of each region is strengthened. The outer layer material uses an aluminum alloy material with higher strength, the middle layer material uses aluminum foam to enhance the energy absorption characteristics, and the inner layer material selects glass fiber reinforced plastic (GFRP) or carbon fiber reinforced composite material (CFRP) to further improve the overall strength and corrosion resistance.

[0099] To make the objectives, technical solutions and advantages of the present invention clearer, the following combines the attached Figures 3 to 5 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0100] The following is a complete solution for applying the method of the above embodiments to the optimized design of the battery pack housing for multi-layer composite materials.

[0101] (1) Material design

[0102] As Figure 3 shown, Figure 3 a is the battery pack, Figure 3 b is the explosion diagram of the battery pack, Figure 3 c is the schematic diagram of the battery pack housing material layer. As can be seen from Figure 3 b, the battery pack is composed of a battery pack housing and battery cells arranged in the battery pack housing. The battery pack housing includes an upper housing 301 and a lower housing 302. The upper housing 301 and the lower housing 302 are respectively laminated and compounded with an outer layer material 303, a middle layer material 304, and an inner layer material 305. The selection of the three-layer materials is as follows.

[0103] Outer layer material: Aluminum alloy is selected as the outer layer material, and an aluminate coating (thickness 50 - 100 μm) is covered on the surface to improve corrosion resistance and durability and prevent the erosion of factors such as moisture and salt spray.

[0104] Middle layer material: Aluminum foam is used as the middle layer material. The porosity of the aluminum foam is 70%, and the pore diameter is 2 mm. The aluminum foam, as an energy absorption layer, can significantly improve the energy absorption capacity and effectively slow down the transmission of the collision force.

[0105] Inner layer material: Glass fiber reinforced plastic (GFRP) or carbon fiber reinforced composite material (CFRP) is selected as the inner layer material. Different materials are selected according to specific performance requirements to provide additional strength and structural stability.

[0106] (2) Preparation method

[0107] Taking the inner layer material as GFRP as an example, the aluminum alloy, aluminum foam, and GFRP are tightly combined by a hot pressing process. In the temperature range of 300 - 500 °C, a pressure of 50 - 100 MPa is applied to ensure that the layers of materials are tightly combined without bubbles or delamination defects. The hot pressing process effectively improves the interfacial bonding strength through pressing under high temperature and high pressure conditions, ensuring that the bonding strength of each layer of material reaches more than 90%. At the same time, by precisely controlling the temperature and pressure of the hot pressing, the negative impact of too high or too low temperature on the material properties is avoided, ensuring the overall stability of the material.

[0108] (3) Structural optimization

[0109] Using the method provided in the above embodiment, by combining finite element simulation analysis and a support vector regression (SVR) model, the performance data (stress, deformation, energy absorption) under different thickness combinations are predicted, and the thickness of each layer of material is adjusted by optimizing the objective function, and finally the optimal thickness combination is obtained. The optimization process includes the following steps:

[0110] The first step, material model and physical parameters:

[0111] A three-dimensional model of the battery pack housing is established, and the model is divided into three parts: the outer layer material (aluminum alloy), the middle layer material (aluminum foam), and the inner layer material (GFRP). Ansys Workbench and Solidworks Simulation are used for simulation analysis, and the properties such as density, Young's modulus, and yield strength of each material are set according to the values in the following table:

[0112]

[0113] The second step, collision simulation conditions:

[0114] Three typical collision speeds (50 km / h, 75 km / h, 100 km / h) and collision forces (50 kN, 75 kN, 100 kN) are set to simulate the side collision situation. Fixed boundary conditions and the time history of the applied collision load are set for dynamic loading analysis. The performance of the battery pack housing under the simulated collision conditions is analyzed, with a focus on stress distribution, deformation, and energy absorption performance. Among them, the side collision results under the conditions of a collision speed of 50 km / h and a collision force of 50 kN are as Figure 4 shown, and from Figure 4 it can be seen that the maximum value of the equivalent stress (von Mises) on the side of the upper housing 301 of pure aluminum alloy after side collision, that is, the maximum stress is 180 MPa.

[0115] It can be understood that the operations in the above first step and second step correspond to the specific steps of S202 in the above embodiment.

