Finite element model automatic modeling method and system

Abstract

The invention relates to an automatic modeling method and system for a finite element model. The method comprises the following steps of 1, extracting modeling information in a to-be-modeled text; 2, the extracted modeling information is corrected; 3, the corrected modeling information is converted into finite element model codes; and 4, converting the finite element model code into a visual model. According to the method, the text can be directly converted into the finite element model code, and a series of problems of tedious finite element modeling steps, high difficulty in operation, complex software installation and the like are solved, so that rapid finite element automatic modeling and analysis are realized; and the method is finally displayed in the form of a visual model, the interactive interface is friendly, and the model effect can be more intuitively checked.

Description

Technical Field

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

[0002] In recent years, big data technology and artificial intelligence technology have developed rapidly in the fields of finance, Internet, biomedicine, etc. As a traditional industry, the construction industry also has a large number of tasks that can be solved using big data technology and artificial intelligence technology.

[0003] At present, there are a large number of non-standard components and temporary structures in the implementation of construction projects. When verifying such structures, it is impossible to use conventional standard formulas or empirical formulas for simple verification, and finite element software is often required for modeling and analysis. However, the modeling process of traditional finite element software is complicated and difficult to use, and it cannot meet the on-site needs of rapid modeling and rapid verification. Summary of the invention

[0004] The present invention provides a finite element model automatic modeling method and system to solve the above technical problems.

[0005] In order to solve the above technical problems, the present invention provides a finite element model automatic modeling method, comprising the following steps: Step 1: Extract modeling information from the text to be modeled; Step 2: Correct the extracted modeling information; Step 3: Convert the corrected modeling information into finite element model code; Step 4: Convert the finite element model code into a visual model.

[0006] Preferably, in step 1, the extracted modeling information includes at least geometric information, unit information, load information, boundary condition information and constitutive information.

[0007] Preferably, in step 2, the extracted geometric information, unit information, load information, boundary condition information and constitutive information are compared and verified with the pre-established geometric library, unit library, load library, boundary condition library and constitutive library respectively.

[0008] Preferably, the modeling information is extracted based on a parameterized modeling large language model.

[0009] Preferably, step 3 also includes: pre-building a corresponding database for storing the corresponding relationship between modeling information and finite element model codes, and optimizing the parameterized modeling large language model using the corresponding database.

[0010] Preferably, in step 4, the visual model includes each component, node, constraint and corresponding information thereof.

[0011] The present invention also provides a finite element model automatic modeling system, including a modeling information extraction system, a key information verification system and a parameterized modeling system. The modeling information extraction system is used to extract modeling information from the text to be modeled; The key information verification system is used to correct the extracted modeling information; The parametric modeling system is used to convert modeling information into finite element model codes.

[0012] Preferably, a first server is used to deploy the modeling information extraction system, a second server is used to deploy the parametric modeling system, a third server is used to deploy the key information verification system, a terminal is used to input the text to be modeled and output a visual model converted from the finite element model code, and the terminal, the first server, the second server and the third server are connected via a network.

[0013] Preferably, the modeling information extraction system includes a geometric information extraction module for extracting geometric information, a unit information extraction module for extracting unit information, a load information extraction module for extracting load information, a boundary condition information extraction module for extracting boundary condition information, and a constitutive information extraction module for extracting constitutive information.

[0014] Preferably, the modeling information extraction system extracts the modeling information based on a parameterized modeling large language model.

[0015] Compared with the prior art, the finite element model automatic modeling method and system provided by the present invention have the following advantages: 1. The present invention can directly convert text into finite element model code, solving a series of problems such as cumbersome finite element modeling steps, difficult operation, and complex software installation, thereby realizing rapid finite element automated modeling and analysis; 2. The present invention is finally displayed in the form of a visual model with a friendly interactive interface. Attributes can be assigned to various components, nodes, constraints, etc. in the visual interface, so as to check the model effect more intuitively; 3. The present invention can accurately correct the possible deviations in the information extraction process of the parameterized modeling large language model through the key information verification system, thereby improving the modeling accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process framework of a finite element model automatic modeling method in a specific implementation manner of the present invention; Figure 2 It is a structural schematic diagram of a finite element model automatic modeling system in a specific implementation manner of the present invention.

