Data-driven automobile multi-material body forward material selection method and system

Abstract

The invention provides a data-driven forward material selection method and system for an automobile multi-material body, and relates to the technical field of automobile research and development, and the method comprises the steps: obtaining a material selection target constraint condition and candidate material data of the automobile body; on the basis of the candidate material data, vehicle candidate material schemes are generated, multiple data-driven vehicle target material selection models are called to select the vehicle candidate material schemes in sequence, and vehicle feasible material selection schemes meeting material selection target constraint conditions are obtained; a non-dominated sorting algorithm is called to screen the feasible material selection schemes of the whole automobile, and candidate recommendation schemes of automobile body material selection are obtained; and multi-criterion decision making is carried out on the candidate recommendation schemes to obtain a final recommendation scheme of automobile body material selection. The method is used for solving the technical problem of low material selection process efficiency caused by complex vehicle body materials, material selection constraints and numerous research and development requirements when forward material selection is carried out by depending on manual experience in the prior art in automobile research and development.

Description

Technical Field

[0001] This invention relates to the field of automotive R&D technology, specifically to a data-driven method and system for forward material selection of multi-material automotive bodies. Background Technology

[0002] Forward development in the automotive industry refers to a development model that systematically completes structural design and material selection based on clearly defined performance goals and design requirements during the vehicle development process. Compared to development methods based on existing platforms and engineering experience, forward development is more conducive to coordinating multiple objectives such as safety, lightweighting, and cost control, and has become an important way to improve the independent R&D capabilities of vehicle manufacturers. As the core load-bearing structure of the vehicle, the design level of the body directly affects the vehicle's passive safety performance, overall rigidity, durability, and energy consumption. In the forward development system of the vehicle body, material selection, as a key link connecting design goals and vehicle performance, has a decisive impact on achieving vehicle performance, development cycle, and cost control due to the scientific nature of its decisions. Therefore, constructing a scientific and efficient material selection method is a key technical challenge that needs to be addressed in advancing the forward development of vehicle bodies.

[0003] Currently, to meet energy conservation and emission reduction regulations and market demands for lightweighting, automotive bodies are gradually shifting from traditional low-carbon steel to a multi-material system encompassing high-strength steel, ultra-high-strength steel, aluminum alloys, magnesium alloys, and composite materials. High-strength steel, with its excellent formability and cost advantages, plays a crucial role in vehicle bodies; aluminum alloys and magnesium alloys are used in non-load-bearing areas to reduce overall vehicle weight. However, despite the increasing variety of materials, the material selection methods in the forward development of vehicle bodies still largely rely on experience, i.e., making localized adjustments based on existing models or mature platforms, supplemented by limited performance analysis. This approach, on the one hand, makes it difficult to achieve forward design of the overall vehicle body performance, often only meeting performance requirements in specific areas; on the other hand, its over-reliance on personal experience and lack of systematic decision-making basis leads to inconsistencies between different projects, making it difficult to support the development of complex and diverse vehicle models.

[0004] Furthermore, the selection of materials for vehicle body components is inherently complex, involving multiple objectives and constraints. During the forward development of the vehicle body, materials must not only meet performance indicators such as structural strength, overall stiffness, and collision energy absorption, but also balance lightweighting goals and cost control requirements. These objectives often involve coupling and conflict; for example, increasing body stiffness may lead to increased mass, reducing overall vehicle mass through lightweight materials may increase costs, and simply reducing costs may negatively impact performance. Therefore, material selection is essentially a comprehensive decision-making process involving lightweighting, economy, and multi-dimensional performance. Existing experience-based material adjustment methods rely heavily on engineers' adherence to past designs and limited analytical tools, lacking a systematic quantitative basis when facing such multi-dimensional trade-offs. Due to the lack of a unified evaluation framework and global optimization mechanism, it is difficult to truly achieve the optimal design goal of "using the right materials in the right places," and even more difficult to ensure the coordination and unity between overall vehicle body performance, lightweighting, and cost.

[0005] In conclusion, given the increasing variety of vehicle body materials and the continuously rising demands for lightweighting and performance, traditional experience-based material selection methods are no longer sufficient to meet the needs of forward development of multi-material vehicle bodies. Specifically, in complex decision-making environments that require comprehensive consideration of multiple dimensions such as performance, quality, and cost, the lack of systematic, data-driven decision support tools leads to inefficient material selection processes, insufficient global optimization capabilities, and excessive reliance on human experience, thus hindering improvements in overall vehicle development quality and the shortening of R&D cycles. Therefore, constructing a scientific, efficient, and systematic method and system for selecting vehicle body materials is of significant importance for improving forward development capabilities. Summary of the Invention

[0006] In view of this, it is necessary to provide a data-driven method and system for forward material selection of multi-material automotive bodies to solve the technical problem of low efficiency in the material selection process caused by the complexity of body materials, material selection constraints and numerous R&D needs when relying on manual R&D experience for forward material selection in automotive R&D.

[0007] To address the aforementioned problems, this invention provides a data-driven method for forward material selection of multi-material automotive body panels, comprising: Obtain the material selection target constraints and candidate material data for the automobile body; Based on the candidate material data, a vehicle candidate material scheme is generated, and multiple data-driven vehicle target material selection models are invoked to select the vehicle candidate material scheme in sequence to obtain a vehicle feasible material selection scheme that meets the material selection target constraints. The order in which the vehicle target material selection models select materials includes: the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, the vehicle material selection model driven by economy, and the vehicle material selection model driven by high-strength steel ratio. The non-dominated sorting algorithm is used to filter the feasible material selection schemes for the whole vehicle, and candidate recommended schemes for the selection of automotive body materials are obtained. A multi-criteria decision-making process is performed on the candidate recommendations to obtain the final recommended solution for automobile body materials.

[0008] In one possible implementation, the constraints of the vehicle material selection targets include a range of values ​​corresponding to multiple vehicle material selection targets, including safety performance targets, stiffness performance targets, vehicle quality targets, construction cost targets, and high-strength steel application ratio targets.

[0009] In one possible implementation, the data-driven vehicle target material selection model is constructed as follows: A first mapping relationship is established between the material mechanical properties and thickness parameters of automotive parts and the collision absorption energy of automotive parts, and a second mapping relationship is constructed between the collision absorption energy and the collision absorption energy of the whole vehicle. Based on the first mapping relationship and the second mapping relationship, a safety performance-driven whole vehicle material selection model is constructed. A third mapping relationship is established between the material mechanical properties and thickness parameters of automotive parts and the stiffness performance of the automotive body, and a stiffness performance-driven whole vehicle material selection model is constructed based on the third mapping relationship. A first quantitative relationship model is constructed as a vehicle material selection model driven by lightweighting. The first quantitative relationship model is used to calculate the vehicle body mass based on the material selection scheme output by the vehicle material selection model driven by safety performance and the vehicle material selection model driven by stiffness performance. A second quantitative relationship model is constructed as an economically driven vehicle material selection model. The second quantitative relationship model is used to calculate the construction cost of the car body based on the material selection scheme output by the safety performance driven vehicle material selection model, the stiffness performance driven vehicle material selection model, and the lightweight driven vehicle material selection model. A third quantitative relationship model is constructed as a vehicle material selection model driven by the proportion of high-strength steel. The third quantitative relationship model is used to calculate the proportion of high-strength steel used in the car body based on the material selection schemes output by the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, and the vehicle material selection model driven by economy.

