Nuclear system model optimization method and system, control device and storage medium
By obtaining the feature embeddings of the kernel system model and using optimization algorithms and natural language processing, the kernel system model is automatically optimized, and the problem of efficiency dependence on manual experience in the existing technology is solved, and efficient and flexible model optimization and file compatibility are achieved.
Patent Information
- Application Number
- CN202510364108.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2025-03-21
- Filing Date
- 2025-03-26
- Publication Date
- 2025-07-08
AI Technical Summary
The efficiency of the prior art in the process of optimizing nuclear system model design depends on designer experience, is prone to errors and lacks flexibility, making it difficult to achieve rapid iteration.
By obtaining the feature embeddings of the kernel system model to be optimized, using preset optimization algorithms and natural language processing models, an optimization instruction sequence is generated, and the model is automatically modified to meet the design requirements.
Automatic optimization of the nuclear system model is realized, design efficiency and accuracy are improved, and the flexibility and controllability of model optimization are enhanced, ensuring the compatibility and availability of model files in the engineering process.
Smart Images
Figure CN120278019A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and specifically provides a method, system, control device, and storage medium for optimizing a nuclear system model. Background Art
[0002] In the process of nuclear system design and optimization, in order to improve design efficiency and calculation accuracy, it is usually necessary to continuously optimize and modify the nuclear system model to meet the design goals. In the industry, to solve the efficiency problem in the design and optimization process of the nuclear system model, the conventional method is usually to directly manually modify the model by professional designers using computer-aided design software, and perform particle transport calculations based on the modified model. Although this method can meet certain optimization requirements, its efficiency is severely dependent on the experience of the designers, and it is prone to errors in complex optimization scenarios and difficult to achieve rapid iteration. Or, by pre-writing model generation rules and using parametric design means to achieve partial automatic modification of the model, this method can improve the efficiency to a certain extent, but due to the limitations of the rules, when the matters to be optimized exceed the scope of the predefined rules, the model cannot be automatically updated and requires manual intervention, lacking flexibility.
[0003] Correspondingly, there is a need in this field for a new solution for a method, system, control device, and storage medium for optimizing a nuclear system model to solve the above problems. Summary of the Invention
[0004] To overcome at least one of the above defects, this application is proposed to provide a method, system, control device, and storage medium for optimizing a nuclear system model that solves or at least partially solves the technical problem that the nuclear system model cannot achieve automatic optimization.
[0005] In a first aspect, this application provides a method for optimizing a nuclear system model, the method comprising:
[0006] Obtaining the feature embedding amount of the nuclear system model to be optimized;
[0007] Based on a preset optimization algorithm, obtaining the result to be optimized of the nuclear system model to be optimized;
[0008] Parsing the result to be optimized to obtain an optimization instruction sequence;
[0009] Based on the optimization instruction sequence, modifying the feature embedding amount to obtain an optimized nuclear system model.
[0010] In a technical solution of the above method for optimizing a nuclear system model, the obtaining the feature embedding amount of the nuclear system model to be optimized comprises:
[0011] Obtain the data file of the nuclear system model to be optimized, where the data file is used to characterize the geometric features and attribute information of the nuclear system model to be optimized;
[0012] Based on a preset feature extraction network and the data file, obtain the feature embedding of the nuclear system model to be optimized.
[0013] In a technical solution of the above nuclear system model optimization method, before obtaining the feature embedding of the nuclear system model to be optimized, the method further includes:
[0014] Obtain the natural language text and the data file of the preset initial nuclear system model;
[0015] Based on a preset natural language processing model, convert the natural language text into a text embedding;
[0016] Based on a preset feature extraction network and the data file, obtain the feature embedding of the initial nuclear system model;
[0017] Based on the text embedding, modify the feature embedding to obtain the nuclear system model to be optimized.
