CN117421940B - Global mapping method and device between digital twin lightweight model and physical entity - Google Patents

Abstract

This application discloses a global mapping method and device between a digital twin lightweight model and a physical entity, which belongs to the field of digital twin technology. The method includes the following steps: collecting data information of lightweight products, establishing a digital twin lightweight model; Perform finite element analysis on the digital twin lightweight model of the quantitative product to obtain its stress and strain cloud image in the virtual environment; convert the stress and strain cloud image into an equal-scale stress density image based on the constitutive relationship between stress and strain and the color gradient change rule; The image is segmented to obtain the global mapping area between the digital twin lightweight model and the physical entity; the parameters are trained based on the single variable method to obtain the final global mapping area between the digital twin lightweight model and the physical entity; the digital twin lightweight model of the lightweight product is obtained. Global mapping between quantitative models and physical entities. This application improves the efficiency and accuracy of data transmission between the digital twin lightweight model and the physical entity.

Description

Global mapping method and device between digital twin lightweight model and physical entity

Technical Field

The present application relates to a global mapping method and device between a digital twin lightweight model and a physical entity, belonging to the field of digital twin technology.

Background Art

The transportation sector has become the focus of energy work. Lightweighting is an effective way to achieve the dual carbon goals of automobiles. When lightweight products are used in application scenarios, they often need to face complex working conditions, large sizes and heavy loads, and these factors have a great impact on the design cycle of lightweight products. In order to shorten the design cycle of lightweight products, digital twin technology has been introduced into the field of lightweighting.

Digital twin technology effectively uses virtual analysis to develop lightweight products, which must be combined with feedback information from physical entities. This means that a good feedback mechanism needs to be established between virtual analysis and physical entities to ensure the accuracy of virtual analysis results. When physical entity information needs to be fed back to the twin model, it is necessary to collect the operating data of the physical entity in the real scene and map this data into the virtual space to further optimize the design of lightweight products. However, the precise global mapping of physical entities and virtual spaces is affected by many factors, and it is difficult to accurately find a limited number of global mapping areas.

At present, most of the methods for finding the mapping area between the digital twin model and the physical entity are based on the simulation analysis results of the virtual model, and the areas with large stress or strain are subjectively selected as the mapping area between them, thereby mapping the data collection area of the physical entity. However, the above methods for finding the mapping area between the digital twin model and the physical entity are highly subjective, prone to misselection and omission, and difficult to accurately cover the entire virtual twin model. Therefore, when digital twin technology is applied to the design process of lightweight automotive products, especially when lightweight automotive products are facing real application scenarios, they often encounter actual situations such as large size, complex and multi-working conditions, resulting in incomplete and inaccurate mapping between the twin model in the virtual environment of the digital twin and the physical entity in the real environment.

Summary of the invention

In order to solve the above problems, the present application proposes a global mapping method and device between a digital twin lightweight model and a physical entity, which can realize the global mapping between the digital twin lightweight model of a lightweight product and the physical entity, and improve the efficiency and accuracy of data transmission between the digital twin lightweight model and the physical entity.

The technical solution adopted by this application to solve its technical problems is:

In a first aspect, an embodiment of the present application provides a global mapping method between a digital twin lightweight model and a physical entity, comprising the following steps:

Collect data information of lightweight products and establish a digital twin lightweight model; the data information includes design parameters of lightweight products, real data of physical entities and physical principle information;

Conduct finite element analysis on the digital twin lightweight model of lightweight products to obtain the stress-strain cloud map of lightweight products in the virtual environment;

Based on the constitutive relationship between stress and strain and the law of color gradient change, the stress-strain cloud map is converted into a proportional stress density image;

The stress density image is segmented based on the mean shift method to obtain the global mapping area between the digital twin lightweight model and the physical entity;

The parameters are trained based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity;

The global mapping area between the final digital twin lightweight model and the physical entity is used to perform global mapping between the digital twin lightweight model and the physical entity of the lightweight product.

As a possible implementation of this embodiment, the finite element analysis is performed on the digital twin lightweight model of the lightweight product to obtain the stress and strain cloud map in the virtual environment of the lightweight product, including:

A virtual analysis module of the digital twin lightweight model is established, and after setting the solver and analysis options, a finite element analysis is performed on the digital twin lightweight model of the lightweight product to obtain the stress and strain cloud map of the lightweight product in the virtual environment; the virtual analysis module includes a geometric model module, a boundary condition module, a material property module, a meshing module and an application loading module.

As a possible implementation of this embodiment, the stress density image is segmented based on the mean shift method to obtain a global mapping area between the digital twin lightweight model and the physical entity, including:

Segment the stress density image to form a finite number of cluster centroids;

A finite number of cluster centroids are used as the feature mapping area between the digital twin lightweight model and the physical entity, the data collection area of the physical entity is mapped out, and the global mapping area between the digital twin lightweight model and the physical entity is obtained.

As a possible implementation of this embodiment, the parameters are trained based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity, including:

The single variable contrast method is used to conduct multiple combination training on the variance of drift radius and density estimation function in the image segmentation process to determine the optimal drift radius and variance of density estimation function.

Based on the optimal drift radius and variance of the density estimation function, the global mapping area between the final digital twin lightweight model and the physical entity is obtained.

As a possible implementation of this embodiment, the method of converting the stress-strain cloud map into a proportional stress density image based on the constitutive relationship between stress and strain and the color gradient change law includes:

A. Determine the stress and strain constitutive relations:

The relationship between stress and strain is described by the elastic modulus E: , , ,in, is stress, For strain; is the magnitude of the force; is the area over which the force acts; Indicates the change in length; is the initial length.

B. Determine the proportional relationship between discrete units and pixel units:

The proportional relationship between the discrete unit size and the pixel size is: ,in, Discrete element sizes for stress and strain modules of digital twin lightweight models; Lightweight model stress and strain modules for digital twins to reduce the overall model size; is the pixel unit size; The entire pixel size of the color cloud image that needs data conversion is obtained by pixel adjustment to obtain the final density image.

C, convert the color cloud image into a density image through pixel units and the RGB red channel value of each pixel unit as a medium:

The pixel units of the color stress-strain cloud image are stored in a 3D array of m×n×3, and the red channel value of each pixel unit is used as the reference value of the stress density; the density storage unit of the stress density image converted from the pixel unit at position g = ( i, j ) is defined as , whose density value is m , where 1≤ i ≤m; 1≤ j ≤n; 0≤ m ≤255; extract the red channel value and return it to a matrix of size m×n: ,in, In the matrix is a density storage unit, the value of which is equal to the RGB red channel value of each pixel unit, and its position is g=(i,j); matrix density storage unit The density value in is the density storage unit of the stress density image. The density value m ; Based on the Gaussian distribution function, in the density storage unit of the stress density image Randomly generate m points inside to obtain point set D, which is the density point set that can be used for density image segmentation.

