Structural model processing method and device, network equipment and storage medium

Abstract

The embodiment of the invention provides a structure model processing method and device, network equipment and a storage medium, and the method comprises the steps: carrying out the three-dimensional structure scanning of a target object through scanning equipment, obtaining a microstructure image, dividing the target object into a plurality of modeling regions, and enabling the target object to be composed of a composite material; performing enhancement processing on the microstructure image by adopting a deep learning model trained based on a deep learning mode to obtain an enhanced image; based on the enhanced image, modeling each modeling area of the target object, configuring mechanical properties of each modeling area according to material attributes of each modeling area, and forming an area modeling result of each modeling area; integration is carried out according to the area modeling results of all the modeling areas, and a structure model of the target object is obtained; according to the scheme, analysis can be carried out from the microcosmic angle, and a more accurate structure model is generated.

Description

Technical Field

[0001] The present application relates to the field of computer information technology, and in particular to a structural model processing method, device, network equipment and storage medium. Background Art

[0002] In the engineering field, the growing demand for high-performance materials has driven the development and application of heterogeneous materials such as composites. However, these composites usually have complex microstructures and multi-scale properties.

[0003] Existing solutions only focus on properties at the macroscopic scale, and assume homogenized properties for the device's microstructure. However, some materials may not be homogenized at the microstructural scale. Therefore, the structural models modeled by existing solutions have low accuracy. Summary of the invention

[0004] The embodiments of the present application provide a structural model processing method, apparatus, network device and storage medium, which can improve the accuracy of the modeled structural model.

[0005] The technical solution is as follows:

[0006] In a first aspect, the present application provides a structural model processing method, the method comprising: performing a three-dimensional structural scan of a target object by a scanning device to obtain a microstructure image, and dividing the target object into multiple modeling areas, wherein the target object is composed of a composite material; using a deep learning model trained based on a deep learning method to enhance the microstructure image to obtain an enhanced image; based on the enhanced image, modeling each modeling area of ​​the target object, and configuring the mechanical properties of each modeling area according to the material properties of each modeling area to form regional modeling results of each modeling area; integrating the regional modeling results of each modeling area to obtain a structural model of the target object.

[0007] Furthermore, the regional modeling results of the respective modeling areas are integrated to obtain the structural model of the target object, including: obtaining first and second regional modeling results of adjacent first and second modeling areas; performing smooth transition processing on the first and second regional modeling results based on the mechanical properties of the first and second regional modeling results; and integrating the first and second regional modeling results after the smooth transition processing to obtain the structural model of the target object.

[0008] Furthermore, the enhancement process includes: identifying the microstructure edge of the target object and enhancing the microstructure edge of the target object.

[0009] Furthermore, based on the enhanced image, each modeling area of ​​the target object is modeled, and according to the material properties of each modeling area, the mechanical properties of each modeling area are configured, including: obtaining structural composition information of the target modeling area, the structural composition information is used to determine the materials, material ratios, and material positions that constitute the target modeling area; based on the structural composition information, the target modeling area of ​​the target object is modeled, and according to the material properties of each material in the target modeling area, the mechanical properties of the target modeling area are configured, and the material properties include the modulus and Poisson's ratio of the material.

[0010] Furthermore, the target object is divided into multiple modeling areas, including: determining the similarity between adjacent microstructure images based on multiple microstructure images of the target object; and determining whether to divide sub-areas corresponding to the microstructure images into the same area to form modeling areas based on the similarity between adjacent microstructure images.

[0011] Furthermore, the method of determining whether to divide the sub-regions corresponding to the microstructure images into the same region to form a modeling region based on the similarity between adjacent microstructure images includes: determining whether the similarity between adjacent microstructure images exceeds a first threshold; if so, dividing the sub-regions corresponding to the microstructure images into the same region.

[0012] Furthermore, the method also includes: determining whether the similarity between adjacent microstructure images is lower than a second threshold; if so, performing a secondary scan on the sub-region corresponding to the microstructure image to subdivide the sub-region corresponding to the microstructure image to obtain a modeling area of ​​the target object.

