Automatic modeling system and method for interactive nuclear system

Abstract

The invention relates to the technical field of modeling, in particular to an interactive nuclear system automatic modeling system and method. The system comprises a text input module used for acquiring text information describing a to-be-modeled nuclear system; the natural language processing module is used for carrying out semantic analysis on the text information to generate model data, and the model data are data describing components forming the to-be-modeled nuclear system, relationships among the components and design parameters of the components; the model generation module is used for generating a three-dimensional model of the nuclear system to be modeled according to the model data; and the model optimization editing module is used for acquiring modification information sent by a user and adjusting the three-dimensional model of the to-be-modeled nuclear system based on the modification information. According to the method, the modeling process is simplified, automatic modeling of the nuclear system is realized, and the modeling efficiency and accuracy are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of modeling, and in particular to an interactive nuclear system automatic modeling system and method. Background Art

[0002] In nuclear system modeling, engineers usually rely on manually building models in modeling software, but manual operations are complex and time-consuming, which can easily lead to inefficient model generation, and the accuracy of complex systems depends on the experience and skills of designers. In addition, conventional methods are difficult to quickly iterate and optimize model design, especially for highly complex and demanding application scenarios such as systems.

[0003] To address these challenges, some existing technical solutions attempt to improve the traditional modeling process by introducing interactive and automated modeling tools. For example, by integrating the InstantCAD tool into existing CAD software, designers can edit and optimize models in real time, greatly improving design efficiency. However, InstantCAD still requires manual operation, and its main focus is on model optimization rather than directly generating models from text descriptions.

[0004] In addition, generative design technologies use artificial intelligence and machine learning to automatically generate and optimize multiple design options, such as Creo's generative design tools. Such technologies can quickly explore different design options, automatically generate the best design that meets specific goals, and reduce material waste and development costs. However, these technologies are mainly used to optimize existing designs rather than directly generate models from text.

[0005] In recent years, the development of text-to-3D technology has brought new possibilities for automated modeling. Generative models like DALL-E demonstrate the potential to generate images or three-dimensional models directly from text descriptions. This technology has been initially applied in fields such as architectural design and product development, and has shown significant efficiency improvements and flexibility. However, these technologies have not yet been optimized and adjusted for complex industrial systems such as nuclear systems. In addition, nuclear system modeling tools still lack support for natural language input, making it impossible to generate models directly from text. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide an interactive nuclear system automatic modeling system and method to solve the above technical problems.

[0007] The technical solution of the present invention to solve the above technical problems is as follows: an interactive nuclear system automatic modeling system, comprising:

[0008] A text input module is used to obtain text information describing the nuclear system to be modeled;

[0009] A natural language processing module, used for performing semantic analysis on the text information to generate model data, wherein the model data is data describing the components constituting the core system to be modeled, the relationship between the components, and the design parameters of the components;

[0010] A model generation module, used for generating a three-dimensional model of the nuclear system to be modeled according to the model data;

[0011] The model optimization and editing module is used to obtain the modification information sent by the user and adjust the three-dimensional model of the nuclear system to be modeled based on the modification information.

[0012] The beneficial effects of the present invention are as follows: the present invention realizes automatic generation of a three-dimensional model of a nuclear system that meets the requirements by inputting text information describing the nuclear system to be modeled. Moreover, the three-dimensional model of the nuclear system can be automatically optimized and adjusted according to the modification information in the form of text input by the user. Therefore, the present method realizes the automated modeling of the nuclear system, greatly improves the modeling efficiency and accuracy, overcomes the drawbacks of the traditional method that relies on manual operation and complex design processes, and makes the nuclear system modeling more efficient and intelligent.

[0013] Based on the above technical solution, the present invention can also be improved as follows.

[0014] Further, the model data includes functional component data, structural feature data and design parameter data, and the natural language processing module includes:

[0015] A context understanding unit, used for understanding the context of the text information and generating the functional component data; the functional component data represents data in the text information for describing the components constituting the core system to be modeled and the relationship between the components;

[0016] A semantic mapping unit, used to generate the structural feature data based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph for describing the components constituting the nuclear system to be modeled and the relationship between the components;

[0017] A parameter extraction unit is used to generate the design parameter data according to the text information, wherein the design parameter data is represented in the text information and is used to describe the data of the design parameters of each component constituting the nuclear system to be modeled.