[0018] In a technical solution of the above nuclear system model optimization method, the modifying the initial nuclear system model based on the text embedding and the feature embedding to obtain the nuclear system model to be optimized includes:
[0019] Align the text embedding with the feature embedding based on a preset first rule;
[0020] Based on the alignment result, determine the modification parameter and the feature embedding to be modified;
[0021] Based on the modification parameter, modify the feature embedding to be modified to obtain the nuclear system model to be optimized.
[0022] In a technical solution of the above nuclear system model optimization method, the modifying the feature embedding to obtain the nuclear system model to be optimized based on the text embedding includes: obtaining the target file of the nuclear system model in the target format based on a preset second rule and the modified feature embedding.
[0023] In a technical solution of the above nuclear system model optimization method, the modifying the feature embedding based on the optimization instruction sequence to obtain the optimized nuclear system model includes: obtaining the target file of the nuclear system model in the target format based on a preset third rule and the modified feature embedding.
[0024] In one technical solution of the above nuclear system model optimization method, the method further includes:
[0025] Based on a preset fourth rule, determine whether the optimized nuclear system model meets the preset requirements;
[0026] If not,
[0027] Re-obtain the feature embedding of the optimized nuclear system model;
[0028] Re-obtain the optimization result of the nuclear system model to be optimized based on the preset optimization algorithm;
[0029] Re-execute the step of modifying the feature embedding until the finally obtained optimized nuclear system model meets the preset requirements.
[0030] In a second aspect, the present application provides a nuclear system model optimization system, including:
[0031] An acquisition module, configured to acquire the feature embedding of the nuclear system model to be optimized;
[0032] An analysis module, configured to obtain the optimization result of the nuclear system model to be optimized based on a preset optimization algorithm; parse the optimization result to obtain an optimization instruction sequence;
[0033] A processing module, configured to modify the feature embedding based on the optimization instruction sequence to obtain an optimized nuclear system model.
[0034] In a third aspect, a control device is provided, which includes a processor and a storage device. The storage device is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the nuclear system model optimization method described in any one of the technical solutions of the above nuclear system model optimization method.
[0035] In a fourth aspect, a computer-readable storage medium is provided, which stores multiple program codes, and the program codes are adapted to be loaded and run by a processor to execute the nuclear system model optimization method described in any one of the technical solutions of the above nuclear system model optimization method.
[0036] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:
[0037] In implementing the technical solution of this application, based on a preset optimization algorithm, an optimization result of the nuclear system model to be optimized is obtained. After parsing the optimization result into an optimization instruction sequence, the feature embedding amount of the nuclear system model to be optimized is modified based on the optimization instruction sequence, and an optimized nuclear system model is obtained. Through this application, the optimization result output by the optimization algorithm is parsed into a model modification instruction indicating the corresponding parameters to be optimized, realizing the automatic optimization of the nuclear system model, improving the optimization efficiency while ensuring the optimization effect.
[0038] Further, in implementing the technical solution of this application, the feature embedding amount of the nuclear system model to be optimized is extracted, and the complex geometric features and attribute information of the nuclear system model are converted into a structured representation form, which can provide a structured basis for model modification, so as to clearly confirm the existing state of the nuclear system model to be optimized and provide accurate basic data for subsequent optimization.
[0039] Further, in implementing the technical solution of this application, the initial nuclear system model is pre-modified using the input natural language to obtain the aforementioned nuclear system model to be optimized. Through the input natural language from the outside world, preliminary rapid adjustment can be achieved by combining historical experience, providing a reasonable starting point for the subsequent optimization algorithm. Moreover, by combining the input natural language from the outside world, the flexibility and controllability of the model optimization process are enhanced.
[0040] Further, in implementing the technical solution of this application, the natural language text is converted into a text embedding amount to unify the semantic expression, so as to ensure that diverse or ambiguous natural languages can be accurately understood. The text embedding amount is aligned with the feature embedding amount to determine the modification intention and the feature embedding amount to be modified, thereby enhancing the pertinence of the modification and improving the modification accuracy.
