Aerodynamics evaluation method and device for automobile shape and electronic equipment

Abstract

The invention provides an aerodynamic evaluation method and device for an automobile shape and electronic equipment, and the method comprises the steps: obtaining three-dimensional point cloud data describing the automobile shape, and generating a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve; determining a spatial similarity matrix corresponding to the point cloud data, and extracting large-scale features corresponding to the point cloud data according to the spatial similarity matrix; serializing the point cloud data according to the forward index, extracting small-scale features corresponding to the point cloud data, and returning the point cloud data to an original sequence according to the reverse index; and fusing the large-scale features and the small-scale features to generate point cloud fusion features, and determining an automobile surface flow field according to the point cloud fusion features. According to the method, the large-scale and small-scale structural features in the automobile shape can be effectively extracted, the surface pressure distribution and the wall shear stress distribution of the automobile shape can be accurately predicted and the wind resistance coefficient can be calculated under relatively low calculation complexity and video memory occupation, and the evaluation efficiency and the prediction precision can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of automobile design, and in particular to an aerodynamic evaluation method, device and electronic equipment for automobile appearance. Background Art

[0002] With the rapid development of the new energy vehicle industry, the energy efficiency of automobiles has become an important factor affecting vehicle performance and market competitiveness. Among them, the drag coefficient, as an important factor affecting the high-speed driving of a car, is closely related to the aerodynamic performance of the vehicle's exterior design. Optimizing the car's exterior to reduce wind resistance can not only significantly increase the driving range, but also effectively reduce energy consumption, which is in line with the industry development trend of energy conservation and environmental protection. Therefore, how to quickly and accurately evaluate the aerodynamic performance of the car's exterior has become a key technical issue in the research and development of new energy vehicles.

[0003] Traditionally, the evaluation of aerodynamic performance of automobile exteriors relies on computational fluid dynamics simulation methods. By simulating the interaction between fluid and solid surface through numerical calculation, the surface pressure and wall shear stress distribution and drag coefficient of automobile exteriors can be accurately calculated. However, the demand for computing resources is extremely huge, especially when dealing with complex three-dimensional geometric models. The calculation process often takes days or even weeks. This high time cost limits the efficiency of automobile design optimization and is not conducive to the actual needs of rapid iterative design. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a method, device and electronic device for aerodynamic evaluation of automobile appearance. By introducing spatial aggregation technology and serialization technology of point clouds, large-scale and small-scale structural features in the automobile appearance can be effectively extracted. The surface pressure and wall shear stress distribution and drag coefficient of the automobile appearance can be accurately predicted with low computational complexity and video memory occupancy, thereby significantly improving evaluation efficiency and prediction accuracy.

[0005] The present disclosure provides a method for evaluating the aerodynamics of a vehicle appearance, including: Acquire three-dimensional point cloud data describing the appearance of the car, and generate forward indexes and reverse indexes corresponding to the point cloud data according to a preset space filling curve; Determine a spatial similarity matrix corresponding to the point cloud data, and extract large-scale features corresponding to the point cloud data according to the spatial similarity matrix; Serializing the point cloud data according to the forward index, extracting small-scale features corresponding to the point cloud data, and returning the point cloud data to the original order according to the reverse index; The large-scale features and the small-scale features are fused to generate a point cloud fusion feature, and the flow field on the surface of the vehicle is determined according to the point cloud fusion feature.

[0006] In an optional implementation, generating a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve specifically includes: Divide the three-dimensional space into multiple cubic blocks; Sorting the cubic blocks according to the preset space filling curve, wherein the preset space filling curve includes at least a Z-order curve, a Hilbert curve, a Tran Z-order curve and a Tran Hilbert curve; A corresponding index is assigned to each of the cubic blocks, and the point cloud data belonging to the same cubic block are arranged in ascending order according to the indexes, and the forward index and the reverse index for serializing the point cloud data are determined.

