Method, device, equipment and storage medium for generating porous structure model

Abstract

The present application provides a method, apparatus, device, and storage medium for generating a porous structure model. The method generates a target parameter expression protocol for a first porous structure model based on an example parameter expression protocol by calling a pre-trained large language model, generating guidance information according to the structure, and drawing the model based on the target parameter expression protocol to generate the first porous structure model; the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol. The embodiments of the present application can improve the structural performance of the model.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional modeling, and in particular to a method, device, equipment and storage medium for generating a porous structure model. Background Art

[0002] In the field of additive manufacturing, the design and application of porous microstructures are important research areas. Appropriate porous structures can reduce structural weight while maintaining the required strength and stiffness. Currently, porous structure models suitable for additive manufacturing scenarios are mainly divided into TPMS structures and classic rod-plate structures. The classic rod-plate structure mainly relies on planning the material's microstructural units (i.e., cells) to control and optimize its macroscopic properties.

[0003] However, due to the extremely large design space of the cell topology, there are many shapes, sizes, and permutations of different basic topologies. When manually designing the topology of a porous structure model, finding the cell with the best performance at the same volume fraction is very labor-intensive and difficult, thus affecting design efficiency. Summary of the Invention

[0004] In view of this, the present application provides a method, device, equipment and storage medium for generating a porous structure model to at least solve the problems existing in the related art.

[0005] Specifically, this application is implemented through the following technical solutions:

[0006] This application provides a method for generating a porous structure model, comprising:

[0007] Obtaining target prompt information; wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for the first porous structure model;

[0008] calling a pre-trained large language model, generating a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol according to the instruction of the structure generation guidance information, and performing model rendering based on the target parameter expression protocol to generate the first porous structure model;

[0009] Among them, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

[0010] Optionally, the method further includes:

[0011] Acquiring the modified target prompt information multiple times, and returning to the step of calling the pre-trained large language model to generate the first porous structure model, thereby obtaining multiple first porous structure models;

[0012] Based on the multiple first porous structure models, a target porous structure model set is determined.

[0013] Optionally, determining a target porous structure model set based on the multiple first porous structure models includes:

[0014] Obtaining a porous cell cubic structure;

[0015] Based on the porous cellular cubic structure, generating a plurality of second porous structure models;

[0016] The plurality of first porous structure models and the plurality of second porous structure models are mixed to obtain a porous structure model set, and the target porous structure model set is generated based on the porous structure model set.

[0017] Optionally, generating a plurality of second porous structure models based on the porous cell cubic structure includes:

[0018] Dividing the porous cellular cubic structure into equal parts to obtain a plurality of sub-cubic structures;

[0019] A plurality of points are randomly determined in any sub-cubic structure, and a flat plate structure passing through the plurality of points is constructed; wherein the flat plate structure intersects with each face of the sub-cubic structure.

[0020] Performing mirror symmetry on the flat plate structure in each of the other sub-cubic structures to obtain a mirrored flat plate structure corresponding to each sub-cubic structure, and generating the second porous structure model based on the flat plate structure and each of the mirrored flat plate structures;

[0021] The step of randomly determining a plurality of points in any sub-cubic structure is returned to obtain the plurality of second porous structure models.

[0022] Optionally, generating a target porous structure model set based on the porous structure model set includes:

[0023] For each porous structure model in the porous structure model set, randomly selecting a target structure performance enhancement method from a plurality of structure performance enhancement methods, and generating performance enhancement prompt information based on the target structure performance enhancement method; the performance enhancement prompt information includes enhancement processing guidance information of the performance enhancement process;

[0024] Calling the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model;

[0025] Based on each of the new porous structure models, the target porous structure model set is generated.

[0026] Optionally, the multiple structural performance enhancement methods include an enhancement method based on a cubic lattice and an enhancement method based on a tube-sheet hybrid structure; wherein the enhancement method based on a cubic lattice includes at least one of an enhancement method based on a body-centered cubic lattice, an enhancement method based on a simple cubic lattice, and an enhancement method based on a mixed cubic lattice.

[0027] Optionally, the multiple structural performance enhancement methods include an enhancement method based on a cubic lattice; and the calling of the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model includes:

[0028] Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model;

[0029] Migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model according to the property characteristics;

[0030] According to the connection rules of the target cubic lattice, a rod structure is created, and based on the parameter expression protocol of the rod structure, a parameter expression protocol of a first truss model is generated, and the first truss model is used as the new porous structure model; wherein the layout of the rod structure meets preset requirements.

[0031] Optionally, using the first truss model as the new porous structure model includes:

[0032] A first structural detection is performed on the first truss model. If the first detection result indicates that there is no abnormality in the structure of the first truss model, the first truss model is used as the new porous structure model.

[0033] Optionally, performing a first structural inspection on the first truss model includes:

[0034] Determine whether the mirror image structures of the rod structure under the X-axis, Y-axis and Z-axis are identical to the rod structure; and

[0035] It is determined whether lattice characteristics of the target cubic lattice in the first truss model meet preset characteristics.

[0036] Optionally, the target structure performance enhancement method includes the hybrid cubic lattice enhancement method; the method further includes:

[0037] Acquire a target axis; the target axis is an axis that needs performance enhancement;

[0038] Adding an oblique rod structure in the axial direction of the target axis;

[0039] The generating of a parameter expression protocol of a first truss model based on the parameter expression protocol of the rod structure includes:

[0040] The parameter expression protocol based on the oblique rod structure is added to the parameter expression protocol of the porous structure model to generate the parameter expression protocol of the first truss model.

[0041] Optionally, the target structure performance enhancement method includes the hybrid cubic lattice enhancement method; the method further includes:

[0042] Acquire a target axis; the target axis is an axis that needs performance enhancement;

[0043] Adding an oblique rod structure in the axial direction of the target axis;

[0044] The generating of a parameter expression protocol of a first truss model based on the parameter expression protocol of the rod structure includes:

[0045] The parameter expression protocol based on the oblique rod structure is added to the parameter expression protocol of the porous structure model to generate the parameter expression protocol of the first truss model.

[0046] Optionally, the target structure performance enhancement method includes an enhancement method of the tube-sheet hybrid structure; calling the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model includes:

[0047] Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model;

[0048] Determining a placement position and a placement path of the tube structure based on the attribute characteristics of the porous structure model; wherein the placement position of the tube structure meets preset placement requirements, and the placement path includes a start and end point;

[0049] Acquiring thickness information of the tube structure, and generating a parameter expression protocol of the tube structure based on the thickness information and the start and end points;

[0050] Based on the parameter expression protocol of the tube structure and the parameter expression protocol of the porous structure model, a parameter expression protocol of the second truss model is generated, and model drawing is performed based on the parameter expression protocol of the second truss model to obtain the new porous structure model.

[0051] Optionally, the example parameter expression protocol includes cell size, cell array size, and model information of the basic model contained in the cell; the model information includes the type of the basic model, the geometric parameters of the basic model, and the Boolean operation type of the basic model.

[0052] The present application also provides a device for generating a porous structure model, the device comprising:

[0053] An information acquisition module, configured to acquire target prompt information; wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for the first porous structure model;

[0054] a model generation module, configured to call a pre-trained large language model, generate a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol according to the instruction of the structure generation guidance information, and perform model rendering based on the target parameter expression protocol to generate the first porous structure model;

[0055] Among them, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

[0056] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for generating a porous structure model described in any of the aforementioned embodiments.