As a possible implementation of this embodiment, the stress density image is segmented based on the mean shift method to obtain a global mapping area between the digital twin lightweight model and the physical entity, including:

A, perform kernel density estimation:

Different working conditions in three-dimensional space Given n data units in , , Point cloud transformed from stress cloud map; kernel function and the symmetric positive definite 3×3 bandwidth matrix D as parameters, and calculate at the point Multivariate kernel density estimate at : , ,in, is a kernel function with a bandwidth matrix D, and |D| represents the determinant of the bandwidth matrix D.

3D Kernel Function is a bounded function that satisfies the following conditions: , , , ;in is a constant, I is a set of integers, ‖ ‖ represents a vector The norm of Representation vector The transpose of .

The multidimensional kernel function is derived from the symmetric univariate kernel function in two different ways: generate: , ,in, Obtained by the product of univariate kernels; By Mid-rotation And obtain, that is is radially symmetric. is a constant.

Considering the radially symmetric kernel function, the symmetric multidimensional kernel function satisfies: , where for a function called the kernel function profile , need to make , the standardization constant When it is strictly positive, the kernel function The score is 1.

Make the bandwidth matrix D proportional to the same matrix ; Provide a bandwidth parameter , then the kernel density estimator is: .

B, probability density gradient estimation:

Calculate the density gradient: .

Assumptions The derivative of If the interval exists, define the kernel function for: ,in, , is the kernel profile function The derivative of is the corresponding normalized function, which can be introduced into the density gradient formula: .

Calculated The density estimate at is proportional to: .

The mean shift vector is: .

Using Kernels As weight, As the center of the nucleus, we have: , .

Will be The window function with center and bandwidth h Along the mean shift vector Translate to get a new window function .

C, All density storages in the stress density image are seed points for the mean shift procedure; for each seed point , set its drift radius h, calculate The kernel density weighted average vector of all other sample points in the window with a center and a radius of h , for each seed point To translate, , until the seed point converges, that is ; Perform mean shift iteration to achieve density image segmentation.

D. Based on stress density image segmentation, the stress danger points of the twin model virtual analysis are found, the data sampling area of the physical entity during runtime is mapped, and the global mapping area between the digital twin lightweight model and the physical entity is constructed.

As a possible implementation of this embodiment, the global mapping method between the digital twin lightweight model and the physical entity further includes:

Use real data from physical entities to verify the digital twin lightweight model: Collect and analyze lightweight product operation data based on sampling points in real operation scenarios, and then compare it with the analysis data in the digital twin mapping area in the virtual environment to verify the accuracy of the digital twin lightweight model.

In a second aspect, an embodiment of the present application provides a global mapping device between a digital twin lightweight model and a physical entity, comprising:

A data acquisition module is used to collect data information of lightweight products and establish a digital twin lightweight model; the data information includes design parameters of lightweight products, real data of physical entities and physical principle information;

The finite element analysis module is used to perform finite element analysis on the digital twin lightweight model of lightweight products to obtain the stress-strain cloud map in the virtual environment of lightweight products;

Cloud map conversion module, used to convert stress-strain cloud map into proportional stress density image based on stress and strain constitutive relationship and color gradient change law;

The image segmentation module is used to segment the stress density image based on the mean shift method to obtain the global mapping area between the digital twin lightweight model and the physical entity;

The parameter training module is used to train the parameters based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity;

The global mapping module is used to perform global mapping between the digital twin lightweight model and the physical entity of the lightweight product by using the global mapping area of the final digital twin lightweight model and the physical entity.

In the third aspect, an embodiment of the present application provides a computer device, including a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the global mapping method between any digital twin lightweight model and the physical entity as described above.

In a fourth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the global mapping method between any digital twin lightweight model and a physical entity are executed.

The technical solution of the embodiment of the present application may have the following beneficial effects:

In order to achieve more comprehensive, accurate and faster data transmission between digital twin lightweight models and physical entities, the present application uses automatic global twin model recognition to find more representative mapping areas between them; uses stress density image segmentation technology to automatically and accurately identify the feature mapping areas of digital twin lightweight models, and then maps out the feature sampling areas of physical entities, thereby achieving global mapping between digital twin lightweight models of lightweight products and physical entities.

This application realizes cloud map-density image conversion based on the constitutive relationship of stress and strain, the law of color gradient change, and the proportional relationship between discrete units and pixel units. By converting the stress cloud map into a stress density image that can perform image segmentation, a better foundation is provided for subsequent image segmentation. This application realizes stress density image segmentation based on the mean shift method, which can quickly and accurately automatically identify the virtual global stress danger area of the twin model, thereby mapping the entire physical entity sampling area. In order to find the limited critical virtual-real mapping areas in the real scenes of complex multi-working conditions, large size and heavy load of lightweight products, this application screens a more comprehensive mapping area, so that the limited number of twin models found have a high consistency rate with the physical entity mapping area and strong representativeness.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a flow chart of a global mapping method between a digital twin lightweight model and a physical entity according to an exemplary embodiment;

FIG2 is a schematic diagram of a global mapping device between a digital twin lightweight model and a physical entity according to an exemplary embodiment;

FIG3 is a schematic diagram of a digital twin of a cargo box according to an exemplary embodiment;

FIG4 is a stress cloud diagram of a working condition simulation according to an exemplary embodiment;

FIG5 is a local stress cloud diagram of a cargo box of a cargo box twin model under a static load condition according to an exemplary embodiment;

FIG. 6 is a plan view of a density image after density image conversion according to an exemplary embodiment;

FIG7 is a three-dimensional display diagram of a density image according to an exemplary embodiment;

Fig. 8 is a diagram showing a density image segmentation result according to an exemplary embodiment.

DETAILED DESCRIPTION

The present application is further described below with reference to the accompanying drawings and embodiments:

In order to clearly illustrate the technical features of the present solution, the present application is described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The disclosure below provides many different embodiments or examples for realizing different structures of the present application. In order to simplify the disclosure of the present application, the components and settings of specific examples are described below. In addition, the present application may repeat reference numbers and/or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and/or settings discussed. It should be noted that the components illustrated in the accompanying drawings are not necessarily drawn to scale. The present application omits the description of known components and processing techniques and processes to avoid unnecessary limitations on the present application.