[0041] Further, in implementing the technical solution of this application, after modifying the corresponding feature embedding amount, a target file of the nuclear system model in a target format is generated based on a preset rule. Through this application, a file in a unified format for representing the nuclear system model is obtained, which is convenient for adapting to personalized requirements in different engineering stages, different design fields, etc., and ensuring the compatibility and usability of the description file of the nuclear system model in the engineering process.
[0042] Further, in implementing the technical solution of this application, if the optimized nuclear system model does not meet the preset requirements, the optimization process is re-executed until the preset requirements are met. Through this application, when the optimized nuclear system model does not meet the requirements, the optimization steps are automatically re-executed, which can ensure that the finally obtained nuclear system model meets the preset requirements. Brief Description of the Drawings
[0043] Referring to the accompanying drawings, the disclosure of the present application will become more readily understandable. It is easily understood by those skilled in the art that these drawings are only for illustrative purposes and are not intended to limit the protection scope of the present application. In addition, similar numbers in the drawings are used to represent similar components, where:
[0044] Figure 1 is a schematic diagram of the main step process of the nuclear system model optimization method according to an embodiment of the present application;
[0045] Figure 2 is a schematic diagram of the main step process of obtaining the nuclear system model to be optimized according to an embodiment of the present application;
[0046] Figure 3 is a schematic diagram of the main step process of obtaining the nuclear system model to be optimized according to an embodiment of the present application;
[0047] Figure 4 is a schematic diagram of the logical structure framework of the nuclear system model optimization method according to an embodiment of the present application;
[0048] Figure 5 is a schematic diagram of the main step program process of the nuclear system model optimization method according to an embodiment of the present application;
[0049] Figure 6 is a schematic diagram of the main structural block diagram of the nuclear system model optimization system according to an embodiment of the present application.
[0050] List of reference numerals:
[0051] 11: Acquisition module; 12: Analysis module; 13: Processing module. Detailed implementation manners
[0052] The following describes some implementation manners of the present application with reference to the accompanying drawings. It should be understood by those skilled in the art that these implementation manners are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.
[0053] In the description of this application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, memory, and may also include a software part, such as program code, or may be a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor can be implemented in software, in hardware, or in a combination of both. A non-transitory computer-readable storage medium includes any suitable medium that can store program code, such as magnetic disks, hard disks, optical discs, flash memories, read-only memories, random access memories, and so on. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one of A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" and "the" may also include the plural form.
[0054] Please refer to the attached Figure 1 , Figure 1 which is a schematic diagram of the main steps of the nuclear system model optimization method according to an embodiment of this application. As Figure 1 shown, the nuclear system model optimization method of this application mainly includes steps S1 - S4:
[0055] Step S1, obtain the feature embedding of the nuclear system model to be optimized;
[0056] Step S2, based on a preset optimization algorithm, obtain the result to be optimized of the nuclear system model to be optimized;
[0057] Step S3, parse the result to be optimized to obtain an optimization instruction sequence;
[0058] Step S4, based on the optimization instruction sequence, modify the feature embedding to obtain an optimized nuclear system model.
[0059] In this embodiment, a pre-trained model, neural network, etc. can be used to extract and encode the geometric features (such as shape, topology, size, etc.) and attribute information (such as material properties) of the nuclear system model to be optimized, so as to obtain feature embeddings in vector form suitable for computer processing and analysis. These feature embeddings contain the key feature data of the model.
