Typical structure identification method, device, equipment, storage medium and program product

Abstract

The present application relates to the technical field of numerical simulation analysis, and particularly relates to a typical structure identification method, device, equipment, storage medium and program product. The method comprises the following steps: obtaining a three-dimensional particle point set of a target to be identified, and calculating porosity, directional eigenvalue, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set; determining whether the target to be identified belongs to a first typical category set, a second typical category set or a third typical category set based on the porosity; when the target to be identified belongs to the first typical category set, identifying the typical structure of the target to be identified based on the porosity; when the target to be identified belongs to the second typical category set, identifying the typical structure of the target to be identified based on the sphericity; and when the target to be identified belongs to the third typical category set, identifying the typical structure of the target to be identified based on the directional eigenvalue, the overall linearity and the overall flatness. The method can effectively improve the efficiency of structure type identification and space debris impact spacecraft risk simulation evaluation.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of numerical simulation analysis technology, and in particular to methods, devices, equipment, storage media and program products for identifying typical structures. Background Technology

[0002] The increasing number of space launches generates a large amount of space debris, which can move at speeds exceeding several thousand meters per second relative to spacecraft. The risk of space debris impacting spacecraft is rising, posing a significant threat to current space activities and the safety of spacecraft in orbit. Therefore, it is urgent to conduct rapid risk assessments of space debris impacts to support improvements in the survivability of spacecraft in orbit.

[0003] Risk assessment of space debris impacting spacecraft primarily involves obtaining the damage probability of equivalent space debris impacting various internal components of the spacecraft at different speeds and angles using experimental or simulation methods, and then evaluating the risk level. Numerical simulation, with its significant advantages such as rapid iterative optimization, ability to display process details, low cost, and high efficiency, has become one of the main methods in scientific and engineering research. It is particularly suitable for simulating high-risk conditions such as hypervelocity impacts, and can avoid the dangers and destructiveness of actual experiments.

[0004] The risk assessment of spacecraft impacted by space debris is analyzed using meshless numerical simulation techniques such as Smoothed Particle Hydrodynamics (SPH). The main steps include rapid modeling, parallel computing, damage extraction, and probabilistic analysis. Rapid modeling primarily involves constructing simplified spacecraft models using typical structures such as spheres, cuboids, frustums, and plates for parallel computation of hypervelocity impacts. Damage extraction requires automatically reading typical structures from the spacecraft model, quickly identifying structure types, and specifically extracting physical damage quantities and assessing the degree of functional degradation.

[0005] Although the individual structures that make up a spacecraft in simulation calculations are simple, they are numerous, numbering in the dozens or even hundreds. Currently, the main method involves manually opening visualization software to examine each component of the spacecraft model and recording its structural category, which is inefficient.

[0006] Therefore, there is an urgent need for a method to identify typical structures. Summary of the Invention

[0007] To address the inefficiency caused by manually reading and recording the typical structures of a spacecraft model in space debris impact risk simulation assessment, this invention provides a method, apparatus, device, storage medium, and program product for identifying typical structures.

[0008] On one hand, the present invention provides a method for identifying typical structures, the method comprising:

[0009] Obtain a three-dimensional particle point set of the target to be identified, and calculate porosity, directional feature value, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set;

[0010] Based on the porosity, the target to be identified is determined to belong to a first typical category set, a second typical category set, or a third typical category set; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums.

[0011] When the target to be identified belongs to the first typical category set, the typical structure of the target to be identified is identified based on the porosity;

[0012] When the target to be identified belongs to the second typical category set, the typical structure of the target to be identified is identified based on the sphericity;

[0013] When the target to be identified belongs to the third typical category set, the typical structure of the target to be identified is identified based on the directional feature value, the overall linearity, and the overall flatness.

[0014] On the other hand, a typical structure identification device is provided, the device comprising:

[0015] The computing unit is used to acquire a three-dimensional particle point set of the target to be identified, and to calculate porosity, directional feature value, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set;

[0016] The determination unit is used to determine, based on the porosity, whether the target to be identified belongs to a first typical category set, a second typical category set, or a third typical category set; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums.