[0007] In an optional implementation, determining a spatial similarity matrix corresponding to the point cloud data, and extracting large-scale features corresponding to the point cloud data according to the spatial similarity matrix specifically includes: Encoding the point cloud data into high-dimensional point cloud basic features through linear transformation; Performing point-by-point linear transformation on the basic features of the point cloud, calculating the corresponding spatial similarity weights using a global Softmax function, and integrating all the spatial similarity weights into the spatial similarity matrix; Converting the point cloud data into a plurality of spatial slices, and determining spatial aggregation features between the spatial slices according to the spatial similarity matrix; The spatial aggregation features are processed through a self-attention mechanism to determine the large-scale features.

[0008] In an optional implementation, serializing the point cloud data according to the forward index and extracting small-scale features corresponding to the point cloud data specifically includes: Sort the point cloud data according to the forward index to generate serialized point cloud data; The serialized point cloud data is divided into a plurality of point cloud groups, local features of each point cloud group are extracted through a self-attention mechanism, and the small-scale features corresponding to the point cloud group are determined.

[0009] In an optional implementation, returning the point cloud data to the original order according to the reverse index specifically includes: Connecting the point cloud groups to form the point cloud data of the original shape; The point cloud data formed by connecting the point cloud groups are sorted according to the reverse index, and the point cloud data are returned to the original order.

[0010] In an optional implementation, fusing the large-scale features with the small-scale features to generate a point cloud fusion feature, and determining the surface flow field of the vehicle according to the point cloud fusion feature, specifically includes: Residual connection is performed on the large-scale features, the small-scale features and the point cloud basic features, and the features are input into a fully connected network for feature fusion to determine the point cloud fusion features; Inputting the point cloud fusion features into a pre-trained pressure distribution prediction model to determine the pressure value at each point on the car surface corresponding to the point cloud data; Inputting the point cloud fusion features into a pre-trained wall shear stress distribution prediction model to determine the wall shear stress vector at each point on the automobile surface corresponding to the point cloud data; Determining the pressure distribution on the surface of the vehicle according to the pressure value, and determining the wall shear stress distribution on the surface of the vehicle according to the wall shear stress vector; The drag coefficient of the automobile is determined according to the pressure distribution and the wall shear stress distribution.

[0011] In an optional implementation, after extracting the large-scale features corresponding to the point cloud data according to the spatial similarity matrix, the method further includes: The large-scale features are returned to the point cloud space according to the spatial similarity matrix.

[0012] The present disclosure also provides an aerodynamic evaluation device for an automobile appearance, comprising: A point cloud acquisition module, used to acquire three-dimensional point cloud data describing the appearance of the car, and generate a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve; A large-scale feature extraction module, used to determine a spatial similarity matrix corresponding to the point cloud data, and extract large-scale features corresponding to the point cloud data according to the spatial similarity matrix; A small-scale feature extraction module, used to serialize the point cloud data according to the forward index, extract the small-scale features corresponding to the point cloud data, and return the point cloud data to the original order according to the reverse index; The vehicle surface flow field prediction module is used to fuse the large-scale features with the small-scale features to generate point cloud fusion features, and determine the vehicle surface flow field according to the point cloud fusion features.

[0013] The present disclosure also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the above-mentioned method for aerodynamic evaluation of automobile appearance or steps in any possible implementation of the above-mentioned method for aerodynamic evaluation of automobile appearance is executed.

[0014] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the aerodynamic evaluation method for the vehicle appearance described above or the steps in any possible implementation of the aerodynamic evaluation method for the vehicle appearance described above are executed.

[0015] The disclosed embodiments further provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the above-mentioned aerodynamic evaluation method for automobile appearance, or the steps in any possible implementation of the above-mentioned aerodynamic evaluation method for automobile appearance.

