Vehicle cover design method and related device
By establishing the correspondence between the vehicle cover structure and performance, the problem of excessive design cycle in the existing design methods is solved, and the efficient and intelligent design of the vehicle cover is achieved.
Patent Information
- Application Number
- CN202311106713.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-29
- Publication Date
- 2025-02-28
AI Technical Summary
The existing vehicle cover design methods require repeated modeling, simulation and inspection, resulting in too long design cycles and cannot meet the needs of efficient design.
By establishing the correspondence between the vehicle cover structure and performance, determining the candidate structure based on the target performance, and screening out the final structure that meets the performance and shape through the target shape, achieving efficient and intelligent design.
It greatly improves the design efficiency of vehicle covers and shortens the design cycle. It does not require repeated modeling, simulation and inspection. It can design a vehicle cover that meets the requirements under any given shape.
Smart Images
Figure CN119538395A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle cover design method and related devices. Background Art
[0002] As the popularity of vehicles increases, vehicle models are also moving from a single model to a diversified model. As an important part of vehicle model design, vehicle covers need to be designed in a variety of ways according to the diverse vehicle models to meet the market demand for vehicle models.
[0003] The design steps of the vehicle hood in the related technology are as follows: first, according to the given vehicle hood shape and preliminary layout section, the modeling parameters for building the vehicle hood are input into the modeling software to build the model, and then the model is input into the simulation software for simulation to obtain the vehicle hood performance under the current modeling parameters, and check whether it meets the required performance. If not, modify the modeling parameters of the vehicle hood and repeat the above operations to design a vehicle hood that meets the required performance.
[0004] However, this design method requires repeated modeling, simulation and testing, which is time-consuming and labor-intensive. As a result, the design cycle of the vehicle hood is too long and cannot meet the needs of efficient design of the vehicle hood. Summary of the Invention
[0005] In order to solve the above technical problems, the present application provides a vehicle hood design method and related devices, which establish a correspondence between the vehicle hood structure and the vehicle hood performance, and perform hood design according to the correspondence to achieve efficient and intelligent vehicle hood design.
[0006] The embodiments of this application disclose the following technical solutions:
[0007] In a first aspect, an embodiment of the present application discloses a vehicle hood design method, the method comprising:
[0008] Obtaining a target cover shape and target cover performance of a cover to be designed;
[0009] Determining, based on the target hood performance and the hood correspondence relationship, a plurality of candidate hood structures corresponding to the target hood performance; the hood correspondence relationship being established based on a plurality of hood structures and a plurality of hood performances corresponding to a plurality of vehicle hoods, the hood structures including hood shape, hood cross-sectional form, hood middle beam form, and hood cross-sectional dimensions;
[0010] Performing contour projection on the target cover shape to obtain the target cover shape of the cover to be designed;
[0011] According to the target cover shape, a target cover structure that meets the target cover shape is determined from the multiple candidate cover structures.
[0012] Optionally, the establishment of the cover-cap correspondence relationship includes:
[0013] Establishing a cover structure database based on the multiple cover structures corresponding to the multiple vehicle covers; establishing a cover performance database based on the multiple cover performances corresponding to the multiple vehicle covers;
[0014] Establishing a plurality of cover fitting models of the cover structures and the cover performance according to the cover structure database and the cover performance database;
[0015] The cover-cap fitting model is determined as the cover-cap correspondence.
[0016] Optionally, performing contour projection on the target cover shape to obtain the target cover shape of the cover to be designed includes:
[0017] Performing contour projection on the target cover shape to obtain an initial cover shape of the cover to be designed;
[0018] A cover shape in the cover structure database whose similarity to the initial cover shape satisfies a similarity condition is determined as the target cover shape.
[0019] Optionally, the method further includes:
[0020] Decomposing the cover structure database into a plurality of cover structure sub-databases according to a plurality of cover shapes of the plurality of vehicle covers;
[0021] The step of determining, according to the target cover shape, a target cover structure that meets the target cover shape from among the plurality of candidate cover structures comprises:
[0022] A target cover structure that meets the target cover performance is searched in a cover structure sub-database corresponding to a cover shape whose similarity to the initial cover shape satisfies a similarity condition.
[0023] Optionally, the establishment of the cover-cap correspondence relationship includes:
[0024] Training a machine learning model using the plurality of cover structures and the plurality of cover performances having a corresponding relationship as training data to obtain a cover structure prediction model;
[0025] The cover structure prediction model is determined as the cover correspondence relationship.