[0013] In the second aspect, the present application provides a structural model processing device, which includes: a structural image acquisition module, which is used to perform a three-dimensional structural scan of a target object through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas, and the target object is composed of a composite material; an enhanced image acquisition module, which is used to adopt a deep learning model trained based on a deep learning method to enhance the microstructure image to obtain an enhanced image; a regional modeling processing module, which is used to model each modeling area of ​​the target object based on the enhanced image, and configure the mechanical properties of each modeling area according to the material properties of each modeling area to form a regional modeling result of each modeling area; a structural model acquisition module, which is used to integrate the regional modeling results of each modeling area to obtain a structural model of the target object.

[0014] In a third aspect, the present application provides a network device comprising: a memory, a transceiver, and a processor; wherein the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and execute the method described in the first aspect.

[0015] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in the first aspect.

[0016] The beneficial effects of the technical solution provided by this application are:

[0017] The solution of the present application can be applied in the scenario of modeling composite materials. The target object can be scanned by scanning equipment, and each modeling area of ​​the target object can be modeled and integrated respectively. In the process of modeling the modeling area, the mechanical properties of each modeling area can be determined based on the scanning results, so as to integrate a more accurate structural model. Specifically, the existing solution assumes that the target object formed by the composite material is homogenized by default, without considering the difference in mechanical properties caused by the difference in the microstructure of the material. This solution can perform a three-dimensional structural scan of a target object composed of composite materials through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas. Based on the microstructure image, the composition materials, material ratios, and material positions of the modeling area can be analyzed, so as to analyze the unique mechanical properties of the modeling area; before modeling, a deep learning model trained based on a deep learning method is used to enhance the edges of the microstructure image to obtain an enhanced image, such as by sharpening processing. Afterwards, based on the enhanced image, each modeling area of ​​the target object is modeled, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area to form a regional modeling result of each modeling area; the regional modeling results of each modeling area are integrated to obtain a structural model of the target object; in the process of integrating the regional modeling results of multiple modeling areas, the boundaries of the modeling areas can be smoothly transitioned to better conform to the actual state of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0019] Figure 1 It is a flowchart of a structural model processing method according to an embodiment of the present application;

[0020] Figure 2is a schematic diagram of the structure of a structural model processing device according to an embodiment of the present application;

[0021] Figure 3 It is a structural block diagram of a network device according to an embodiment of the present application;

[0022] Figure 4 This is a structural block diagram of a user device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout identify the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0024] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms, and "multiple" refers to two or more, and other quantifiers are similar. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may be intermediate elements. In addition, the "connection" or "coupling" used here may include wireless connection or wireless coupling. The term "and / or" used here describes the association relationship of associated objects, indicating that there may be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0025] The solution of the present application can be applied in the scenario of modeling composite materials. The target object can be scanned by scanning equipment, and each modeling area of ​​the target object can be modeled and integrated respectively. In the process of modeling the modeling area, the mechanical properties of each modeling area can be determined based on the scanning results, so as to integrate a more accurate structural model. Specifically, the existing solution assumes that the target object formed by the composite material is homogenized by default, without considering the difference in mechanical properties caused by the difference in the microstructure of the material. This solution can perform a three-dimensional structural scan of a target object composed of composite materials through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas. Based on the microstructure image, the composition materials, material ratios, and material positions of the modeling area can be analyzed, so as to analyze the unique mechanical properties of the modeling area; before modeling, a deep learning model trained based on a deep learning method is used to enhance the edges of the microstructure image to obtain an enhanced image, such as by sharpening processing. Afterwards, based on the enhanced image, each modeling area of ​​the target object is modeled, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area to form a regional modeling result of each modeling area; the regional modeling results of each modeling area are integrated to obtain a structural model of the target object; in the process of integrating the regional modeling results of multiple modeling areas, the boundaries of the modeling areas can be smoothly transitioned to better conform to the actual state of the target object.