As shown in FIG1 , the embodiment of the present application provides a global mapping method between a digital twin lightweight model and a physical entity, comprising the following steps:

Collect data information of lightweight products and establish a digital twin lightweight model; the data information includes design parameters of lightweight products, real data of physical entities and physical principle information;

Conduct finite element analysis on the digital twin lightweight model of lightweight products to obtain the stress-strain cloud map of lightweight products in the virtual environment;

Based on the constitutive relationship between stress and strain and the law of color gradient change, the stress-strain cloud map is converted into a proportional stress density image;

The stress density image is segmented based on the mean shift method to obtain the global mapping area between the digital twin lightweight model and the physical entity;

The parameters are trained based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity;

The global mapping area between the final digital twin lightweight model and the physical entity is used to perform global mapping between the digital twin lightweight model and the physical entity of the lightweight product.

As a possible implementation of this embodiment, the finite element analysis is performed on the digital twin lightweight model of the lightweight product to obtain the stress and strain cloud map in the virtual environment of the lightweight product, including:

A virtual analysis module of the digital twin lightweight model is established, and after setting the solver and analysis options, a finite element analysis is performed on the digital twin lightweight model of the lightweight product to obtain the stress and strain cloud map of the lightweight product in the virtual environment; the virtual analysis module includes a geometric model module, a boundary condition module, a material property module, a meshing module and an application loading module.

As a possible implementation of this embodiment, the stress density image is segmented based on the mean shift method to obtain a global mapping area between the digital twin lightweight model and the physical entity, including:

Segment the stress density image to form a finite number of cluster centroids;

A finite number of cluster centroids are used as the feature mapping area between the digital twin lightweight model and the physical entity, the data collection area of the physical entity is mapped out, and the global mapping area between the digital twin lightweight model and the physical entity is obtained.

As a possible implementation of this embodiment, the training of parameters based on the single variable method to obtain the final global mapping area between the digital twin lightweight model and the physical entity includes:

The single variable contrast method is used to conduct multiple combination training on the variance of drift radius and density estimation function in the image segmentation process to determine the optimal drift radius and variance of density estimation function.

Based on the optimal drift radius and variance of the density estimation function, the global mapping area between the final digital twin lightweight model and the physical entity is obtained.

As a possible implementation of this embodiment, the method of converting the stress-strain cloud map into a proportional stress density image based on the constitutive relationship between stress and strain and the color gradient change law includes:

A. Determine the stress and strain constitutive relations:

The relationship between stress and strain is described by the elastic modulus E:

,in, is stress, ; For strain, ; is the magnitude of the force; is the area over which the force acts; Indicates the change in length; is the initial length.

B. Determine the proportional relationship between discrete units and pixel units:

The proportional relationship between the discrete unit size and the pixel size is:

,in, Discrete element sizes for stress and strain modules of digital twin lightweight models; Lightweight model stress and strain modules for digital twins to reduce the overall model size; is the pixel unit size; The total pixel size of the color cloud image that needs data conversion; the final density image is obtained by pixel adjustment.

C, convert the color cloud image into a density image through pixel units and the RGB red channel value of each pixel unit as a medium:

The pixel units of the color stress-strain cloud image are stored in a 3D array of m×n×3, and the red channel value of each pixel unit is used as the reference value of the stress density; the density storage unit of the stress density image converted from the pixel unit at position g=(i,j) is defined as , whose density is , where 1≤i≤m; 1≤j≤n; 0≤ ≤255; extract the red channel value and return it to a matrix of size m×n: ,in, In the matrix is a density storage unit, the value of which is equal to the RGB red channel value of each pixel unit, and its position is g=(i,j); matrix density storage unit The density value in is the density storage unit of the stress density image. Density value ; Based on the Gaussian distribution function, in the density storage unit of the stress density image Randomly generated points, and obtain the point set D, which is the density point set that can be used for density image segmentation.

As a possible implementation of this embodiment, the stress density image is segmented based on the mean shift method to obtain a global mapping area between the digital twin lightweight model and the physical entity, including:

A, perform kernel density estimation:

Different working conditions in three-dimensional space Given n data units in , , Point cloud transformed from stress cloud map; kernel function and the symmetric positive definite 3×3 bandwidth matrix D as parameters, and calculate at the point Multivariate kernel density estimate at : , ,in, is a kernel function with a bandwidth matrix D, and |D| represents the determinant of the bandwidth matrix D.

3D Kernel Function is a bounded function that satisfies the following conditions: , , , ;in is a constant, I is a set of integers, ‖ ‖ represents a vector The norm of Representation vector The transpose of .

The multidimensional kernel function is derived from the symmetric univariate kernel function in two different ways: generate: , ,in, Obtained by the product of univariate kernels; By Mid-rotation And obtain, that is is radially symmetric. is a constant.

Considering the radially symmetric kernel function, the symmetric multidimensional kernel function satisfies: , where for a function called the kernel function profile , need to make , the standardization constant When it is strictly positive, the kernel function The score is 1.

Make the bandwidth matrix D proportional to the same matrix ; Provide a bandwidth parameter , then the kernel density estimator is: .

B, probability density gradient estimation:

Calculate the density gradient: .

Assumptions The derivative of If the interval exists, define the kernel function for: ,in, , is the kernel profile function The derivative of is the corresponding normalized function, which can be introduced into the density gradient formula: .

Calculated The density estimate at is proportional to: .

The mean shift vector is: .

Using Kernels As weight, As the center of the nucleus, we have: , .

Will be The window function with center and bandwidth h Along the mean shift vector Translate to get a new window function .

C, All density storages in the stress density image are seed points for the mean shift procedure; for each seed point , set its drift radius h, calculate The kernel density weighted average vector of all other sample points in the window with a center and a radius of h , for each seed point To translate, , until the seed point converges, that is ; Perform mean shift iteration to achieve density image segmentation.

D. Based on stress density image segmentation, the stress danger points of the twin model virtual analysis are found, the data sampling area of the physical entity during runtime is mapped, and the global mapping area between the digital twin lightweight model and the physical entity is constructed.

As a possible implementation of this embodiment, the global mapping method between the digital twin lightweight model and the physical entity further includes:

Use real data from physical entities to verify the digital twin lightweight model: Collect and analyze the lightweight product operation data based on the sampling area in the actual operation scenario, and then compare it with the analysis data in the digital twin mapping area in the virtual environment to verify the accuracy of the digital twin lightweight model.