[0016] The disclosed embodiment provides an aerodynamic evaluation method, device and electronic device for automobile appearance, which obtains three-dimensional point cloud data describing the automobile appearance, and generates forward index and reverse index corresponding to the point cloud data according to a preset space filling curve; determines the spatial similarity matrix corresponding to the point cloud data, and extracts the large-scale features corresponding to the point cloud data according to the spatial similarity matrix; serializes the point cloud data according to the forward index, extracts the small-scale features corresponding to the point cloud data, and returns the point cloud data to the original order according to the reverse index; fuses the large-scale features with the small-scale features to generate point cloud fusion features, and determines the automobile surface flow field according to the point cloud fusion features. By introducing the spatial aggregation technology and serialization technology of point clouds, the large-scale and small-scale structural features in the automobile appearance are effectively extracted, and the surface pressure and wall shear stress distribution and drag coefficient of the automobile appearance can be accurately predicted at a lower computational complexity and video memory occupancy, thereby significantly improving the evaluation efficiency and prediction accuracy.

[0017] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0019] Figure 1 A flow chart showing a method for evaluating aerodynamics of a vehicle appearance provided by an embodiment of the present disclosure is shown; Figure 2 A flow chart showing another aerodynamic evaluation method for automobile appearance provided by an embodiment of the present disclosure; Figure 3 A schematic diagram of an aerodynamic evaluation device for automobile appearance provided by an embodiment of the present disclosure is shown; Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0023] According to research, traditionally, the evaluation of aerodynamic performance of automobile exteriors relies on computational fluid dynamics simulation methods. By simulating the interaction between fluid and solid surface through numerical calculation, the surface pressure and wall shear stress distribution and drag coefficient of automobile exteriors can be accurately calculated. However, the demand for computing resources is extremely huge, especially when dealing with complex three-dimensional geometric models. The calculation process often takes days or even weeks. This high time cost limits the efficiency of automobile design optimization and is not conducive to the actual needs of rapid iterative design.

[0024] Based on the above research, the present disclosure provides an aerodynamic evaluation method, device and electronic device for automobile appearance, which obtains three-dimensional point cloud data describing the automobile appearance, and generates forward index and reverse index corresponding to the point cloud data according to a preset space filling curve; determines the spatial similarity matrix corresponding to the point cloud data, and extracts the large-scale features corresponding to the point cloud data according to the spatial similarity matrix; serializes the point cloud data according to the forward index, extracts the small-scale features corresponding to the point cloud data, and returns the point cloud data to the original order according to the reverse index; fuses the large-scale features with the small-scale features to generate point cloud fusion features, and determines the automobile surface flow field according to the point cloud fusion features. By introducing the spatial aggregation technology and serialization technology of point clouds, the large-scale and small-scale structural features in the automobile appearance are effectively extracted, and the surface pressure and wall shear stress distribution and drag coefficient of the automobile appearance can be accurately predicted at a lower computational complexity and video memory occupancy, thereby significantly improving the evaluation efficiency and prediction accuracy.

[0025] To facilitate understanding of this embodiment, a method for evaluating the aerodynamics of a car's appearance disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the method for evaluating the aerodynamics of a car's appearance provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method for evaluating the aerodynamics of a car's appearance may be implemented by a processor calling computer-readable instructions stored in a memory.

[0026] See also Figure 1 FIG. 1 is a flow chart of a method for evaluating aerodynamics of a vehicle appearance provided by an embodiment of the present disclosure, the method comprising steps S101 to S104, wherein: S101, acquiring three-dimensional point cloud data describing the appearance of a car, and generating a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve.

[0027] In a specific implementation, the point cloud data consists of a set of unordered points in a three-dimensional space, each of which is represented by a three-dimensional coordinate system, and is used to accurately describe the geometric shape of the vehicle's exterior. The point cloud data collection method can generate three-dimensional point cloud data by scanning the vehicle's exterior with a laser, or generate a point cloud by projecting a grating pattern and recording the reflected light, or obtain point cloud data by shooting with a multi-view camera and performing three-dimensional reconstruction.

[0028] Here, the point cloud data is disordered, there is no fixed order between the points, and the number of points can be very large, with the surface of a car usually containing hundreds of thousands to millions of points.

[0029] Specifically, the point cloud is sorted by a preset space-filling curve to construct a serialized index of the point cloud. The forward index is used to convert the unordered point cloud into ordered data, and the reverse index is used to restore the original order of the point cloud after serialization to ensure data consistency.