[0026] In the field of engineering, the growing demand for high-performance materials has driven the development and application of heterogeneous materials such as composites. However, these composites often have complex microstructures and multi-scale properties, making it extremely difficult and impractical to accurately simulate them directly at the macroscale. Therefore, homogenization technology has emerged as a computational method for analyzing and simulating multi-scale materials, which can treat heterogeneous materials with complex microstructures as continuous media with equivalent uniform properties. The core of this method is to link the macroscopic properties of materials with microstructures, thereby simplifying the material model without losing important physical properties. The main advantage of this method is that by digitally defining the microstructure, whether through experimental imaging or idealized geometry, users can evaluate effective properties and optimize numerical microstructural models. In addition, computational homogenization avoids explicitly describing all heterogeneities of materials at the structural level, which is not feasible with current computer technology. This method can significantly save the time and cost of experimental testing and manufacturing, while providing a broader framework for predicting the effective properties of materials with fewer restrictions on microscopic morphology and local phenomena. Therefore, homogenization not only improves the efficiency and effectiveness of material design, but also provides a powerful tool for the rapid development and optimization of new materials.

[0027] In the traditional homogenization model construction method, the three-dimensional structure construction and material properties of the device are obtained from the macroscopic scale, lacking the refined sampling and modeling of the device microstructure, which causes the accuracy of the model to be affected by the complexity and non-uniformity of the device microstructure. Since composite materials are inherently anisotropic and non-homogeneous, they cannot be simply regarded as isotropic bodies for modeling, especially for composite materials. Therefore, the traditional homogenization method may not accurately capture the impact of microstructure on macroscopic performance, especially for materials with high non-uniformity.

[0028] The purpose of the present invention is to address the problem that traditional homogenization model construction methods do not take the microstructure of the device itself into consideration enough, and further propose a homogenization model construction method based on micro-computed tomography three-dimensional structure data.

[0029] This solution is based on scanning data from scanning equipment (such as Micro-CT) and homogenization simulation design. First, use Micro-CT to obtain the microscopic three-dimensional structure data of the device, and then divide the device sample into several regions. For each region, fine modeling is performed based on the Micro-CT scanning data. After the model is established, the material modulus, coefficient of thermal expansion (CTE), Poisson's ratio, etc. are used as input parameters, and finite element simulation software (such as Geodict, Comosol, etc.) is used to calculate the overall mechanical parameters of the corresponding region. After obtaining the homogenized physical parameters of each region, the overall macroscopic homogenization simulation model of the device is obtained by applying appropriate boundary conditions, and the smooth transition of mechanical parameters between regions is guaranteed during the integration process.

[0030] This solution includes the following steps: use Micro-CT to perform three-dimensional structural scanning on the device to obtain microstructure information; use deep learning methods to enhance image quality and improve the recognition rate of microstructure edges. According to the scanning results, the device is divided into several regions, and each region is finely modeled according to the information of CT scanning; the intrinsic properties of the device material such as modulus and Poisson's ratio are used as input parameters of the simulation model of each region to obtain the overall mechanical properties of each region; appropriate boundary conditions are adopted to ensure that the mechanical properties between each region can smoothly transition, and each region is integrated into a macroscopic simulation structure model.

[0031] This solution uses the three-dimensional structure data of Micro-CT scans to build a refined simulation model; uses deep learning methods to improve the image quality of CT scans; uses linear interpolation methods to process boundary conditions when building a macro simulation model to ensure the continuity of the mechanical properties of the macro simulation model; uses the method of the present invention to build an accurate macro homogenization simulation model and apply it to processes such as device mechanics and sintering property simulation.

[0032] Based on the above embodiments, the present application also provides a structural model processing method, such as Figure 1 As shown, the method includes:

[0033] Step 102: perform a three-dimensional structure scan on the target object by using a scanning device to obtain a microstructure image, and divide the target object into multiple modeling areas, wherein the target object is composed of a composite material.