[0017] The first identification unit is used to identify the typical structure of the target to be identified based on the porosity when the target to be identified belongs to a first typical category set.

[0018] The second identification unit is used to identify the typical structure of the target to be identified based on the sphericity when the target to be identified belongs to the second typical category set.

[0019] The third identification unit is used to identify the typical structure of the target to be identified based on the directional feature value, the overall linearity, and the overall flatness when the target to be identified belongs to the third typical category set.

[0020] On the other hand, a computing device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in any embodiment of this specification.

[0021] On the other hand, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the methods described in any embodiment of this specification.

[0022] On the other hand, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0023] This invention provides a method for identifying typical structures. It identifies rings and curves based on porosity, and further identifies hollow boxes and spheres by combining sphericity. It identifies spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, or frustums of cones based on directional eigenvalues, overall linearity, and overall flatness. This method can quickly and automatically identify 12 commonly used typical structures composed of three-dimensional particle point sets in meshless numerical simulations, effectively improving the efficiency of structure type identification and space debris impact risk simulation assessment for spacecraft. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a typical structure identification method provided in an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of a three-dimensional particle point set of a curve provided in an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of a three-dimensional particle point set on a sphere provided in an embodiment of the present invention;

[0028] Figure 4 This is a hardware architecture diagram of an electronic device provided in an embodiment of the present invention;

[0029] Figure 5 This is a structural diagram of a typical identification device provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0031] The specific implementation method is described below.

[0032] Please refer to Figure 1 This invention provides a method for identifying a typical structure, the method comprising:

[0033] Step 100: Obtain the three-dimensional particle point set of the target to be identified, and calculate the porosity, directional feature value, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set;

[0034] Step 102: Determine whether the target to be identified belongs to the first typical category set, the second typical category set, or the third typical category set based on porosity; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums.

[0035] Step 104: When the target to be identified belongs to the first typical category set, identify the typical structure of the target to be identified based on porosity;

[0036] Step 106: When the target to be identified belongs to the second typical category set, identify the typical structure of the target to be identified based on sphericity;

[0037] Step 108: When the target to be identified belongs to the third typical category set, the typical structure of the target to be identified is identified based on the directional feature value, overall linearity, and overall flatness.

[0038] In this embodiment of the invention, loops and curves are identified by porosity, and hollow boxes and spheres are further identified by combining sphericity. Spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, or frustums are identified by directional eigenvalues, overall linearity, and overall flatness. This allows for rapid and automatic identification of 12 commonly used typical structures composed of three-dimensional particle point sets in meshless numerical simulations, significantly improving the efficiency of structure type identification compared to manual interpretation methods. Furthermore, it can effectively enhance the efficiency of space debris impact risk simulation assessment of spacecraft.

[0039] For step 100:

[0040] In this embodiment, a three-dimensional particle point set of the target to be identified is obtained for the identification of 12 commonly used typical structures, with a dimension of N×3. Only schematic diagrams of the three-dimensional particle point sets for curves and spheres are shown here, as shown in the figures below. Figure 2 and Figure 3 As shown.

[0041] The calculation methods for porosity, directional eigenvalue, overall linearity, overall flatness, and sphericity are explained below:

[0042] Porosity is calculated as follows: calculate the convex hull volume of the three-dimensional particle point set, denoted as v0, where v1 represents the actual volume of the three-dimensional particle point set. Porosity α is defined as (1-v1 / v0)*100%. The theoretical range of porosity is 0~1.

[0043] The directional eigenvalues ​​are calculated by constructing the covariance matrix. ,in Let X represent the row center of the particle set, X be the three-dimensional particle point set, and T represent the transpose. Calculate the covariance matrix. The three eigenvalues ​​of the matrix, arranged in ascending order, are a, b, and c. Since the covariance matrix is ​​a real symmetric positive semi-definite matrix, its eigenvalues ​​are non-negative.