[0030] Here, a space filling curve is a mathematical method for mapping a high-dimensional space to a low-dimensional space (usually one-dimensional), traversing all points in the high-dimensional space through a continuous curve while maintaining local adjacency. The space filling curves used in the embodiments of the present application include at least a Z-order curve, a Hilbert curve, a Tran Z-order curve, and a Tran Hilbert curve. The Z-order curve is based on binary segmentation and constructs an index according to the interleaved order of the bits of each dimensional coordinate; the Hilbert curve is a recursively defined curve that can better maintain spatial locality.

[0031] Here, the Tran Z-order curve and the Tran Hilbert curve are obtained by changing the traversal order of the original Z-order curve and the Hilbert curve for different dimensions. The traversal order of the Z-order curve and the Hilbert curve is xyz; the traversal order of the Tran Z-order curve and the Tran Hilbert curve is zyx.

[0032] As a possible implementation, the process of generating the forward index and the reverse index corresponding to the point cloud data can be seen in Figure 2 FIG. 1 is a flowchart of another aerodynamic evaluation method for automobile appearance provided by an embodiment of the present disclosure, wherein the method comprises steps S1011 to S1013, wherein: S1011, dividing the three-dimensional space into a plurality of cubic blocks.

[0033] S1012. Sort the cubic blocks according to the preset space-filling curve, where the preset space-filling curve at least includes a Z-order curve, a Hilbert curve, a Tran Z-order curve, and a Tran Hilbert curve.

[0034] S1013. Assign a corresponding index to each of the cube blocks, and arrange the point cloud data belonging to the same cube block in ascending order according to the indexes, and determine the forward index and the reverse index for serializing the point cloud data.

[0035] In the specific implementation, for the normalized n-dimensional point cloud set , the unit cube space Divide into equal parts according to each dimension small cubes, each with a side length of . Using n-dimensional vector Represents the index of each small cube block.

[0036] For example, for n=3 and = 4, the index of a cube block may be , indicating the second segmentation of the cube in the x direction, the third segmentation in the y direction, and the first segmentation in the z direction.

[0037] Here, the space-filling curve is used to Sort the cube blocks and convert the high-dimensional index Mapped to a one-dimensional sequential index, it can be expressed by the following formula:

[0038] in, It is a mapping function from n-dimensional space to one-dimensional space to define the access order of cube blocks; Represents the number of cube blocks; Represents the index of the cube block.

[0039] Furthermore, the index of each cube block are assigned a unique sort value , that is, the sequential position in the space-filling curve. Group them together and then use the formula Sort the point clouds of different groups, perform integer multiplication on the coordinates of the points and the side length of the cube block, and map them to the index of the cube block where they are located. .

[0040] Here, for different cube point cloud groups, the space filling curve order of the cube blocks is Sorting; for point clouds in the same cube, sort by Arrange in ascending order to ensure that the point clouds within the group are in the same order.

[0041] Among them, the position of the sorted point cloud data in the sequence is recorded to generate a forward index, which is used to convert the unordered point cloud into a serialized point cloud; an inverse mapping relationship is constructed according to the forward index to restore the original order of the point cloud in subsequent processing.

[0042] S102: Determine a spatial similarity matrix corresponding to the point cloud data, and extract large-scale features corresponding to the point cloud data according to the spatial similarity matrix.

[0043] In the specific implementation, the point cloud data is encoded into high-dimensional point cloud basic features through linear transformation; the point cloud basic features are linearly transformed point by point, and the corresponding spatial similarity weights are calculated using the global Softmax function, and all spatial similarity weights are integrated into a spatial similarity matrix; the point cloud data is converted into multiple spatial slices, and the spatial aggregation features between the spatial slices are determined according to the spatial similarity matrix; the spatial aggregation features are processed through the self-attention mechanism to determine the large-scale features.