[0060] In this embodiment, the preset optimization algorithm is used to determine the best parameter combination that can make the nuclear system meet the requirements, including but not limited to genetic algorithms, particle swarm optimization algorithms, etc. For example, the geometric dimensions, material properties, etc. of the fuel assemblies in the nuclear system can be used as gene coding, and through operations such as selection, crossover, and mutation, continuous iteration is carried out. After multiple generations of evolution, a parameter combination that optimizes the neutron multiplication factor and maximizes the energy output efficiency is found. A pre-trained model containing the preset optimization algorithm can also be used, with the feature embedding of the nuclear system model to be optimized as the input and the output being the result to be optimized. The specific implementation method is not limited in this embodiment. The final result to be optimized can be specific modification suggestions for the size of a certain component or the material property of a certain component in the nuclear system. For example, it is recommended that the length of the fuel rod be changed from the original 10 cm to 12 cm, or, it is recommended that the area of the absorption cross-section be changed from the original 0.5 cm 2 to 0.7 cm 2 .
[0061] In this embodiment, the instruction sequence is a set of instructions indicating how to specifically modify the model, and the instruction sequence can execute each instruction in the set order. The result to be optimized can be used as the input, and a pre-trained parsing model such as the BERT model or the Transformer model can be used to output the parsed instruction sequence. Among them, when training the parsing model, the training samples can include a large number of results to be optimized output by the optimization algorithm and their corresponding instruction sequences. Or, a pre-trained model parsing network such as sequence-to-sequence (Seq2Seq) can also be used to parse the result to be optimized. The specific implementation method is not limited in this embodiment.
[0062] In this embodiment, a pre-trained modification model can be used, with the optimized instruction sequence and feature embedding as the input, and the optimized nuclear system model is output. Or, according to the optimized instruction sequence, the parameters of the feature embedding to be modified are directly modified to the target parameters, and finally the optimized nuclear system model is obtained based on the modified feature embedding.
[0063] In one embodiment, step S1 may include the following steps S11 - step S12:
[0064] Step S11, obtain the data file of the nuclear system model to be optimized, where the data file is used to characterize the geometric features and attribute information of the nuclear system model to be optimized;
[0065] Step S12, based on the preset feature extraction network and the data file, obtain the feature embedding of the nuclear system model to be optimized.
[0066] In this embodiment, the data file of the nuclear system model to be optimized is the file containing the nuclear system model to be optimized, such as the CAD file, point cloud, edge-face connection relationship diagram, B-rep structure, etc. of the nuclear system model, which is used to characterize the geometric features and attribute information of the initial nuclear system model.
[0067] In this embodiment, a geometric feature extraction network based on a Graph Neural Network (GNN) or PointNet++ can be used to extract the feature embedding in the data file to represent the geometric and topological features of the nuclear system model.
[0068] Please refer to the appendix Figure 2 , Figure 2 which is a schematic diagram of the main steps for obtaining the nuclear system model to be optimized according to an embodiment of the present application. As Figure 2 shown, before performing the steps of the embodiment shown in Figure 1 , the nuclear system model to be optimized of the present application is obtained based on at least the following steps:
[0069] Step S01: Obtain the natural language text and the data file of the preset initial nuclear system model;
[0070] Step S02: Based on the preset natural language processing model, convert the natural language text into a text embedding;
[0071] Step S03: Based on the preset feature extraction network and the data file, obtain the feature embedding of the initial nuclear system model;
[0072] Step S04: Based on the text embedding, modify the feature embedding to obtain the nuclear system model to be optimized.
[0073] In this embodiment, the natural language text is generally an expression in the form of human natural language input or transmitted from the outside, such as "the length of the fuel rod is increased by 2 cm", which is used to characterize the modification intention of the initial nuclear system model. The data file is the file containing the initial nuclear system model, such as the CAD file, point cloud, edge-face connection relationship diagram, B-rep structure, etc. of the nuclear system model, which is used to characterize the geometric features and attribute information of the initial nuclear system model.
[0074] In this embodiment, the preset natural language processing model may include, but is not limited to, the BERT model, T5 model, ELMo model, etc. Using the natural language processing model, the natural language is converted into a text embedding that can be recognized by a computer and can represent the semantics of the natural language text.
[0075] In this embodiment, a geometric feature extraction network based on a Graph Neural Network (GNN) or PointNet++ can be used to extract the feature embedding in the data file to represent the geometric and topological features of the nuclear system model.