[0018] Furthermore, the model generation module includes:

[0019] A latent space representation unit, used for mapping the model data into the latent space of the trained DreamFusion model;

[0020] A three-dimensional model generating unit, used for generating an initial three-dimensional model of the nuclear system to be modeled in the latent space based on DreamFusion technology;

[0021] The model optimization unit is used to optimize the initial three-dimensional model of the nuclear system to be modeled based on DreamFusion technology to generate a three-dimensional model of the nuclear system to be modeled.

[0022] Furthermore, the model optimization editing module includes:

[0023] A model reading and parsing unit, used for reading the three-dimensional model of the nuclear system to be modeled;

[0024] A modification instruction generating unit, used for acquiring modification information sent by a user, and performing natural language processing on the modification information through a large language model to generate a modification instruction;

[0025] The instruction execution unit is used to control the model editing software to modify the three-dimensional model of the nuclear system to be modeled according to the modification instruction.

[0026] Furthermore, the system also includes a model verification module for verifying the three-dimensional model of the nuclear system to be modeled.

[0027] Further, the model verification module includes:

[0028] An automatic verification unit, used to check whether the three-dimensional model of the nuclear system to be modeled complies with the modeling specification;

[0029] The standard checking unit is used to check whether the three-dimensional model of the nuclear system to be modeled complies with the nuclear system design specifications.

[0030] Furthermore, the system includes:

[0031] The model export module is used to export the three-dimensional model of the nuclear system to be modeled into a nuclear system three-dimensional model file in a preset format.

[0032] In order to solve the above technical problems, the present invention also proposes an interactive nuclear system automatic modeling method, comprising:

[0033] Obtain text information describing the nuclear system to be modeled;

[0034] Performing semantic analysis on the text information to generate model data, wherein the model data is data describing components constituting the core system to be modeled, relationships between the components, and design parameters of the components;

[0035] generating a three-dimensional model of the nuclear system to be modeled according to the model data;

[0036] The modification information sent by the user is obtained, and the three-dimensional model of the nuclear system to be modeled is adjusted based on the modification information.

[0037] Further, the model data includes functional component data, structural feature data and design parameter data, and the semantic analysis of the text information to generate the model data includes:

[0038] Performing contextual understanding on the text information to generate the functional component data; the functional component data represents data in the text information for describing the components constituting the core system to be modeled and the relationship between the components;

[0039] The structural feature data is generated based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph for describing components constituting the nuclear system to be modeled and the relationship between the components;

[0040] The design parameter data is generated according to the text information, wherein the design parameter data represents data in the text information for describing design parameters of various components constituting the nuclear system to be modeled.

[0041] Further, generating the three-dimensional model of the nuclear system to be modeled according to the model data includes:

[0042] Mapping the model data into the latent space of the trained DreamFusion model;

[0043] Based on DreamFusion technology, generating an initial three-dimensional model of the nuclear system to be modeled in the latent space;

[0044] Based on DreamFusion technology, the initial three-dimensional model of the core system to be modeled is optimized to generate a three-dimensional model of the core system to be modeled. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of an interactive nuclear system automatic modeling system of the present invention;

[0046] Figure 2 The present invention is a flowchart of an interactive nuclear system automatic modeling method. DETAILED DESCRIPTION

[0047] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0048] Embodiment 1

[0049] like Figure 1As shown, this embodiment provides an interactive nuclear system automatic modeling system, including:

[0050] The text input module is used to obtain text information describing the nuclear system to be modeled.

[0051] The user can input text information describing the nuclear system to be modeled through the text input module. This module supports users to describe various components and features of the nuclear system to be modeled in a free form, such as "reactor pressure vessel, primary cooling loop, double containment", "design a pressurized water reactor including reactor pressure vessel, primary cooling loop and double containment", etc. This module also supports the input of more complex parameters and constraints, such as size, material, functional requirements, etc.