As shown in FIG2 , an embodiment of the present application provides a global mapping device between a digital twin lightweight model and a physical entity, including:

A data acquisition module is used to collect data information of lightweight products and establish a digital twin lightweight model; the digital twin model includes design parameters of lightweight products, real data of physical entities and physical principle information;

The finite element analysis module is used to perform finite element analysis on the digital twin lightweight model of lightweight products to obtain the stress-strain cloud map in the virtual environment of lightweight products;

Cloud map conversion module, used to convert stress-strain cloud map into proportional stress density image based on stress and strain constitutive relationship and color gradient change law;

The image segmentation module is used to segment the stress density image based on the mean shift method to obtain the global mapping area between the digital twin lightweight model and the physical entity;

The parameter training module is used to train the parameters based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity;

The global mapping module is used to use the global mapping area of the final digital twin lightweight model and the physical entity to perform global mapping between the digital twin lightweight model of the lightweight product and the physical entity.

The specific process of using the device described in the present invention to perform global mapping between the digital twin lightweight model of a lightweight product and the physical entity is as follows.

Step 1: Collect data information of lightweight products and establish a digital twin lightweight model; the data information includes design parameters of lightweight products, real data of physical entities and physical principle information.

The digital twin lightweight model is actually a virtual model, and its initial model is a virtual model established in computer software, which contains information such as the geometry, material properties, physical characteristics and engineering parameters of each component of the vehicle. Figure 3 is a schematic diagram of the digital twin of the cargo box. Through the digital twin lightweight model, simulation analysis, predictive evaluation of the vehicle during design, manufacturing and use can be performed to achieve product optimization on the basis of ensuring safety and reliability. For dump truck cargo boxes with large geometric dimensions and load characteristics, their most important mechanical properties are manifested in stress and strain conditions. Therefore, this application will first perform pre-analysis processing on the initial digital twin lightweight model, including finite element meshing, material parameter confirmation, boundary condition confirmation, and multi-condition loading. Then perform virtual calculation analysis to obtain virtual stress and strain data of lightweight products. Finally, the obtained ground stress and strain cloud map is converted into a stress density image for image segmentation.

Step 2: Perform finite element analysis on the digital twin lightweight model of the lightweight product to obtain the stress-strain cloud map of the lightweight product in the virtual environment.

The method of performing finite element analysis on the digital twin lightweight model of the lightweight product to obtain stress and strain cloud maps in a virtual environment of the lightweight product includes: establishing a virtual analysis module of the digital twin lightweight model, setting a solver and analysis options, performing finite element analysis on the digital twin lightweight model of the lightweight product, and obtaining stress and strain cloud maps in a virtual environment of the lightweight product; the virtual analysis module includes a geometric model module, a boundary condition module, a material property module, a meshing module, and an application loading module.

After discretizing the twin model of the cargo box and adding boundary conditions, finite element simulation analysis is performed to obtain the distribution of stress and strain of the entire cargo box. The analysis results will include the numerical values and directional components of various types of stress and strain, as shown in Figure 4. The actual situation Figure 4 is displayed in the form of a color cloud map, which can intuitively reflect the stress and strain of the entire cargo box. Engineers usually determine the location of the data mapping area based on the color distribution of the stress cloud map. However, traditional methods are often time-consuming and labor-intensive and have errors in determining the location of the mapping area. Another possible method is to use software to output the stress and strain values of all units, and then determine the mapping area through simple screening. However, the mapping area obtained by this simple screening often cannot well represent the characteristics of the entire system. Therefore, it is necessary to find a more effective method to determine the location of the mapping area.

Step three, based on the constitutive relationship between stress and strain and the law of color gradient change, the stress-strain cloud map is converted into a proportional stress density image.

Stress and strain cloud images cannot be directly segmented. They need to be converted into stress density images and the image segmentation is completed by executing the mean shift procedure. This process realizes the conversion of cloud images to density images based on the constitutive relationship between stress and strain, the law of color gradient change, and the proportional relationship between discrete units and pixel units.

3.1 Stress and strain constitutive relations.

For elastic materials, the relationship between stress and strain can be described by Hooke's law. Hooke's law states that within the elastic limit, stress is proportional to strain, and the proportional constant is the elastic modulus. The physical entity of an elastic material undergoes elastic deformation under the action of external stress, and this deformation is proportional to the stress. Stress refers to the magnitude of the force per unit area, and is a quantity that describes the ability of a material to resist external forces. It is represented by the symbol It is expressed as: ,in, is the magnitude of the force; is the area over which the force acts.

Strain refers to the degree of change in the length, volume or shape of an object under the action of a force. The formula is: ,in, Indicates the change in length; is the initial length.

The relationship between stress and strain can be described by the elastic modulus E. The elastic modulus is a physical quantity that reflects the ability of an object to resist deformation within its elastic range. Its formula is: , usually, the elastic modulus is a constant, that is, each material has a fixed value under certain conditions.

Strictly speaking, stress and strain are two different quantities and cannot be directly expressed as one quantity. However, in elastic materials, there is a linear relationship between stress and strain, which can be linked by the elastic modulus. This linear relationship makes it possible to express the proportional relationship between stress and strain using the elastic modulus. Therefore, based on this constitutive relationship between stress and strain, stress values and strain values can be converted to each other under certain conditions.

3.2 Color gradient rules.

The clustering object of the density image segmentation method is the density point, while the color cloud image cannot be directly segmented. The color cloud image needs to be segmented through the pixel unit and the RGB red channel value of each pixel unit. As a medium to convert into a density image. The RGB law of color images is based on the additive color mixing principle of the three primary colors (red, green, and blue). R, G, and B represent the brightness values of the three channels of red, green, and blue, respectively. Images of different colors can be obtained by adjusting the brightness values of these three channels. In the RGB model, the color of each pixel is composed of the intensity values of the three components of red, green, and blue. The intensity value range of each component is 0-255, and the intensity value of the component represents the brightness intensity of the color. Among them, 0 represents the lowest brightness and 255 represents the highest brightness. The color cloud map of the prediction results output by the computer software used in the specific implementation process of this application conforms to the RGB law, so the stress density of the color cloud map can be extracted according to the RGB law of the color cloud map.

Figure 5 shows the stress cloud diagram of the cargo box twin model under static load conditions, with the specific location being the cargo box front panel area.

The color cloud image pixel units are stored in a 3D array of m×n×3, and the red channel value of each pixel unit is used as the reference value of stress density. The density storage unit of the stress density image converted from the pixel unit at position g=(i,j) is defined as , whose density is . Where 1≤i≤m; 1≤j≤n; 0≤ ≤255. Then extract the red channel value and get The size of the value makes it return a matrix of size m×n, which ultimately contains the red channel information of all pixel units in the image.