[0044] Here, it is assumed that the car surface point cloud is ,in is the number of points. First, the input layer will be linearly transformed and encoded into a high-dimensional space ,in Representation dimension. Generate high-dimensional basic features of point cloud through linear transformation (such as fully connected layer), calculate the similarity between each pair of points through point-by-point linear transformation, capture the relationship of point cloud in the global scope, and weight the similarity between all point pairs. The spatial similarity matrix W is obtained by combining the spatial similarity matrix W, which is a symmetric matrix, and each row or column corresponds to the global relationship of a point.

[0045] Furthermore, the information of the spatial similarity matrix W is used to divide the point cloud into several spatial slices, each slice containing points that are highly correlated with a certain area. Using the above-mentioned spatial similarity weights, the grid points can be encoded into spatial aggregation features to obtain spatial aggregation features.

[0046] For example, for point cloud basic features , first use a point-by-point linear transformation And the global Softmax function Calculate spatial similarity weights:

[0047] in, represents the spatial similarity weight; represents the basic features of the point cloud, and .

[0048] Furthermore, the grid points are encoded into spatial aggregation features according to the spatial similarity weights, namely:

[0049] in, Then, the self-attention mechanism is used to process these spatial aggregation features according to the query, key, and value of the features, and the attention weights between the generated points are used to dynamically adjust the global relationship between the points. After the multi-head attention mechanism, the large-scale features of the point cloud data are output.

[0050] It should be noted that after extracting the large-scale features corresponding to the point cloud data according to the spatial similarity matrix, the large-scale features are returned to the point cloud space according to the spatial similarity matrix. The large-scale features represent the correlation of the point cloud in the global space, which captures the large-scale geometric structure of the point cloud surface, such as the overall outline of the car, the streamlined surface area, etc.

[0051] In this way, the global relationship information between all points is integrated through the spatial similarity matrix, and the self-attention mechanism dynamically adjusts the feature weights, retains important global characteristics, and avoids directly calculating the adjacency matrix, reducing resource consumption.

[0052] S103, serializing the point cloud data according to the forward index, extracting small-scale features corresponding to the point cloud data, and returning the point cloud data to the original order according to the reverse index.

[0053] In a specific implementation, the point cloud data is sorted according to the forward index to generate serialized point cloud data; the serialized point cloud data is divided into multiple point cloud groups, and the local features of each point cloud group are extracted through the self-attention mechanism to determine the small-scale features corresponding to the point cloud group; the point cloud groups are connected to form point cloud data of the original shape; the point cloud data formed by connecting the point cloud groups is sorted according to the reverse index, and the point cloud data is returned to the original order.

[0054] Here, the forward index is generated based on the space-filling curve and is used to organize the point cloud data into ordered serialized data. The order of the index reflects the spatial locality of the point cloud in the three-dimensional space, for example, adjacent points are also closer in the serialized data.

[0055] Specifically, the serialized point cloud data is divided into multiple point cloud groups, each group contains two adjacent point clouds, and each point cloud group mainly represents the geometric characteristics within the local range of the point cloud to capture detailed information. In each point cloud group, the local small-scale features of the point cloud are extracted through the self-attention mechanism. The query, key, and value used by the self-attention mechanism are generated through linear transformation, and then the Softmax function is used to calculate the attention weights between points to capture the correlation of the local range of the point cloud. After that, the small-scale features of all point cloud groups are combined to form a small-scale feature representation of the complete point cloud.

[0056] Specifically, the forward index generates a serialized point cloud, organizes the point cloud according to the space-filling curve, and enhances locality; extracts small-scale features by grouping, and captures local geometric details through the self-attention mechanism; the reverse index restores the original order to ensure the integrity and consistency of the point cloud data after serialization.

[0057] Here, the reverse index is the inverse mapping of the forward index, which is used to restore the serialized point cloud data to its original order, and sort the small-scale features according to the reverse index so that each point cloud feature returns to the corresponding original position.

[0058] For example, assuming the point cloud data is [abc], the forward index is [2 0 1], which becomes [cab] after serialization, and the corresponding reverse index is [1 2 0]. The reverse index can be used to get the original sequence [abc].