[0052] The natural language processing module is used to perform semantic analysis on the text information to generate model data, wherein the model data is data describing the components constituting the core system to be modeled, the relationships between the components, and the design parameters of the components.

[0053] Advanced natural language processing technology is used to perform semantic analysis on the text information input by users, using pre-trained language models such as BERT (Bidirectional Encoder Representations from Transformers). BERT can generate corresponding structured data in dictionary / JSON (JavaScript Object Notation) format based on the complex text information input.

[0054] Optionally, in an embodiment, the model data includes functional component data, structural feature data and design parameter data, and the natural language processing module includes:

[0055] A context understanding unit is used to perform context understanding on the text information and generate the functional component data; the functional component data is represented in the text information and is used to describe the components constituting the core system to be modeled and the relationship between the components.

[0056] The context understanding unit is able to understand the context of complex descriptions in text information, ensuring that descriptions involving multiple components and functional relationships can be correctly identified and processed. BERT is based on the Transformer architecture, especially the Self-Attention Mechanism. The self-attention mechanism enables the BERT model to dynamically focus on other words related to it in the sentence when processing each word in the text information. This mechanism enables BERT to capture long-distance dependencies and enhance context understanding. For example, BERT can be used to understand the subordinate relationship between "control rods" and "reactor pressure vessels" in "control rods in reactor pressure vessels need to be replaced regularly."

[0057] A semantic mapping unit is used to generate the structural feature data based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph that is used to describe the components that constitute the nuclear system to be modeled and the relationship between the components.

[0058] BERT extracts key terms from text information and converts them into high-dimensional vectors (embeddings) that represent the semantics of the terms. By leveraging pre-built or existing nuclear system knowledge graphs, key terms parsed from text information are mapped to entities or concepts in the knowledge graph. The nuclear system knowledge graph contains not only the definitions of terms in the nuclear system field, but also the relationships between the terms, which ensures the accuracy of the mapping process. For example, "reactor pressure vessel" is associated with multiple components in the nuclear system knowledge graph, and the specific component can be determined by the relationship path during mapping. "Pressurized water reactor" is mapped to a specific structural model that includes a reactor pressure vessel, a steam generator, and a cooling system. For special terms or highly structured descriptions in the nuclear field, rule-based semantic parsing can be used to define clear mapping rules and directly convert terms in text information into predefined components or functional modules.

[0059] A parameter extraction unit is used to generate the design parameter data according to the text information, wherein the design parameter data is represented in the text information and is used to describe the data of the design parameters of each component constituting the nuclear system to be modeled.

[0060] The parameter extraction unit is used to extract specific design parameters from text information, such as the size, positional relationship and material information of components. These parameters will serve as an important basis for the subsequent generation of 3D models. For example, in "the diameter of the reactor pressure vessel is 5 meters", BERT can recognize "diameter" and "5 meters" as design parameter data.

[0061] The natural language processing module of this system can accurately parse the text description related to the nuclear system and generate structured model data through the BERT model and the nuclear system knowledge graph. The code example of the generated structured model data is as follows:

[0062]

[0063]

[0064] The model generation module is used to generate a three-dimensional model of the nuclear system to be modeled according to the model data. The model generation module applies DreamFusion technology to generate a three-dimensional model of the nuclear system according to the structured model data, and realizes the conversion from natural language description to three-dimensional model.

[0065] Optionally, in an embodiment, the model generation module includes:

[0066] A data acquisition unit is used to acquire the model data.

[0067] The latent space representation unit is used to map the model data into the latent space of the trained DreamFusion model.

[0068] By mapping the model data into the latent space of the DreamFusion model, the geometric and texture features of the 3D object can be effectively captured. The latent space is pre-trained by Google's DreamFusion technology and contains the geometric shapes, positional relationships, and material properties of each component of the core system.

[0069] A three-dimensional model generating unit is used to generate an initial three-dimensional model of the core system to be modeled in the latent space based on DreamFusion technology.