[0026] Optionally, the step of training a machine learning model using the corresponding plurality of cover structures and the corresponding plurality of cover performances as training data to obtain a cover structure prediction model includes:
[0027] Performing cover structure prediction on the plurality of cover performances using the machine learning model to obtain a plurality of cover structure prediction results;
[0028] Constructing a cover structure loss function according to a plurality of the cover structure prediction results and a plurality of the cover structures having a corresponding relationship with a plurality of the cover performances;
[0029] Training the machine learning model according to the cover structure loss function;
[0030] The trained machine learning model is determined as the cover structure prediction model.
[0031] Optionally, the method further includes:
[0032] Performing variance analysis based on the target cover cross-sectional form, the target cover middle beam form, and the target cover performance to determine a first influence weight of the target cover cross-sectional form on the target cover performance, a second influence weight of the target cover middle beam form on the target cover performance, and a cross-influence weight of the target cover cross-sectional form and the target cover middle beam form on the target cover performance;
[0033] The influence relationship between the target cover middle beam form and the target cover cross-section form on the target cover performance is determined according to the first influence weight, the second influence weight and the cross-influence weight.
[0034] In a second aspect, an embodiment of the present application discloses a vehicle hood design device, the device comprising:
[0035] A target cover data acquisition unit, used to acquire the target cover shape and target cover performance of the cover to be designed;
[0036] a candidate cover structure determining unit, configured to determine, based on the target cover performance and a cover correspondence relationship, a plurality of candidate cover structures corresponding to the target cover performance; the cover correspondence relationship being established based on a plurality of cover structures and a plurality of cover performances corresponding to a plurality of vehicle covers, the cover structure including a cover shape, a cover cross-sectional form, a cover intermediate beam form, and a cover cross-sectional size;
[0037] a target cover shape determining unit, configured to perform contour projection on the target cover form to obtain the target cover shape of the cover to be designed;
[0038] The target cover structure determining unit is configured to determine, according to the target cover shape, a target cover structure that meets the target cover shape from among the plurality of candidate cover structures.
[0039] Optionally, the establishment of the cover-cap correspondence relationship includes:
[0040] A cover database establishing unit, configured to establish a cover structure database based on a plurality of cover structures corresponding to the plurality of vehicle covers; and to establish a cover performance database based on a plurality of cover performances corresponding to the plurality of vehicle covers;
[0041] a cover fitting model establishing unit, configured to establish a plurality of cover fitting models of the cover structures and the cover performances according to the cover structure database and the cover performance database;
[0042] The first cover-cap correspondence determination unit is configured to determine the cover-cap fitting model as the cover-cap correspondence.
[0043] Optionally, the target cover shape determining unit is further configured to:
[0044] Performing contour projection on the target cover shape to obtain an initial cover shape of the cover to be designed;
[0045] A cover shape in the cover structure database whose similarity to the initial cover shape satisfies a similarity condition is determined as the target cover shape.
[0046] Optionally, the device further includes:
[0047] a database decomposition unit, configured to decompose the cover structure database into a plurality of cover structure sub-databases according to a plurality of cover shapes of a plurality of vehicle covers;
[0048] The target cover structure determination unit is further configured to:
[0049] A target cover structure that meets the target cover performance is searched in a cover structure sub-database corresponding to a cover shape whose similarity to the initial cover shape satisfies the similarity condition.
[0050] Optionally, the establishment of the cover-cap correspondence relationship includes:
[0051] a prediction model obtaining unit, configured to train a machine learning model using a plurality of the cover structures and a plurality of the cover performances having a corresponding relationship as training data to obtain a cover structure prediction model;
[0052] The second cover-cap correspondence relationship determining unit is configured to determine the cover-cap structure prediction model as the cover-cap correspondence relationship.
[0053] Optionally, the prediction model obtaining unit is further configured to:
[0054] Performing cover structure prediction on the plurality of cover performances using the machine learning model to obtain a plurality of cover structure prediction results;
[0055] Constructing a cover structure loss function according to a plurality of the cover structure prediction results and a plurality of the cover structures having a corresponding relationship with a plurality of the cover performances;
[0056] Training the machine learning model according to the cover structure loss function;
[0057] The trained machine learning model is determined as the cover structure prediction model.
[0058] Optionally, the device further includes:
[0059] an influence weight determination unit, configured to perform variance analysis based on the target cover cross-sectional form, the target cover middle beam form, and the target cover performance, to determine a first influence weight of the target cover cross-sectional form on the target cover performance, a second influence weight of the target cover middle beam form on the target cover performance, and a cross-influence weight of the target cover cross-sectional form and the target cover middle beam form on the target cover performance;
[0060] The influence relationship determining unit is used to determine the influence relationship between the target cover middle beam form and the target cover cross-section form on the target cover performance according to the first influence weight, the second influence weight and the cross influence weight.