[0059] Among them, the serialization operation converts the originally disordered point cloud into ordered data, uses the space-filling curve to maintain local adjacency, provides a basis for extracting local features, and effectively captures the geometric details of the point cloud in the local range through the grouped self-attention mechanism, such as surface undulations, boundary characteristics, etc. The reverse index ensures that serialization and local feature extraction will not destroy the original geometric structure of the point cloud, and the restored data can be directly used for subsequent fusion and prediction.

[0060] S104, fusing the large-scale features with the small-scale features to generate a point cloud fusion feature, and determining the flow field on the surface of the vehicle according to the point cloud fusion feature.

[0061] In the specific implementation, the large-scale features, small-scale features and point cloud basic features are residually connected and input into a fully connected network for feature fusion to determine the point cloud fusion features; the point cloud fusion features are input into the pre-trained pressure distribution prediction model and wall shear stress distribution prediction model to determine the pressure value and wall shear stress vector at each point on the car surface corresponding to the point cloud data; the car's drag coefficient is determined based on the pressure value and the wall shear stress vector.

[0062] Here, layer normalization (LayerNorm) is performed on the basic features of the point cloud to standardize each feature dimension to ensure that the features have a stable numerical range. Then the physical attention mechanism (Physics-Attention) is used to extract the global correlation and large-scale structural features of the point cloud. The physical attention mechanism uses the spatial similarity matrix of the point cloud and combines the self-attention mechanism to perform weighted aggregation on the global information to generate large-scale features that represent the global geometric characteristics of the point cloud, such as the overall contour or aerodynamically important areas.

[0063] Here, the difference between the large-scale features and the basic features of the point cloud is calculated, and the difference is layer-normalized (LayerNorm) to ensure that the numerical range of the local features is adapted to the subsequent attention mechanism, and the serialized attention mechanism (Serialized-Attention) is applied to extract the local features of the point cloud. The serialized attention mechanism is based on the local grouping relationship after serialization of the point cloud, and uses the proximity information between points to capture detailed characteristics and reflect the local geometric characteristics of the point cloud, such as surface details or boundary features.

[0064] Furthermore, the large-scale features, small-scale features and point cloud basic features are fused through residual connections to generate point cloud fusion features:

[0065] in, Represents point cloud fusion features; Represents large-scale features; Represents small-scale features; Represents the basic features of point cloud. It consists of two layers of linear transformation and nonlinear activation function to enhance the expressiveness of features.

[0066] Furthermore, the trained deep neural network model is used, and the fusion features are input into it to predict the pressure value corresponding to each point cloud. The overall flow field distribution on the car surface is determined according to the pressure distribution of all points, and the drag coefficient is calculated based on the pressure distribution using a preset physical formula.

[0067] In this way, the global geometric structure and local detail characteristics of the point cloud are considered at the same time, which improves the accuracy of flow field prediction for complex automobile shapes. The residual connection ensures information integrity, and the nonlinear transformation enhances the expression ability after feature fusion.

[0068] The disclosed embodiment provides an aerodynamic evaluation method for a car's appearance, which obtains three-dimensional point cloud data describing the car's appearance, and generates forward and reverse indices corresponding to the point cloud data according to a preset space filling curve; determines a spatial similarity matrix corresponding to the point cloud data, and extracts large-scale features corresponding to the point cloud data according to the spatial similarity matrix; serializes the point cloud data according to the forward index, extracts small-scale features corresponding to the point cloud data, and returns the point cloud data to the original order according to the reverse index; fuses the large-scale features with the small-scale features to generate point cloud fusion features, and determines the car's surface flow field according to the point cloud fusion features. By introducing point cloud spatial aggregation technology and serialization technology, large-scale and small-scale structural features in the car's appearance can be effectively extracted, and the surface pressure and wall shear stress distribution and drag coefficient of the car's appearance can be accurately predicted at a lower computational complexity and video memory occupancy, thereby significantly improving evaluation efficiency and prediction accuracy.