[0057] The present application also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for generating a porous structure model described in any one of the aforementioned embodiments are implemented.

[0058] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, executes the steps of any of the above-described methods for generating a possible porous structure model.

[0059] The technical solutions provided by the embodiments of the present application may have the following beneficial effects:

[0060] In the embodiment of the present application, due to the randomness and flexibility of the large language model, the guidance information generated based on the above structure can be used to guide the large model, which can enable the large model to explore a larger topological design space, which is conducive to improving the performance and generation efficiency of the porous structure model. In this way, the porous structure model generated by the above modeling method can be used to produce solid porous materials. For example, in the metal 3D printing scenario of additive manufacturing (such as medical implant materials and industrial parts), the above modeling method can be used to optimize the model topology and improve the production accuracy of solid porous materials.

[0061] Furthermore, the structure generation guidance information provided in the embodiments of the present application describes in detail the generation process of the porous structure model, thereby further improving the accuracy of the porous structure model.

[0062] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a flow chart of a method for generating a porous structure model according to an exemplary embodiment of the present application;

[0064] Figure 2 This is a flow chart showing a method of determining a target porous structure model set according to an exemplary embodiment of the present application;

[0065] Figure 3 This is a flow chart of a porous structure model optimization shown in an exemplary embodiment of the present application;

[0066] Figure 4 is a flow chart of a performance enhancement process shown in an exemplary embodiment of the present application;

[0067] Figure 5 1 is a schematic structural diagram of a device for generating a porous structure model according to an exemplary embodiment of the present application;

[0068] Figure 6 1 is a schematic structural diagram of another device for generating a porous structure model according to an exemplary embodiment of the present application;

[0069] Figure 7 It is a hardware structure diagram of a computer device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0070] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0071] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0072] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0073] In the field of additive manufacturing, the design and application of porous microstructures are important research areas. Appropriate porous structures can reduce structural weight while maintaining the required strength and stiffness. Currently, porous structure models suitable for additive manufacturing scenarios are mainly divided into TPMS structures and classic rod-plate structures. The classic rod-plate structure mainly relies on planning the material's microstructural units (i.e., cells) to control and optimize its macroscopic properties.

[0074] The study found that due to the extremely large design space of the topological structure of the cell, there are many shapes, sizes, and permutations of different basic topologies. When relying on manual methods to design porous structure models, if one wants to find the cell with the best performance at the same volume fraction, the workload and difficulty are very large, thus affecting the design efficiency.

[0075] Based on the above research, the present disclosure provides a method for generating a porous structure model, which first obtains target prompt information; wherein, the target prompt information includes an example parameter expression protocol and structure generation guidance information for a first porous structure model; then, a pre-trained large language model is called, and according to the instructions of the structure generation guidance information, a target parameter expression protocol for the first porous structure model is generated based on the example parameter expression protocol, and a model is drawn based on the target parameter expression protocol to generate the first porous structure model; wherein, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure being symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure being the boundary of the preset range; the grid structure is stretched along the Z-axis direction to obtain a three-dimensional mesh structure, and according to the expression form of the example parameter expression protocol, the three-dimensional mesh structure is parameter expressed to obtain the target parameter expression protocol.

[0076] In the embodiment of the present application, due to the randomness and flexibility of the large language model, the guidance information generated based on the above structure can be used to guide the large model, which can enable the large model to explore a larger topological design space, which is conducive to improving the performance and generation efficiency of the porous structure model. In this way, the porous structure model generated by the above modeling method can be used to produce solid porous materials. For example, in the metal 3D printing scenario of additive manufacturing (such as medical implant materials and industrial parts), the above modeling method can be used to optimize the model topology and improve the production accuracy of solid porous materials.

[0077] Furthermore, the structure generation guidance information provided in the embodiments of the present application describes in detail the generation process of the porous structure model, thereby further improving the accuracy of the porous structure model.

[0078] To facilitate understanding of this embodiment, a method for generating a porous structure model disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the method for generating a porous structure model provided in an embodiment of the present disclosure is generally a computer device, and the computer device can be a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms. In other embodiments, the computer device can also be a terminal device, wherein the terminal device can be a mobile device, a user terminal, a terminal, a handheld device, a computing device, a vehicle-mounted device, a wearable device, and the like.

[0079] In other embodiments, the method can also be applied to an implementation environment consisting of a terminal device and a server. In addition, the method for generating a porous structure model can also be implemented by a processor calling computer-readable instructions stored in a memory.

[0080] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0081] Please attend the attached Figure 1 , is a flow chart of a method for generating a porous structure model according to an exemplary embodiment of the present application. Figure 1 As shown, the method for generating a porous structure model in the embodiment of the present disclosure may include the following steps S101 to S104:

[0082] S101: Obtain target prompt information, wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for a first porous structure model.

[0083] The target prompt information is the prompt word. The prompt information can provide some key information or guiding sentences to the large language model to help the model better understand the question requirements and generate more accurate and targeted answers.

[0084] The first porous structure model is a three-dimensional model.

[0085] The example parameter expression protocol can express the vertex coordinates and thickness of a plate structure. For example, there is a plate structure whose complete parametric expression is: "{"plate": {"points": [[0.5, -0.0, -0.06], [0.5, -0.5, -0.31], [-0.5, -0.5, -0.31], [-0.5, -0.0, -0.06]], "thickness": 0.064}}", where points represents the vertex coordinates of the plate structure and thickness represents the thickness of the plate structure.

[0086] An example parameter expression protocol may refer to a parameterized description generated by specific rules. In an embodiment of the present application, the example parameter expression protocol is a schema protocol in json format, which is used to express a load topology structure composed of multiple basic models and Boolean operations. The protocol includes cell size, cell array size, basic model type and parameters, etc., as well as Boolean operators such as union, intersection, difference, etc.

[0087] For example, the example parameter expression protocol is as follows:

[0088] {

[0089] "lattice":{

[0090] "cell_size":[1,1,1],

[0091] "period_count":[1,1,1],

[0092] "models":[

[0093] {

[0094] "op_union":{

[0095] "type":"op_union",

[0096] "models":{

[0097] "op_union":{

[0098] type":"op_union",

[0099] "models": [

[0100] {

[0101] "cylinder":{

[0102] "points":[

[0103] [0,0,0],

[0104] [0.5,0.5,0.5]

[0105] ],

[0106] "radius":0.05

[0107] }

[0108] },

[0109] {

[0110] "cylinder":{

[0111] "points":[

[0112] [0,0,0],

[0113] [-0.5,0.5,0.5]

[0114] ],

[0115] "radius":0.05

[0116] }

[0117] } ]

[0119] }…

[0120] Among them, the content in lattice is used to describe the complex topological structure, cell_size can be used to represent the cell size data corresponding to the cell model. This example defaults to the cell space corresponding to the cell model being a rectangular structure, and the three values ​​in the corresponding array respectively represent the sizes of the cell space corresponding to the cell model on the x-axis, y-axis, and z-axis; period_count can be used to represent the porous array data corresponding to the cell model, and the three values ​​in the corresponding array are used to represent the number of arrangements of the cell model on the x-axis, y-axis, and z-axis when the target three-dimensional model is subsequently constructed; the value of models is a CSG tree node; op_union represents the union Boolean operation, and the objects under it contain models, which means that the structures of its child nodes are merged with the Boolean operation; the cylinder in the child node represents a basic model rod, and the parameters are points and radius, which are used to describe the position and shape of the basic model rod in space respectively.