[0061] In a third aspect, an embodiment of the present application discloses a computer device, comprising a processor and a memory:
[0062] The memory is used to store program code and transmit the program code to the processor;
[0063] The processor is configured to execute the vehicle hood design method as described in the first aspect and any optional item of the first aspect according to the instructions in the program code.
[0064] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, it is used to execute the vehicle hood design method as described in the first aspect and any optional option of the first aspect.
[0065] It can be seen from the above technical solution that a cover correspondence is established through multiple cover structures and multiple cover performances corresponding to multiple vehicle covers. The cover structure includes cover shape, cover cross-sectional form, cover middle beam form and cover cross-sectional size. When designing a vehicle cover, the target cover shape and target cover performance of the cover to be designed are first obtained, and then the target cover shape is contour projected to obtain the target cover shape of the cover to be designed. Then, based on the correspondence and starting from the target cover performance, multiple candidate cover structures are determined in the cover correspondence. Then, through the target cover shape, the required target cover structure is determined among the multiple candidate cover structures. The vehicle cover is designed based on the correspondence between performance and structure. Under any given shape, a vehicle cover that meets the required performance can be designed without repeated modeling, simulation and testing, which greatly improves the design efficiency of the vehicle cover and shortens the design cycle of the vehicle cover. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0067] Figure 1 A flow chart of a vehicle hood design method provided in an embodiment of the present application;
[0068] Figure 2 A schematic diagram of the numbering rules for a vehicle cover design method provided in an embodiment of the present application;
[0069] Figure 3 A system structure diagram of a vehicle hood design system provided in an embodiment of the present application;
[0070] Figure 4 A schematic diagram of a vehicle cover projection outline provided in an embodiment of the present application;
[0071] Figure 5 A structural block diagram of a vehicle cover design device provided in an embodiment of the present application;
[0072] Figure 6 A structural block diagram of a computer device for vehicle cover design provided in an embodiment of the present application;
[0073] Figure 7 A schematic diagram of the interaction effect inside a vehicle hood provided in an embodiment of the present application. DETAILED DESCRIPTION
[0074] In order to enable people in this technical field to better understand the solution of this application, the technical solution in the embodiment of this application will be clearly and completely described below in combination with the drawings in the embodiment of this application. Obviously, the described embodiment is only a part of the embodiment of this application, not all of the embodiments.
[0075] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, and are merely used to describe the manner in which objects with the same attributes are distinguished in the embodiments of this application.
[0076] Due to the market's demand for more diverse vehicle models, companies need to develop new models in a shorter cycle to seize the market. As a key part of vehicle design, vehicle covers need to be designed in a variety of ways to meet the market's demand for diverse models.
[0077] The vehicle hood has a complex structure, specifically including outer panels, inner panels, middle beams, hinges, hinge reinforcement plates, lock reinforcement plates, gas strut reinforcement plates, buffer block mounting bosses, reinforcement ribs, and other structures. The current vehicle hood design process first obtains the modeling parameters for building the vehicle hood based on the given vehicle hood shape and the initial layout section. These modeling parameters are input into the modeling software to build the model. The model is then input into the simulation software for simulation to obtain the vehicle hood performance under the current modeling parameters. The simulated vehicle hood is then tested based on the required performance of the vehicle hood. If the required performance is not met, the modeling parameters are modified, and the modeling, simulation, and testing work is repeated to finally obtain a vehicle hood that meets the required performance. However, this method requires a large number of repeated iterations. The repeated execution of the modeling, simulation, and testing steps makes the design inefficient and prolongs the design cycle of the vehicle hood.
[0078] In order to solve the above technical problems, the present application provides a vehicle hood design method and related devices. By establishing a correspondence between the vehicle hood structure and the vehicle hood performance, the law between the hood structure design parameters and the required performance can be obtained according to the pre-established correspondence, so that the vehicle hood design can be made efficient and intelligent during the hood design.
[0079] The following describes a vehicle cover design method provided by an embodiment of the present application in conjunction with the accompanying drawings. The vehicle cover design method provided by an embodiment of the present application can be applied to a physical server or a cloud server.
[0080] See also Figure 1 , Figure 1This is a flow chart of a vehicle hood design method provided in an embodiment of the present application. The method includes:
[0081] S101: Obtain a target cover shape and target cover performance of a cover to be designed.
[0082] The cover to be designed is a vehicle cover that needs to be designed.
[0083] The target cover shape may be obtained by drawing a three-dimensional (3D) model using software such as Computer Aided Design (CAD) software, or may be obtained by drawing a cover shape model using other drawing software.
[0084] The target cover performance is the performance that the cover to be designed can achieve in actual application. In some possible implementations of this embodiment, the target cover performance may include cover stiffness, cover mode, or pedestrian protection performance of the cover.