[0010] In one possible implementation, the step of sequentially selecting the candidate material schemes for the vehicle from multiple data-driven vehicle target material selection models to obtain a feasible vehicle material selection scheme that meets the material selection target constraints includes: The vehicle material selection model driven by safety performance and the vehicle material selection model driven by stiffness performance are called to calculate the target values ​​of safety performance and stiffness performance of the candidate vehicle material selection schemes, respectively. The first vehicle material selection scheme that satisfies the target values ​​of safety performance and stiffness performance from the candidate vehicle material selection schemes is selected. The vehicle material selection model driven by lightweight design is called to calculate the target vehicle quality value of the first vehicle material selection scheme, and a second vehicle material selection scheme whose target vehicle quality value meets the material selection target constraint is selected from the first vehicle material selection scheme. The construction cost target value of the second vehicle material selection scheme is calculated by calling the economic-driven vehicle material selection model, and a third vehicle material selection scheme whose construction cost target value meets the material selection target constraint is selected from the second vehicle material selection scheme. The target value of the high-strength steel application ratio in the third vehicle material selection scheme is calculated by calling the vehicle material selection model driven by the proportion of high-strength steel. Then, feasible vehicle material selection schemes that satisfy the vehicle material selection target constraint conditions are selected from the third vehicle material selection scheme.

[0011] In one possible implementation, the step of using a non-dominated sorting algorithm to filter feasible material selection schemes for the entire vehicle and obtain candidate recommended schemes for vehicle body material selection includes: The non-dominated sorting algorithm is called to perform non-dominated sorting on the feasible material selection schemes for the whole vehicle, and the material selection schemes that only include non-dominated solutions after sorting are used as candidate recommended schemes for the selection of automotive body materials.

[0012] In one possible implementation, the step of performing multi-criteria decision-making on the candidate recommendation schemes to obtain the final recommended scheme for automobile body materials includes: For the aforementioned candidate recommendation schemes, the weights of each vehicle material selection evaluation criterion are determined based on the entropy weight method. According to the weights of the vehicle material selection evaluation criteria, the multi-criteria decision algorithm is called to sort the candidate recommendation schemes in reverse order, and the candidate recommendation scheme at the head of the sequence is determined as the final recommendation scheme for vehicle body material selection.

[0013] In one possible implementation, determining the weights corresponding to each material selection evaluation criterion based on the entropy weight method includes: When it is found that the weight corresponding to the material selection evaluation criterion has been customized, the customized material selection evaluation criterion weight will be used as the weight corresponding to the material selection evaluation criterion. When it is found that the weights corresponding to the material selection evaluation criteria are not customized, the information entropy of each material selection evaluation criterion in the candidate recommendation scheme is determined based on the entropy weight method. The weights of each selection criterion are calculated based on the magnitude of the information entropy, and the magnitude of the information entropy is positively correlated with the weights of the selection criteria.

[0014] This invention also provides a data-driven forward material selection system for automotive multi-material body, comprising: The materials database module is used to obtain the material selection target constraints and candidate material data for automobile bodies; The material selection model construction module is used to generate vehicle candidate material schemes based on the candidate material data, and to call multiple data-driven vehicle target material selection models to select the vehicle candidate material schemes in sequence, so as to obtain a feasible vehicle material selection scheme that meets the material selection target constraints. The order in which the vehicle target material selection models select materials includes: the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, the vehicle material selection model driven by economy, and the vehicle material selection model driven by high-strength steel ratio. The non-dominated sorting module is used to call the non-dominated sorting algorithm to filter the feasible material selection schemes for the whole vehicle and obtain the candidate recommended schemes for the selection of automotive body materials. The multi-criteria decision module is used to make multi-criteria decisions on the candidate recommendation schemes to obtain the final recommended scheme for automobile body materials.

[0015] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a program; the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the above-described data-driven forward material selection method for automotive multi-material body.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described data-driven forward material selection method for multi-material automotive body.

[0017] The beneficial effects of adopting the above implementation method are as follows: The data-driven forward material selection method and system for automotive multi-material bodies provided by this invention, by establishing multiple data-driven material selection models and a multi-criteria decision-making mechanism, transforms the traditional material selection process that relies on human experience into a system decision-making process driven by quantitative material data and mathematical models. This significantly improves the objectivity, consistency, and repeatability of automotive material selection, and reduces decision-making bias and quality fluctuations caused by human experience. Furthermore, the whole-vehicle target material selection model, when selecting materials sequentially, can balance multiple objectives such as stiffness, safety, lightweighting, economy, and the proportion of high-strength steel. Under the premise of meeting the preset material selection target constraints, it can screen multiple material solutions. While improving material selection efficiency, the multi-criteria decision-making mechanism also overcomes the limitation of traditional methods in coordinating multiple material selection objectives, supporting the overall optimization of vehicle performance, lightweighting, and cost. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic flowchart illustrating a data-driven forward material selection method for automotive multi-material body provided by the present invention; Figure 2 A schematic diagram illustrating the constraints for determining the material selection targets for the whole vehicle, provided by the present invention; Figure 3 A schematic diagram of the candidate material database provided by the present invention; Figure 4 A schematic diagram illustrating the configuration of material information for a benchmark vehicle model provided by this invention; Figure 5 A schematic diagram of the area defining the relationship between vehicle body safety performance provided by this invention; Figure 6 A schematic diagram of the defined area for the relationship between vehicle body stiffness and performance provided by the present invention; Figure 7 This is a schematic diagram illustrating the determination of material selection criteria weights provided by the present invention; Figure 8 This is a schematic diagram showing the information of the material selection evaluation criteria of the candidate recommendation scheme provided by the present invention; Figure 9 This is a schematic diagram showing the information of the final recommended scheme for automobile body material selection and the evaluation criteria for each vehicle material selection provided by this invention; Figure 10 This is a schematic diagram illustrating the effect of the final recommended solution for automobile body material selection provided by the present invention; Figure 11 This is a schematic diagram of the data-driven forward material selection system for automotive multi-material body provided by the present invention; Figure 12 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] In the description of the embodiments of this application, unless otherwise stated, "a plurality of" means two or more.

[0022] In this embodiment of the invention, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, apparatus, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product or device.