[0069] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0070] Based on the same inventive concept, the embodiment of the present disclosure also provides an aerodynamic evaluation device for a vehicle appearance corresponding to the aerodynamic evaluation method for a vehicle appearance. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the aerodynamic evaluation method for a vehicle appearance in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0071] See also Figure 3 , Figure 3 A schematic diagram of an aerodynamic evaluation device for a vehicle exterior provided by an embodiment of the present disclosure. Figure 3 As shown in FIG. , the aerodynamic evaluation device 300 for the automobile appearance provided by the embodiment of the present disclosure includes: The point cloud acquisition module 310 is used to acquire three-dimensional point cloud data describing the appearance of the car, and generate a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve.

[0072] The large-scale feature extraction module 320 is used to determine the spatial similarity matrix corresponding to the point cloud data, and extract the large-scale features corresponding to the point cloud data according to the spatial similarity matrix.

[0073] The small-scale feature extraction module 330 is used to serialize the point cloud data according to the forward index, extract the small-scale features corresponding to the point cloud data, and return the point cloud data to the original order according to the reverse index.

[0074] The vehicle surface flow field prediction module 340 is used to fuse the large-scale features and the small-scale features to generate a point cloud fusion feature, and determine the vehicle surface flow field according to the point cloud fusion feature.

[0075] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0076] The embodiment of the present disclosure provides an aerodynamic evaluation device for the appearance of an automobile, which obtains three-dimensional point cloud data describing the appearance of the automobile, and generates forward indexes and reverse indexes corresponding to the point cloud data according to a preset space filling curve; determines the spatial similarity matrix corresponding to the point cloud data, and extracts large-scale features corresponding to the point cloud data according to the spatial similarity matrix; serializes the point cloud data according to the forward index, extracts small-scale features corresponding to the point cloud data, and returns the point cloud data to the original order according to the reverse index; fuses the large-scale features with the small-scale features to generate point cloud fusion features, and determines the surface flow field of the automobile according to the point cloud fusion features. By introducing the spatial aggregation technology and serialization technology of point clouds, the large-scale and small-scale structural features in the automobile appearance are effectively extracted, and the surface pressure distribution and drag coefficient of the automobile appearance can be accurately predicted at a lower computational complexity and video memory occupancy, thereby significantly improving the evaluation efficiency and prediction accuracy.

[0077] Corresponds to Figure 1 The aerodynamic evaluation method of the automobile appearance in the present disclosure also provides an electronic device 400, such as Figure 4FIG. 4 is a schematic diagram of the structure of an electronic device 400 provided in an embodiment of the present disclosure, including: Processor 41, memory 42, and bus 43; memory 42 is used to store execution instructions, including memory 421 and external memory 422; memory 421 here is also called internal memory, which is used to temporarily store operation data in processor 41 and data exchanged with external memory 422 such as hard disk. Processor 41 exchanges data with external memory 422 through memory 421. When the electronic device 400 is running, the processor 41 communicates with the memory 42 through bus 43, so that the processor 41 executes Figure 1 and Figure 2 The steps of the aerodynamic evaluation method of the automobile appearance are described in detail.

[0078] The embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aerodynamic evaluation method of the vehicle appearance described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0079] The disclosed embodiment also provides a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, the steps of the aerodynamic evaluation method of the vehicle appearance described in the above method embodiment can be executed. For details, please refer to the above method embodiment, which will not be repeated here.

[0080] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0081] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0084] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0085] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for evaluating the aerodynamics of a vehicle's exterior, characterized in that: include: Acquire three-dimensional point cloud data describing the appearance of the car, and generate forward indexes and reverse indexes corresponding to the point cloud data according to a preset space filling curve; Determine a spatial similarity matrix corresponding to the point cloud data, and extract large-scale features corresponding to the point cloud data according to the spatial similarity matrix; Serializing the point cloud data according to the forward index, extracting small-scale features corresponding to the point cloud data, and returning the point cloud data to the original order according to the reverse index; The large-scale features and the small-scale features are fused to generate a point cloud fusion feature, and the flow field on the surface of the vehicle is determined according to the point cloud fusion feature.