First, construct an m×n matrix:

,in, In the matrix is a density storage unit, that is, the RGB red channel value of each pixel unit, its position is g=(i,j); matrix density storage unit The density value in is the density storage unit of the stress density image. Density value .

Then, based on the Gaussian distribution function, the density storage unit of the stress density image Randomly generated points. Finally, the point set D is obtained. The point set D is the density point set that can be used for density image segmentation.

3.3 The discrete unit and the pixel unit are in proportional relationship.

Usually, the pixels of the directly output color cloud image are large, and if it is directly converted into a density image, the workload will be very large. However, larger pixels do not have a more favorable effect on the segmentation results of the density image. Therefore, before performing the density conversion, the pixels of the color cloud image need to be adjusted to an appropriate size. Considering that the stress and strain module of the digital twin lightweight model in the specific implementation process of this application is a discrete model, the discrete unit has a certain size. Therefore, this application proposes a proportional relationship between the discrete unit size and the pixel size, which is an innovative point of view. In this way, a more reasonable density image can be obtained through appropriate pixel adjustment, providing a better basis for subsequent image segmentation.

The proportional relationship between the discrete unit size and the pixel size is:

,in, Discrete element sizes for stress and strain modules of digital twin lightweight models; Lightweight model stress and strain modules for digital twins to reduce the overall model size; is the pixel unit size; The total pixel size of the color cloud image that needs data conversion.

According to the proportional relationship between the discrete unit size and the pixel size, the present application adjusts the pixels of Figure 5 to 108×101, and further constructs a 108×101 matrix based on the m×n matrix. Through Gaussian distribution, the density point set A, that is, the stress density image, is obtained. Figure 6 is a plane diagram of the stress density image after the transformation, and Figure 7 is a three-dimensional display diagram of the density image. In Figures 6 and 7, the horizontal and vertical coordinates represent the m vector and n vector in the matrix, that is, the i coordinate and j coordinate of the stress density storage unit in the matrix, and the vertical coordinate represents the density size in each matrix unit, which is also the stress density size in the stress density storage unit. By comparing Figures 5 and 6, it can be intuitively found that the gradient change in the color cloud map is the same as the density gradient change in the density image it is converted into. This conversion method can accurately capture the stress and strain characteristics of the cloud map, thereby providing a basis for image segmentation processing.

Step 4: Segment the stress density image based on the mean shift method to obtain the global mapping area between the digital twin lightweight model and the physical entity.

The stress density image is segmented based on the mean shift method to obtain the global mapping area of the digital twin lightweight model and the physical entity, including:

A, perform kernel density estimation:

Different working conditions in three-dimensional space Given in Data Unit , , The point cloud is transformed from the stress cloud map. and symmetric positive definite Bandwidth Matrix As the parameter, calculate at point Multivariate kernel density estimate at : , .

is a density estimation function, represents the point at which the density estimate is currently being calculated, and Represents each individual data point in the dataset. is a specific location or point at which the density estimate is calculated. is the index of the data point in the data set, which is used to loop over and calculate the sum of the cumulative function. The kernel density estimation is done by calculating for each data point For current location and weighted sum them to generate The density estimate at .

is a kernel function with bandwidth matrix D. is a symmetric non-negative function that takes values on the domain and is used to calculate density estimates; |D| represents the determinant of bandwidth matrix D. The determinant represents the matrices of matrices, i.e., the scale used to adjust the bandwidth. In kernel density estimation, by adjusting the scale of the bandwidth, the smoothness and sensitivity of the estimate can be adjusted; the second half of this formula is the inverse operation of the bandwidth matrix D, i.e. ; then multiply it by the point , and pass the result as input to the kernel function. The kernel function with bandwidth matrix D will be obtained This is done to take into account the influence of the bandwidth matrix in the parameters of the kernel function, so as to better adjust the window size and shape of the density estimation.

3D Kernel Function is a bounded function that satisfies the following conditions: , , , ,in, is a constant, I is the set of integers; ‖ represents a vector The norm (also called modulus or length) of a vector. The norm is a function that maps a vector to a non-negative value and is used to provide a measure of the size or distance of a vector. Representation vector The transpose of .

Multidimensional kernel functions can be derived from symmetric univariate kernel functions in two different ways: generate: , ,in, Obtained by the product of univariate kernels; By Mid-rotation And obtain, that is is radially symmetric. is a constant.

Considering the radially symmetric kernel function, the symmetric multidimensional kernel function satisfies: , where for a function called the kernel function profile , need to make . Standardization constant When it is strictly positive, the kernel function The score is 1.

Make the bandwidth matrix D proportional to the same matrix ; Provide a bandwidth parameter , then the kernel density estimator is: .

B, probability density gradient estimation:

Calculate the density gradient: .

Assumptions The derivative of If the interval exists, define the kernel function for: ,in, ; is the corresponding normalized function, which can be introduced into the density gradient formula: .

Calculated The density estimate at is proportional to: .

The mean shift vector is: .

Using Kernels As weight, As the center of the nucleus, we have: , .

Will be The window function with center and bandwidth h Along the mean shift vector Translate to get a new window function .

C. All density storages in the stress density image are seed points for the mean shift procedure. For each seed point , set its drift radius h. Then calculate The kernel density weighted average vector of all other sample points in the window with a center and a radius of h Finally, for each seed point To translate, , until the seed point converges, that is ; Perform mean shift iteration to achieve density image segmentation.

D. Based on stress density image segmentation, the stress danger points of the twin model virtual analysis are found, the data sampling area of the physical entity during runtime is mapped, and the global mapping area between the digital twin lightweight model and the physical entity is constructed.

The stress density image is segmented, and the segmented density image will form a finite number of cluster centroids. These cluster centroids are the dangerous areas of the virtual analysis results of the twin model, which are used to map the data collection area of the physical entity. This finds the global mapping area between the digital twin lightweight model and the physical entity.

The density image transformed from the color cloud map is input into the iterative program, and the stress density image segmentation result is shown in Figure 8. Each iteration in this process calculates the weighted average of the density around each seed point and moves the surrounding density points toward the average. This process gradually moves the density points to the area with the highest density and forms a cluster centroid. Figure 8 shows the position of the cluster centroid formed after the mean shift is completed in the density image. In Figure 8, "*" is the stress density drift centroid, which is called the stress danger point, that is, the twin model mapping area. Observing Figure 8, it can be found that the distribution law of the mapping points is consistent with the density distribution law of the density image. However, the mapping area also faces some problems, such as overlapping or distributed in areas with less stress and smaller gradient changes. Therefore, it is necessary to further screen the mapping area to ensure that the filtered mapping area can construct an accurate mapping area.