[0121] The basic model and Boolean operation types defined in the embodiments of the present application are introduced in detail below.

[0122] (1) Truss: The truss model is defined by the coordinates of the two vertices [P1, P2] and the radius of the central axis. This model can be used to simulate a truss structure in space.

[0123] (2) Plate structure basic model (plate): The plate structure basic model is defined by the coordinates of all vertices of the plate center plane [V1, V2, V3, V4, ...] and the thickness of the plate T. This model is suitable for simulating planar structures with a specific thickness.

[0124] (3) Basic model of rectangular structure (box): This model contains a set of vertices used to define the two diagonal vertices of the rectangular block.

[0125] (4) Tube basic model: The tube basic model is defined by the coordinates of the two vertices [P1, P2] of the central axis and the outer radius and inner radius. This model can be used to express tubular structures in space.

[0126] Boolean operation types:

[0127] 1. Intersection operation: The intersection operation is used to create a new geometry that contains the common parts of two geometries. The intersection operation is implemented by calculating the point-by-point minimum of the two SDF distance fields.

[0128] 2. Union operation: The union operation is used to merge the SDF distance fields of two geometries to generate a new geometry that contains all parts of both geometries. The union operation is implemented by calculating the point-by-point maximum of the two SDF distance fields.

[0129] 3. Subtraction: The subtraction operation is used to subtract parts of one geometry from another to create a new geometry. In the CSG tree, the subtraction operation is represented by a node with a subtrahend child node and a subtrahend child node. The subtraction operation can be calculated by calculating the point-by-point minimum of one SDF distance field and the complement of another.

[0130] 4. Offset operation: The offset operation is used to translate the SDF distance field to generate new geometry. The offset operation is achieved by subtracting an offset value from the original SDF distance field.

[0131] 5. Shell Out: The Shell Out operation is used to generate the outer shell of a geometry. The Shell Out operation is implemented by calculating the difference between the offset version of the geometry's SDF distance field and itself, where the offset value is the absolute value.

[0132] S102: calling a pre-trained large language model, using the structure to generate guidance information, generating a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol, and performing model rendering based on the target parameter expression protocol to generate the first porous structure model;

[0133] Among them, the structure generates guidance information including: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure being symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure being the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

[0134] Here, the preset range can be set according to actual needs. In this embodiment, the preset range is -0.5~0.5. When the grid structure is stretched along the Z-axis direction, a corresponding stretching range can also be set. In this embodiment, the stretching range is -0.5~0.5.

[0135] The grid structure may also be formed by a set of line segments, and for any line segment, other line segments may be reached through intersections between the line segments.

[0136] It can be understood from the above content that the target parameter expression protocol can describe the structure of the model in detail. Therefore, by drawing the model based on the target parameter expression protocol, the first porous structure model can be generated.

[0137] In the embodiment of the present application, since the large language model has the characteristics of randomness and flexibility, guiding the large model based on the above-mentioned structure-generated guidance information can enable the large model to explore a larger topological design space, which is conducive to improving the performance and generation efficiency of the porous structure model.

[0138] Furthermore, the structure generation guidance information provided in the embodiments of the present application describes in detail the generation process of the porous structure model, which is helpful to improve the accuracy of the porous structure model.

[0139] In the specific implementation process, in order to generate the first porous model in large quantities, the following steps (A) to (B) can be performed:

[0140] (A) Acquire the modified target prompt information multiple times, and return to call the pre-trained large language model to generate the first porous structure model.

[0141] (B) Determining a target porous structure model set based on the plurality of first porous structure models.

[0142] Here, by repeatedly acquiring the modified target prompt information, different grid structures can be obtained, thereby obtaining multiple first porous structure models of different shapes and sizes. The modified target prompt information may refer to the grid structure obtained by modifying the target prompt information. In this way, based on the above steps, the efficiency of batch production of first porous models can be improved.

[0143] Furthermore, after the first porous structure model is generated, a target porous model set may be directly generated based on multiple first porous structure models.

[0144] In other embodiments, when determining the target porous structure model set based on the plurality of first porous structure models, the target porous structure model set may also be determined by the following steps, see Figure 2 , including steps S201 to S203:

[0145] S201: Obtain a porous cellular cubic structure.

[0146] Among them, the porous cell cubic structure is a three-dimensional structure that is symmetrical about the x-axis, y-axis and z-axis respectively.

[0147] S202: Based on the porous cellular cubic structure, a plurality of second porous structure models are generated.

[0148] Here, since the porous cell cubic structure is a symmetrical structure, in this embodiment, the second porous structure model can be generated based on the symmetry of the porous cell cubic structure.

[0149] Specifically, step S202 may include the following steps:

[0150] (1) The porous cell cubic structure is divided into equal parts to obtain a plurality of sub-cubic structures.

[0151] (2) Randomly determine a plurality of points in any sub-cubic structure, and construct a flat plate structure passing through the plurality of points for the plurality of points; wherein the flat plate structure intersects with all faces of the sub-cubic structure.

[0152] In this step, the porous cell cubic structure can be divided into eight equal parts based on the x-axis, y-axis, and z-axis to obtain eight sub-cubic structures, and multiple points (at least three points) can be determined in any sub-cubic structure. In this way, a flat plate structure passing through the multiple points can be constructed based on the determined multiple points.

[0153] Specifically, when constructing a flat plate structure based on multiple points, corresponding normal vectors can be determined for each of the multiple points, and the normal vectors corresponding to the multiple points can be used as the normal vectors of the flat plate structure. In this way, the flat plate structure can pass through these multiple points and intersect with all six faces of the sub-cube structure.

[0154] (3) The flat plate structure is mirror-symmetric in each of the other sub-cubic structures to obtain a mirror-image flat plate structure corresponding to each sub-cubic structure, and the second porous structure model is generated based on the flat plate structure and each of the mirror-image flat plate structures.

[0155] As can be seen from the previous article, since the flat plate structure intersects with the six faces of the sub-cubic structure, by mirroring the flat plate structure in other sub-cubic structures, a mirrored flat plate structure corresponding to each sub-cubic structure can be obtained, and the flat plate structure is connected to each mirrored flat plate structure. In this way, a second porous structure model can be generated based on the flat plate structure and each mirrored flat plate structure.

[0156] (4) Returning to the step of randomly determining a plurality of points in any sub-cubic structure, generating the plurality of second porous structure models.

[0157] It can be understood that by randomly determining a plurality of points each time, the shape of the contour can be changed, so that flat plate structures of different shapes can be constructed, thereby generating a plurality of second porous structure models of different shapes.

[0158] S203: Mixing the multiple first porous structure models and the multiple second porous structure models to obtain a porous structure model set, and generating a target porous structure model set based on the porous structure model set.

[0159] Based on the above content, it can be seen that this embodiment provides two technologies for generating porous structure models, one is based on a large model, and the other is based on the mirror symmetry of the porous cell cubic structure. Finally, the first porous structure model and the second porous structure model are mixed to obtain a porous structure model set, and a target porous structure model set is generated based on the porous structure model set.