[0044] The calculation methods for overall linearity and overall flatness are as follows: Overall linearity is defined as follows: Flatness is defined as When the point sets are collinear, the linearity is at its maximum value of 1. When the point sets are coplanar, the flatness is at its maximum value of 1. Therefore, GL and GP range from 0 to 1. When the particle set is randomly rotated by an angle... ,in, Covariance matrix Let X be the covariance matrix of a particle set after random rotation by an angle, where X is the three-dimensional particle point set and R represents an arbitrary rotation matrix. It can be seen that linearity and flatness are rotation-invariant, meaning the shape of the point set is independent of the viewing angle.

[0045] The sphericity is calculated as follows: First, the 3D particle point set is decentered, and the optimal radius and center position are fitted using least squares to obtain the optimal sphere. Then, the average distance error between all points in the 3D particle point set and the optimal sphere is calculated, and then divided by the dimensionless optimal radius. The reciprocal of the dimensionless optimal radius is the sphericity. When the point set lies entirely on a sphere, the sphericity is very large.

[0046] Regarding step 102:

[0047] The porosity of the target to be identified is determined. When the porosity is greater than 90%, the target belongs to the first typical category set, namely a curve or ring. When the porosity is greater than 10% and less than 90%, the target belongs to the second typical category set and is identified as a hollow box or a sphere. When the porosity is less than 10%, the target belongs to the third typical category set and is identified as a sphere, rod, plate, frustum, cuboid, tetrahedron, cylinder or frustum.

[0048] Regarding step 104:

[0049] In some implementations, when the target to be identified belongs to a first typical category set, the typical structure of the target to be identified is determined based on porosity, including:

[0050] When the porosity is greater than 90%, the target to be identified belongs to the first typical category set;

[0051] Determine if the porosity is greater than 99%;

[0052] If so, the target to be identified is a curve;

[0053] If not, then the target to be identified is a ring.

[0054] Regarding step 106:

[0055] In some implementations, when the target to be identified belongs to a second typical category set, the typical structure of the target to be identified is determined based on sphericity, including:

[0056] When the porosity is greater than 10% and less than 90%, the target to be identified belongs to the second typical category set.

[0057] Determine if the sphericity is greater than 15;

[0058] If so, then the target to be identified is a sphere;

[0059] If not, then the target to be identified is a hollow box.

[0060] Regarding step 108:

[0061] In some implementations, when the target to be identified belongs to the third typical category set, the typical structure of the target to be identified is identified based on directional feature values, overall linearity, and overall flatness, including steps S1-S6:

[0062] S1, when the porosity is less than 10%, the target to be identified belongs to the third typical category set;

[0063] S2, when the feature values ​​in the three directions are equal, the target to be identified is a sphere;

[0064] S3, when the overall linearity is greater than 0.9, the target to be identified is a pole;

[0065] S4, determine whether the overall flatness is greater than 0.9;

[0066] S5, if so, then the target to be identified belongs to the first subset of the third typical category set. Based on the directional feature value and the projection length in several random directions, the typical structure of the target to be identified is identified; wherein, the first subset contains plates and frustums of cones.

[0067] S6. If not, the target to be identified belongs to the second subset of the third typical category set. Based on the directional feature value and the ratio of the projected area of ​​the three-dimensional particle point set, the typical structure of the target to be identified is identified. The second subset contains cuboids, tetrahedrons, cylinders and frustums.

[0068] In step S5, based on directional feature values ​​and projection lengths in several random directions, the typical structure of the target to be identified is determined, including:

[0069] Based on the eigenvector corresponding to the minimum directional eigenvalue as the perpendicular line, the plane perpendicular to the perpendicular line is determined as the target plane, and the three-dimensional particle point set of the target to be identified is projected onto the target plane;

[0070] For each randomly selected two-dimensional direction, the projection length of the target plane's projection point set in the current random direction is calculated.