[0023] The naming or numbering of steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical order indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effect can be achieved.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] The data-driven forward material selection method for automotive multi-material bodies provided by this invention can be applied to scenarios involving forward material selection during automotive R&D. The execution entity can be various terminals, servers, or remote cloud systems, specifically within automotive R&D design systems or software. When selecting materials for automotive R&D, users operate the automotive R&D design system or software, inputting and setting material selection target constraints and candidate material data. This triggers the data-driven forward material selection method provided by this invention to perform material selection, ultimately generating a final recommended solution for the automotive body material selection. This solution is then fed back to the automotive R&D design system or software, for example, by displaying it to the user visually for selection, providing a theoretical basis for automotive R&D material selection.

[0026] The following section details the data-driven forward material selection method for multi-material automotive bodies provided by this invention.

[0027] Figure 1 A flowchart illustrating the data-driven forward material selection method for automotive multi-material body provided by this invention is shown below. Figure 1 As shown, the data-driven forward material selection method for multi-material automotive bodies can be implemented through steps 101 to 104, which will be explained in detail below.

[0028] Step 101: Obtain the material selection target constraints and candidate material data for the automobile body.

[0029] Here, the material selection target constraints are preset according to the current needs of automotive body material selection, and are used to characterize the overall target of automotive body material selection.

[0030] In one possible implementation, the material selection target constraints include a range of values ​​for multiple material selection targets. The material selection targets are performance criteria to be considered when selecting materials for the automotive body, specifically including safety performance targets, stiffness performance targets, vehicle weight targets, construction cost targets, and high-strength steel application ratio targets. The value range is used to limit the target values ​​of the material selection targets, generally representing an upper limit and / or a lower limit. The value range is typically set as needed, using a benchmark vehicle model as a reference. In this embodiment of the invention, the automotive body mainly uses a commercial vehicle cab as an example.

[0031] See Figure 4 , Figure 4 The document displays material configuration information for the benchmark vehicle, specifically the initial cab material structure, including basic configuration information for the 11 components that make up the vehicle body. As the primary basic architecture for automotive development, this basic configuration information allows for the determination of various performance characteristics of the benchmark vehicle, corresponding one-to-one with material selection targets. The range of target values ​​for multiple material selection targets within the material selection constraints is set individually based on the performance characteristics of these benchmark vehicles.

[0032] Specifically, the upper limit of the overall vehicle quality target. Setting it to 95% of the baseline model will establish the upper limit of the construction cost target. It is set at 105% of the baseline model. Regarding stiffness performance targets, they are generally divided into two categories: bending stiffness and torsional stiffness. The lower limit of bending stiffness is set as follows: The lower limit of torsional stiffness is set at 92% of the baseline model. It is set at 90% of the baseline model. Regarding safety performance targets, the lower limit corresponding to the safety performance targets is... The target is set at 105% of the baseline model, while the lower limit of the high-strength steel application ratio is set at that level. Set at 150% of the baseline model.

[0033] It should be noted that the proportion of high-strength steel used in the embodiments of this invention mainly refers to the proportion of high-strength steel used in the construction of automobile bodies. High-strength steel is a metallic material with significantly higher strength than ordinary steel. Its strength is generally set according to the actual automobile R&D standards. Since the overall strength of steel in the cab of commercial vehicles is relatively low, it is not appropriate to define the strength of high-strength steel too high. Here, high-strength steel is defined as steel with a tensile strength of not less than 450MPa.

[0034] For example Figure 2 When setting material selection target constraints, upper and lower limits relative to the benchmark model can be set one by one under the corresponding whole vehicle material selection target. For example, the whole vehicle weight is set to 95% of the benchmark model, the construction cost is set to 105% of the benchmark model, the safety is set to 105% of the benchmark model, the bending stiffness and torsional stiffness are set to 92% and 90% of the benchmark model, respectively, and the proportion of high-strength steel is set to 150% of the benchmark model.

[0035] The range of target values ​​for the various vehicle material selection objectives set above constitutes the material selection objective constraints, which are used to screen subsequent material options.

[0036] In this embodiment of the invention, by obtaining the material selection target constraints, the performance targets that the automotive body material selection must meet are set, so that the body material selection scheme can be designed globally under various material selection targets, ensuring the optimal overall performance of the vehicle.

[0037] Candidate material data refers to the data information of various components in the automotive body structure, which is generally obtained from a pre-set candidate material library. For example... Figure 3 As shown, Figure 3The document displays data on various components in the candidate material library, including material mechanical properties, thickness parameters, and costs. When formulating a material selection plan, it's necessary to first define the scope of components involved, i.e., determine the number of key structural parts to be selected. The number of components can be set according to the material selection requirements; in this embodiment, it's set to 11. After defining the scope of components involved in the selection, material information can be obtained from the material library as candidate material data for these 11 components, used to generate a basic material selection plan for subsequent selection.

[0038] Step 102: Based on the candidate material data, generate candidate material schemes for the whole vehicle, and call various data-driven target material selection models for the whole vehicle to select candidate material schemes for the whole vehicle, so as to obtain feasible material selection schemes for the whole vehicle that meet the material selection target constraints.

[0039] First, for each component's candidate material data, corresponding candidate material schemes are generated. Based on the component's energy absorption empirical formula, candidate material schemes based on equivalent crashworthiness are obtained. The candidate material scheme for component 1 satisfies the following formula: (1) in, , as well as The symbols represent the material flow stress, material constitutive model parameters, and structural thickness of component 1, respectively. , as well as The symbols represent the candidate material flow stress, candidate material constitutive model parameters, and corresponding structural thickness of component 1, respectively. The parameters are different for different components.

[0040] Similarly, candidate material schemes for the remaining 10 components can be obtained. By combining these candidate material schemes, the candidate material schemes for the entire vehicle can be obtained. These candidate material schemes for the entire vehicle do not take into account the material selection objectives or constraints of the entire vehicle. They are numerous and generated through free combination, and each material selection scheme is different from the others.

[0041] The data-driven vehicle material selection model is constructed based on multiple vehicle material selection objectives involved in the material selection objective constraints. Based on these objectives, corresponding vehicle material selection models can be constructed, including: a safety performance-driven model, a stiffness performance-driven model, a lightweighting-driven model, an economy-driven model, and a high-strength steel ratio-driven model. These vehicle material selection models are all constructed based on mathematical models, and each objective material model has set an optimization objective to match the vehicle material selection objectives. Specifically, the safety performance-driven model optimizes vehicle collision safety performance, the stiffness performance-driven model optimizes stiffness performance, the lightweighting-driven model optimizes vehicle body mass, the economy-driven model optimizes construction cost, and the high-strength steel ratio-driven model optimizes the proportion of high-strength steel used.