[0116] The third step, the basis for thickness setting and optimization analysis:

[0117] Based on the simulation data, a non-linear relationship between thickness and performance is established through the SVR model, and the thickness of multi-layer materials is optimized using the objective function. The objective function includes penalty terms for stress and deformation (the higher the value, the higher the penalty) and a reward term for energy absorption (the higher the value, the higher the reward), and the optimal thickness combination is found by calculating the objective function value of each combination.

[0118] Please refer to Figure 5 , and the detailed steps of the thickness optimization process of the three-layer material of the battery pack housing are as follows:

[0119] 1. Provision of simulation data

[0120] At the beginning of the optimization process, different combinations of battery pack thicknesses and their corresponding performance simulation results are provided. For example, more than 10 sets of performance data obtained through finite element simulation analysis for different thickness combinations are provided. The performance data of stress, deformation, and energy absorption of each material layer (outer layer material aluminum alloy, middle layer material aluminum foam, inner layer material GFRP) at different thicknesses will be used as the input data for optimization. Each set of data includes the thickness of the outer layer material, the thickness of the middle layer material, the thickness of the inner layer material, and the corresponding performance data, that is, the stress, deformation, and energy absorption of the battery pack corresponding to each thickness combination under the set collision conditions. These data serve as the sample data for training the regression model.

[0121] 2. Training the regression model

[0122] Obtain the performance data corresponding to different thickness combinations, and establish a non - linear relationship between the thickness combination and the performance through a Support Vector Regression (SVR) model. Use the thickness and performance data in the above - mentioned simulation data to train the SVR model. The SVR model can capture the complex non - linear relationship between thickness and performance (stress, deformation, energy absorption). After training, the SVR model can predict the stress, deformation, and energy absorption for any given thickness combination. The core advantage of this process is the ability to predict thickness configurations that have not been simulated before, improving the computational efficiency. It can be understood that this operation corresponds to the operation of S203 in the above - mentioned embodiment.

[0123] 3. Designing the objective function

[0124] The goal of optimization is to consider stress, deformation, and energy absorption simultaneously. To this end, an initial comprehensive objective function is designed, which can impose penalties on stress and deformation, while rewarding energy absorption. The objective function is designed in the following way, comprehensively considering the relationship between stress, deformation, and energy absorption:

[0125] Objective function = stress_penalty + deformation_penalty + energy_reward;

[0126]

[0127] energy_reward = -γ × predicted_energy.

[0128] Among them, stress_penalty is the stress penalty term, deformation_penalty is the deformation penalty term, energy_reward is the energy absorption reward term, α is the stress penalty coefficient, predicted_stress is the predicted stress, stress_limit is the upper limit stress, β is the deformation penalty coefficient, predicted_deformation is the predicted deformation, deformation_limit is the upper limit deformation, γ is the energy absorption reward coefficient, and predicted_energy is the predicted energy absorption.

[0129] The predicted stress, predicted deformation, and predicted energy absorption used to train the objective function are the performance data corresponding to different thickness combinations obtained in the above step 1 operation. For the stress penalty term, when the predicted stress exceeds the upper limit stress, this term is weighted and penalized according to the exceeding ratio; if the predicted stress does not exceed the upper limit stress, this term is 0. For the deformation penalty term, when the predicted deformation exceeds the upper limit deformation, this term is weighted and penalized according to the exceeding ratio: if the predicted deformation does not exceed the upper limit deformation, this term is 0. For the energy absorption reward term, a reward is given according to the predicted energy absorption value, and the larger the value, the smaller the objective function value.

[0130] What the objective function returns is the sum of the stress, deformation penalty term, and energy absorption reward term. When the stress or deformation exceeds the set limit, calculate the exceeding ratio and amplify its influence through the coefficient to ensure that these limits are preferentially met during the optimization process. Energy absorption is a positive indicator, and the larger its value, the better. Therefore, a negative value is introduced as a reward, and the objective function value will decrease. The smaller the objective function value, the better the performance. By adjusting the penalty coefficients (α, β) and the reward coefficient (γ), the weights among stress, deformation, and energy absorption can be balanced to ensure compliance with the design requirements.