[0085] S102: Determine multiple candidate cover structures corresponding to the target cover performance based on the target cover performance and the cover correspondence relationship; the cover correspondence relationship is established based on multiple cover structures and multiple cover performances corresponding to multiple vehicle covers, and the cover structure includes the cover shape, cover cross-sectional form, cover middle beam form and cover cross-sectional size.
[0086] The cover correspondence relationship is the correspondence between multiple cover structures and multiple cover performances. The cover structure includes the cover shape, cover cross-sectional form, cover center beam form, and cover cross-sectional dimensions. It is understood that when the cover shape, cover cross-sectional form, cover center beam form, and cover cross-sectional dimensions are determined, the cover structure is also determined, and the determined cover structure corresponds to a set of determined cover performances. Consistent with the aforementioned target cover performance, cover performance can also include cover stiffness, cover modality, or the cover's pedestrian protection performance.
[0087] It should be noted that, since different vehicle models result in different shapes of vehicle hoods, different hood structures may correspond to the same hood performance, and a certain hood structure corresponds to a certain set of hood performance.
[0088] To establish a cover-cover correspondence, it is necessary to perform performance simulation on multiple covers with determined structures. In some possible implementations of this embodiment, an automatic simulation process can be built using software, and covers with determined structures can be input into the simulation process to obtain their cover performance.
[0089] In this embodiment, the target cover performance required by the cover to be designed is input into the pre-established correspondence relationship, thereby obtaining a plurality of candidate cover structures that meet the target cover performance.
[0090] Regarding the process of establishing the cover-cap correspondence relationship, in order to facilitate engineers to add new test data to the cover-cap correspondence relationship, and also to facilitate the computer or server to automatically acquire candidate cover-cap structures based on the cover-cap correspondence relationship and input target cover performance data, in some possible implementations of this embodiment, based on the above embodiment, further, establishing the cover-cap correspondence relationship includes:
[0091] A cover structure database is established according to a plurality of cover structures corresponding to a plurality of vehicle covers; and a cover performance database is established according to a plurality of cover performances corresponding to a plurality of vehicle covers.
[0092] According to the cover structure database and the cover performance database, a cover fitting model of multiple cover structures and multiple cover performances is established.
[0093] The cap fitting model is determined as the cap correspondence.
[0094] In some possible implementations of this embodiment, a cover structure database can be built through software, and a cover type can be defined by the cover shape, cover cross-sectional form and cover middle beam form, and then a cover structure can be determined within a certain cover type by the cover cross-sectional size.
[0095] In some possible implementations of this embodiment, covers of different structures can be numbered to correspond to the numbers one by one. Figure 2 , Figure 2 A schematic diagram of the numbering rules for a vehicle hood design method provided in an embodiment of the present application.
[0096] The cover shape is numbered as ZXXX, the cover cross-section is numbered as SXXX, and the cover center beam is numbered as TXX. For example, a cover numbered (Z000-S000-T00) has a cover shape of Z000, a cover cross-section of S000, and a cover center beam of T00. The same logic applies to other covers, which will not be detailed here.
[0097] By establishing a cover structure database and a cover performance database, it is convenient to add new cover structure data and corresponding cover performance data in the future. In addition, a fitting model is established based on the cover structure database and the cover performance database to facilitate the computer or server to automatically obtain candidate cover structures based on the cover correspondence relationship and the input target cover performance data.
[0098] S103: Performing contour projection on the target cover shape to obtain the target cover shape of the cover to be designed.
[0099] Among them, the target cover shape is the cover shape corresponding to the future vehicle model.
[0100] In some possible implementations of this embodiment, the vehicle preliminary modeling surface (ConceptASurface, CAS) can be projected onto three mutually perpendicular planes, namely, the XY, YZ, and XZ planes, to obtain the target cover modeling. Figure 4 , Figure 4 This is a schematic diagram of the vehicle cover projection outline provided in an embodiment of the present application. Figure 4 The left picture shows the projection of the target cover shape CAS in the XY plane, including the complete cover shape edge contour curve; Figure 4 The upper right picture shows the projection of the target cover shape CAS on the XZ plane, including the contour curve of the target shape's side; Figure 4 The lower right figure is the projection of the target cover shape CAS on the YZ plane, including the contour curve of the front of the target shape.
[0101] In some possible implementations of this embodiment, the projection information of the vehicle hood may be saved in a hood structure database in the form of a picture.
[0102] In some other possible implementations of this embodiment, to facilitate the subsequent production process and accelerate the transition between vehicle hood design and actual production, based on the above embodiment, further, performing contour projection on the target hood shape to obtain the target hood shape of the hood to be designed includes:
[0103] Perform contour projection on the target cover shape to obtain the initial cover shape of the cover to be designed;
[0104] The cover shape in the cover structure database whose similarity with the initial cover shape satisfies the similarity condition is determined as the target cover shape.