[0071] Based on the projection lengths corresponding to all random directions, calculate the root mean and mean, and then calculate the ratio of the root mean and mean.

[0072] When the ratio is greater than 0.01, the set of projection points representing the target plane is square, and the target to be identified is a board;

[0073] When the ratio is less than 0.01, the set of projection points representing the target plane is circular, and the target to be identified is a frustum.

[0074] In this embodiment, the perpendicular line to the target plane (i.e., the eigenvector corresponding to the smallest eigenvalue of the point set covariance matrix) is found, and the three-dimensional particle point set is projected onto the target plane. Ten two-dimensional directions are randomly selected, and the projection length of the projected point set of the target plane in each two-dimensional direction is calculated. After obtaining the projection lengths in the ten two-dimensional directions, the ratio of the root mean square error to the mean of all projection lengths is calculated. A variance / mean greater than 0.01 indicates a plate, and the projection surface is square; a variance / mean less than 0.01 indicates a frustum, and the projection surface is circular.

[0075] In step S6, based on the directional feature values ​​and the projected area ratio of the three-dimensional particle point set, the typical structure of the target to be identified is determined, including:

[0076] Using the eigenvector corresponding to the largest directional eigenvalue as the axis, the three-dimensional particle point set of the target to be identified is projected onto the plane perpendicular to the axis, and the two-dimensional projected area s0 is calculated.

[0077] Project the three-dimensional particle point set of the target to be identified onto the axis. Place an infinitely large rectangular box with a thickness of the target value at the first endpoint, the center point, and the second endpoint of the axis, respectively, to extract the three-dimensional particles inside the infinitely large rectangular boxes corresponding to the first endpoint, the center point, and the second endpoint.

[0078] For each three-dimensional particle in an infinitely large rectangular box, the current three-dimensional particle is projected onto the plane perpendicular to the axis, and the two-dimensional projected area after projection is calculated. The two-dimensional projected areas corresponding to the first endpoint, the center point, and the second endpoint are respectively denoted as s1, s2, and s3.

[0079] When s1 / s0=s2 / s0=s3 / s0=1, the target to be identified belongs to the third subset of the third typical category set, and the typical structure of the target to be identified is identified based on the directional feature value and the projection length in several random directions; among them, the third subset contains cylinders and cuboids.

[0080] If the difference between s1 / s0, s2 / s0, and s3 / s0 and 1 is less than a preset threshold, then the target to be identified is a frustum.

[0081] Otherwise, the target to be identified is identified as a tetrahedron.

[0082] In this embodiment, the target value is 2.2 times the average particle spacing dx of the first endpoint, the center point, or the second endpoint. The average particle spacing is calculated by calculating the distance between the particle and its neighboring particles and then averaging the distances.

[0083] In this embodiment of the invention, when s1 / s0=s2 / s0=s3 / s0=1, the target to be identified belongs to the third subset of the third typical category set, and the typical structure of the target to be identified is identified based on the directional feature value and the projection length in several random directions; wherein, the third subset contains cylinders and cuboids.

[0084] Specifically: Locate the axis (i.e., the eigenvector corresponding to the largest eigenvalue of the point set covariance matrix), and project the 3D points onto a plane perpendicular to the axis. Randomly select 10 two-dimensional directions, and calculate the projection length of the target plane's projection point set in each direction. After obtaining the projection lengths in the 10 two-dimensional directions, calculate the ratio of the root mean square error to the mean of all projection lengths. Lengths with a variance / mean less than 0.01 are identified as cylinders, and lengths with a variance / mean greater than 0.01 are identified as cuboids.

[0085] It should be noted that this structure recognition method is based on the basic information of the three-dimensional particle point set, and the porosity, directional characteristic value, overall linearity, overall flatness and sphericity are rotationally invariant, that is, the shape of the point set is independent of the observation angle.