[0131] 4. Optimal Thickness Combination and Corresponding Performance Prediction

[0132] To find the optimal thickness combination, different thickness configurations need to be explored. First, the thickness ranges of the outer layer material, middle layer material, and inner layer material are respectively set to be from 0.5 mm to 10 mm, with a step size of 0.5 mm. These ranges are reasonably determined based on the mechanical properties, energy absorption properties, and lightweight requirements of the materials.

[0133] Call the optimize_thickness function to traverse the thickness values of the outer layer material, middle layer material, and inner layer material, and gradually calculate the objective function value for each combination. For each thickness combination, the specific operation of traversing is as follows: first, use the SVR model to predict stress, deformation, and energy absorption, and then substitute these prediction results into the objective function to calculate the objective function value for each combination.

[0134] By traversing different thickness combinations, the corresponding objective function values are calculated. After each iteration, the thickness combination with the minimum objective function value will be recorded and updated. This process continues until all combinations are traversed or a preset optimization termination condition is reached. Finally, when all thickness combinations have been traversed, the thickness combination with the minimum objective function value, i.e., the optimal solution, will be obtained.

[0135] 5. Output the optimal thickness combination and corresponding performance

[0136] Once the optimal thickness combination is found, the optimal thickness combination will be output, including the thicknesses of the outer layer material, middle layer material, and inner layer material, as well as the corresponding performance data (stress, deformation, energy absorption). Through the calculation of the objective function, it is ensured that this combination can exhibit the best comprehensive performance under all collision conditions.

[0137] The above operations 1 to 5 give the thickness optimization process of the three-layer material of the battery pack housing, which can be stored in a computer-readable storage medium by editing a computer program. When the computer program is executed by a processor, the computer performs the methods of the above operations 1 to 5. It can be understood that the computer program can use Python code, and the specific code will not be elaborated here.

[0138] (4) Conclusions and analysis:

[0139] According to different collision speeds and collision forces, the optimized thickness configuration and the maximum stress, maximum deformation, and energy absorption performance of each material layer are analyzed as follows:

[0140] After the above operations, the optimized thicknesses of each layer of the composite material composed of the inner layer material, middle layer material, and outer layer material under the collision condition of a collision speed of 50 km / h and a collision force of 50 kN are shown in the following table:

[0141] Composite material Material Optimized thickness (mm) Outer layer material Aluminum alloy 1 Middle layer material Aluminum foam 3 Inner layer material GFRP 1

[0142] After the above operations, the stress, deformation, and energy absorption of the composite material under the collision condition of a collision speed of 50 km / h and a collision force of 50 kN are also optimized and compared with the existing pure aluminum alloy and pure high-strength steel, as shown in the following table:

[0143]

[0144]

[0145] As can be seen from the above two tables, under low-speed collision conditions, the energy absorption of composite materials is superior to that of aluminum alloy and high-strength steel. Although the maximum stress of composite materials is slightly higher than that of aluminum alloy, composite materials maintain a smaller deformation amount, enhancing the structural stability of the battery pack housing. Therefore, as the inner layer material, composite materials exhibit better energy absorption characteristics under low-speed collisions, taking into account both energy absorption and structural protection.

[0146] After the above operations, the composite materials composed of the optimized inner layer material, middle layer material, and outer layer material are output. The optimized thicknesses of each layer under the collision conditions of a collision speed of 75 km / h and a collision force of 75 kN are shown in the following table:

[0147] Composite material Material Optimized thickness (mm) Outer layer material Aluminum alloy 2.0 Middle layer material Aluminum foam 4.5 Inner layer material GFRP 1.5

[0148] After the above operations, the stress, deformation, and energy absorption of the composite materials under the collision conditions of a collision speed of 75 km / h and a collision force of 75 kN are simultaneously optimized and compared with the existing pure aluminum alloy and pure high-strength steel, as shown in the following table:

[0149] Material type Maximum stress (MPa) Maximum deformation (mm) Energy absorption (J) Pure aluminum alloy 222 6 23 Pure high-strength steel 378 4.5 31 Composite material 230 4.2 45

[0150] At medium speeds, the energy absorption efficiency of composite materials is again superior to that of aluminum alloy and high-strength steel. The composite material layer can not only provide higher energy absorption capacity but also maintain a lower maximum stress and a smaller deformation, ensuring the integrity of the structure. Although the weight of the composite material increases under higher collision forces, its performance in energy absorption and structural protection is remarkable. Especially while enhancing energy absorption, it maintains good structural stability.