Step five, train the parameters based on the single variable method to obtain the global mapping area between the final digital twin lightweight model and the physical entity.

The quality of the distribution of the twin model mapping area depends on the quality of the image segmentation, and the image segmentation based on mean shift is affected by two main factors:

1) Distribution of seed points: The distribution of seed points is an important factor affecting the segmentation results. In the specific implementation of this application, the density image is randomly generated based on the Gaussian distribution function, so the variance s of the density estimation function is a factor affecting the image segmentation quality. A larger variance s will cause the seed points to be distributed more widely, making the density estimation in the clustering process smoother, which may cause the segmentation results to be too fuzzy; while a smaller variance s will make the seed points distributed more concentrated, resulting in a more detailed density estimation in the clustering process, which may cause the segmentation results to be too subdivided. Therefore, choosing an appropriate variance s can affect the accuracy and effect of the segmentation results.

2) The size of the drift radius: The drift radius is a parameter that determines the color space and spatial distance range considered when the density point is drifted. A larger drift radius will make the drift process take into account a wider range of color differences and spatial distances, making the segmentation result too smooth and obtaining fewer feature areas; while a smaller drift radius may ignore some detail information, resulting in more feature areas, resulting in inaccurate segmentation results. Therefore, it is necessary to select an appropriate drift radius size to maintain the accuracy and representativeness of the segmentation results.

In summary, the distribution of seed points and the size of the drift radius are two main factors that affect the quality of image segmentation based on the mean drift program. By selecting appropriate variance s and drift radius, more accurate and effective segmentation results can be obtained, thereby obtaining a representative mapping area. In the specific implementation process of this application, a variety of Gaussian random distribution variance and drift radius operation combinations are set for multiple training. The specific training parameter settings are listed in Table 1.

Table 1: Image segmentation training parameters

In the specific implementation of this application, the single variable comparison method is used for multiple combination training for the two parameters of Gaussian variance s and drift radius h. Specifically, the parameter variation range of Gaussian variance s is 0.1 to 1, and the scale of each change is 0.1; the parameter variation range of drift radius h is 5 to 50, and the scale of each change is 5.

Through the univariate comparison method, the values of Gaussian variance s and drift radius h can be changed respectively, and then the segmentation effect under each parameter combination can be evaluated. Through multi-combination training, the impact of different parameter combinations on the segmentation results can be analyzed, and the best parameter combination can be selected to improve the segmentation quality. First, the value of drift radius h is fixed, and then the value of Gaussian variance s is changed. For example, the first group fixed h to 5, s value changed, the value range is 0.1 to 1; the second group fixed h to 10, s value changed, its value range is 0.1 to 1, and so on.

Then fix the Gaussian variance s, and then change the drift radius h. For example, the first group fixes s to 0.1, and changes h to a value range of 5 to 50; the second group fixes s to 0.2, and changes s to a value range of 5 to 50, and so on.

According to the results of multiple trainings, the Gaussian variance s has almost no effect on the results of image segmentation, while the drift radius has a greater impact on image segmentation. This means that when adjusting the parameters, the change in the drift radius has a more significant effect on the results of image segmentation. Therefore, in the process of optimizing image segmentation, it is necessary to focus on the adjustment of the drift radius. By changing the size of the drift radius, the image segmentation can be optimized to obtain more accurate and effective segmentation results. By optimizing the image segmentation parameters, the distribution of the mapping area can be better controlled to avoid overlap and unreasonable distribution. By continuously improving the algorithm parameters, the accuracy and representativeness of the mapping area selection can be improved, thereby improving the interaction effect between the digital twin lightweight model and the physical entity.

Step six, use the global mapping area of the final digital twin lightweight model and the physical entity to perform global mapping between the digital twin lightweight model and the physical entity of the lightweight product.

Based on the above process, the cargo box twin model-physical entity mapping area can be constructed.

Step seven: Use real data from physical entities to verify the digital twin lightweight model.

In the actual operation scenario, the operation data of the lightweight product is collected and analyzed based on the sampling area, and then compared with the analysis data in the digital twin mapping area in the virtual environment to verify the accuracy of the digital twin lightweight model.

There is a certain error between the physical entity and the twin model, and the error rate directly affects the accuracy of the twin model. In order to evaluate the accuracy of the cargo box twin model, this application proposes an accuracy evaluation standard, which comprehensively considers factors such as historical experience, existing research, and actual engineering needs, and introduces a safety factor. The accuracy evaluation standard requires that the error between the virtual data of the twin model and the real data of the physical entity does not exceed 15%, and the number of mapping areas that meet this error requirement accounts for no less than 80% of the total number of mapping areas. Based on this standard, the virtual data of the cargo box twin model is compared and verified with the real data of the physical entity. Table 2 lists the verification results of 84 mapping areas.

Table 2: Error range and ratio

According to Table 2, it can be seen that the proportion of measurement points within the error range of 15% is 88.09%. This meets the accuracy standard and shows the accuracy of the method for finding physical entity data sampling areas for real scenarios studied in this application. At the same time, this also shows that under the existing circumstances, the twin model of the cargo box is accurate, ensuring the reliability and accuracy of the twin model in simulating actual operation data, and providing a reliable basis for subsequent application and analysis.

This application successfully generates a stress cloud map that can capture the constitutive relationship of stress and strain by analyzing and extracting features from the twin model in a virtual environment; the mean shift method is used to segment the proportionally transformed stress density image, and the cluster centroid is obtained as the characteristic mapping area of the digital space and the physical entity, thereby mapping the physical entity sampling area and achieving global mapping; by comparing the stress data collected by the physical entity and the virtual analysis data of the twin model, the results show that the twin model meets the accuracy standard. The method proposed in this application can accurately identify the important stress areas required for mapping between the digital twin lightweight model and the physical entity, and accurately find the corresponding mapping area, thereby mapping the physical entity sampling area and establishing a reliable mapping area. This method provides an effective auxiliary means for the application and development of digital twin technology in lightweight automobiles.

Through the application of digital twin technology, this application can make the lightweight design and optimization of automobiles more accurate and efficient. Through accurate mapping, researchers and engineers can simulate multiple optimization schemes in the digital model, thereby reducing actual test and development costs. In short, this application provides strong support for automobile lightweighting and demonstrates its potential in achieving dual carbon goals and promoting sustainable development.