[0160] Optionally, the porous structure model set can be directly used as the target porous structure model set.

[0161] In other embodiments, each porous structure model in the porous structure model set may be optimized separately, and a target porous structure model set may be obtained based on each optimized porous structure model.

[0162] See Figure 3 , is a flowchart of a porous structure model optimization shown in an exemplary embodiment of this application. Figure 3 As shown, the following steps S301 to S303 may be included:

[0163] S301: For each porous structure model in the porous structure model set, randomly select a target structure performance enhancement method from a plurality of structure performance enhancement methods, and generate performance enhancement prompt information based on the target structure performance enhancement method; the performance enhancement prompt information includes enhancement processing guidance information of the performance enhancement process.

[0164] Among them, the various structural performance enhancement methods include an enhancement method based on a cubic lattice and an enhancement method based on a tube-sheet hybrid structure; the enhancement method based on a cubic lattice includes at least one of an enhancement method based on a body-centered cubic lattice, an enhancement method based on a simple cubic lattice, and an enhancement method based on a mixed cubic lattice.

[0165] Here, the cubic lattice-based enhancement method may refer to connecting the model nodes based on the connection rules of the cubic lattice to add a rod structure to the model to achieve performance enhancement, and the tube-sheet hybrid structure-based enhancement method may refer to adding hollow tubes to the model to achieve performance enhancement.

[0166] S302: Calling a large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model.

[0167] Here, the performance enhancement prompt information includes the enhanced processing guidance information of the performance enhancement process, that is, using the prompt information and the thinking chain method to guide the large model to structurally optimize the porous structure model to obtain a new porous structure model.

[0168] S303: generating the target porous structure model set based on each of the new porous structure models.

[0169] It can be understood that after optimizing each porous structure model, the corresponding new porous structure model can be obtained. In this way, the performance of the new porous structure model can be improved, for example, the support of the model can be improved or the quality of the model can be reduced to generate a target porous structure model set with higher performance.

[0170] Specifically, if the target structure performance enhancement method is the cubic lattice-based enhancement method, then for step S302, when calling the large language model according to the enhancement processing guidance information, the performance enhancement processing of the model structure of the porous structure model is performed to obtain a new porous structure model, the following may be included: Figure 4 Steps S3021 to S3024 shown:

[0171] S3021: Determine the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model.

[0172] Among them, the attribute features may include the spatial features and geometric features of the porous structure model. The spatial features may include the vertex coordinates of the porous structure model and the connection relationship of the flat plate structure contained in the porous structure model in three-dimensional space. The geometric features may include the symmetry and directionality of the flat plate structure.

[0173] As can be seen from the foregoing, since the parameter expression protocol refers to a parametric expression according to specific rules, the property characteristics of the porous structure model can be determined based on the parameter expression protocol of the porous structure model.

[0174] S3022: Migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model according to the attribute characteristics.

[0175] As can be seen from the foregoing, the enhancement method based on cubic crystals includes at least one of the enhancement method based on body-centered cubic lattice, the enhancement method based on simple cubic lattice, and the enhancement method based on mixed cubic lattice. The target cubic lattice corresponds to the selected enhancement method.

[0176] In this embodiment, since the attribute characteristics include the coordinates of the model nodes, the lattice nodes of the target cubic lattice can be migrated to the model nodes of the porous structure model according to the coordinates of the model nodes.

[0177] It can be understood that the porous structure model includes a plurality of model nodes, including model vertices and model body centers, and the target cubic lattice includes a plurality of lattice nodes.

[0178] Specifically, if the cubic lattice enhancement method is a body-centered cubic lattice enhancement method, the target cubic lattice is a body-centered cubic lattice, and the multiple lattice nodes of the body-centered cubic lattice include lattice corners and lattice body centers. Based on this, when migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model, the lattice corners can be migrated to the model vertices of the porous structure model, and the lattice body centers can be migrated to the model body centers of the porous structure model.

[0179] Similarly, if the cubic lattice enhancement method is a simple cubic lattice-based enhancement method, the target cubic lattice is a simple cubic lattice, and the multiple lattice nodes of the simple cubic lattice include lattice corner points. Based on this, when migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model, the lattice corner points of the simple cubic lattice can be migrated to the model vertices of the porous structure model.

[0180] Optionally, you can add model nodes to the edges and center of the porous structure model to create a simple cubic lattice with a higher density, thereby increasing the number of rod structures.

[0181] If the cubic lattice enhancement method is a hybrid cubic lattice enhancement method, the target cubic lattice includes a body-centered cubic lattice and a simple cubic lattice. When migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model, the lattice nodes of the body-centered cubic lattice and the lattice nodes of the simple cubic lattice can be migrated to the model nodes. Since the connection rule of the simple cubic lattice is to connect the lattice nodes, by mixing the simple cubic lattice with the body-centered cubic lattice, the structural diversity of the porous structure model can be increased, especially the Z-axis direction can be strengthened, and the Young's modulus can be improved.

[0182] S3023: Creating a rod structure according to the connection rules of the target cubic lattice, generating a parameter expression protocol of a first truss model based on the parameter expression protocol of the rod structure, and performing model drawing based on the parameter expression protocol of the first truss model to use the first truss model as the new porous structure model; wherein the layout of the rod structure meets preset requirements.

[0183] The rod structure layout meeting the preset requirements means that the symmetry of the rod structure is the same as the symmetry of the target cubic lattice, and the position of the rod structure is complementary to the geometric features of the porous structure model. Here, the position of the rod structure is complementary to the geometric features of the porous structure model, which may mean that the rod structure is placed at a position in the porous structure model where a flat plate structure is absent.

[0184] In this embodiment, the radius of the rod structure is set to 0.07. In other embodiments, the rod radius can be set according to actual needs and is not limited here.

[0185] Here, if the target cubic lattice is a body-centered cubic lattice (BCC), the connection rule is to connect the lattice corners to the lattice body center. Since the body-centered cubic lattice has been migrated to the porous structure model in the previous step, a rod structure can be created between the model vertices and the model body center.

[0186] Similarly, if the target cubic lattice is a simple cubic structure (SC), the connection rule is to connect adjacent lattice corners. Therefore, rod structures can be created between adjacent model vertices in the porous structure model.

[0187] Similarly, if the target cubic lattice includes a body-centered cubic lattice and a simple cubic lattice, the connection rules include the connection between the model vertex and the model body center, and the connection between adjacent model vertices. Therefore, in this case, a rod structure can be created between the model vertex and the model body center, and a rod structure can be created between adjacent model vertices.

[0188] S3024: Generate a parameter expression protocol for a first truss model based on the parameter expression protocol of the rod structure and the parameter expression protocol of the porous structure model, and generate the new porous structure model based on the parameter expression protocol of the first truss model.

[0189] For example, the parameter expression protocol of the rod structure can be as follows:

[0190] "cylinder": {{\"points\": [[starting point coordinates], [ending point coordinates]], \"radius\": radius}}.

[0191] It can be understood that since the rod structure is connected to the model nodes and the node coordinates of the model nodes are known, the parameter expression protocol of the rod structure can be obtained.