[0151] After the above operations, the composite materials composed of the optimized inner layer material, middle layer material, and outer layer material are output. The optimized thicknesses of each layer under the collision conditions of a collision speed of 100 km / h and a collision force of 100 kN are shown in the following table:

[0152]

[0153] After the above operations, the stress, deformation, and energy absorption of the composite materials under the collision conditions of a collision speed of 100 km / h and a collision force of 100 kN are simultaneously optimized and compared with the existing pure aluminum alloy and pure high-strength steel, as shown in the following table:

[0154] Material type Maximum stress (MPa) Maximum deformation (mm) Energy absorption (J) Pure aluminum alloy 250 8 25 Pure high-strength steel 422 6.2 34 Composite material 250 5.5 49

[0155] Under high-speed collision conditions, the energy absorption efficiency of composite materials is significantly higher than that of aluminum alloys and high-strength steels. Especially under large collision forces, composite materials can maintain low stress and small deformation, demonstrating excellent energy absorption and protection effects. By optimizing the thickness design, composite materials can effectively reduce the risk of damage to the battery pack housing, and can still provide good energy absorption characteristics and structural protection especially under extreme conditions.

[0156] Finally, the optimized thickness ranges of each layer of materials are as follows:

[0157] (1) Aluminum alloy for the outer layer material: The optimized thickness range is 1 - 2.5 mm, aiming to ensure sufficient impact resistance, resist external impact forces, and absorb impact energy to a certain extent.

[0158] (2) Aluminum foam for the middle layer material: The optimized thickness range is 3 - 5 mm, which can effectively improve the energy absorption performance and protect the inner layer material and other components of the battery pack housing by alleviating the impact force.

[0159] (3) Composite material (GFRP) for the inner layer material: The optimized thickness range is 1 - 2 mm, which provides the required strength and structural stability, and effectively improves the energy absorption ability during collision.

[0160] Through the method provided by the embodiments of this application, within the initial thickness range of 0.5 mm to 10 mm, the optimized thicknesses of the outer layer material, middle layer material, and inner layer material under different collision conditions can be determined, and then the value ranges of the optimized thicknesses of the outer layer material, middle layer material, and inner layer material can be determined.

[0161] In summary, the solution in the embodiments of this application, by adopting a multi-layer composite material design and thickness optimization scheme, can provide excellent energy absorption effects and structural protection under different collision conditions, and has the following significant advantages:

[0162] (1) Optimized performance: Through finite element simulation analysis and SVR model optimization, the thickness of each layer can be accurately adjusted to balance the requirements of energy absorption, strength, and lightweight, and obtain the best thickness combination.

[0163] (2) Improved safety: The multi-layer composite material design effectively improves the impact resistance of the battery pack housing during collision, and the energy absorption efficiency is significantly better than that of traditional aluminum alloy and high-strength steel materials.

[0164] (3) Lightweight advantage: By reasonably selecting the thickness and structural design of composite materials, taking into account lightweight and safety, it is especially suitable for the design requirements of new energy vehicles and enhances the market competitiveness of the battery pack housing.

[0165] Based on the same inventive concept, the embodiments of this application provide a device for determining the structural parameters of a battery pack, as Figure 6As shown in the figure, the device 600 for determining the structural parameters of the battery pack includes:

[0166] An acquisition unit 601, configured to acquire multiple groups of candidate structural parameters of the battery pack housing. The battery pack housing includes an inner layer material, a middle layer material, and an outer layer material arranged in sequence. The multiple groups of candidate structural parameters include multiple combinations of the candidate thickness of the inner layer material, the candidate thickness of the middle layer material, and the candidate thickness of the outer layer material.

[0167] A prediction unit 602, configured to input the candidate structural parameters into a preset prediction model for each group of candidate structural parameters to obtain prediction data, where the prediction data is used to indicate the mechanical properties and energy absorption properties of the deformation of the battery pack housing corresponding to the candidate structural parameters under the set collision condition.