[0034] Step 104: Use a deep learning model trained based on a deep learning method to enhance the microstructure image to obtain an enhanced image.

[0035] Step 106: Model each modeling region of the target object based on the enhanced image, and configure the mechanical properties of each modeling region according to the material properties of each modeling region to form a regional modeling result of each modeling region.

[0036] Step 108: Integrate the regional modeling results of each modeling area to obtain a structural model of the target object.

[0037] The solution of the present application can be applied in the scenario of modeling composite materials. The target object can be scanned by scanning equipment, and each modeling area of ​​the target object can be modeled and integrated respectively. In the process of modeling the modeling area, the mechanical properties of each modeling area can be determined based on the scanning results, so as to integrate a more accurate structural model. Specifically, the existing solution assumes that the target object formed by the composite material is homogenized by default, without considering the difference in mechanical properties caused by the difference in the microstructure of the material. This solution can perform a three-dimensional structural scan of a target object composed of composite materials through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas. Based on the microstructure image, the composition materials, material ratios, and material positions of the modeling area can be analyzed, so as to analyze the unique mechanical properties of the modeling area; before modeling, a deep learning model trained based on a deep learning method is used to enhance the edges of the microstructure image to obtain an enhanced image, such as by sharpening processing. Afterwards, based on the enhanced image, each modeling area of ​​the target object is modeled, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area to form a regional modeling result of each modeling area; the regional modeling results of each modeling area are integrated to obtain a structural model of the target object; in the process of integrating the regional modeling results of multiple modeling areas, the boundaries of the modeling areas can be smoothly transitioned to better conform to the actual state of the target object.

[0038] For each modeling area, the microstructure image corresponding to each area may only represent the characteristics of a part of the structure in the area, and cannot fully represent the complete structural characteristics of the area. Therefore, at the boundary of the two areas, if only the modeling area is considered as homogenized, there may be large differences at the boundary of the modeling area. Therefore, corresponding to the boundary of the modeling area, this solution can perform a smooth transition process to generate a more accurate structural model. Specifically, as an optional embodiment, the regional modeling results of each modeling area are integrated to obtain the structural model of the target object, including: obtaining the first regional modeling results and the second regional modeling results of the adjacent first modeling area and the second modeling area; performing a smooth transition process on the first regional modeling results and the second regional modeling results according to the mechanical properties of the first regional modeling results and the second regional modeling results; integrating the first regional modeling results and the second regional modeling results after the smooth transition process to obtain the structural model of the target object.

[0039] In this solution, the image enhancement can enhance the overall clarity of the image, and can also enhance the edge of the microstructure of the target object. Specifically, as an optional embodiment, the enhancement process includes: identifying the edge of the microstructure of the target object, and enhancing the edge of the microstructure of the target object. Specifically, the edge of the microstructure of the target object can be enhanced by methods such as sharpening. The edge of the microstructure of the target object can be understood as the edge of different materials in the microstructure image. By enhancing the recognition of the edge, the position and composition of different materials in the microstructure can be better determined to better simulate the mechanical properties.

[0040] This solution can identify the information of materials in each modeling area based on the enhanced image, so as to simulate the mechanical properties of the modeling area according to information such as material properties. Specifically, as an optional embodiment, the modeling areas of the target object are modeled based on the enhanced image, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area, including: obtaining structural composition information of the target modeling area, the structural composition information is used to determine the materials, material ratios, and material positions that constitute the target modeling area; based on the structural composition information, the target modeling area of ​​the target object is modeled, and the mechanical properties of the target modeling area are configured according to the material properties of each material in the target modeling area, and the material properties include the modulus and Poisson's ratio of the material.

[0041] This solution can divide the target object into multiple modeling areas based on the enhanced image after enhancing the image, or divide the modeling areas based on the correlation of the microstructure images. In one solution, the microstructure image can correspond to the sub-area of ​​the target object, and then determine whether the adjacent sub-areas can be merged based on the similarity between the microstructure images to obtain the modeling area. Specifically, as an optional embodiment, the target object is divided into multiple modeling areas, including: determining the similarity between adjacent microstructure images based on multiple microstructure images of the target object; determining whether to divide the sub-areas corresponding to the microstructure images into the same area to form the modeling area based on the similarity between the adjacent microstructure images.