[0105] As a possible implementation method, in order to speed up the comparison of cover shapes, the similarity condition can be set to a similarity threshold. In the process of comparing the target cover shape with the cover shapes in the cover structure database, the first cover shape whose similarity exceeds the similarity threshold is directly determined as the target cover shape.
[0106] As another possible implementation method, the obtained initial cover shape can be compared with all cover shapes in the cover structure database through a similarity calculation algorithm, and the cover structure with the highest similarity can be determined as the target cover shape, so as to obtain a cover shape with the highest possible similarity to the target cover shape in the cover structure database.
[0107] Search the established hood structure database for a target hood shape that is similar to the initial hood shape, that is, determine a certain determined hood shape as the shape of the hood to be designed. When transitioning from structural design to actual production, the relevant data in the database has been obtained in advance, which can shorten the transition time and improve the design efficiency of the vehicle hood.
[0108] S104: Determine a target cover structure that meets the target cover shape from a plurality of candidate cover structures according to the target cover shape.
[0109] It is understood that after multiple candidate hood structures are determined based on the target hood performance, different hood shapes and structures are associated with different vehicle models, but the target hood performance is the same. Once the target hood shape is determined, a target hood structure that matches the target hood shape can be determined, including the target hood cross-sectional form, target hood intermediate beam form, and target hood cross-sectional dimensions corresponding to the target hood structure.
[0110] In order to directionally amplify database data, improve the generalization of the fitting model, and reduce the amount of calculation, based on the above embodiment, the method further includes:
[0111] Decomposing a cover structure database into a plurality of cover structure sub-databases according to a plurality of cover shapes of a plurality of vehicle covers;
[0112] In the cover structure sub-database corresponding to the cover shape whose similarity with the initial cover shape satisfies the similarity condition, a target cover structure that meets the target cover performance is searched.
[0113] In some possible implementations of this embodiment, a hood numbered (Z001-S001-T01) has a Z001 shape and can therefore be assigned to the Z001 sub-database. Within the Z001 sub-database, various hood structures with a Z001 shape can be obtained by sampling and combining modeling parameters. For example, the hood cross-section can be replaced with S000, and the hood center beam can be replaced with T00. The resulting hood, numbered (Z001-S000-T00), also belongs to the Z001 sub-database. In other words, all vehicle hoods with the same shape and structure constitute a hood structure sub-database.
[0114] By decomposing the cover structure database into multiple sub-databases based on their shape, engineers can obtain new cover shapes through sampling and combining modeling parameters. By then simulating the performance of these new covers and adding them to the cover performance database, the number of cover structures with the same shape can be expanded, improving the generalization of the fitting model. Furthermore, when implementing cover design, a similarity comparison can be performed based on the target cover shape. After determining the cover structure sub-database with the corresponding cover performance, the determined cover structure can be searched. This reduces the amount of computation required to find the cover structure and improves cover design efficiency.
[0115] In order to realize the design of a new cover to meet the target cover performance to the greatest extent, based on the above embodiment, further, when establishing the cover correspondence relationship:
[0116] Training a machine learning model using a plurality of cover structures and a plurality of cover performances having a corresponding relationship as training data to obtain a cover structure prediction model;
[0117] The cover structure prediction model is determined as the cover correspondence relationship.
[0118] In some possible implementations of this embodiment, the cover structure prediction model can be trained by machine learning. In this case, the cover shape and cover performance data can be used as the data source for machine learning, the cover section type, cover middle beam form and cover section size of each sub-database can be used as the input of the training model, and the cover performance corresponding to the cover structure can be used as the output of the training model. The model between the input and output is obtained by fitting the machine learning regression algorithm. In some possible implementations, the cover section form and the cover middle beam form are used as categorical variables, and one-hot encoding is performed through data preprocessing, and the machine learning adopts the gradient boosting algorithm.
[0119] In some other possible implementations of this embodiment, the cover structure prediction model may also be trained using a gradient descent method. In this case:
[0120] The machine learning model is trained using a plurality of cover structures and a plurality of cover performances having a corresponding relationship as training data to obtain a cover structure prediction model, including:
[0121] Using a machine learning model to predict the structure of multiple covers based on their performance, multiple cover structure prediction results are obtained;
[0122] Constructing a cover structure loss function based on a plurality of cover structure prediction results and a plurality of cover structures having corresponding relationships with a plurality of cover performances;
[0123] Training the machine learning model based on the cover structure loss function;
[0124] The trained machine learning model is determined as the cover structure prediction model.
[0125] At this time, the machine learning model can be a traditional learning model such as a multi-layer perceptron, or a deep learning model such as a deep neural network (DNN) or a convolutional neural network (CNN).