2. The method according to claim 1, characterized in that Generating a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve specifically includes: Divide the three-dimensional space into multiple cubic blocks; Sorting the cubic blocks according to the preset space filling curve, wherein the preset space filling curve includes at least a Z-order curve, a Hilbert curve, a Tran Z-order curve and a Tran Hilbert curve; A corresponding index is assigned to each of the cubic blocks, and the point cloud data belonging to the same cubic block are arranged in ascending order according to the indexes, and the forward index and the reverse index for serializing the point cloud data are determined.

3. The method according to claim 1, characterized in that Determining a spatial similarity matrix corresponding to the point cloud data, and extracting large-scale features corresponding to the point cloud data according to the spatial similarity matrix, specifically includes: Encoding the point cloud data into high-dimensional point cloud basic features through linear transformation; Performing point-by-point linear transformation on the basic features of the point cloud, calculating the corresponding spatial similarity weights using a global Softmax function, and integrating all the spatial similarity weights into the spatial similarity matrix; Converting the point cloud data into a plurality of spatial slices, and determining spatial aggregation features between the spatial slices according to the spatial similarity matrix; The spatial aggregation features are processed through a self-attention mechanism to determine the large-scale features.

4. The method according to claim 1, characterized in that: Serializing the point cloud data according to the forward index and extracting small-scale features corresponding to the point cloud data specifically includes: Sort the point cloud data according to the forward index to generate serialized point cloud data; The serialized point cloud data is divided into a plurality of point cloud groups, local features of each point cloud group are extracted through a self-attention mechanism, and the small-scale features corresponding to the point cloud group are determined.

5. The method according to claim 4, characterized in that Returning the point cloud data to the original order according to the reverse index specifically includes: Connecting the point cloud groups to form the point cloud data of the original shape; The point cloud data formed by connecting the point cloud groups are sorted according to the reverse index, and the point cloud data are returned to the original order.

6. The method according to claim 3, characterized in that: The large-scale features and the small-scale features are fused to generate a point cloud fusion feature, and the flow field on the surface of the vehicle is determined according to the point cloud fusion feature, specifically including: Residual connection is performed on the large-scale features, the small-scale features and the point cloud basic features, and the features are input into a fully connected network for feature fusion to determine the point cloud fusion features; Inputting the point cloud fusion features into a pre-trained pressure distribution prediction model to determine the pressure value at each point on the car surface corresponding to the point cloud data; Inputting the point cloud fusion features into a pre-trained wall shear stress distribution prediction model to determine the wall shear stress vector at each point on the automobile surface corresponding to the point cloud data; Determining the pressure distribution on the surface of the vehicle according to the pressure value, and determining the wall shear stress distribution on the surface of the vehicle according to the wall shear stress vector; The drag coefficient of the vehicle is determined according to the pressure distribution and the wall shear stress distribution.

7. The method according to claim 1, characterized in that After extracting the large-scale features corresponding to the point cloud data according to the spatial similarity matrix, the method further includes: The large-scale features are returned to the point cloud space according to the spatial similarity matrix.

8. An aerodynamic evaluation device for automobile appearance, characterized in that: include: A point cloud acquisition module, used to acquire three-dimensional point cloud data describing the appearance of the car, and generate a forward index and a reverse index corresponding to the point cloud data according to a preset space filling curve; A large-scale feature extraction module, used to determine a spatial similarity matrix corresponding to the point cloud data, and extract large-scale features corresponding to the point cloud data according to the spatial similarity matrix; A small-scale feature extraction module, used to serialize the point cloud data according to the forward index, extract the small-scale features corresponding to the point cloud data, and return the point cloud data to the original order according to the reverse index; The vehicle surface flow field prediction module is used to fuse the large-scale features with the small-scale features to generate point cloud fusion features, and determine the vehicle surface flow field according to the point cloud fusion features.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the aerodynamic evaluation method for the automobile appearance as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the aerodynamic evaluation method of the vehicle appearance as claimed in any one of claims 1 to 7 are executed.

Images