[0042] This solution can merge sub-regions with high similarity. Specifically, as an optional embodiment, the similarity between adjacent microstructure images is used to determine whether to divide the sub-regions corresponding to the microstructure images into the same region to form a modeling region, including: determining whether the similarity between adjacent microstructure images exceeds a first threshold; if so, dividing the sub-regions corresponding to the microstructure images into the same region. This solution can also model sub-regions with low similarity as modeling regions. In addition, a microstructure image (or enhanced image) in this solution can also correspond to multiple sub-regions, so that by analyzing a single microstructure image, multiple sub-regions in the same microstructure image can be merged or further divided to obtain multiple modeling regions.

[0043] For adjacent microstructure images, if the similarity is too low, it is possible that the structure of the part is quite different, and more scanning data can be obtained by secondary scanning to re-divide the modeling area and perform modeling. Specifically, as an optional embodiment, the method further includes: determining whether the similarity between adjacent microstructure images is lower than a second threshold; if so, performing secondary scanning on the sub-area corresponding to the microstructure image to subdivide the sub-area corresponding to the microstructure image to obtain the modeling area of ​​the target object.

[0044] Based on the above embodiments, the present application also provides a structural model processing device, such as Figure 2 As shown, the device comprises:

[0045] The structural image acquisition module 202 is used to perform a three-dimensional structural scan on the target object through a scanning device, acquire a microstructure image, and divide the target object into multiple modeling areas. The target object is composed of a composite material.

[0046] The enhanced image acquisition module 204 is used to enhance the microstructure image by using a deep learning model trained in a deep learning manner to obtain an enhanced image.

[0047] The regional modeling processing module 206 is used to model each modeling region of the target object based on the enhanced image, and configure the mechanical properties of each modeling region according to the material properties of each modeling region to form a regional modeling result of each modeling region.

[0048] The structural model acquisition module 208 is used to integrate the regional modeling results of each modeling area to obtain the structural model of the target object.

[0049] The implementation of the embodiments of the present application is similar to that of the above embodiments. The specific implementation can refer to the specific implementation of the above embodiments, which will not be repeated here.

[0050] The solution of the present application can be applied in the scenario of modeling composite materials. The target object can be scanned by scanning equipment, and each modeling area of ​​the target object can be modeled and integrated respectively. In the process of modeling the modeling area, the mechanical properties of each modeling area can be determined based on the scanning results, so as to integrate a more accurate structural model. Specifically, the existing solution assumes that the target object formed by the composite material is homogenized by default, without considering the difference in mechanical properties caused by the difference in the microstructure of the material. This solution can perform a three-dimensional structural scan of a target object composed of composite materials through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas. Based on the microstructure image, the composition materials, material ratios, and material positions of the modeling area can be analyzed, so as to analyze the unique mechanical properties of the modeling area; before modeling, a deep learning model trained based on a deep learning method is used to enhance the edges of the microstructure image to obtain an enhanced image, such as by sharpening processing. Afterwards, based on the enhanced image, each modeling area of ​​the target object is modeled, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area to form a regional modeling result of each modeling area; the regional modeling results of each modeling area are integrated to obtain a structural model of the target object; in the process of integrating the regional modeling results of multiple modeling areas, the boundaries of the modeling areas can be smoothly transitioned to better conform to the actual state of the target object.

[0051] It should be noted that the division of units and / or modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit and / or module in each embodiment of the present application may be integrated into a processing unit and / or module, or each unit and / or module may exist physically separately, or two or more units and / or modules may be integrated into one unit and / or module. The above-mentioned integrated units and / or modules may be implemented in the form of hardware or in the form of software functional units and / or modules.