[0042] During material selection, each data-driven vehicle target material selection model can select candidate material schemes that meet the corresponding target requirements of the vehicle. In this embodiment of the invention, optionally, the material selection order of the vehicle target material selection models includes: selecting materials in the following order: safety performance-driven vehicle material selection model, stiffness performance-driven vehicle material selection model, lightweighting-driven vehicle material selection model, economy-driven vehicle material selection model, and high-strength steel ratio-driven vehicle material selection model. However, in actual implementation, the material selection order can be adjusted; for example, the material selection order between the safety performance-driven vehicle material selection model and the stiffness performance-driven vehicle material selection model can be interchanged.

[0043] When selecting materials using the vehicle target material selection model, candidate material schemes for components are first generated based on the principle of equivalent crashworthiness. By combining these candidate material schemes, a vehicle candidate material scheme is obtained. Then, for each vehicle candidate material scheme, the target value of the corresponding vehicle material selection target is calculated using the vehicle target material selection model to determine whether it meets the material selection target constraints. This allows for the selection of feasible vehicle material selection schemes from the candidate schemes.

[0044] In one possible implementation, the data-driven vehicle target material selection model can be constructed in the following manner, which is explained in detail below.

[0045] For the safety performance-driven vehicle material selection model, the first step is to establish a first mapping relationship between the material mechanical properties and thickness parameters of automotive parts and the collision energy absorbed by the automotive parts, and then construct a second mapping relationship between the collision energy absorbed and the collision energy absorbed by the whole vehicle. Based on the first and second mapping relationships, a safety performance-driven vehicle material selection model is constructed.

[0046] The first and second mapping relationships are constructed based on preset coefficients, specifically energy absorption coefficients. These energy absorption coefficients are defined through part-level and vehicle-level material selection relationships. They characterize the mapping relationship between part-level material mechanical properties, thickness parameters, and part-level collision absorption energy. The collision absorption energy of components can generally be obtained through finite element analysis (FEA) of the component's crashworthiness relationship. Figure 5 As shown, the crashworthiness relationship of each component is illustrated.

[0047] Here, when selecting materials in the vehicle material selection model driven by safety performance, by obtaining the material mechanical performance parameters and thickness parameters of the corresponding parts in the candidate material data of the vehicle candidate material scheme, the collision absorption energy of the corresponding parts can be calculated according to the first mapping relationship corresponding to the energy absorption coefficient. Then, according to the second mapping relationship, the collision absorption energy of the whole vehicle can be calculated as the safety performance target value, and then the material selection scheme that meets the safety performance target value can be selected.

[0048] For the stiffness performance-driven vehicle material selection model, a third mapping relationship is established between the material mechanical performance parameters and thickness parameters of automotive parts and the overall stiffness performance of the vehicle body, and a stiffness performance-driven vehicle material selection model is constructed based on the third mapping relationship.

[0049] Similarly, the third mapping relationship here is constructed based on the vehicle model stiffness mapping relationship coefficients, such as... Figure 6 As shown, Figure 6 The stiffness performance mapping relationship of each component is displayed. The vehicle stiffness mapping relationship coefficient is determined through the vehicle-level to component-level stiffness performance mapping relationship, which is used to characterize the mapping relationship between component-level stiffness performance and vehicle-level stiffness performance. Specifically, it can be determined through Design of Experiments (DOE). Vehicle mass, construction cost, and high-strength steel ratio are solved using built-in functions, without the need to input relevant coefficients.

[0050] Here, in the stiffness performance-driven vehicle material selection model, by obtaining the material mechanical property parameters and thickness parameters of the corresponding components in the candidate material data of the vehicle candidate material schemes, the overall stiffness performance of the vehicle body can be calculated according to the third mapping relationship corresponding to the vehicle stiffness mapping relationship coefficient. This is used as the stiffness performance target value, and then material selection schemes that meet the stiffness performance target value are selected. In actual calculation, calculating the overall stiffness performance requires calculating the bending stiffness performance and torsional stiffness performance separately.

[0051] For the vehicle material selection model driven by lightweighting, a first quantitative relationship model is constructed as the vehicle material selection model driven by lightweighting. The first quantitative relationship model is used to calculate the vehicle body mass based on the material selection schemes output by the vehicle material selection models driven by safety performance and stiffness performance.

[0052] Here, the material selection of the vehicle material selection model driven by lightweight needs to be based on the material selection results of the vehicle material selection model driven by safety performance and the vehicle material selection model driven by stiffness performance. The first quantitative relationship model calculates the vehicle body mass by statistically analyzing the mass of each component used in these material selection results.

[0053] For the vehicle material selection model driven by economic efficiency, a second quantitative relationship model is constructed as the vehicle material selection model driven by economic efficiency. The second quantitative relationship model is used to calculate the construction cost of the car body based on the material selection schemes output by the vehicle material selection models driven by safety performance, stiffness performance, and lightweighting.

[0054] Here, the material selection for the economy-driven vehicle material selection model needs to be based on the material selection results of the safety-driven, stiffness-driven, and lightweight-driven vehicle material selection models. The second quantitative relationship model calculates the construction cost of the car body by statistically analyzing the cost of each component used in these material selection results.

[0055] For the vehicle material selection model driven by the proportion of high-strength steel, a third quantitative relationship model is constructed as the vehicle material selection model driven by the proportion of high-strength steel. The third quantitative relationship model is used to calculate the proportion of high-strength steel used in the car body based on the material selection schemes output by the vehicle material selection models driven by safety performance, stiffness performance, lightweighting, and economy.

[0056] Here, the material selection model driven by the proportion of high-strength steel in the vehicle needs to be based on the material selection results of the vehicle material selection models driven by safety performance, stiffness performance, lightweighting, and economy. The third quantitative relationship model calculates the proportion of high-strength steel used in the entire vehicle body by statistically analyzing the proportion of high-strength steel used in each component in these material selection results.

[0057] This invention, through the construction of a data-driven vehicle target material selection model, transforms the traditional material selection process, which relies on engineer experience, into a system decision-making process based on quantitative data and mathematical models. This significantly improves the objectivity, consistency, and repeatability of vehicle body material selection, and reduces decision-making biases and quality fluctuations caused by individual experience differences. Furthermore, by integrating a prediction and trade-off mechanism for multiple material selection objectives such as stiffness, safety, lightweighting, economy, and the proportion of high-strength steel, rapid material selection can be achieved while meeting various constraints.

[0058] In one possible implementation, multiple data-driven vehicle target material selection models are invoked sequentially to select candidate material schemes for the whole vehicle, thereby obtaining a feasible material selection scheme for the whole vehicle that meets the material selection target constraints. This can be achieved in the following ways, which are explained in detail below.

[0059] When selecting materials using the data-driven vehicle target material selection model, the material selection processes of the safety performance-driven vehicle material selection model and the stiffness performance-driven vehicle material selection model are executed in sequence.