[0070] The Neural Radiance Field (NeRF) and generative algorithms in DreamFusion technology are used to generate an initial 3D model in a high-dimensional latent space. The initial 3D model contains all specified components and relationships, and conforms to the input description in terms of geometry, position, and material. DreamFusion can generate highly realistic 3D models by learning the interaction between light and objects in 3D space, which is particularly suitable for nuclear system components with complex structures.

[0071] The model optimization unit is used to optimize the initial three-dimensional model of the nuclear system to be modeled based on DreamFusion technology to generate a three-dimensional model of the nuclear system to be modeled.

[0072] The initial 3D model of the nuclear system to be modeled is then optimized within DreamFusion to further improve the accuracy of details and the rationality of the model structure. This process ensures that the generated model is not only visually realistic, but also meets the input design requirements in terms of physical parameters.

[0073] The model optimization and editing module is used to obtain the modification information sent by the user and adjust the three-dimensional model of the nuclear system to be modeled based on the modification information.

[0074] The model optimization editing module allows users to fine-tune the generated 3D model of the nuclear system to ensure the accuracy of the model and meet the design requirements. Specifically, users can adjust parameters: users can adjust the parameters of the generated 3D model according to specific design requirements, such as the thickness, position and connection method of the components; structural fine-tuning: users can manually adjust the tiny structures of the generated 3D model to ensure that the model accurately matches the design requirements; material and texture adjustment: users can specify different materials and textures for each component in the generated 3D model to simulate the material properties of the actual nuclear system.

[0075] Optionally, in an embodiment, the model optimization editing module includes:

[0076] The model reading and parsing unit is used to read the three-dimensional model of the nuclear system to be modeled.

[0077] The model optimization and editing module can also optimize and edit the previous 3D model of the nuclear system. First, the existing 3D model file of the nuclear system is read and parsed through the GPT-4 large language model interface, and key information such as the model's geometric structure, material properties, and component relationships are extracted and stored in a structured form for subsequent operations.

[0078] The modification instruction generating unit is used to obtain the modification information sent by the user, and perform natural language processing on the modification information through a large language model to generate a modification instruction.

[0079] The user describes the modification requirements for the 3D model in the form of text input, which is the modification information. The large language model performs natural language processing on the modification information input by the user, parses its semantics and generates corresponding modification instructions, such as geometric adjustment, component replacement, material modification, position change, etc. The user inputs "increase the diameter of the reactor pressure vessel to 6 meters and change the material to titanium alloy", and the large language model parses it, identifies the keywords "reactor pressure vessel", "diameter", "6 meters", and "titanium alloy", and generates modification instructions.

[0080] The instruction execution unit is used to control the model editing software to modify the three-dimensional model of the nuclear system to be modeled according to the modification instruction.

[0081] According to the generated modification instructions, the instruction execution unit automatically operates the model editing software to accurately modify the 3D model. Through the interface integration with the model editing software, the system can update the model in real time and display the modification results.

[0082] Optionally, in the embodiment, a model verification module is also included, which is used to verify the three-dimensional model of the nuclear system to be modeled.

[0083] The 3D model is verified through the model verification module to ensure that it meets the design requirements and satisfies relevant engineering specifications or standards.

[0084] Optionally, in an embodiment, the model verification module includes:

[0085] The automatic verification unit is used to check whether the three-dimensional model of the nuclear system to be modeled meets the modeling specifications.

[0086] The automatic verification unit provides automatic verification tools to conduct a comprehensive check on the 3D model and report possible errors or conflicts. Modeling specifications include geometric consistency, structural integrity, material assignment, etc.

[0087] The standard checking unit is used to check whether the three-dimensional model of the nuclear system to be modeled complies with the nuclear system design specifications.

[0088] Nuclear system design specifications include industry standards, project requirements, etc. The standard checking unit automatically checks whether the design of the 3D model meets the relevant specifications, such as size, tolerance, material, etc.

[0089] The model verification module also includes a simulation test unit, which is used to import the three-dimensional model of the nuclear system into relevant simulation software for transport / burnup / activation calculations.

[0090] When the modeling specifications are not met, or the nuclear system design specifications are not met, or the simulation results cannot meet expectations, you can return to the model optimization editing module to make modifications and adjustments.