[0052] If the integrated units and / or modules are implemented in the form of software functional units and / or modules and sold or used as independent products, they can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0053] In addition, the data transmission device and the data transmission method provided in the above embodiments are based on the same application concept. Since the principles of solving problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0054] Figure 3 A structural block diagram of a network device is shown according to an exemplary embodiment.

[0055] like Figure 3 As shown, the network device 1100 includes at least: a processor 1110 , a memory 1120 , and a transceiver 1130 .

[0056] The transceiver 1130 is used to receive and send data under the control of the processor 1110 .

[0057] exist Figure 3In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1110 and memory represented by memory 1120. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1130 may be a plurality of components, namely, a transmitter and a receiver, providing units and / or modules for communicating with various other devices on a transmission medium, which may include a wireless channel, a wired channel, an optical cable, and other transmission media.

[0058] The processor 1110 is responsible for managing the bus architecture and general processing, and the memory 1120 can store data used by the processor 1110 when performing operations.

[0059] Optionally, the processor 1110 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor 1110 may also adopt a multi-core architecture. The processor 1110 and the memory 1120 may also be physically arranged separately.

[0060] The processor 1110 calls the computer program stored in the memory 1120 to execute any one of the methods for allocating a cell radio network temporary identifier provided in the above embodiments of the present application according to the obtained executable instructions.

[0061] Figure 4 A structural block diagram of a user equipment is shown according to an exemplary embodiment.

[0062] like Figure 4 As shown, the user equipment 1300 includes at least: a processor 1310 , a memory 1320 , and a transceiver 1330 .

[0063] The transceiver 1330 is used to receive and send data under the control of the processor 1310 .

[0064] exist Figure 4In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1310 and various circuits of memory represented by memory 1320 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1330 may be a plurality of components, namely, a transmitter and a receiver, providing units and / or modules for communicating with various other devices on a transmission medium, including transmission media such as wireless channels, wired channels, and optical cables. For different user devices, the user interface 1340 may also be an interface capable of externally and internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like.

[0065] The processor 1310 is responsible for managing the bus architecture and general processing, and the memory 1320 can store data used by the processor 1310 when performing operations.

[0066] Optionally, the processor 1310 may be a CPU (central processing unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or a CPLD (Complex Programmable Logic Device), and the processor 1310 may also adopt a multi-core architecture. The processor 1310 and the memory 1320 may also be physically arranged separately.

[0067] The processor 1310 calls the computer program stored in the memory 1320 to execute any one of the methods for allocating a cell radio network temporary identifier provided in the above embodiments of the present application according to the obtained executable instructions.

[0068] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0069] In addition, a storage medium is provided in an embodiment of the present application, on which a computer program is stored, and when the computer program is executed by the processor, the data transmission method in the above embodiments is implemented. The storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (such as floppy disk, hard disk, tape, magneto-optical disk (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid state drive (SSD)), etc.

[0070] In an embodiment of the present application, a program product is provided, for example, the program product is an FPGA chip or a DSP chip, and the program product includes executable instructions, and the executable instructions are stored in a storage medium. The processor reads the executable instructions from the storage medium, so that when the executable instructions are executed by the processor, the data transmission method in each of the above embodiments is implemented.

[0071] The solution of the present application can be applied in the scenario of modeling composite materials. The target object can be scanned by scanning equipment, and each modeling area of ​​the target object can be modeled and integrated respectively. In the process of modeling the modeling area, the mechanical properties of each modeling area can be determined based on the scanning results, so as to integrate a more accurate structural model. Specifically, the existing solution assumes that the target object formed by the composite material is homogenized by default, without considering the difference in mechanical properties caused by the difference in the microstructure of the material. This solution can perform a three-dimensional structural scan of a target object composed of composite materials through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas. Based on the microstructure image, the composition materials, material ratios, and material positions of the modeling area can be analyzed, so as to analyze the unique mechanical properties of the modeling area; before modeling, a deep learning model trained based on a deep learning method is used to enhance the edges of the microstructure image to obtain an enhanced image, such as by sharpening processing. Afterwards, based on the enhanced image, each modeling area of ​​the target object is modeled, and the mechanical properties of each modeling area are configured according to the material properties of each modeling area to form a regional modeling result of each modeling area; the regional modeling results of each modeling area are integrated to obtain a structural model of the target object; in the process of integrating the regional modeling results of multiple modeling areas, the boundaries of the modeling areas can be smoothly transitioned to better conform to the actual state of the target object.