[0060] Specifically, the safety performance-driven vehicle material selection model and the stiffness performance-driven vehicle material selection model are first called to calculate the safety performance target value and stiffness performance target value of the candidate material schemes, respectively. Then, the first vehicle material selection scheme that satisfies the material selection target constraint conditions in terms of safety performance target value and stiffness performance target value is selected from the candidate material schemes.

[0061] Among them, the safety performance-driven vehicle material selection model calculates the sum of the collision absorption energy of each component for each candidate material scheme to obtain the target value of vehicle safety performance, denoted as Q, which is used to reflect the level of vehicle safety performance. The calculation formula is expressed as follows: (2) Where i represents the i-th component. , as well as Let represent the material flow stress, material constitutive model parameters, and collision deformation strain rate parameters of the i-th component, respectively. and These represent the collision deformation energy absorption parameters of the i-th component, respectively. This indicates the collision energy absorbed by all components in the vehicle other than the 11 designated components. This represents the thickness of the i-th component; different components have different thicknesses.

[0062] The stiffness performance-driven vehicle material selection model calculates the target value of vehicle stiffness performance through the vehicle model stiffness mapping relationship coefficient. Specifically, it calculates the target value of bending stiffness performance for each candidate material scheme for the vehicle. and torsional stiffness performance target value The formula is as follows: (3) (4) in, , , , These are all vehicle model stiffness mapping coefficients, representing the bending stiffness fitting coefficient, bending stiffness fitting constant, torsional stiffness fitting coefficient, and torsional stiffness fitting constant of the i-th component, respectively. Let represent the elastic modulus of the material of the i-th component. This represents the thickness of the i-th component.

[0063] The above steps allow us to calculate the safety performance target value Q and stiffness performance target value (including...) for each candidate material scheme for the whole vehicle. , Next, the first vehicle material selection scheme that meets the material selection target constraints in terms of safety performance target value and stiffness performance target value can be selected from the candidate material schemes for the whole vehicle.

[0064] The material selection target constraints specify the value ranges (upper and lower limits) of the corresponding target values ​​for safety performance and stiffness performance. These ranges allow us to determine the corresponding safety performance target value Q and stiffness performance target value for the current candidate material schemes for the vehicle. , Does it meet the lower limit corresponding to the safety performance target? Lower limit of bending stiffness target The lower limit of the torsional stiffness target If the conditions are not met, the material will be filtered out; if the conditions are met, it will be retained as the first material selection option for the whole vehicle.

[0065] Next, the lightweight-driven vehicle material selection model is called to calculate the vehicle quality target value of the first vehicle material selection scheme, and a second vehicle material selection scheme that satisfies the material selection target constraint condition is selected from the first vehicle material selection scheme.

[0066] Here, the lightweight-driven vehicle material selection model calculates the corresponding vehicle mass target value, denoted as M, for each first vehicle material selection scheme by accumulating the mass of each component. The formula is as follows: (5) in, , , Let these represent the structural area, thickness, and material density of the i-th component, respectively. This indicates the mass of all components in the vehicle other than the 11 main components.

[0067] Furthermore, a second vehicle material selection scheme is selected from the first vehicle material selection scheme to ensure that the vehicle quality target value meets the material selection target constraints. The material selection target constraints specify the range of values ​​corresponding to the vehicle quality target. This range allows us to determine whether the vehicle quality target value M corresponding to the current first vehicle material selection scheme meets the upper limit of the vehicle quality target. If the conditions are not met, the material will be eliminated; if the conditions are met, it will be retained as the second material selection option for the whole vehicle.

[0068] Next, the economic-driven vehicle material selection model is used to calculate the construction cost target value of the second vehicle material selection scheme, and the third vehicle material selection scheme that meets the material selection target constraint condition is selected from the second vehicle material selection scheme.

[0069] Here, the economy-driven vehicle material selection model calculates the corresponding construction cost target value, denoted as C, for each second vehicle material selection scheme by cumulatively calculating the cost of each component. The formula is as follows: (6) in, , , Let these represent the mass, cost, and thickness of the i-th component, respectively. This indicates the cost of all components in the vehicle other than the 11 main components.

[0070] Furthermore, a third vehicle material selection scheme is selected from the second vehicle material selection schemes, whose construction cost target value meets the material selection target constraints. The material selection target constraints specify the range of values ​​corresponding to the construction cost target. This range allows us to determine whether the construction cost target value C corresponding to the current second vehicle material selection scheme meets the upper limit of the construction cost target. If the conditions are not met, the material will be filtered out; if the conditions are met, it will be retained as the third vehicle material selection option.

[0071] Finally, the target value of the high-strength steel application ratio in the third vehicle material selection scheme is calculated by calling the vehicle material selection model driven by the proportion of high-strength steel. Then, feasible vehicle material selection schemes that satisfy the material selection target constraint conditions are selected from the third vehicle material selection schemes.

[0072] Here, the high-strength steel proportion-driven vehicle material selection model calculates the corresponding target value of high-strength steel application ratio, denoted as R, for each third vehicle material selection scheme by accumulating the mass of high-strength steel in each component. The formula is as follows: (7) in, This indicates the number of high-strength steel components out of the 11 components. Indicates the first The quality of high-strength steel components. This indicates the mass of all high-strength steel components in the vehicle other than the 11 designated parts. The target vehicle mass value is calculated using a lightweight-driven vehicle material selection model. The calculation method is not detailed here. , , They represent the first The structural area, material density, and thickness of each high-strength steel component.

[0073] Furthermore, feasible vehicle material selection schemes that satisfy the material selection target constraints are selected from the third vehicle material selection scheme. The material selection target constraints specify the range of values ​​for the target value corresponding to the high-strength steel application ratio. This range allows us to determine whether the current high-strength steel application ratio target value R of the third vehicle material selection scheme meets the lower limit of the high-strength steel application ratio target. If the conditions are not met, the material will be filtered out; if the conditions are met, it will be retained as a feasible material selection option for the whole vehicle.

[0074] In this embodiment of the invention, candidate material schemes for the whole vehicle are generated based on candidate material data. Various data-driven target material selection models for the whole vehicle are constructed to select materials layer by layer. In the material selection process, multi-layer screening is achieved by using material selection target constraints. Under the condition of prediction and trade-off of multiple material selection targets such as stiffness, safety, lightweight, economy and high-strength steel ratio, the screening of multiple candidate material schemes for the whole vehicle is realized. While improving the material selection efficiency, it overcomes the limitation of traditional methods that are difficult to coordinate multiple material selection targets.

[0075] Step 103: Use the non-dominated sorting algorithm to filter feasible material selection schemes for the whole vehicle and obtain candidate recommended schemes for automobile body material selection.