[0168] A determination unit 603, configured to determine the target structural parameters of the battery pack housing from multiple groups of candidate structural parameters based on the prediction data corresponding to each group of candidate structural parameters.

[0169] In some alternative embodiments, as Figure 7 shown, the determination unit 603 includes:

[0170] A multi-objective optimization unit 701, configured to input the prediction data corresponding to each group of candidate structural parameters into a preset multi-objective optimization model to obtain the objective function value corresponding to the prediction data, where the multi-objective optimization model includes an objective function and constraint conditions;

[0171] A value-taking unit 702, configured to use the candidate structural parameters corresponding to the prediction data with the minimum objective function value as the target structural parameters of the battery pack housing.

[0172] The device for determining the structural parameters of the battery pack provided by the embodiments of the present application can be used to perform the operations of S101 to S103 provided by the above embodiments, quickly determine the optimal thicknesses of the inner layer material, the middle layer material, and the outer layer material, so that the battery pack housing has good mechanical and energy absorption properties under the set collision condition, and at the same time achieve a multi-faceted demand balance in terms of mechanical properties, energy absorption properties, and lightweight.

[0173] Regarding the above device, the specific functions of each unit have been described in detail in the embodiments of the method for determining the structural parameters of the battery pack provided in this specification, and will not be elaborated here.

[0174] Based on the same inventive concept, the embodiments of the present application provide a battery pack, including a battery pack housing. The battery pack housing includes an inner layer material, a middle layer material, and an outer layer material arranged in sequence. The structural parameters of the battery pack housing, that is, the thicknesses of the inner layer material, the middle layer material, and the outer layer material, are obtained by using the method of the above embodiments.

[0175] In some alternative embodiments, the target structural parameters of the battery pack housing include the optimized thickness of the inner layer material, the optimized thickness of the middle layer material, and the optimized thickness of the outer layer material. Among them, the inner layer material is glass fiber reinforced plastic or carbon fiber reinforced composite material, and the value range of the optimized thickness of the inner layer material is [1 mm, 2 mm]; the middle layer material is aluminum foam, and the value range of the optimized thickness of the middle layer material is [3 mm, 5 mm]; the outer layer material is pure aluminum alloy, and the value range of the optimized thickness of the outer layer material is [1 mm, 2.5 mm].

[0176] Based on the same inventive concept, an embodiment of the present application provides a vehicle, including the battery pack of the above embodiment.

[0177] An embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a computer, the computer is enabled to execute the method provided in the above embodiment. Specifically, the coding of the computer program has been described in detail in the embodiment of the above battery pack structure parameter determination method, and will not be elaborated here.

[0178] An embodiment of the present application further provides a server, as Figure 8 shown. The server 800 includes a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and executable on the processor 802. When the processor 802 executes the computer program 803, the server 800 is enabled to execute the method provided in the above embodiment.

[0179] An embodiment of the present application further provides a computer program product, including a computer program. When the computer program is run, the computer is enabled to execute the method provided in the above embodiment.

[0180] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0181] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

[0182] In the specification provided herein, numerous specific details are set forth. However, it will be understood that embodiments of the present application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

Claims

1. A method for determining structural parameters of a battery pack, characterized in that: include: Acquire multiple sets of candidate structural parameters of a battery pack shell, the battery pack shell comprising an inner layer material, a middle layer material and an outer layer material arranged in sequence, the multiple sets of candidate structural parameters comprising multiple combinations of candidate thicknesses of the inner layer material, candidate thicknesses of the middle layer material and candidate thicknesses of the outer layer material; For each group of candidate structural parameters, the candidate structural parameters are input into a preset prediction model to obtain prediction data, where the prediction data is parameter data for indicating the mechanical properties and energy absorption properties of the battery pack shell corresponding to the candidate structural parameters when deformed under a set collision condition; Based on the prediction data corresponding to each group of candidate structural parameters, target structural parameters of the battery pack shell are determined from the multiple groups of candidate structural parameters.