[0192] In this way, the parameter expression protocol of the first truss model can be generated based on the parameter expression protocol of the rod structure and the parameter expression protocol of the porous structure model. Here, the first truss model is a fusion structure of the rod structure and the porous structure model.

[0193] Furthermore, when a new porous structure model is generated based on the parameter expression protocol of the first truss structure model, a first truss model can be obtained by model drawing based on the parameter expression protocol of the first truss structure model, and the first truss model can be used as the new porous structure model.

[0194] In this embodiment, the first truss model is generated through the above steps, which can improve the diversity of the structure. The generated rod structure can also enhance the structure of the porous structure model according to the geometric characteristics of the porous structure model while maintaining symmetry. For example, the performance of the stress concentration point can be enhanced. Its high symmetry and multi-directional load-bearing characteristics can effectively resist multi-directional loads, thereby improving the overall stiffness.

[0195] In addition, the plate structure in the rod-plate structure can provide in-plane stiffness and the rod structure can provide out-of-plane stiffness. The two complement each other to improve the Young's modulus of the new porous structure model.

[0196] The following examples provide performance enhancement tips corresponding to different cubic lattice enhancement methods.

[0197] (1) The target prompt corresponding to the enhancement method of the body-centered cubic lattice is as follows:

[0198] Mission objective: Generate a corresponding truss body-centered cubic lattice rod structure based on a given porous structure model to improve the structural diversity and Young's modulus.

[0199] Input: The given porous structure model parameters are as follows: {porous structure model schema}

[0200] Task step breakdown:

[0201] 1. Extract nodes and geometric features of the porous structure model:

[0202] 1.1 Extract the node coordinates of each plate structure and determine their connection relationship in three-dimensional space.

[0203] 1.2 Analyze the geometric characteristics of the porous structure model, including symmetry and directionality.

[0204] 2. Mapping to the node positions of the body-centered cubic lattice:

[0205] 2.1 According to the characteristics of the body-centered cubic lattice (BCC), the lattice nodes of the BCC are mapped to the vertices of the porous structure model to ensure that the lattice nodes of the BCC are located at the corners or body centers of the porous structure model.

[0206] 3. Generate rod structure:

[0207] 3.1 Create a rod structure according to the connection rules of the BCC lattice and connect the mapped nodes.

[0208] 3.2 Ensure that the rod structure conforms to the symmetry of the BCC lattice; the layout of the rods should be complementary to the geometric features of the porous structure model; the rod radius is fixed at 0.07.

[0209] 4. Output the schema of the generated truss body-centered cubic lattice rod structure (without comments):

[0210] 4.1 Example of parametric expression of a rod: "cylinder": {{\"points\": [[starting point coordinates], [end point coordinates]], \"radius\": radius}}.

[0211] 4.2 Ensure the high symmetry of the BCC lattice structure.

[0212] 5. Verification of the generated rod structure:

[0213] 5.1 Symmetry verification: The generated rod structure should remain unchanged after mirroring along the X / Y / Z axes.

[0214] 5.2 BCC Feature Verification: Verify that all nodes are located only at the corners or body centers of the porous structure model, and that there are no face-to-face center connections. If the structure does not meet the requirements, it must be regenerated up to three times.

[0215] In this way, by inputting the above prompt information into the large language model, BCC-based structural enhancement can be achieved.

[0216] (2) The target prompt corresponding to the simple cubic lattice enhancement method is as follows:

[0217] Task objective: Generate the corresponding truss simple cubic lattice rod structure based on the given porous structure model:

[0218] Input: The given porous structure model parameters are as follows: {porous structure model schema}

[0219] Task step breakdown:

[0220] 1. Extract the nodes and geometric features of the porous structure model:

[0221] 1.1 Extract the node coordinates of each flat plate structure in the porous structure model and determine their connection relationship in three-dimensional space.

[0222] 1.2 Analyze the geometric characteristics of the porous structure model, including symmetry and orientation, and identify areas that may require additional support.

[0223] 2. Mapping to the node positions of the simple cubic lattice SC:

[0224] 2.1 According to the characteristics of the simple cubic lattice SC lattice, the nodes of the SC lattice are mapped to the vertices of the porous structure model to ensure that the nodes of the SC lattice are located at the vertices of the porous structure model.

[0225] 2.2 To increase the number of rods, one can consider adding additional nodes at the edge and center of the porous structure model to create a denser SC lattice structure.

[0226] 3. Generate rod structure:

[0227] 3.1 Create a rod structure to connect the mapped nodes according to the connection rules of the SC lattice. Create a rod between each node and its nearest neighbor.

[0228] 3.2 Increasing the number of rods can be achieved by adding additional connections between the nodes of the SC lattice.

[0229] 3.3 Ensure that the rod structure conforms to the symmetry of the SC lattice; the layout of the rods should be complementary to the geometric features of the plate; the rod radius is fixed at 0.07.

[0230] 4. Output the generated truss SC lattice rod structure schema (without comments):

[0231] 4.1 Example of parametric expression of a rod: {{"cylinder": {{"points": [[starting point coordinates], [end point coordinates]], "radius": radius}}}}}.

[0232] 4.2 Pay attention to the difference between the generation methods of SC lattice and BCC / FCC lattice, and ensure the high symmetry of SC lattice structure.

[0233] 5. Verify the generated rod structure:

[0234] 5.1 Symmetry verification: The generated rod structure should remain unchanged after mirroring along the X / Y / Z axes.

[0235] 5.2 SC Feature Verification: Verify that all nodes are located only at the corners of the cube and that there are no body-center-to-body-center or face-center-to-face-center connections. If the structure does not meet the requirements, it must be regenerated up to three times.

[0236] (3) The target prompt information corresponding to the hybrid cubic lattice enhancement method is as follows:

[0237] Task objective: Based on the provided porous structure model parameters, generate a truss BCC lattice rod structure with a strengthened {max_axis} axis direction, and integrate the SC lattice strategy to improve the structural diversity and Young's modulus.

[0238] The given porous structure model parameters are as follows:

[0239] Task step breakdown:

[0240] 1. Extract nodes and geometric features of the porous structure model:

[0241] 1.1 Extract the node coordinates of each flat plate structure of the porous structure model and determine their connection relationship in three-dimensional space.

[0242] 1.2 Analyze the geometric characteristics of the board, focusing on the symmetry and directionality along the {max_axis} axis, and how to combine it with SC to enhance the diversity of the structure.

[0243] 2. Mapping to the node positions of the BCC lattice and considering the fusion of SC:

[0244] 2.1 According to the characteristics of the BCC lattice, the vertex coordinates of the plate are mapped to the node positions of the BCC lattice, ensuring that the nodes are located at the eight corner points or the body center of the cube.

[0245] 2.2 Combining the characteristics of SC lattice, the nodes are allowed to be located at each lattice point of the cube to increase the diversity of the structure, especially strengthening in the Z-axis direction to improve the Young's modulus.

[0246] 3. Generate the rod structure and strengthen it in the {max_axis} axis direction:

[0247] 3.1 According to the connection rules of BCC lattice and SC lattice, create a rod structure and connect the mapped nodes.

[0248] 3.2Add additional connections in the Z-axis direction to strengthen the stability of the structure and ensure that the layout of the rods complements the geometric characteristics of the plate.