[0076] After the aforementioned vehicle target material selection models are used to select materials layer by layer, the feasible material selection schemes for the vehicle meet all material selection target constraints. However, there are many feasible material selection schemes for the vehicle. It is necessary to further filter all feasible material selection schemes for the vehicle based on the non-dominated sorting algorithm to obtain the recommended candidate schemes for vehicle body material selection that only contain non-dominated solutions.

[0077] In one possible implementation, a non-dominated sorting algorithm is used to filter feasible material selection schemes for the whole vehicle to obtain candidate recommended schemes for automobile body materials. This can be achieved in the following way, which is explained in detail below.

[0078] First, a non-dominated sorting algorithm is used to perform a non-dominated sorting of feasible material selection schemes for the entire vehicle. During the material selection process, multiple selection objectives need to be considered, including stiffness, safety, lightweighting, economy, and the proportion of high-strength steel. All feasible material selection schemes satisfy these objectives. Through non-dominated sorting, non-dominated solutions can be selected from a large number of feasible schemes. These solutions achieve an optimal balance among multiple objectives, and other material selection schemes cannot outperform them in all aspects.

[0079] Then, the sorted material selection schemes, including only non-dominated solutions, are used as candidate recommended schemes for automotive body material selection. The non-dominated sorting algorithm significantly reduces the size of the material selection schemes and improves selection efficiency. The selected candidate recommended schemes can be visualized using radar charts or similar methods for display to users. See also Figure 8 , Figure 8 A radar chart of candidate recommended solutions is displayed. The chart shows the specific gravity, torsional stiffness, bending stiffness, safety, total cost, and total mass of high-strength steel, allowing users to quickly understand the specific evaluation criteria for each material selection option among the candidate recommended solutions. It can be seen that no single solution is superior to the others in all objectives.

[0080] In this embodiment of the invention, based on a non-dominated sorting algorithm, a systematic evaluation and rapid comparison of various feasible material selection schemes for complete vehicles is achieved, resulting in a smaller set of candidate recommended schemes.

[0081] Step 104: Perform multi-criteria decision-making on the candidate recommended solutions to obtain the final recommended solution for the selection of automotive body materials.

[0082] The purpose of multi-criteria decision-making is to comprehensively evaluate and rank the candidate recommendations. This requires pre-determining the weight allocation of each material selection criterion in the candidate recommendations, and then implementing a multi-criteria decision-making method to ultimately select the final recommended material for the automotive body.

[0083] The material selection evaluation criteria here refer to the performance criteria that need to be considered when selecting materials for the automotive body, which are also the overall vehicle material selection objectives. Specifically, these include safety performance objectives, stiffness performance objectives, overall vehicle quality objectives, construction cost objectives, and high-strength steel application ratio objectives. Allocating the weights of the material selection evaluation criteria is to assign weights to these overall vehicle material selection objectives. The weights are used to characterize the degree of emphasis on the material selection objectives. The higher the weight allocation, the more emphasis is placed on the material selection objective.

[0084] In one possible implementation, multi-criteria decision-making is performed on candidate recommended solutions to obtain the final recommended solution for automobile body materials. This can be achieved in the following ways, which are explained in detail below.

[0085] First, for each candidate recommendation scheme, the weights of each selection evaluation criterion are determined based on the entropy weight method.

[0086] like Figure 7 As shown, there are two ways to obtain the weights of the material selection criteria. The first is that the user pre-defines them according to their needs, which can be obtained directly. The second is that the user does not define them, which needs to be determined by the entropy weight method.

[0087] In one possible implementation, the weights of each selection criterion are determined based on the entropy weight method, which can be achieved in the following way, as explained in detail below.

[0088] When it is found that the weight corresponding to the material selection evaluation criterion has been customized, the customized material selection evaluation criterion weight will be used as the material selection criterion weight. When the weights corresponding to the material selection evaluation criteria are not defined, the information entropy of each material selection evaluation criterion in the candidate recommendation scheme is determined based on the entropy weight method, and the weight of each material selection evaluation criterion is set according to the magnitude of the information entropy.

[0089] Here, during the multi-criteria decision-making process, the weight of each material selection evaluation criterion in the candidate recommendation scheme is automatically triggered for querying. When it is found that the weight corresponding to the material selection evaluation criterion has been customized, it means that the user has manually set the weight of each material selection target according to actual needs, and it can be directly obtained. Therefore, the customized material selection evaluation criterion weight is used as the weight corresponding to the material selection evaluation criterion.

[0090] If the weights of the material selection evaluation criteria are not customized, it means that the user has not manually set the weights of each material selection target. In this case, the entropy weight method is used to calculate the weights of the material selection evaluation criteria.

[0091] The entropy weight method calculates the information entropy of each selection criterion corresponding to the candidate recommendation scheme by constructing an evaluation matrix. Then, it sets and assigns weights to each selection criterion based on the magnitude of the information entropy. The magnitude of the information entropy is positively correlated with the weight of the selection criterion. That is, the greater the information entropy, the greater the weight of the selection criterion, and vice versa.

[0092] Once the weights corresponding to each material selection evaluation criterion have been determined, a multi-criteria decision-making method is used to analyze the candidate recommendation schemes to obtain the final material selection recommendation scheme. Specifically, according to the weights of the whole vehicle material selection evaluation criteria, the multi-criteria decision-making algorithm is used to sort the candidate recommendation schemes in reverse order, and the candidate recommendation scheme at the beginning of the sequence is determined as the final recommendation scheme for the vehicle body material selection.

[0093] Here, the multi-criteria decision-making method can be the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS), and other multi-criteria decision-making methods can also be used in appropriate scenarios. Multi-criteria decision-making methods can calculate the positive and negative ideal solutions based on the weights of these material selection evaluation criteria.

[0094] Finally, the relative closeness between each material selection scheme and the ideal solution in the candidate recommended schemes is calculated, and the material selection scheme with the highest relative closeness is determined as the final recommended scheme for automobile body material selection.

[0095] Here, the positive and negative ideal solutions are the optimal and worst-performing material selection schemes obtained by the superior-inferior solution distance method based on the existing candidate recommendation schemes. For each candidate recommendation scheme, the relative fit with the ideal solution can be calculated, and then they are sorted in descending order of relative fit. A higher relative fit indicates a closer fit to the positive ideal solution and a greater distance from the negative ideal solution, resulting in a higher ranking. Ultimately, by searching the first part of the sequence, a candidate solution with the highest relative fit can be determined. This candidate solution can then be used as the final recommended solution for selecting automotive body materials.

[0096] like Figure 9 As shown, Figure 9 A radar chart shows the final recommended material selection for the automotive body. The chart displays the proportion of high-strength steel, torsional stiffness, bending stiffness, safety, total cost, and total mass of the vehicle corresponding to the final recommended solution, allowing users to quickly understand the specific details of each material selection objective in the final recommended solution.