[0076] In this embodiment, a pre-trained modification model can be utilized, taking the text embedding and the feature embedding as inputs, and outputting the to-be-optimized nuclear system model. Alternatively, according to the modification intention characterized by the text embedding, the parameters of the feature embedding to be modified are directly modified to the target parameters, and finally, the to-be-optimized nuclear system model is obtained based on the modified feature embedding.
[0077] In one embodiment, please refer to the attached Figure 2 to the attached Figure 4 , Figure 3 which is a schematic diagram of the main steps for obtaining the to-be-optimized nuclear system model according to an embodiment of the present application, Figure 4 and is a schematic diagram of the logical structure framework of the nuclear system model optimization method according to an embodiment of the present application. As Figure 3 shown, step S04 of the present application may further include:
[0078] Step S041: Align the text embedding and the feature embedding based on a preset first rule;
[0079] Step S042: Determine the modification parameters and the feature embedding to be modified based on the alignment result;
[0080] Step S043: Modify the feature embedding to be modified based on the modification parameters to obtain the to-be-optimized nuclear system model.
[0081] In this embodiment, a cross-modal attention mechanism for multi-modal alignment (such as Transformer) can be used to implement the alignment operation of the text embedding and the feature embedding. Also, machine learning methods such as linear regression or principal component analysis (PCA) can be used to perform dimensionality reduction on the high-dimensional text embedding and feature embedding, and find the corresponding relationship between the two in the low-dimensional space to achieve semantic alignment.
[0082] In this embodiment, based on the alignment result, the feature embedding aligned with the text embedding is recorded as the feature embedding to be modified, and the modification parameters (i.e., the expected modification effect) are determined according to the semantics characterized by the text embedding.
[0083] In this embodiment, a conditional generative adversarial network (Conditional GAN) or a diffusion model can be utilized to implement an operation for modifying the feature embedding quantity to be modified, so as to obtain an updated feature embedding quantity, and finally, an optimized kernel system model can be obtained according to the updated feature embedding quantity.
[0084] In one embodiment, based on a preset rule and the modified feature embedding quantity, a target file of the kernel system model in a target format is obtained. By performing reverse decoding on the modified feature embedding quantity, CAD files, point clouds, edge-face connection relation diagrams, B-rep structures, etc. of the kernel system model are obtained, and corresponding decoders are used according to the actual application scenario, so as to obtain a target file of the kernel system model that meets the file type requirements.
[0085] In one embodiment, the method for optimizing the kernel system model of the present application may further include:
[0086] Step S5: Based on a preset fourth rule, determine whether the optimized kernel system model meets the preset requirements;
[0087] Step S6: If not, re-obtain the feature embedding quantity of the optimized kernel system model; re-obtain the to-be-optimized result of the to-be-optimized kernel system model based on a preset optimization algorithm; re-execute the step of modifying the feature embedding quantity until the finally obtained optimized kernel system model meets the preset requirements.
[0088] In this embodiment, it is first necessary to verify and evaluate whether the optimized kernel system model meets the optimization goal. For example, the updated model is imported into particle transport simulation software (such as MCNP, OpenMC) to perform complete physical simulation calculations, so as to evaluate the performance of the updated model. If the optimization goal is not met, the to-be-optimized kernel system model is updated to the optimized kernel system model obtained in this optimization, and the corresponding optimization steps in the Figure 1 illustrated embodiment are re-executed.