[0126] The cover structure loss function may be an L1 or L2 regularization loss function, or a loss function such as mean square error, mean absolute error, or a self-set loss function, which is not limited in the embodiment of the present application.
[0127] A hood structure prediction model is trained using a machine learning model or a deep learning model. When the target hood performance and target hood shape are input, the hood structure prediction model automatically generates the appropriate hood cross-section form, hood intermediate beam form, and hood cross-section dimensions, thereby automatically designing the hood to be designed. The designed hood is not necessarily an existing hood structure in the database, but is generated by the hood structure prediction model trained based on hood structure and performance. This can produce a vehicle hood that best meets the target hood performance and target hood shape, achieving intelligent and efficient vehicle hood design.
[0128] To determine the extent to which the cross-sectional form and the intermediate beam form of the cover affect the performance of the cover, so that engineers can analyze the relationship between the cover structure and the cover performance, based on the above embodiment, the method further includes:
[0129] Perform variance analysis based on the target cover cross-sectional form, the target cover middle beam form and the target cover performance to determine the first influence weight of the target cover cross-sectional form on the target cover performance, the second influence weight of the target cover middle beam form on the target cover performance, and the cross-influence weight of the target cover cross-sectional form and the target cover middle beam form on the target cover performance;
[0130] According to the first influence weight, the second influence weight and the cross influence weight, the influence relationship between the target cover middle beam form and the target cover cross-section form on the target cover performance is determined.
[0131] In some possible implementations of this embodiment, a two-way analysis of variance (ANOVA) is performed on the two factors of the cover cross-sectional form and the cover middle beam form to determine whether the cover cross-sectional form has a significant effect on the cover stiffness, cover mode and pedestrian protection performance of the cover, whether the cover middle beam form has a significant effect on the cover stiffness, cover mode and pedestrian protection performance of the cover, and whether there is an interaction effect between the two factors, that is, whether the cover cross-sectional form and the cover middle beam form affect each other's cover stiffness, cover mode and pedestrian protection performance of the cover.
[0132] For example, through variance analysis, it is found that the cover stiffness performance of a certain cover middle beam form is better than that of other cover middle beam forms, but it will be affected by another cover cross-section form, resulting in a decrease in the cover stiffness performance.
[0133] See also Figure 7 , Figure 7 A schematic diagram of the interaction effects within a vehicle hood, provided in an embodiment of the present application. As previously described for the numbering convention for vehicle hood designs, T00, T01, and T02 represent three types of hood center beams, and S000 and S100 represent two types of hood cross-sections. Interaction effects may exist between these two factors. In a two-way ANOVA of the hood stiffness performance, the cross-effect weight for hoods with a center beam of T00 and a cross-section of S000 is higher, indicating that this type of hood consistently exhibits greater stiffness than other types.
[0134] Therefore, through the first influence weight, the second influence weight and the cross-influence weight, the influence of the cross-section form and the middle beam form of the cover on the performance of the cover is obtained, thereby revealing the inherent law between the cover structure and the cover performance to engineers, and becoming the basis for engineers to select when designing vehicle covers.
[0135] See also Figure 3 , Figure 3 This is a system structure diagram of a vehicle hood design system provided in an embodiment of the present application. The vehicle hood simulation system includes:
[0136] 310: a cover structure database, used to store cover structure information of a vehicle cover;
[0137] 320: a hood shape database, used to store hood shape information of a vehicle hood, and decompose the hood structure database into multiple hood structure sub-databases according to different hood shapes;
[0138] 330: a cover performance database, used to store cover performance information of vehicle covers;
[0139] 340: a data analysis module, configured to establish a cover correspondence relationship between a cover structure database and a cover performance database;
[0140] 350: Vehicle hood design module, used to obtain the target hood cross-section form, target hood middle beam form and target hood cross-section size that conform to the target hood structure based on the hood correspondence relationship and the input target hood shape and target hood performance.
[0141] See also Figure 5 , Figure 5 This is a structural block diagram of a vehicle cover design device provided in an embodiment of the present application. The device includes:
[0142] The target cover data acquisition unit 510 is used to acquire the target cover shape and target cover performance of the cover to be designed;
[0143] a candidate hood structure determining unit 520 for determining, based on the target hood performance and a hood correspondence relationship, a plurality of candidate hood structures corresponding to the target hood performance; the hood correspondence relationship being established based on a plurality of hood structures and hood performances corresponding to a plurality of vehicle hoods, the hood structure including a hood shape, a hood cross-sectional form, a hood intermediate beam form, and hood cross-sectional dimensions;
[0144] A target cover shape determining unit 530 is configured to perform contour projection on the target cover form to obtain the target cover shape of the cover to be designed;
[0145] The target cover structure determining unit 540 is configured to determine, according to the target cover shape, a target cover structure that meets the target cover shape from among the multiple candidate cover structures.