[0097] like Figure 10 As shown, Figure 10 This diagram illustrates the final recommended material selection for automotive bodies. It lists the recommended material types and corresponding structural thicknesses for each component, and provides a direct comparison with corresponding components in a benchmark vehicle in terms of material selection and thickness parameters. This result provides a clear reference for material selection design in actual automotive development.

[0098] This invention, through the establishment of multiple data-driven vehicle material selection models and a multi-criteria decision-making mechanism, transforms the traditional material selection process, which relies on human experience, into a system decision-making process driven by quantitative material data and mathematical models. This significantly improves the objectivity, consistency, and repeatability of automotive material selection, and reduces decision-making biases and quality fluctuations caused by human experience. Furthermore, the vehicle target material selection model, during sequential material selection, integrates prediction and trade-off mechanisms for multiple objectives such as stiffness, safety, lightweighting, economy, and the proportion of high-strength steel. It can select from multiple material options while meeting preset material selection objective constraints. The non-dominated ranking and multi-criteria decision-making mechanism not only improve material selection efficiency but also overcome the limitations of traditional methods in coordinating multiple material selection objectives, supporting the overall optimization of vehicle performance, lightweighting, and economy.

[0099] Furthermore, the data-driven forward material selection method for automotive multi-material bodies provided by this invention offers a fully transparent material selection process, from material data management and material selection model construction to scheme screening and decision support. It also visualizes certain screening results according to requirements, enabling users to flexibly set goals, monitor the process in real time, and compare and analyze various feasible material selection schemes for the entire vehicle, significantly shortening the material selection cycle. Simultaneously, the system supports vehicle-specific parameter configuration and historical data backtracking, significantly enhancing the controllability and decision traceability of the automotive R&D process, providing a platform foundation for continuous optimization of body materials. This helps to establish unified material selection standards and standardized processes at the enterprise and even industry levels, reducing decision-making differences between different R&D teams or projects, strengthening technical collaboration and data exchange between OEMs, material suppliers, and component manufacturers, and providing efficient platform support for the innovation and application of body materials.

[0100] The following section details the data-driven forward material selection system for automotive multi-material bodies provided by this invention.

[0101] Figure 11 This is a schematic diagram of the data-driven forward material selection system for automotive multi-material bodies provided by this invention. Figure 11 As shown, the data-driven forward material selection system for automotive multi-material body includes: a material database module 1101, a material selection model construction module 1102, a dominance ranking module 1103, and a multi-criteria decision-making module 1104.

[0102] Specifically, the material database module 1101 is used to acquire the material selection target constraints and candidate material data for the automobile body; the material selection model construction module 1102 is used to generate candidate material schemes for the whole vehicle based on the candidate material data, and call multiple data-driven whole vehicle target material selection models to select the candidate whole vehicle material schemes in sequence to obtain feasible whole vehicle material selection schemes that meet the material selection target constraints. The order in which the whole vehicle target material selection models select materials includes: the whole vehicle material selection model driven by safety performance, the whole vehicle material selection model driven by stiffness performance, the whole vehicle material selection model driven by lightweighting, the whole vehicle material selection model driven by economy, and the whole vehicle material selection model driven by high-strength steel ratio; the non-dominated sorting module 1103 is used to call the dominant sorting algorithm to sort and filter the feasible whole vehicle material selection schemes to obtain candidate recommended schemes for automobile body material selection; and the multi-criteria decision module 1104 is used to perform multi-criteria decision-making on the candidate recommended schemes to obtain the final recommended scheme for automobile body material selection.

[0103] The data-driven forward material selection system for automotive multi-material body provided in the above embodiments can realize the technical solutions described in the above embodiments of the data-driven forward material selection method for automotive multi-material body. The specific implementation principles of each module or unit can be found in the corresponding content in the above embodiments of the data-driven forward material selection method for automotive multi-material body, and their technical effects can also be referred to each other, which will not be repeated here.

[0104] like Figure 12 As shown, the present invention also provides an electronic device 1200. The electronic device 1200 includes a processor 1201, a memory 1202, and a display 1203. Figure 11 Only some components of the electronic device 1200 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0105] In some embodiments, memory 1202 may be an internal storage unit of electronic device 1200, such as a hard disk or memory of electronic device 1200. In other embodiments, memory 1202 may also be an external storage device of electronic device 1200, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 1200.

[0106] Furthermore, the memory 1202 may include both internal storage units of the electronic device 1200 and external storage devices. The memory 1202 is used to store application software and various types of data installed on the electronic device 1200.

[0107] In some embodiments, processor 1201 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 1202 or process data, such as the data-driven forward material selection method for multi-material car bodies in this invention.

[0108] In some embodiments, display 1203 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 1203 is used to display information from electronic device 1200 and to display a visual user interface. Components 1201-1203 of electronic device 1200 communicate with each other via a system bus.

[0109] In some embodiments of the present invention, when the processor 1201 executes the vehicle body forward material selection program in the memory 1202, the following steps can be implemented: obtaining the material selection target constraints and candidate material data of the vehicle body; generating a whole vehicle candidate material scheme based on the candidate material data, and calling multiple data-driven whole vehicle target material selection models to select the whole vehicle candidate material scheme in sequence, thereby obtaining a whole vehicle feasible material selection scheme that meets the material selection target constraints. The order in which the whole vehicle target material selection models select materials includes: selecting materials in the order of safety performance-driven whole vehicle material selection model, stiffness performance-driven whole vehicle material selection model, lightweight-driven whole vehicle material selection model, economy-driven whole vehicle material selection model, and high-strength steel ratio-driven whole vehicle material selection model; calling a non-dominated sorting algorithm to filter the whole vehicle feasible material selection scheme, thereby obtaining a candidate recommended scheme for vehicle body material selection; and performing multi-criteria decision-making on the candidate recommended scheme to obtain the final recommended scheme for vehicle body material selection.

[0110] It should be understood that when the processor 1201 executes the vehicle body forward material selection program in the memory 1202, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0111] Furthermore, the embodiments of the present invention do not specifically limit the type of the electronic device 1200 mentioned. The electronic device 1200 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1200 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0112] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a data-driven forward material selection method for automotive multi-material bodies provided by the methods described above. This method includes: acquiring material selection target constraints and candidate material data for the automotive body; generating candidate material schemes for the entire vehicle based on the candidate material data; and sequentially selecting the candidate material schemes for the entire vehicle using multiple data-driven target material selection models for the entire vehicle to obtain feasible material selection schemes for the entire vehicle that meet the material selection target constraints. The order in which the target material selection models for the entire vehicle select materials includes: sequentially selecting materials according to the following order: safety performance-driven model, stiffness performance-driven model, lightweight model, economy-driven model, and high-strength steel ratio-driven model; using a non-dominated sorting algorithm to filter the feasible material selection schemes for the entire vehicle to obtain candidate recommended schemes for automotive body material selection; and performing multi-criteria decision-making on the candidate recommended schemes to obtain the final recommended scheme for automotive body material selection.