[0017] In the figure: 110 - first server, 120 - second server, 130 - third server, 140 - terminal. DETAILED DESCRIPTION

[0018] In order to describe the technical solution of the above invention in more detail, specific embodiments are listed below to demonstrate the technical effects; it should be emphasized that these embodiments are used to illustrate the present invention but not to limit the scope of the present invention.

[0019] The finite element model automatic modeling method provided by the present invention is as follows: Figure 1 As shown, the following steps are included: Step 1: Extract modeling information from the text to be modeled; Step 2: Correct the extracted modeling information; Step 3: Convert the corrected modeling information into finite element model code; Step 4: Convert the finite element model code into a visual model.

[0020] The present invention can accurately extract the modeling information in the text to be modeled (i.e., text description), then correct the extracted information, and finally convert the structured information into finite element model code, which is displayed in the form of a visual model to facilitate manual verification and review. The present invention solves a series of problems such as cumbersome finite element modeling steps, difficult operation, and complex software installation, thereby realizing rapid finite element automated modeling and analysis.

[0021] In some embodiments, please refer to Figure 1 ,In step 1, the extracted modeling information includes at least geometric information, unit information, load information, boundary condition information and constitutive information.

[0022] Specifically, the geometric information includes floor information, the number of spans and frames of the building, geometric dimensions of components, etc. The geometric information can be extracted by a geometric information extraction module, and all the extracted geometric information can be stored.

[0023] The unit information includes the number, position, direction, etc. of beams, plates, and columns, and the unit information can be extracted by a unit information extraction module. If there is no unit information in the text to be modeled, it needs to be assigned and stored one by one according to the specification requirements.

[0024] The load information includes the size, location, type, etc. of the load, which can be extracted and stored by the load information extraction module. If no obvious load information is found, it is necessary to further extract the implicit load information in the modeling text, for example, load information in the form of mass, load information replaced by keywords of building use, etc.

[0025] The expression of the boundary condition information is generally more obscure, for example, "this structure is a simply supported beam", where only "simply supported" is related to the boundary condition. Based on the two words "simply supported", it can be inferred that the boundary condition is a supporting structure in which the supports at both ends only provide vertical constraints but no rotational constraints. Similarly, this embodiment uses a boundary condition information extraction module to perform simple reasoning and verification based on the relevant information in the text to be modeled, thereby realizing the extraction and storage of boundary condition information.

[0026] The constitutive information includes the strength grade of concrete, the strength grade of steel bars, etc. The constitutive information can be extracted and stored by a constitutive information extraction module.

[0027] In some embodiments, the above-mentioned geometric information extraction module, unit information extraction module, load information extraction module, boundary condition information extraction module and constitutive information extraction module can all be based on a parameterized modeling large language model (Large Language Model, LLM for short), that is, a deep learning model trained using a large amount of text data to extract the modeling information.

[0028] In some embodiments, in step 2, the extracted geometric information, unit information, load information, boundary condition information and constitutive information are compared and verified with the pre-established geometric library, unit library, load library, boundary condition library and constitutive library respectively to correct the unclear and confusing information and erroneous information and modify them into professional expressions.

[0029] In some embodiments, step 3 further includes: pre-building a corresponding database for storing the corresponding relationship between the modeling information and the finite element model code, and optimizing the parameterized modeling large language model using the corresponding database. Specifically, the corresponding database can be used to fine-tune the parameters of the parameterized modeling large language model to make the generated finite element model code expression more accurate.

[0030] In some embodiments, step 4 may be implemented by a modeling visualization system. Specifically, in step 4, the visualization model includes each component, node, constraint and corresponding information thereof, which is convenient for manual verification and review.

[0031] Please focus on Figure 1 and Figure 2 The present invention also provides a finite element model automatic modeling system, including a modeling information extraction system, a key information verification system and a parameterized modeling system. The modeling information extraction system is used to implement step 1, i.e. extracting modeling information from the text to be modeled; The key information verification system is used to implement step 2, i.e., correct the extracted modeling information; The parametric modeling system is used to implement step 3, that is, to convert the modeling information into finite element model code. Of course, a modeling visualization system can also be included to implement step 4.