[0146] As a possible implementation, the establishment of the cover-cap correspondence relationship includes:
[0147] A cover database establishing unit, configured to establish a cover structure database based on a plurality of cover structures corresponding to the plurality of vehicle covers; and to establish a cover performance database based on a plurality of cover performances corresponding to the plurality of vehicle covers;
[0148] a cover fitting model establishing unit, configured to establish a plurality of cover fitting models of the cover structures and the cover performances according to the cover structure database and the cover performance database;
[0149] The first cover-cap correspondence determination unit is configured to determine the cover-cap fitting model as the cover-cap correspondence.
[0150] As a possible implementation manner, the target cover shape determination unit is further configured to:
[0151] Performing contour projection on the target cover shape to obtain an initial cover shape of the cover to be designed;
[0152] A cover shape in the cover structure database whose similarity to the initial cover shape satisfies a similarity condition is determined as the target cover shape.
[0153] As a possible implementation, the device further includes:
[0154] a database decomposition unit, configured to decompose the cover structure database into a plurality of cover structure sub-databases according to a plurality of cover shapes of a plurality of vehicle covers;
[0155] The target cover structure determination unit is further configured to:
[0156] A target cover structure that meets the target cover performance is searched in a cover structure sub-database corresponding to a cover shape whose similarity to the initial cover shape satisfies the similarity condition.
[0157] As a possible implementation, the establishment of the cover-cap correspondence relationship includes:
[0158] a prediction model obtaining unit, configured to train a machine learning model using a plurality of the cover structures and a plurality of the cover performances having a corresponding relationship as training data to obtain a cover structure prediction model;
[0159] The second cover-cap correspondence relationship determining unit is configured to determine the cover-cap structure prediction model as the cover-cap correspondence relationship.
[0160] As a possible implementation manner, the prediction model obtaining unit is further configured to:
[0161] Performing cover structure prediction on the plurality of cover performances using the machine learning model to obtain a plurality of cover structure prediction results;
[0162] Constructing a cover structure loss function according to a plurality of the cover structure prediction results and a plurality of the cover structures having a corresponding relationship with a plurality of the cover performances;
[0163] Training the machine learning model according to the cover structure loss function;
[0164] The trained machine learning model is determined as the cover structure prediction model.
[0165] As a possible implementation, the device further includes:
[0166] an influence weight determination unit, configured to perform variance analysis based on the target cover cross-sectional form, the target cover middle beam form, and the target cover performance, to determine a first influence weight of the target cover cross-sectional form on the target cover performance, a second influence weight of the target cover middle beam form on the target cover performance, and a cross-influence weight of the target cover cross-sectional form and the target cover middle beam form on the target cover performance;
[0167] The influence relationship determining unit is used to determine the influence relationship between the target cover middle beam form and the target cover cross-section form on the target cover performance according to the first influence weight, the second influence weight and the cross influence weight.
[0168] It can be seen from the above technical solution that a cover correspondence is established through multiple cover structures and multiple cover performances corresponding to multiple vehicle covers. The cover structure includes cover shape, cover cross-sectional form, cover middle beam form and cover cross-sectional size. When designing a vehicle cover, the target cover shape and target cover performance of the cover to be designed are first obtained, and then the target cover shape is contour projected to obtain the target cover shape of the cover to be designed. Then, based on the correspondence and starting from the target cover performance, multiple candidate cover structures are determined in the cover correspondence. Then, through the target cover shape, the required target cover structure is determined among the multiple candidate cover structures. The vehicle cover is designed based on the correspondence between performance and structure. Under any given shape, a vehicle cover that meets the required performance can be designed without repeated modeling, simulation and testing, which greatly improves the design efficiency of the vehicle cover and shortens the design cycle of the vehicle cover.
[0169] See also Figure 6 , Figure 6 This is a block diagram of a computer device for vehicle hood design provided in an embodiment of the present application. The computer device includes a processor 610 and a memory 620:
[0170] The memory 620 is used to store program codes and transmit the program codes to the processor;
[0171] The processor 610 is configured to execute any one of the vehicle hood design methods provided in the above embodiments according to the instructions in the program code.
[0172] The embodiments of the present application further disclose a computer-readable storage medium, which is used to store a computer program. When the computer program is executed by a processor, it is used to execute any one of the vehicle hood design methods provided in the above embodiments.
[0173] It is understood that this method can be applied to a processing device capable of performing motion control, such as a terminal device or server with motion control functionality. This method can be executed independently by a terminal device or server, or it can be applied to a network scenario where a terminal device and a server communicate, with the terminal device and the server working together to execute the method. The terminal device can be a computer, a mobile phone, or other device. The server can be understood as an application server or a web server. In actual deployment, the server can be a standalone server or a clustered server.