[0249] 3.3 Rod radius is fixed at 0.07.

[0250] 4. Output the generated schema combining the truss BCC Lattice and the SC lattice (only JSON is output without any comments):

[0251] 4.1 Example of parametric expression of a rod: {{"cylinder": {{"points": [[starting point coordinates], [end point coordinates]], "radius": radius}}}}}.

[0252] 4.2 Pay attention to the generation methods of truss BCC lattice and truss FCC lattice, and ensure that the structure of the combined BCCLattice and SC lattice is highly symmetrical and has a strong feature in the {max_axis} direction. Exclude the few redundant rods generated in other directions.

[0253] 5. Verification of the generated rod structure:

[0254] 5.1 Symmetry verification: The generated rod structure should maintain a high degree of symmetry.

[0255] 5.2 Structural Feature Verification: Verify that all nodes are located at the corners, body centers, grid points, or face centers of the cube. Face-center-to-face-center connections are permitted. If the structure does not meet the design requirements, it must be regenerated up to three times.

[0256] Optionally, after the first truss model is generated, a structural inspection may be performed on the rod structure of the first truss model to improve the accuracy of the model.

[0257] Specifically, when the first truss model is used as the new porous structure model, a first structural detection can be performed on the rod structure in the first truss model to obtain a first detection result. If the first detection result indicates that there is no abnormality in the rod structure in the first truss model, the first truss model is used as the new porous structure model.

[0258] Here, the first structure detection of the rod structure in the first truss model may include symmetry detection and cubic lattice feature detection, wherein the symmetry detection refers to determining whether the mirrored rod structure obtained after the rod structure is mirrored along the X-axis, Y-axis, and Z-axis is the same as the rod structure, and the cubic lattice feature detection refers to determining whether all lattice nodes of the cubic lattice are located at the model nodes of the first truss model.

[0259] If the mirrored rod structure obtained by mirroring along the X-axis, Y-axis, and Z-axis is identical to the rod structure, all lattice nodes of the cubic lattice are located at the model nodes of the first truss model, and the rod structure is not connected between the face centers of the cubic lattice, then it can be considered that there is no abnormality in the rod structure in the first truss model, and the first truss model can be used as a new porous structure model.

[0260] If there is an abnormality in the rod structure in the first truss model, the rod structure is regenerated.

[0261] The above examples are for illustrative purposes only and can be adjusted according to actual needs.

[0262] The following is a detailed description of the enhancement method based on the tube-sheet hybrid structure.

[0263] In some embodiments, if the target structural performance enhancement method is the enhancement method based on the tube-sheet hybrid structure, then for step S10332, when calling the large language model according to the enhancement processing guidance information to perform performance enhancement processing on the model structure of the porous structure model to obtain a new porous structure model, the following steps (I) to (III) may be included:

[0264] (I) Determining property characteristics of the porous structure model based on a parameter expression protocol of the porous structure model.

[0265] Among them, the porous structure model includes multiple model nodes (i.e., vertices), and the porous structure model is based on multiple flat plate structures. Therefore, the attribute characteristics may include spatial characteristics and geometric characteristics. The spatial characteristics include the coordinates of each model node and the connection relationship of each flat plate structure in three-dimensional space. The geometric characteristics include the unit cell size and periodic characteristics of the flat plate structure.

[0266] (II) Determining a placement position and a placement path of the tube structure based on the attribute characteristics of the porous structure model; wherein the placement position of the tube structure meets a preset placement requirement, and the placement path includes a starting point and an ending point.

[0267] The placement position of the tube structure conforming to the preset placement requirements means that the tube structure and the porous structure model are symmetrical, and the tube structure is aligned with the intersection line and the support point respectively.

[0268] The placement path of the tube structure extends along the reinforcement axis and passes through the intersection line and the support point.

[0269] Optionally, when determining the placement path of the tube structure based on the attribute characteristics of the porous structure model, the starting and ending points of the tube structure can be determined based on the node coordinates of the porous structure model, the intersection positions between the various flat plate structures in the porous structure model, and the support point coordinates of the porous structure model, and the placement path can be determined based on the starting and ending points.

[0270] (III) Obtaining thickness information of the tube structure, and generating a parameter expression protocol for the tube structure based on the thickness information and the start and end points, and generating a parameter expression protocol for a second truss model based on the parameter expression protocol for the tube structure, and generating the new porous structure model based on the parameter expression protocol for the second truss model.

[0271] It can be understood that the size of the tube structure includes length and thickness, and the thickness is determined by the outer radius and inner radius of the tube structure. In this embodiment, the outer radius and inner radius of the tube structure are pre-set.

[0272] Illustratively, an example of a parameter expression protocol for a tube structure is as follows:

[0273] {{"tube": {{"points": [[starting point coordinates], [ending point coordinates]], "radius": radius, "inner_radius": inner radius}}}}.

[0274] Specifically, when the new porous structure model is generated based on the parameter expression protocol of the second truss model, model drawing can be performed based on the parameter expression protocol of the second truss model to obtain the second truss model, and the second truss model can be determined as the new porous structure model.

[0275] In this embodiment, based on the provided plate structure, a corresponding tube structure is designed and generated, which can enhance the diversity of the structure. Furthermore, this embodiment also focuses on the performance enhancement in the direction of the reinforcement axis, so that the Young's modulus in the direction of the reinforcement axis can be improved.

[0276] The following example shows the target prompt corresponding to the hybrid cubic lattice enhancement method:

[0277] Task objective: Based on the provided porous structure model, design and generate corresponding hollow tube structures to enhance structural diversity and improve Young's modulus in the {max_axis} axis direction.

[0278] Input: The porous structure model parameters are as follows: {schema}

[0279] Detailed breakdown of task steps:

[0280] 1. Analysis of porous structure model parameters:

[0281] 1.1 Accurately extract the coordinates of each node of the porous structure model and determine their connection relationship in three-dimensional space.

[0282] 1.2 Clarify the unit cell size and periodic characteristics of the porous structure model.

[0283] 2. Generate tube structure:

[0284] 2.1 Set the outer radius of the tube to 0.07 and the inner radius to 0.05.

[0285] 2.2 Accurately determine the position of the tube in the porous structure model to ensure high matching and high symmetry with the porous structure model. Pay special attention to the alignment of the tube structure with the intersection line and support points.

[0286] 2.3 Based on the node coordinates of the porous structure model and the coordinates of the identified intersections and support points, design the starting and ending points of the hollowed-out tubes. Ensure that the tube paths extend along the specific direction of the plate structure and preferentially cross intersections and support points to effectively enhance the Young's modulus in the Z-axis. The path design should follow the predetermined strengthening direction, such as diagonal or other paths that are conducive to improving the Young's modulus in the {max_axis} direction.

[0287] 3. Output only the generated pipe schema (without comments):

[0288] 3.1 Example of parametric expression of a tube: {{"tube": {{"points": [[starting point coordinates], [end point coordinates]],"radius":radius, "inner_radius": inner radius}}}}}.

[0289] 4. Verification of the hollowed-out plate structure:

[0290] 4.1 Strictly check whether the generated tube structure maintains a high degree of symmetry and integrity, and ensures that it matches the porous structure model correctly.