[0091] Optionally, in an embodiment, the method further includes:

[0092] The model export module is used to export the three-dimensional model of the nuclear system to be modeled into a nuclear system three-dimensional model file in a preset format.

[0093] The model export module can output the final generated 3D model of the nuclear system in a standardized file format (such as FDS format, STEP format, STL format or OBJ format). Users can choose the export format of the model according to actual needs, so that it can be used for subsequent engineering simulation, manufacturing or virtual reality display, etc.

[0094] In summary, the present invention integrates BERT and DreamFusion models to realize the automatic generation of three-dimensional models from text descriptions, greatly improving the modeling efficiency. The three-dimensional model is directly generated through natural language description, without the need for complex professional skills and modeling experience, which lowers the threshold for use. In addition, the present invention provides powerful model optimization and editing functions, allowing users to further adjust the model according to specific needs, ensuring that the final model has high accuracy and meets actual design requirements. It should be noted that this system is not only suitable for nuclear system modeling, but can also be extended to the design and modeling of other complex industrial systems.

[0095] Embodiment 2

[0096] like Figure 2 As shown, this embodiment provides an interactive nuclear system automatic modeling method, including:

[0097] Obtain text information describing the nuclear system to be modeled;

[0098] Performing semantic analysis on the text information to generate model data, wherein the model data is data describing components constituting the core system to be modeled, relationships between the components, and design parameters of the components;

[0099] generating a three-dimensional model of the nuclear system to be modeled according to the model data;

[0100] The modification information sent by the user is obtained, and the three-dimensional model of the nuclear system to be modeled is adjusted based on the modification information.

[0101] Optionally, in an embodiment, the model data includes functional component data, structural feature data and design parameter data, and the semantic analysis of the text information to generate the model data includes:

[0102] Performing contextual understanding on the text information to generate the functional component data; the functional component data represents data in the text information for describing the components constituting the core system to be modeled and the relationship between the components;

[0103] The structural feature data is generated based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph for describing components constituting the nuclear system to be modeled and the relationship between the components;

[0104] The design parameter data is generated according to the text information, wherein the design parameter data represents data in the text information for describing design parameters of various components constituting the nuclear system to be modeled.

[0105] Optionally, in an embodiment, generating the three-dimensional model of the nuclear system to be modeled according to the model data includes:

[0106] Mapping the model data into the latent space of the trained DreamFusion model;

[0107] Based on DreamFusion technology, generating an initial three-dimensional model of the nuclear system to be modeled in the latent space;

[0108] Based on DreamFusion technology, the initial three-dimensional model of the core system to be modeled is optimized to generate a three-dimensional model of the core system to be modeled.

[0109] Optionally, in an embodiment, the acquiring modification information sent by the user and adjusting the three-dimensional model of the nuclear system to be modeled based on the modification information includes:

[0110] Reading the three-dimensional model of the nuclear system to be modeled;

[0111] Acquire modification information sent by the user, and perform natural language processing on the modification information through a large language model to generate modification instructions;

[0112] According to the modification instruction, the model editing software is controlled to modify the three-dimensional model of the nuclear system to be modeled.

[0113] Optionally, in an embodiment, the method further comprises: verifying the three-dimensional model of the nuclear system to be modeled.

[0114] Optionally, in an embodiment, the verifying the three-dimensional model of the nuclear system to be modeled includes:

[0115] Checking whether the three-dimensional model of the nuclear system to be modeled complies with the modeling specification;

[0116] Check whether the three-dimensional model of the nuclear system to be modeled meets the nuclear system design specifications.

[0117] Optionally, in an embodiment, the method further includes: exporting the three-dimensional model of the nuclear system to be modeled into a nuclear system three-dimensional model file in a preset format.

[0118] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0119] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An interactive nuclear system automatic modeling system, characterized in that: include: A text input module is used to obtain text information describing the nuclear system to be modeled; A natural language processing module, used for performing semantic analysis on the text information to generate model data, wherein the model data is data describing the components constituting the core system to be modeled, the relationship between the components, and the design parameters of the components; A model generation module, used for generating a three-dimensional model of the nuclear system to be modeled according to the model data; The model optimization and editing module is used to obtain the modification information sent by the user and adjust the three-dimensional model of the nuclear system to be modeled based on the modification information.