[0174] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the above-mentioned storage medium can be at least one of the following media: read-only memory (English: read-only memory, abbreviated: ROM), RAM, magnetic disk or optical disk, etc., various media that can store program codes.
[0175] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.
[0176] The above is merely one specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.
Claims
1. A vehicle cover design method, characterized in that: The method comprises: Obtaining a target cover shape and target cover performance of a cover to be designed; According to the target cover performance and the cover correspondence relationship, a plurality of candidate cover structures corresponding to the target cover performance are determined; the cover correspondence relationship is established according to a plurality of cover structures and a plurality of cover performances corresponding to a plurality of vehicle covers, the cover structure including a cover shape, a cover cross-sectional form, a cover middle beam form and a cover cross-sectional size; Performing contour projection on the target cover shape to obtain the target cover shape of the cover to be designed; According to the target cover shape, a target cover structure that meets the target cover shape is determined from among the multiple candidate cover structures.
2. The method according to claim 1, characterized in that The establishment of the cover-cap correspondence relationship includes: Establishing a cover structure database according to the multiple cover structures corresponding to the multiple vehicle covers; establishing a cover performance database according to the multiple cover performances corresponding to the multiple vehicle covers; Establishing a plurality of cover fitting models of the cover structures and the cover performance according to the cover structure database and the cover performance database; The cover-cap fitting model is determined as the cover-cap correspondence.
3. The method according to claim 2, characterized in that The step of performing contour projection on the target cover shape to obtain the target cover shape of the cover to be designed comprises: Performing contour projection on the target cover shape to obtain an initial cover shape of the cover to be designed; A cover shape in the cover structure database whose similarity with the initial cover shape satisfies a similarity condition is determined as the target cover shape.
4. The method according to claim 3, characterized in that The method further comprises: Decomposing the cover structure database into a plurality of cover structure sub-databases according to a plurality of cover shapes of a plurality of vehicle covers; The step of determining, according to the target cover shape, a target cover structure that meets the target cover shape from among the plurality of candidate cover structures comprises: In the cover structure sub-database corresponding to the cover shape whose similarity with the initial cover shape satisfies the similarity condition, a target cover structure that satisfies the target cover performance is searched.
5. The method according to claim 1, characterized in that The establishment of the cover-cap correspondence relationship includes: Using the plurality of cover structures and the plurality of cover performances having corresponding relationships as training data to train a machine learning model, and obtaining a cover structure prediction model; The cover structure prediction model is determined as the cover correspondence relationship.
6. The method according to claim 5, characterized in that The method of training a machine learning model using a plurality of the cover structures and a plurality of the cover performances having a corresponding relationship as training data to obtain a cover structure prediction model comprises: Performing cover structure prediction on the plurality of cover performances through the machine learning model to obtain a plurality of cover structure prediction results; Constructing a cover structure loss function according to a plurality of the cover structure prediction results and a plurality of the cover structures having a corresponding relationship with a plurality of the cover performances; Training the machine learning model according to the cover structure loss function; The trained machine learning model is determined as the cover structure prediction model.
7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Perform variance analysis according to the target cover cross-sectional form, the target cover middle beam form and the target cover performance to determine a first influence weight of the target cover cross-sectional form on the target cover performance, a second influence weight of the target cover middle beam form on the target cover performance, and a cross-influence weight of the target cover cross-sectional form and the target cover middle beam form on the target cover performance; The influence relationship between the target cover middle beam form and the target cover cross-sectional form on the target cover performance is determined according to the first influence weight, the second influence weight and the cross-influence weight.
8. A vehicle cover design device, characterized in that: The device comprises: A target cover data acquisition unit, used to acquire the target cover shape and target cover performance of the cover to be designed; A candidate cover structure determination unit is used to determine a plurality of candidate cover structures corresponding to the target cover performance according to the target cover performance and the cover correspondence relationship; the cover correspondence relationship is established according to a plurality of cover structures and a plurality of cover performances corresponding to a plurality of vehicle covers, the cover structure including a cover shape, a cover cross-sectional form, a cover middle beam form and a cover cross-sectional size; A target cover shape determining unit is used to perform contour projection on the target cover shape to obtain the target cover shape of the cover to be designed; The target cover structure determining unit is used to determine a target cover structure that meets the target cover shape from among the multiple candidate cover structures according to the target cover shape.
9. A computer device, characterized in that: The computer device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the vehicle cover design method according to any one of claims 1 to 7 according to the instructions in the program code.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the computer program is used to execute the vehicle hood design method according to any one of claims 1 to 7.