[0291] 4.2 Confirm that the generated tube structure has an adverse effect on the overall stability of the porous structure model. If the structure is found to be not in compliance with the requirements, it needs to be regenerated, and repeated up to three times.

[0292] Optionally, after obtaining the second truss model, a second structural test may be performed on the second truss model to obtain a second test result. If the second test result indicates that there is no abnormality in the structure of the second truss model, the second truss model is determined as the new porous structure model.

[0293] The second structure detection may include determining whether the tube structure is still symmetrical and whether the tube structure is complete, and detecting the stability of the second truss model.

[0294] If the tube structure is symmetrical and complete, and does not affect the stability of the second truss model, it means that there is no abnormality in the structure of the second truss model, and the second truss model can be determined as a new porous structure model.

[0295] Specifically, in the above optimization process, since the rod structure between the body-centered nodes and the corner nodes of the body-centered cubic lattice forms a spatial diagonal connection, its high symmetry and multi-directional load-bearing characteristics can effectively resist multi-directional loads, thereby improving the overall stiffness.

[0296] Corresponding to the aforementioned embodiment of the method for generating a porous structure model, the present application also provides an embodiment of an apparatus for generating a porous structure model.

[0297] Please refer to Figure 5 , is a schematic diagram of a device for generating a porous structure model according to an exemplary embodiment of the present application. Figure 5 As shown, the apparatus 500 includes:

[0298] An information acquisition module 510 is configured to acquire target prompt information, wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for the first porous structure model;

[0299] a model generation module 520 configured to call a pre-trained large language model, generate a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol according to the instruction of the structure generation guidance information, and perform model rendering based on the target parameter expression protocol to generate the first porous structure model;

[0300] Among them, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

[0301] See Figure 6 , is a schematic diagram of another apparatus for generating a porous structure model according to an exemplary embodiment of the present application. The apparatus further includes a set generation module 530, which is configured to:

[0302] Acquiring the modified target prompt information multiple times, and returning to the step of calling the pre-trained large language model to generate the first porous structure model, thereby obtaining multiple first porous structure models;

[0303] Based on the multiple first porous structure models, a target porous structure model set is determined.

[0304] In some implementations, the set generation module 530 is specifically configured to:

[0305] Obtaining a porous cell cubic structure;

[0306] Based on the porous cellular cubic structure, generating a plurality of second porous structure models;

[0307] The plurality of first porous structure models and the plurality of second porous structure models are mixed to obtain a porous structure model set, and the target porous structure model set is generated based on the porous structure model set.

[0308] In some implementations, the set generation module 530 is specifically configured to:

[0309] For each porous structure model in the porous structure model set, randomly selecting a target structure performance enhancement method from a plurality of structure performance enhancement methods, and generating performance enhancement prompt information based on the target structure performance enhancement method; the performance enhancement prompt information includes enhancement processing guidance information of the performance enhancement process;

[0310] Calling the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model;

[0311] Based on each of the new porous structure models, the target porous structure model set is generated.

[0312] In some embodiments, the multiple structural performance enhancement methods include an enhancement method based on a cubic lattice and an enhancement method based on a tube-sheet hybrid structure, wherein the enhancement method based on the cubic lattice includes at least one of an enhancement method based on a body-centered cubic lattice, an enhancement method based on a simple cubic lattice, and a hybrid enhancement method based on a body-centered cubic lattice and a simple cubic lattice.

[0313] In some implementations, the set generation module 530 is specifically configured to:

[0314] The multiple structural performance enhancement methods include an enhancement method based on a cubic lattice; the calling of the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model, including:

[0315] Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model;

[0316] Migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model according to the property characteristics;

[0317] According to the connection rules of the target cubic lattice, a rod structure is created, and based on the parameter expression protocol of the rod structure, a parameter expression protocol of a first truss model is generated, and the first truss model is used as the new porous structure model; wherein the layout of the rod structure meets preset requirements.

[0318] In some embodiments, when using the first truss model as the new porous structure model, the set generation module 530 is specifically configured to:

[0319] A first structural detection is performed on the first truss model. If the first detection result indicates that there is no abnormality in the structure of the first truss model, the first truss model is used as the new porous structure model.

[0320] In some implementations, the set generation module 530 is specifically configured to:

[0321] Determine whether the mirror image structures of the rod structure under the X-axis, Y-axis and Z-axis are identical to the rod structure; and

[0322] It is determined whether lattice characteristics of the target cubic lattice in the first truss model meet preset characteristics.

[0323] In some embodiments, the target structure performance enhancement method includes the hybrid cubic lattice enhancement method; the model generation module 520 is specifically configured to:

[0324] Acquire a target axis; the target axis is an axis that needs performance enhancement;

[0325] Adding an oblique rod structure in the axial direction of the target axis;

[0326] The model generation module 520 generates a parameter expression protocol for a first truss model based on the parameter expression protocol of the rod structure, specifically for:

[0327] The parameter expression protocol based on the oblique rod structure is added to the parameter expression protocol of the porous structure model to generate the parameter expression protocol of the first truss model.

[0328] In some embodiments, the target structural performance enhancement method includes an enhancement method of the tube-sheet hybrid structure; the model generation module 520 is specifically configured to:

[0329] Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model;

[0330] Determining a placement position and a placement path of the tube structure based on the attribute characteristics of the porous structure model; wherein the placement position of the tube structure meets preset placement requirements, and the placement path includes a start and end point;

[0331] Acquiring thickness information of the tube structure, and generating a parameter expression protocol of the tube structure based on the thickness information and the start and end points;

[0332] Based on the parameter expression protocol of the tube structure and the parameter expression protocol of the porous structure model, a parameter expression protocol of the second truss model is generated, and model drawing is performed based on the parameter expression protocol of the second truss model to obtain the new porous structure model.

[0333] In some embodiments, the example parameter expression protocol includes cell size, cell array size, and model information of the base model contained in the cell; the model information includes the type of the base model, the geometric parameters of the base model, and the Boolean operation type of the base model.

[0334] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0335] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0336] Corresponding to the above-mentioned method for generating a porous structure model, the embodiment of the present disclosure further provides a computer device, such as Figure 7 FIG. 1 is a schematic diagram of the structure of a computer device provided in an embodiment of the present disclosure, including:

[0337] The computer device 700 includes a processor 710, an internal bus 720, a memory 730, a network interface 740, and a non-volatile memory 750, and may also include hardware required for other functions. One or more embodiments of this specification can be implemented based on software, such as the processor 710 reading the corresponding computer program from the non-volatile memory 750 into the memory 730 and then running it. Of course, in addition to software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0338] Among them, the memory 730 is also called internal memory, which is used to temporarily store the calculation data in the processor 710 and the data exchanged with the non-volatile memory 750 such as the hard disk. The processor 710 exchanges data with the non-volatile memory 750 through the memory 730.

[0339] In the embodiment of the present application, the memory 730 is specifically used to store application code for executing the solution of the present application, and the execution is controlled by the processor 710. That is, when the computer device is running, the processor 710 communicates with the network interface 740, the memory 730, and the non-volatile memory 750 respectively via the internal bus 720, so that the processor 710 executes the application code stored in the memory 730 and the non-volatile memory 750, thereby performing the method for generating a porous structure model described in the above method embodiment.

[0340] Processor 710 may be an integrated circuit chip with signal processing capabilities. Such processors may be general-purpose processors, including central processing units (CPUs) and network processors (NPs). They may also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. They may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor.