[0072] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0073] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0077] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A structural model processing method, characterized in that: The method comprises: Performing a three-dimensional structural scan on a target object by means of a scanning device to obtain a microstructure image, and dividing the target object into a plurality of modeling areas, wherein the target object is composed of a composite material; A deep learning model trained based on deep learning is used to enhance the microstructure image to obtain an enhanced image; Based on the enhanced image, each modeling area of ​​the target object is modeled, and according to the material properties of each modeling area, the mechanical properties of each modeling area are configured to form a regional modeling result of each modeling area; The regional modeling results of each modeling area are integrated to obtain the structural model of the target object.

2. The method according to claim 1, characterized in that The regional modeling results of each modeling area are integrated to obtain a structural model of the target object, including: Obtaining first-area modeling results and second-area modeling results of adjacent first modeling areas and second modeling areas; According to the mechanical properties of the first region modeling result and the second region modeling result, a smooth transition process is performed on the first region modeling result and the second region modeling result; The structural model of the target object is obtained by integrating the first region modeling result and the second region modeling result after smooth transition processing.

3. The method according to claim 1, characterized in that The enhanced processing includes: Identify the microstructure edge of the target object and enhance the microstructure edge of the target object.

4. The method according to claim 1, characterized in that The method of modeling each modeling region of the target object based on the enhanced image and configuring the mechanical properties of each modeling region according to the material properties of each modeling region includes: Acquire structural composition information of the target modeling area, wherein the structural composition information is used to determine the materials, material ratios, and material positions constituting the target modeling area; According to the structural composition information, the target modeling area of ​​the target object is modeled, and according to the material properties of each material in the target modeling area, the mechanical properties of the target modeling area are configured. The material properties include the modulus and Poisson's ratio of the material.

5. The method according to claim 1, characterized in that The target object is divided into a plurality of modeling areas, including: Determining similarities between adjacent microstructure images based on multiple microstructure images of the target object; According to the similarity between adjacent microstructure images, it is determined whether to divide the sub-regions corresponding to the microstructure images into the same region to form a modeling region.

6. The method according to claim 5, characterized in that The step of determining whether to divide the sub-regions corresponding to the micro-structure images into the same region to form a modeling region based on the similarity between adjacent micro-structure images includes: determining whether the similarity between adjacent microstructure images exceeds a first threshold; If so, the sub-regions corresponding to the microstructure image are divided into the same region.

7. The method according to claim 6, characterized in that The method further comprises: determining whether the similarity between adjacent microstructure images is below a second threshold; If so, a second scan is performed on the sub-region corresponding to the microstructure image to subdivide the sub-region corresponding to the microstructure image to obtain a modeling region of the target object.

8. A structural model processing device, characterized in that: The device comprises: A structural image acquisition module is used to perform a three-dimensional structural scan of a target object through a scanning device, obtain a microstructure image, and divide the target object into multiple modeling areas, wherein the target object is composed of a composite material; An enhanced image acquisition module is used to enhance the microstructure image using a deep learning model trained based on a deep learning method to obtain an enhanced image; A regional modeling processing module is used to model each modeling region of the target object based on the enhanced image, and configure the mechanical properties of each modeling region according to the material properties of each modeling region to form a regional modeling result of each modeling region; The structural model acquisition module is used to integrate the regional modeling results of each modeling area to obtain the structural model of the target object.

9. A network device, characterized in that: include: A memory, a transceiver, and a processor; wherein the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; The processor is used to read the computer program in the memory and execute the method according to claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claims 1-7 is implemented.

Images