[0086] Figure 4 , Figure 5 As shown, this embodiment of the invention provides a typical structure identification device. The device embodiment can be implemented through software, hardware, or a combination of both. From a hardware perspective, as... Figure 4 The diagram shown is a hardware architecture diagram of a computing device containing a typical identification device according to an embodiment of the present invention. (Except for...) Figure 4 In addition to the processor, memory, network interface, and non-volatile memory shown, the computing device in the embodiment may also include other hardware. Taking software implementation as an example, such as... Figure 5 As shown, a device in a logical sense is formed by the CPU of the computing device in which it is located reading the corresponding computer program from the non-volatile memory into the memory for execution.

[0087] like Figure 5 As shown, this embodiment provides a typical structure identification device for implementing the method as described in any embodiment of the specification, including:

[0088] The calculation unit 501 is used to acquire a three-dimensional particle point set of the target to be identified, and to calculate porosity, directional eigenvalues, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set.

[0089] The determination unit 502 is used to determine, based on porosity, whether the target to be identified belongs to a first typical category set, a second typical category set, or a third typical category set; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums.

[0090] The first identification unit 503 is used to identify the typical structure of the target to be identified based on porosity when the target to be identified belongs to the first typical category set.

[0091] The second identification unit 504 is used to identify the typical structure of the target to be identified based on sphericity when the target to be identified belongs to the second typical category set.

[0092] The third identification unit 505 is used to identify the typical structure of the target to be identified based on directional feature values, overall linearity, and overall flatness when the target to be identified belongs to the third typical category set.

[0093] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on a typical identification device. In other embodiments of the present invention, a typical identification device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0094] The information interaction and execution process between the various units in the above-mentioned device are based on the same concept as the method embodiment of the present invention, and the specific details can be found in the description of the method embodiment of the present invention, and will not be repeated here.

[0095] This application also provides a computing device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a method for identifying a typical structure in any embodiment of the present invention.

[0096] Embodiments of this application also provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the identification method of the typical structure provided in the above-described method embodiments.

[0097] Embodiments of this application also provide a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium and executes the computer program, causing the computer device to perform the identification method of any of the typical structures described in the above embodiments.

[0098] For ease of description, the above systems or devices are described separately as various modules or units based on their functions. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components.

[0099] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0100] Finally, it should be noted that in this document, relational terms such as first, second, and third are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0101] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of identifying a canonical structure, characterized by, include: Obtain a three-dimensional particle point set of the target to be identified, and calculate porosity, directional feature value, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set; Based on the porosity, the target to be identified is determined to belong to a first typical category set, a second typical category set, or a third typical category set; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums of cones; when the porosity is greater than 90%, the target to be identified belongs to the first typical category set; when the porosity is greater than 10% and less than 90%, the target to be identified belongs to the second typical category set; when the porosity is less than 10%, the target to be identified belongs to the third typical category set. When the target to be identified belongs to the first typical category set, the typical structure of the target to be identified is identified based on the porosity; When the target to be identified belongs to the second typical category set, the typical structure of the target to be identified is identified based on the sphericity; When the target to be identified belongs to the third typical category set, the typical structure of the target to be identified is identified based on the directional feature value, the overall linearity, and the overall flatness.

2. The method of claim 1, wherein, The step of identifying the typical structure of the target to be identified based on the porosity when the target to be identified belongs to the first typical category set includes: Determine whether the porosity is greater than 99%; If so, then the target to be identified is a curve; If not, then the target to be identified is a ring.

3. The method of claim 1, wherein, When the target to be identified belongs to the second typical category set, the typical structure of the target to be identified is determined based on the sphericity, including: Determine whether the sphericity is greater than 15; If so, then the target to be identified is a sphere; If not, then the target to be identified is a hollow box.