An embodiment of the present application provides a computer device, including a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the global mapping method between any digital twin lightweight model and the physical entity as described above.

Specifically, the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, it can execute the above-mentioned global mapping method between the digital twin lightweight model and the physical entity.

Those skilled in the art will appreciate that the structure of the computer device does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently.

In some embodiments, the computer device may also include a touch screen that can be used to display a graphical user interface (e.g., a startup interface of an application) and receive user operations on the graphical user interface (e.g., startup operations on an application). The specific touch screen may include a display panel and a touch panel. The display panel may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. The touch panel may collect the user's contact or non-contact operations on or near it, and generate pre-set operation instructions, for example, the user uses any suitable object or accessory such as a finger, stylus, etc. to operate on or near the touch panel. In addition, the touch panel may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and posture, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into information that the processor can process, and then sends it to the processor, and can receive and execute commands sent by the processor. In addition, the touch panel can be implemented by various types such as resistive, capacitive, infrared and surface acoustic wave, and any technology developed in the future can also be used to implement the touch panel. Further, the touch panel can cover the display panel, and the user can operate on or near the touch panel covered on the display panel according to the graphical user interface displayed on the display panel. After the touch panel detects the operation on or near it, it is transmitted to the processor to determine the user input, and then the processor provides corresponding visual output on the display panel in response to the user input. In addition, the touch panel and the display panel can be implemented as two independent components or integrated.

Corresponding to the startup method of the above-mentioned application, an embodiment of the present application also provides a storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the global mapping method between any digital twin lightweight model and the physical entity are executed.

The application startup device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application, its implementation principle and the technical effect produced are the same as those in the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, 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 devices or modules can be electrical, mechanical or other forms.

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

In addition, each functional module in the embodiments provided in the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

The present application is described with reference to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the processes and/or boxes in the flowchart and/or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present application can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present application should be included in the scope of protection of the claims of the present application.

Claims (9)

1. The global mapping method between the digital twin lightweight model and the physical entity is characterized by comprising the following steps of:

collecting data information of the lightweight product, and establishing a digital twin lightweight model; the data information comprises design parameters of the lightweight product, physical entity real data and physical principle information;

Carrying out finite element analysis on a digital twin light weight model of the light weight product to obtain a stress strain cloud picture of the light weight product in a virtual environment;

converting the stress-strain cloud image into an equal proportion stress density image based on the stress-strain constitutive relation and the color gradient change rule;

dividing the stress density image based on a mean shift method to obtain a global mapping region of the digital twin lightweight model and the physical entity;

training parameters based on a single variable method to obtain a global mapping region of a final digital twin lightweight model and a physical entity;

performing global mapping between the digital twin light weight model of the light weight product and the physical entity by utilizing a global mapping area of the final digital twin light weight model and the physical entity;

the method for dividing the stress density image based on the mean shift to obtain a global mapping region of the digital twin lightweight model and the physical entity comprises the following steps:

a, performing nuclear density estimation:

different working conditions are in three-dimensional spaceIs given by->Data unit->，，Belongs to point clouds converted from stress cloud pictures; by kernel function->And symmetrically positive->Bandwidth matrix->For parameters, calculate at the point +. >Multi-kernel density estimation at:

wherein,is a kernel function with a bandwidth matrix D, D represents the determinant of the bandwidth matrix D;

three-dimensional kernel functionIs a bounded function that satisfies the following conditions:

wherein,is a constant, I is an integer set, | +.>II represents vector +.>Is (are) norms of->Representation vector->Is a transpose of (2);

the multidimensional kernel function is derived from a symmetric univariate kernel function by two different methodsGenerating:

wherein,obtained from the product of the univariate kernels;By->Middle rotation->Obtained, i.e.)>Is radially symmetrical,>is a constant;

considering a radially symmetric kernel function, then the symmetric multidimensional kernel function satisfies:

wherein for a function called kernel function profileNeed to make->Normalized constant->When strictly positive, kernel function->The integral is 1;

making the bandwidth matrix D proportional to the same matrixThe method comprises the steps of carrying out a first treatment on the surface of the Providing a bandwidth parameter->At this time, the kernel density estimator is:

；

and B, estimating probability density gradient:

calculating the density gradient:

assume thatThe derivative of (2) is +.>If the kernel function exists in the interval, the kernel function is defined>The method comprises the following steps:

wherein,，is a kernel contour function +.>Is used for the purpose of determining the derivative of (c),

is a corresponding normalization function, and is introduced into a density gradient formula to obtain the following components:

calculated out The density estimate at that point is proportional to:

the mean shift vector is:

use of coresGAs a weight, andas the core, there are:

will be as followsWindow function with a bandwidth h for the center +.>Along the mean shift vector->Translation, obtaining a new window function->；

C, all density storages in the stress density image are seed points of the mean shift program; for each seed pointSetting the drift radius h, calculating to +.>Kernel density weighted average vector +.f for all other sample points within the centered, radius h window>For each seed point +.>Performing translation, i.e.)>Until the seed point converges, i.e. +.>The method comprises the steps of carrying out a first treatment on the surface of the Performing mean shift iteration to realize density image segmentation;

and D, finding out a twin model virtual analysis stress dangerous point based on stress density image segmentation, mapping out a data sampling area when the physical entity runs, and constructing a global mapping area of the digital twin lightweight model and the physical entity.

2. The global mapping method between a digital twin lightweight model and a physical entity according to claim 1, wherein the performing finite element analysis on the digital twin lightweight model of the lightweight product to obtain a stress and strain cloud image under a virtual environment of the lightweight product comprises:

Establishing a virtual analysis module of the digital twin light weight model, and performing finite element analysis on the digital twin light weight model of the light weight product after setting a solver and analysis options to obtain a stress and strain cloud image under the virtual environment of the light weight product; the virtual analysis module comprises a geometric model module, a boundary condition module, a material attribute module, a grid division module and an application loading module.

3. The global mapping method between a digital twin lightweight model and a physical entity according to claim 2, wherein the dividing the stress density image based on the mean shift method to obtain a global mapping region of the digital twin lightweight model and the physical entity comprises:

dividing the stress density image to form a limited clustering mass center;

and mapping a data acquisition area of the physical entity by taking the limited clustering centroids as feature mapping areas of the digital twin lightweight model and the physical entity to obtain a global mapping area of the digital twin lightweight model and the physical entity.