[0341] It should be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the computer device 700. In other embodiments of the present application, the computer device 700 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0342] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the method for generating a porous structure model described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0343] The presently disclosed embodiment also provides a computer program product, which carries a program code. The program code includes instructions that can be used to execute the steps of the method for generating a porous structure model in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0344] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0345] Embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by the data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0346] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform the corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can be implemented as, special-purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0347] Computers suitable for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operably coupled to such mass storage devices to receive data from them or to transmit data to them, or both. However, a computer does not necessarily have such devices. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0348] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and storage devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0349] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of specific embodiments of specific inventions. Certain features described in multiple embodiments within this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of the sub-combination.

[0350] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0351] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the particular order shown or sequential sequence to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0352] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for generating a porous structure model, characterized in that: The method comprises: Obtaining target prompt information; wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for the first porous structure model; the example parameter expression protocol includes cell size, cell array size, and model information of a basic model contained in the cell; the model information includes the type of the basic model, geometric parameters of the basic model, and Boolean operation type of the basic model; calling a pre-trained large language model, generating a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol according to the instruction of the structure generation guidance information, and performing model rendering based on the target parameter expression protocol to generate the first porous structure model; Among them, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring the modified target prompt information multiple times, and returning to the step of calling the pre-trained large language model to generate the first porous structure model, thereby obtaining multiple first porous structure models; Based on the multiple first porous structure models, a target porous structure model set is determined.

3. The method according to claim 2, characterized in that The step of determining a target porous structure model set based on the plurality of first porous structure models comprises: Obtaining a porous cell cubic structure; Based on the porous cellular cubic structure, generating a plurality of second porous structure models; The plurality of first porous structure models and the plurality of second porous structure models are mixed to obtain a porous structure model set, and the target porous structure model set is generated based on the porous structure model set.

4. The method according to claim 3, characterized in that The step of generating a plurality of second porous structure models based on the porous cell cubic structure includes: Dividing the porous cellular cubic structure into equal parts to obtain a plurality of sub-cubic structures; Randomly determine a plurality of points in any sub-cubic structure, and construct a flat plate structure passing through the plurality of points; wherein the flat plate structure intersects with each face of the sub-cubic structure; Performing mirror symmetry on the flat plate structure in each of the other sub-cubic structures to obtain a mirrored flat plate structure corresponding to each sub-cubic structure, and generating the second porous structure model based on the flat plate structure and each of the mirrored flat plate structures; The step of randomly determining a plurality of points in any sub-cubic structure is returned to obtain the plurality of second porous structure models.

5. The method according to claim 3, characterized in that The step of generating a target porous structure model set based on the porous structure model set includes: For each porous structure model in the porous structure model set, randomly selecting a target structure performance enhancement method from a plurality of structure performance enhancement methods, and generating performance enhancement prompt information based on the target structure performance enhancement method; the performance enhancement prompt information includes enhancement processing guidance information of the performance enhancement process; Calling the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model; Based on each of the new porous structure models, the target porous structure model set is generated.

6. The method according to claim 5, characterized in that The multiple structural performance enhancement methods include an enhancement method based on a cubic lattice and an enhancement method based on a tube-sheet hybrid structure, wherein the enhancement method based on the cubic lattice includes at least one of an enhancement method based on a body-centered cubic lattice, an enhancement method based on a simple cubic lattice, and a hybrid enhancement method based on a body-centered cubic lattice and a simple cubic lattice.

7. The method according to claim 6, characterized in that The multiple structural performance enhancement methods include an enhancement method based on a cubic lattice; the calling of the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model, including: Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model; Migrating the lattice nodes of the target cubic lattice to the model nodes of the porous structure model according to the property characteristics; Creating a rod structure according to the connection rule of the target cubic lattice, and generating a parameter expression protocol of a first truss model based on the parameter expression protocol of the rod structure and the parameter expression protocol of the porous structure model; The parameter expression protocol of the first truss model is modeled to obtain the first truss model, and the first truss model is used as the new porous structure model; wherein the layout of the rod structure meets the preset requirements.

8. The method according to claim 7, characterized in that The step of using the first truss model as the new porous structure model includes: A first structural detection is performed on the first truss model. If the first detection result indicates that there is no abnormality in the structure of the first truss model, the first truss model is used as the new porous structure model.

9. The method according to claim 8, characterized in that The performing a first structural inspection on the first truss model includes: Determine whether the mirror image structures of the rod structure under the X-axis, Y-axis and Z-axis are identical to the rod structure; and It is determined whether lattice characteristics of the target cubic lattice in the first truss model meet preset characteristics.

10. The method according to claim 7, characterized in that The target structure performance enhancement method includes the hybrid enhancement method based on the body-centered cubic lattice and the simple cubic lattice; the method further includes: Acquire a target axis; the target axis is an axis that needs performance enhancement; Adding an oblique rod structure in the axial direction of the target axis; The generating of a parameter expression protocol of a first truss model based on the parameter expression protocol of the rod structure includes: The parameter expression protocol based on the oblique rod structure is added to the parameter expression protocol of the porous structure model to generate the parameter expression protocol of the first truss model.

11. The method according to claim 6, characterized in that The target structure performance enhancement method includes an enhancement method for the tube-sheet hybrid structure; calling the large language model to perform performance enhancement processing on the model structure of the porous structure model according to the enhancement processing guidance information to obtain a new porous structure model, including: Determining the property characteristics of the porous structure model based on the parameter expression protocol of the porous structure model; Determining a placement position and a placement path of the tube structure based on the attribute characteristics of the porous structure model; wherein the placement position of the tube structure meets preset placement requirements, and the placement path includes a start and end point; Acquiring thickness information of the tube structure, and generating a parameter expression protocol of the tube structure based on the thickness information and the start and end points; Based on the parameter expression protocol of the tube structure and the parameter expression protocol of the porous structure model, a parameter expression protocol of the second truss model is generated, and model drawing is performed based on the parameter expression protocol of the second truss model to obtain the new porous structure model.

12. A device for generating a porous structure model, characterized in that: The device comprises: an information acquisition module, configured to acquire target prompt information; wherein the target prompt information includes an example parameter expression protocol and structure generation guidance information for the first porous structure model; the example parameter expression protocol includes a cell size, a cell array size, and model information of a basic model contained in the cell; the model information includes a type of the basic model, geometric parameters of the basic model, and a Boolean operation type of the basic model; a model generation module, configured to call a pre-trained large language model, generate a target parameter expression protocol for the first porous structure model based on the example parameter expression protocol according to the instruction of the structure generation guidance information, and perform model rendering based on the target parameter expression protocol to generate the first porous structure model; Among them, the structure generation guidance information is used to indicate: drawing a grid structure within a preset range of a two-dimensional plane, the grid structure is symmetrical about the X-axis and the Y-axis respectively, and the boundary of the grid structure is the boundary of the preset range; stretching the grid structure along the Z-axis direction to obtain a three-dimensional mesh structure, and performing parameter expression on the three-dimensional mesh structure according to the expression form of the example parameter expression protocol to obtain the target parameter expression protocol.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for generating a porous structure model according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for generating a porous structure model according to any one of claims 1 to 11 are implemented.

Images