2. The method for determining the structural parameters of a battery pack according to claim 1, wherein: The step of determining target structural parameters of the battery pack housing from the plurality of groups of candidate structural parameters based on the prediction data corresponding to each group of candidate structural parameters includes: Inputting the prediction data corresponding to each group of candidate structural parameters into a preset multi-objective optimization model to obtain the objective function value corresponding to the prediction data, wherein the multi-objective optimization model includes an objective function and constraint conditions; The candidate structural parameters corresponding to the predicted data with the smallest objective function value are used as the target structural parameters of the battery pack shell.

3. The method for determining the structural parameters of a battery pack according to claim 2, characterized in that: The prediction data includes the stress prediction value, deformation prediction value and energy absorption prediction value of the battery pack shell corresponding to each group of candidate structural parameters under the set collision condition; the multi-objective optimization model includes an objective function and constraint conditions, and the objective function is expressed as: f(S,D,E)=P(S)+P(D)-R(E); R(E) = γ × E; The constraints are Where f(S,D,E) is the objective function, P(S) is the first penalty term, α is the first penalty coefficient, S is the stress prediction value, S max is the stress upper limit; P(D) is the second penalty term, β is the second penalty coefficient, D is the deformation prediction value, D max is the upper limit of deformation; R(E) is the first reward item, γ is the first reward coefficient, and E is the predicted value of energy absorption.

4. The method for determining the structural parameters of a battery pack according to claim 1, wherein: The prediction model is obtained by the following operations: Construct an initialized support vector regression model as the initial prediction model; Acquire sample data, the sample data comprising: multiple groups of sample structural parameters of battery pack shell samples, and mechanical properties and energy absorption properties of the battery pack shell samples corresponding to each group of the sample structural parameters when deformed under set collision conditions, wherein the multiple groups of sample structural parameters include multiple combinations of the thickness of the inner layer material of the battery pack shell sample, the thickness of the middle layer material of the battery pack shell sample, and the thickness of the outer layer material of the battery pack shell sample; Based on the sample data, the initial prediction model is trained to obtain the prediction model.

5. The method for determining the structural parameters of a battery pack according to claim 4, characterized in that: The mechanical properties and energy absorption properties of the battery pack shell samples corresponding to each group of sample structural parameters that are deformed under the set collision conditions are obtained by the following operations: Based on each group of sample structural parameters, a finite element model of the battery pack shell sample is constructed, and a collision simulation is performed based on the finite element model to determine the mechanical properties and energy absorption properties of the battery pack shell sample corresponding to the sample structural parameters when deformed under set collision conditions.

6. The method for determining the structural parameters of a battery pack according to claim 1, wherein: The target structural parameters of the battery pack shell include the optimized thickness of the inner layer material, the optimized thickness of the middle layer material and the optimized thickness of the outer layer material; wherein, the inner layer material is glass fiber reinforced plastic or carbon fiber reinforced composite material, and the optimized thickness of the inner layer material is in the range of [1mm, 2mm]; the middle layer material is foamed aluminum, and the optimized thickness of the middle layer material is in the range of [3mm, 5mm]; the outer layer material is pure aluminum alloy, and the optimized thickness of the outer layer material is in the range of [1mm, 2.5mm].

7. A device for determining structural parameters of a battery pack, characterized in that: include: an acquisition unit, configured to acquire multiple sets of candidate structural parameters of a battery pack shell, the battery pack shell comprising an inner layer material, a middle layer material and an outer layer material arranged in sequence, the multiple sets of candidate structural parameters comprising multiple combinations of candidate thicknesses of the inner layer material, candidate thicknesses of the middle layer material and candidate thicknesses of the outer layer material; A prediction unit, for inputting the candidate structural parameters into a preset prediction model for each group of candidate structural parameters to obtain prediction data, wherein the prediction data is used to indicate the mechanical properties and energy absorption properties of the battery pack shell corresponding to the candidate structural parameters when deformed under a set collision condition; A determination unit is used to determine the target structural parameters of the battery pack shell from the multiple groups of candidate structural parameters based on the prediction data corresponding to each group of candidate structural parameters.

8. A battery pack, characterized in that: It comprises a battery pack shell, the structural parameters of which are obtained by adopting any one of the methods of claims 1 to 6.

9. A vehicle, characterized in that: A battery pack comprising the battery pack as claimed in claim 8.

10. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the server is caused to perform the method according to any one of claims 1 to 6.

Images