[0113] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0114] The above provides a detailed description of the data-driven forward material selection method and system for automotive multi-material bodies provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A data-driven method for forward material selection of multi-material automotive body, characterized in that, include: Obtain the material selection target constraints and candidate material data for the automobile body; Based on the candidate material data, a vehicle candidate material scheme is generated, and multiple data-driven vehicle target material selection models are invoked to select the vehicle candidate material scheme in sequence to obtain a vehicle feasible material selection scheme that meets the material selection target constraints. The order in which the vehicle target material selection models select materials includes: the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, the vehicle material selection model driven by economy, and the vehicle material selection model driven by high-strength steel ratio. The non-dominated sorting algorithm is used to filter the feasible material selection schemes for the whole vehicle, and candidate recommended schemes for the selection of automotive body materials are obtained. A multi-criteria decision-making process is performed on the candidate recommendations to obtain the final recommended solution for automobile body materials.

2. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The constraints on the material selection targets for the whole vehicle include the range of values ​​corresponding to multiple material selection targets for the whole vehicle. The material selection targets for the whole vehicle include safety performance targets, stiffness performance targets, whole vehicle quality targets, construction cost targets, and high-strength steel application ratio targets.

3. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The data-driven vehicle target material selection model is constructed as follows: A first mapping relationship is established between the material mechanical properties and thickness parameters of automotive parts and the collision absorption energy of automotive parts, and a second mapping relationship is constructed between the collision absorption energy and the collision absorption energy of the whole vehicle. Based on the first mapping relationship and the second mapping relationship, a safety performance-driven whole vehicle material selection model is constructed. A third mapping relationship is established between the material mechanical properties and thickness parameters of automotive parts and the stiffness performance of the automotive body, and a stiffness performance-driven whole vehicle material selection model is constructed based on the third mapping relationship. A first quantitative relationship model is constructed as a vehicle material selection model driven by lightweighting. The first quantitative relationship model is used to calculate the vehicle body mass based on the material selection scheme output by the vehicle material selection model driven by safety performance and the vehicle material selection model driven by stiffness performance. A second quantitative relationship model is constructed as an economically driven vehicle material selection model. The second quantitative relationship model is used to calculate the construction cost of the car body based on the material selection scheme output by the safety performance driven vehicle material selection model, the stiffness performance driven vehicle material selection model, and the lightweight driven vehicle material selection model. A third quantitative relationship model is constructed as a vehicle material selection model driven by the proportion of high-strength steel. The third quantitative relationship model is used to calculate the proportion of high-strength steel used in the car body based on the material selection schemes output by the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, and the vehicle material selection model driven by economy.

4. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The process of sequentially selecting candidate material schemes for the vehicle by calling multiple data-driven vehicle target material selection models to obtain feasible vehicle material selection schemes that meet the material selection target constraints includes: The vehicle material selection model driven by safety performance and the vehicle material selection model driven by stiffness performance are called to calculate the target values ​​of safety performance and stiffness performance of the candidate vehicle material selection schemes, respectively. The first vehicle material selection scheme that satisfies the target values ​​of safety performance and stiffness performance from the candidate vehicle material selection schemes is selected. The vehicle material selection model driven by lightweight design is called to calculate the target vehicle quality value of the first vehicle material selection scheme, and a second vehicle material selection scheme whose target vehicle quality value meets the material selection target constraint is selected from the first vehicle material selection scheme. The construction cost target value of the second vehicle material selection scheme is calculated by calling the economic-driven vehicle material selection model, and a third vehicle material selection scheme whose construction cost target value meets the material selection target constraint is selected from the second vehicle material selection scheme. The target value of the high-strength steel application ratio in the third vehicle material selection scheme is calculated by calling the vehicle material selection model driven by the proportion of high-strength steel. Then, feasible vehicle material selection schemes that satisfy the vehicle material selection target constraint conditions are selected from the third vehicle material selection scheme.

5. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The step of using a non-dominated sorting algorithm to filter feasible material selection schemes for the entire vehicle and obtaining candidate recommended schemes for vehicle body material selection includes: The non-dominated sorting algorithm is called to perform non-dominated sorting on the feasible material selection schemes for the whole vehicle, and the material selection schemes that only include non-dominated solutions after sorting are used as candidate recommended schemes for the selection of automotive body materials.

6. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The step of performing multi-criteria decision-making on the candidate recommended solutions to obtain the final recommended solution for automobile body materials includes: For the aforementioned candidate recommendation schemes, the weights of each vehicle material selection evaluation criterion are determined based on the entropy weight method. According to the weights of the vehicle material selection evaluation criteria, the multi-criteria decision algorithm is called to sort the candidate recommended schemes in reverse order, and the candidate recommended scheme at the head of the sequence is determined as the final recommended scheme for vehicle body material selection.

7. The data-driven forward material selection method for multi-material automotive body as described in claim 1, characterized in that, The determination of the weights corresponding to each material selection evaluation criterion based on the entropy weight method includes: When it is found that the weight corresponding to the material selection evaluation criterion has been customized, the customized material selection evaluation criterion weight will be used as the weight corresponding to the material selection evaluation criterion. When it is found that the weights corresponding to the material selection evaluation criteria are not customized, the information entropy of each material selection evaluation criterion in the candidate recommendation scheme is determined based on the entropy weight method. The weights of each selection criterion are calculated based on the magnitude of the information entropy, and the magnitude of the information entropy is positively correlated with the weights of the selection criteria.

8. A data-driven forward material selection system for automotive multi-material body, characterized in that, include: The materials database module is used to obtain the material selection target constraints and candidate material data for automobile bodies; The material selection model construction module is used to generate vehicle candidate material schemes based on the candidate material data, and to call multiple data-driven vehicle target material selection models to select the vehicle candidate material schemes in sequence, so as to obtain a feasible vehicle material selection scheme that meets the material selection target constraints. The order in which the vehicle target material selection models select materials includes: the vehicle material selection model driven by safety performance, the vehicle material selection model driven by stiffness performance, the vehicle material selection model driven by lightweighting, the vehicle material selection model driven by economy, and the vehicle material selection model driven by high-strength steel ratio. The non-dominated sorting module is used to call the non-dominated sorting algorithm to filter the feasible material selection schemes for the whole vehicle and obtain the candidate recommended schemes for the selection of automotive body materials. The multi-criteria decision module is used to make multi-criteria decisions on the candidate recommendation schemes to obtain the final recommended scheme for automobile body materials.

9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is configured to execute the program stored in the memory to implement the steps of the data-driven forward material selection method for automotive multi-material body as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the data-driven forward material selection method for automotive multi-material body as described in any one of claims 1 to 7.

Images