4. The method of claim 1, wherein, When the target to be identified belongs to the third typical category set, the typical structure of the target to be identified is determined based on the directional feature value, the overall linearity, and the overall flatness, including: When the three directional feature values ​​are equal, the target to be identified is a sphere; When the overall linearity is greater than 0.9, the target to be identified is a pole; Determine whether the overall flatness is greater than 0.9; If so, the target to be identified belongs to the first subset of the third typical category set. Based on the directional feature value and the projection length in several random directions, the typical structure of the target to be identified is identified; wherein, the first subset contains plates and frustums of cones. If not, the target to be identified belongs to the second subset of the third typical category set. Based on the directional feature value and the ratio of the projected area of ​​the three-dimensional particle point set, the typical structure of the target to be identified is identified; wherein, the second subset contains cuboids, tetrahedrons, cylinders and frustums.

5. The method of claim 4, wherein, The step of identifying the typical structure of the target to be identified based on the directional feature value and the projection length in several random directions includes: Based on the feature vector corresponding to the smallest directional feature value as the perpendicular line, the plane perpendicular to the perpendicular line is determined as the target plane, and the three-dimensional particle point set of the target to be identified is projected onto the target plane; For each randomly selected two-dimensional direction, the projection length of the target plane's projection point set in the current random direction is calculated. Based on the projection lengths corresponding to all random directions, calculate the root mean and mean, and calculate the ratio of the root mean and the mean; When the ratio is greater than 0.01, it indicates that the projection point set of the target plane is square, and the target to be identified is a board; When the ratio is less than 0.01, it indicates that the projection point set of the target plane is circular, and the target to be identified is a frustum.

6. The method of claim 4, wherein, The method of identifying the typical structure of the target to be identified based on the directional feature value and the projected area ratio of the three-dimensional particle point set includes: Based on the feature vector corresponding to the largest directional feature value as the axis, the three-dimensional particle point set of the target to be identified is projected onto the plane perpendicular to the axis, and the two-dimensional projected area s0 is calculated. The three-dimensional particle point set of the target to be identified is projected onto the axis. An infinitely large rectangular box with a thickness of the target value is placed at the first endpoint, the center point, and the second endpoint of the axis, respectively, so as to extract the three-dimensional particles inside the infinitely large rectangular box corresponding to the first endpoint, the center point, and the second endpoint. For each three-dimensional particle of an infinitely large rectangular box, the current three-dimensional particle is projected onto the plane perpendicular to the axis, and the two-dimensional projected area after projection is calculated. The two-dimensional projected areas corresponding to the first endpoint, the center point, and the second endpoint are respectively denoted as s1, s2, and s3. When s1 / s0=s2 / s0=s3 / s0=1, the target to be identified belongs to the third subset of the third typical category set, and the typical structure of the target to be identified is identified based on the directional feature value and the projection length in several random directions; wherein, the third subset contains cylinders and cuboids; If the difference between any one of the three results s1 / s0, s2 / s0, and s3 / s0 and 1 is less than a preset threshold, then the target to be identified is a frustum. Otherwise, the target to be identified is identified as a tetrahedron.

7. An identification device of a typical structure, implementing the method according to any one of claims 1 to 6, characterized in that, include: The computing unit is used to acquire a three-dimensional particle point set of the target to be identified, and to calculate porosity, directional feature value, overall linearity, overall flatness and sphericity based on the three-dimensional particle point set; The determination unit is used to determine, based on the porosity, whether the target to be identified belongs to a first typical category set, a second typical category set, or a third typical category set; wherein, the first typical category set contains curves and loops, the second typical category set contains hollow boxes and spheres, and the third typical category set contains spheres, rods, plates, frustums, cuboids, tetrahedrons, cylinders, and frustums. The first identification unit is used to identify the typical structure of the target to be identified based on the porosity when the target to be identified belongs to a first typical category set. The second identification unit is used to identify the typical structure of the target to be identified based on the sphericity when the target to be identified belongs to the second typical category set. The third identification unit is used to identify the typical structure of the target to be identified based on the directional feature value, the overall linearity, and the overall flatness when the target to be identified belongs to the third typical category set.

8. A computing device, comprising: It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images