2. The interactive nuclear system automatic modeling system according to claim 1, characterized in that: The model data includes functional component data, structural feature data and design parameter data, and the natural language processing module includes: A context understanding unit, used for understanding the context of the text information and generating the functional component data; the functional component data represents data in the text information for describing the components constituting the core system to be modeled and the relationship between the components; A semantic mapping unit, used to generate the structural feature data based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph for describing the components constituting the nuclear system to be modeled and the relationship between the components; A parameter extraction unit is used to generate the design parameter data according to the text information, wherein the design parameter data is represented in the text information and is used to describe the data of the design parameters of each component constituting the nuclear system to be modeled.

3. The interactive nuclear system automatic modeling system according to claim 1, characterized in that: The model generation module includes: A latent space representation unit, used for mapping the model data into the latent space of the trained DreamFusion model; A three-dimensional model generating unit, used for generating an initial three-dimensional model of the core system to be modeled in the latent space based on DreamFusion technology; The model optimization unit is used to optimize the initial three-dimensional model of the core system to be modeled based on the DreamFusion technology to generate a three-dimensional model of the core system to be modeled.

4. The interactive nuclear system automatic modeling system according to claim 1, characterized in that: The model optimization editing module includes: A model reading and parsing unit, used for reading the three-dimensional model of the nuclear system to be modeled; A modification instruction generating unit, used for acquiring modification information sent by a user, and performing natural language processing on the modification information through a large language model to generate a modification instruction; The instruction execution unit is used to control the model editing software to modify the three-dimensional model of the nuclear system to be modeled according to the modification instruction.

5. The interactive nuclear system automatic modeling system according to claim 1, characterized in that: It also includes a model verification module, which is used to verify the three-dimensional model of the nuclear system to be modeled.

6. The interactive nuclear system automatic modeling system according to claim 5, characterized in that: The model verification module includes: An automatic verification unit, used to check whether the three-dimensional model of the nuclear system to be modeled complies with the modeling specification; The standard checking unit is used to check whether the three-dimensional model of the nuclear system to be modeled complies with the nuclear system design specifications.

7. The interactive nuclear system automatic modeling system according to claim 1, characterized in that: Also includes: The model export module is used to export the three-dimensional model of the nuclear system to be modeled into a nuclear system three-dimensional model file in a preset format.

8. An interactive nuclear system automatic modeling method, characterized in that: include: Obtain text information describing the nuclear system to be modeled; Performing semantic analysis on the text information to generate model data, wherein the model data is data describing components constituting the core system to be modeled, relationships between the components, and design parameters of the components; generating a three-dimensional model of the nuclear system to be modeled according to the model data; The modification information sent by the user is obtained, and the three-dimensional model of the nuclear system to be modeled is adjusted based on the modification information.

9. The interactive nuclear system automatic modeling method according to claim 8, characterized in that: The model data includes functional component data, structural feature data and design parameter data, and the semantic analysis of the text information to generate the model data includes: Performing contextual understanding on the text information to generate the functional component data; the functional component data represents data in the text information for describing the components constituting the core system to be modeled and the relationship between the components; The structural feature data is generated based on the text information and a preset nuclear system knowledge graph; the structural feature data represents data in the nuclear system knowledge graph for describing components constituting the nuclear system to be modeled and the relationship between the components; The design parameter data is generated according to the text information, wherein the design parameter data represents data in the text information for describing design parameters of various components constituting the nuclear system to be modeled.

10. The interactive nuclear system automatic modeling system according to claim 8, characterized in that: The step of generating a three-dimensional model of the nuclear system to be modeled according to the model data comprises: Mapping the model data into the latent space of the trained DreamFusion model; Based on DreamFusion technology, generating an initial three-dimensional model of the core system to be modeled in the latent space; Based on DreamFusion technology, the initial three-dimensional model of the core system to be modeled is optimized to generate a three-dimensional model of the core system to be modeled.

Images