[0089] Please refer to Figure 1 to Figure 5 , Figure 5 which is a schematic diagram of the main step procedure of the method for optimizing the kernel system model according to an embodiment of the present application. The method for optimizing the kernel system model of the present application can be summarized as:
[0090] Manually input natural language text containing a preliminary modification intention;
[0091] Process the natural language text; modify the feature embedding quantity of the initial kernel system model based on the text embedding quantity obtained after processing to obtain a to-be-optimized kernel system model;
[0092] Extract the feature embedding amount of the nuclear system model to be optimized; run an optimization algorithm for the feature embedding amount of the nuclear system model to be optimized, so as to obtain the result to be optimized of the nuclear system model to be optimized;
[0093] Analyze the result to be optimized to obtain an optimization instruction sequence;
[0094] Modify the feature embedding amount of the nuclear system model to be optimized based on the optimization instruction sequence to obtain an optimized nuclear system model;
[0095] Determine whether the optimized nuclear system model reaches the optimization goal. If so, decode to obtain a model file in the corresponding format based on the modified feature embedding amount; if not, replace the feature embedding amount of the nuclear system model to be optimized with the feature embedding amount of the nuclear system model optimized this time, and re-run the optimization algorithm, so as to iteratively execute the optimization process until the optimized nuclear system model reaches the optimization goal.
[0096] So far, all the steps of the nuclear system model optimization method of the present application have been described. It should be noted that although the above embodiments describe the various steps in a specific order, those skilled in the art can understand that in order to achieve the effects of the present application, it is not necessary for different steps to be executed in such an order, and they can be executed simultaneously (in parallel) or in other orders, and these changes are all within the protection scope of the present application.
[0097] Furthermore, the present application also provides a nuclear system model optimization system.
[0098] Refer to the attached Figure 6 , Figure 6 which is the main structural block diagram of the nuclear system model optimization system according to an embodiment of the present application. As Figure 6As shown in the figure, the nuclear system model optimization system in the embodiments of the present application mainly includes an acquisition module 11, an analysis module 12, and a processing module 13. In some embodiments, one or more of the acquisition module 11, the analysis module 12, and the processing module 13 may be combined into one module. In some embodiments, the acquisition module 11 may be configured to acquire the feature embedding of the nuclear system model to be optimized. The analysis module 12 may be configured to obtain the result to be optimized of the nuclear system model to be optimized based on a preset optimization algorithm; parse the result to be optimized to obtain an optimization instruction sequence. The processing module 13 may be configured to modify the feature embedding based on the optimization instruction sequence to obtain an optimized nuclear system model. In one embodiment, the description of the specific functions implemented by the acquisition module 11 may be referred to in step S1. In one embodiment, the description of the specific functions implemented by the analysis module 12 may be referred to in steps S2 - S3. In one embodiment, the description of the specific functions implemented by the processing module 13 may be referred to in step S4. In one embodiment, the acquisition module 11 may also be configured to acquire a natural language text and a data file of a preset initial nuclear system model; convert the natural language text into a text embedding based on a preset natural language processing model; obtain the feature embedding of the initial nuclear system model based on a preset feature extraction network and the data file, and the processing module 13 may also be configured to modify the feature embedding based on the text embedding to obtain the nuclear system model to be optimized. In one embodiment, the analysis module 12 may also be configured to determine whether the optimized nuclear system model meets the preset requirements based on a preset fourth rule.
[0099] The above nuclear system model optimization system is used to execute Figure 1 the embodiments of the nuclear system model optimization method shown in the figure. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art of the present technology can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the nuclear system model optimization system can refer to the content described in the embodiments of the nuclear system model optimization method, which will not be elaborated here.
[0100] Those skilled in the art can understand that all or part of the processes in the method of the above-mentioned embodiment of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc., that can carry the computer program code.
[0101] Furthermore, the present application also provides a control device. In an embodiment of the control device according to the present application, the control device includes a processor and a storage device. The storage device can be configured to store a program for implementing the core system model optimization method of the above-mentioned method embodiment. The processor can be configured to execute the program in the storage device, and the program includes, but is not limited to, the program for implementing the core system model optimization method of the above-mentioned method embodiment. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The control device can be a control device formed by various electronic devices.