[0032] The above system can be used to quickly realize automatic modeling of finite element models.

[0033] In some embodiments, please refer to Figure 2 In this embodiment, the first server 110 is used to deploy the modeling information extraction system, the second server 120 is used to deploy the parametric modeling system, the third server 130 is used to deploy the key information verification system, and the terminal 140 is used to input the text to be modeled and output the visual model converted from the finite element model code. The terminal 140, the first server 110, the second server 120 and the third server 130 are connected through the network to realize the hardware implementation of the system. Of course, the modeling information extraction system, the parametric modeling system and the key information verification system can also be integrated in one server, as long as the above functions can be realized.

[0034] In some embodiments, the modeling information extraction system includes a geometric information extraction module for extracting geometric information, a unit information extraction module for extracting unit information, a load information extraction module for extracting load information, a boundary condition information extraction module for extracting boundary condition information, and a constitutive information extraction module for extracting constitutive information. Specifically, the modeling information extraction system extracts the modeling information based on a parametric modeling large language model, thereby obtaining comprehensive information required for modeling.

[0035] In summary, the present invention provides a method and system for automatic finite element modeling, which comprises the following steps: Step 1: extracting modeling information from the text to be modeled; Step 2: correcting the extracted modeling information; Step 3: converting the corrected modeling information into finite element model code; Step 4: converting the finite element model code into a visual model. The present invention can accurately extract the modeling information from the text to be modeled, then correct the extracted information, and finally convert the structured information into finite element model code, which is displayed in the form of a visual model for manual verification and review. The present invention solves a series of problems such as cumbersome finite element modeling steps, difficulty in getting started, and complex software installation, thereby realizing rapid finite element automatic modeling and analysis.

[0036] Obviously, those skilled in the art can make various changes and modifications to the invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for automatic modeling of a finite element model, characterized in that: The steps include: Step 1: extracting modeling information from the text to be modeled, the extracted modeling information at least includes geometric information, unit information, load information, boundary condition information and constitutive information; Step 2: Correct the extracted modeling information; Step 3: Convert the corrected modeling information into finite element model code; Step 4: Convert the finite element model code into a visual model.

2. The finite element model automatic modeling method according to claim 1, characterized in that: In step 2, the extracted geometric information, unit information, load information, boundary condition information and constitutive information are compared and verified with the pre-established geometric library, unit library, load library, boundary condition library and constitutive library respectively.

3. The automatic finite element modeling method according to claim 1, characterized in that: The modeling information is extracted based on a parameterized modeling large language model.

4. The automatic finite element modeling method according to claim 3, characterized in that: Step 3 also includes: pre-building a corresponding database for storing the corresponding relationship between modeling information and finite element model codes, and optimizing the parameterized modeling large language model using the corresponding database.

5. The automatic finite element modeling method according to claim 1, characterized in that: In step 4, the visual model includes each component, node, constraint and their corresponding information.

6. A finite element model automatic modeling system, characterized in that: Including modeling information extraction system, key information verification system and parametric modeling system, The modeling information extraction system is used to extract modeling information from the text to be modeled, and the modeling information extraction system includes a geometric information extraction module for extracting geometric information, a unit information extraction module for extracting unit information, a load information extraction module for extracting load information, a boundary condition information extraction module for extracting boundary condition information, and a constitutive information extraction module for extracting constitutive information; The key information verification system is used to correct the extracted modeling information; The parametric modeling system is used to convert modeling information into finite element model codes.

7. The finite element model automatic modeling system according to claim 6, characterized in that: A first server is used to deploy the modeling information extraction system, a second server is used to deploy the parametric modeling system, a third server is used to deploy the key information verification system, a terminal is used to input the text to be modeled and output a visual model converted from the finite element model code, and the terminal, the first server, the second server and the third server are connected through a network.

8. The finite element model automatic modeling system according to claim 6, characterized in that: The modeling information extraction system extracts the modeling information based on a parameterized modeling large language model.

Images