4. The global mapping method between a digital twin lightweight model and a physical entity according to claim 3, wherein the training parameters based on a single variable method to obtain a global mapping region of a final digital twin lightweight model and the physical entity comprises:

Performing multi-combination training on the drift radius and the variance of the density estimation function in the image segmentation process by adopting a univariate contrast method, and determining the optimal drift radius and the variance of the density estimation function;

and obtaining a global mapping region of the final digital twin lightweight model and the physical entity based on the optimal drift radius and the variance of the density estimation function.

5. The global mapping method between a digital twin lightweight model and a physical entity according to any of claims 1-4, wherein the converting the stress-strain cloud into an equal proportion stress density image based on stress and strain constitutive relations and color gradient change rules comprises:

and A, determining the stress and strain constitutive relation:

the relationship between stress and strain is described by the modulus of elasticity E:

wherein,for stress->Is strain;Is the magnitude of the acting force;Is the area of force application;Indicating the amount of change in length;Is the initial length;

b, determining the equal proportional relation between the discrete unit and the pixel unit:

the proportional relationship between discrete cell size and pixel size is:

wherein,the stress and strain module discrete unit size of the digital twin light model is adopted; / >The whole model size of the digital twin light model stress and strain module is provided;Is the pixel cell size;The whole pixel size of the color cloud image which needs to be subjected to data conversion;

obtaining a final density image through pixel adjustment;

c, converting the color cloud image into a density image through pixel units and RGB red channel values of each pixel unit as media:

storing color stress strain cloud image pixel units in a 3D array of m multiplied by n multiplied by 3, and taking a red channel value of each pixel unit as a reference value of stress density;

defining the density storage unit of the stress density image converted by the pixel unit of the position g= (i, j) asIts density value is->Wherein i is more than or equal to 1 and less than or equal to m; j is more than or equal to 1 and less than or equal to n; 0.ltoreq.L>≤255；

Red channel values are extracted and returned to a matrix of size mxn:

wherein,in the matrix, a density storage unit is provided, the value of which is equal to the RGB red channel value of each pixel unit, and the position of which is g= (i, j); matrix density storage unit->The density value in the memory is the density memory cell of the stress density imageDensity value of->；

Density storage unit in stress density image based on Gaussian distribution functionInternal random generation- >And (3) carrying out point separation to obtain a point set D, wherein the point set D is a density point set capable of carrying out density image segmentation.

6. The method of global mapping between a digital twin lightweight model and a physical entity according to any of claims 1-4, further comprising:

verifying the digital twin lightweight model by using physical entity real data: and acquiring and analyzing the light product operation data based on the sampling area in the real operation scene, and comparing the light product operation data with the analysis data at the digital twin mapping area in the virtual environment to verify the accuracy of the digital twin light model.

7. A global mapping device between a digital twin lightweight model and a physical entity, comprising:

the data acquisition module is used for acquiring data information of the lightweight product and establishing a digital twin lightweight model; the data information comprises design parameters of the lightweight product, physical entity real data and physical principle information;

the finite element analysis module is used for carrying out finite element analysis on the digital twin light weight model of the light weight product to obtain a stress strain cloud image of the light weight product in a virtual environment;

the cloud image conversion module is used for converting the stress-strain cloud image into an equal-proportion stress density image based on the stress-strain constitutive relation and the color gradient change rule;

The image segmentation module is used for segmenting the stress density image based on a mean shift method to obtain a global mapping region of the digital twin lightweight model and the physical entity;

the parameter training module is used for training parameters based on a single variable method to obtain a global mapping area of the final digital twin lightweight model and the physical entity;

the global mapping module is used for carrying out global mapping between the digital twin light weight model of the light weight product and the physical entity by utilizing the final global mapping area of the digital twin light weight model and the physical entity;

the method for dividing the stress density image based on the mean shift to obtain a global mapping region of the digital twin lightweight model and the physical entity comprises the following steps:

a, performing nuclear density estimation:

different working conditions are in three-dimensional spaceIs given by->Data unit->，，Belongs to point clouds converted from stress cloud pictures; by kernel function->And symmetrically positive->Bandwidth matrix->For parameters, calculate at the point +.>Multi-kernel density estimation at:

wherein,is a kernel function with a bandwidth matrix D, D represents the determinant of the bandwidth matrix D;

three-dimensional kernel functionIs a bounded function that satisfies the following conditions:

Wherein,is a constant, I is an integer set, | +.>II represents vector +.>Is of (2)Count (n)/(l)>Representation vector->Is a transpose of (2);

the multidimensional kernel function is derived from a symmetric univariate kernel function by two different methodsGenerating:

wherein,obtained from the product of the univariate kernels;By->Middle rotation->Obtained, i.e.)>Is radially symmetrical,>is a constant;

considering a radially symmetric kernel function, then the symmetric multidimensional kernel function satisfies:

wherein, for the sake of scaleAs a function of kernel function contoursNeed to make->Normalized constant->When strictly positive, kernel function->The integral is 1;

making the bandwidth matrix D proportional to the same matrixThe method comprises the steps of carrying out a first treatment on the surface of the Providing a bandwidth parameter->At this time, the kernel density estimator is:

；

and B, estimating probability density gradient:

calculating the density gradient:

assume thatThe derivative of (2) is +.>If the kernel function exists in the interval, the kernel function is defined>The method comprises the following steps:

wherein,，is a kernel contour function +.>Is used for the purpose of determining the derivative of (c),

is a corresponding normalization function, and is introduced into a density gradient formula to obtain the following components:

calculated outThe density estimate at that point is proportional to:

the mean shift vector is:

use of coresGAs a weight, andas the core, there are:

will be as followsWindow function with a bandwidth h for the center +.>Along the mean shift vector- >Translation, obtaining a new window function->；

C, all density storages in the stress density image are seed points of the mean shift program; for each seed pointSetting the drift radius h, calculating to +.>Kernel density weighted average vector +.f for all other sample points within the centered, radius h window>For each seed point +.>Performing translation, i.e.)>Until the seed point converges, i.e. +.>The method comprises the steps of carrying out a first treatment on the surface of the Performing mean shift iteration to realize density image segmentation;

and D, finding out a twin model virtual analysis stress dangerous point based on stress density image segmentation, mapping out a data sampling area when the physical entity runs, and constructing a global mapping area of the digital twin lightweight model and the physical entity.

8. A computer device comprising a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is in operation, the processor executing the machine-readable instructions to perform the steps of the method of global mapping between a digital twin lightweight model as defined in any one of claims 1-6 and a physical entity.

9. A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of global mapping between a digital twin lightweight model and a physical entity as claimed in any of claims 1 to 6.