[0102] Furthermore, the present application also provides a computer-readable storage medium. In an embodiment of the computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for implementing the core system model optimization method of the above-mentioned method embodiment. The program can be loaded and run by a processor to implement the above-mentioned core system model optimization method. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.
[0103] Furthermore, it should be understood that since the setting of each module is only for explaining the functional units of the device of the present application, the corresponding physical devices of these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only illustrative.
[0104] Those skilled in the art can understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principle of this application. Therefore, the technical solutions after splitting or combining will all fall within the protection scope of this application.
[0105] So far, the technical solution of this application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, those skilled in the art can easily understand that the protection scope of this application is obviously not limited to these specific embodiments. Without departing from the principle of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of this application.
Claims
1. A method for optimizing a nuclear system model, characterized in that, The method includes: Obtaining the feature embedding of the nuclear system model to be optimized; Based on a preset optimization algorithm, obtaining the result to be optimized of the nuclear system model to be optimized; Analyzing the result to be optimized to obtain an optimization instruction sequence; Based on the optimization instruction sequence, modifying the feature embedding to obtain an optimized nuclear system model.
2. The nuclear system model optimization method according to claim 1, wherein The obtaining the feature embedding of the nuclear system model to be optimized includes: Obtaining the data file of the nuclear system model to be optimized, where the data file is used to characterize the geometric features and attribute information of the nuclear system model to be optimized; Based on a preset feature extraction network and the data file, obtaining the feature embedding of the nuclear system model to be optimized.
3. The method for optimizing a nuclear system model according to claim 1, wherein Before obtaining the feature embedding of the nuclear system model to be optimized, the method further includes: Obtaining a natural language text and the data file of a preset initial nuclear system model; Based on a preset natural language processing model, converting the natural language text into a text embedding; Based on a preset feature extraction network and the data file, obtaining the feature embedding of the initial nuclear system model; Based on the text embedding, modifying the feature embedding to obtain the nuclear system model to be optimized.
4. The method for optimizing a nuclear system model according to claim 3, wherein The modifying the initial nuclear system model based on the text embedding and the feature embedding to obtain the nuclear system model to be optimized includes: Based on a preset first rule, aligning the text embedding with the feature embedding; Based on the alignment result, determining a modification parameter and the feature embedding to be modified; Based on the modification parameter, modifying the feature embedding to be modified to obtain the nuclear system model to be optimized.
5. The method for optimizing a nuclear system model according to claim 3, wherein The modifying the feature embedding based on the text embedding to obtain the nuclear system model to be optimized includes: Based on a preset second rule and the modified feature embedding, obtaining a target file of the nuclear system model in a target format.
6. The method for optimizing a nuclear system model according to claim 1, wherein The modifying the feature embedding based on the optimization instruction sequence to obtain an optimized nuclear system model includes: Based on a preset third rule and the modified feature embedding, obtaining a target file of the nuclear system model in a target format.
7. The method for optimizing the nuclear system model according to claim 1, characterized in that The method further includes: Based on a preset fourth rule, determining whether the optimized nuclear system model meets a preset requirement; If not, Re-obtaining the feature embedding of the optimized nuclear system model; Re-based on a preset optimization algorithm, obtaining the result to be optimized of the nuclear system model to be optimized; Re-executing the step of modifying the feature embedding until the finally obtained optimized nuclear system model meets the preset requirement.
8. A nuclear system model optimization system, characterized in that, Includes: An obtaining module configured to obtain the feature embedding of the nuclear system model to be optimized; An analyzing module configured to obtain the result to be optimized of the nuclear system model to be optimized based on a preset optimization algorithm; Analyzing the result to be optimized to obtain an optimization instruction sequence; A processing module configured to modify the feature embedding based on the optimization instruction sequence to obtain an optimized nuclear system model.
9. A control device, comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to execute the nuclear system model optimization method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing multiple program codes, characterized in that, The program code is adapted to be loaded and run by a processor to execute the nuclear system model optimization method according to any one of claims 1 to 7.