An Automatic Finite Element Modeling Method and System Based on Construction Drawings

Abstract

This invention discloses an automatic finite element modeling method and system based on construction drawings. The method includes: automatically outputting unannotated construction drawings as annotated ones using a computer vision-based construction drawing recognition module; assigning horizontal and vertical axis numbers and 3D coordinate information to each building component on the annotated construction drawings using a grid dimension recognition module; automatically recognizing and fusing the dimensional information of each building component on the annotated construction drawings with their assigned horizontal and vertical axis numbers and 3D coordinate information using a large language model as an automatic modeling module; naming and assigning material properties to each building component in the 3D geometric model; and automatically creating a visualized finite element model based on the construction drawings by assigning support constraint information and load information to the 3D geometric model. This invention has the advantages of high modeling efficiency, high quality, and replacement of manual labor.

Description

Technical Field

[0001] This invention relates to the field of architectural engineering modeling, and in particular to an automatic modeling method and system for finite element models based on construction drawings. Background Technology

[0002] In the construction industry, construction drawings created using CAD and other software are the most common type of engineering documentation and are widely used in construction projects. While these drawings provide a clear view of the dimensions and positional relationships of building components, their two-dimensional nature makes them unsuitable for finite element analysis (FEM). FEM requires modeling engineers to create finite element models, a process demanding high levels of expertise; not all engineers can create finite element models. Errors are common when assigning material properties, support constraints, and load information, making the modeling process cumbersome, prone to errors and omissions, difficult to learn, and inefficient. Summary of the Invention

[0003] The purpose of this invention is to provide an automatic modeling method and system for finite element models based on construction drawings, so as to solve the problems of high technical requirements, easy errors, easy omissions, and low modeling efficiency for modeling engineers when drawing finite element models.

[0004] To address the aforementioned technical problems, this invention provides an automatic finite element modeling method based on construction drawings, comprising:

[0005] The names, dimensions, and material information of building components in the construction drawings are labeled; a deep learning semantic segmentation network model is constructed, and the construction drawings before labeling are used as input data and the construction drawings after labeling are used as output data as model training data to establish a construction drawing recognition module based on computer vision technology; through the construction drawing recognition module, the unlabeled construction drawings to be modeled are automatically identified, the names, dimensions, and material information of building components are automatically extracted, and the output is automatically converted into labeled construction drawings to be modeled.

[0006] By establishing a grid dimension recognition module, horizontal and vertical axis numbers and three-dimensional coordinate information are assigned to each building component in the construction drawings that are automatically output by the construction drawing recognition module and are yet to be modeled.

[0007] Using a large language model as an automatic modeling module, the system automatically identifies the dimensional information of each building component in the annotated construction drawings to be modeled, along with its assigned horizontal and vertical axis numbers and 3D coordinate information, and integrates them to automatically create a 3D geometric model in 3D drawing software. It also automatically identifies the names and material information of each building component in the annotated construction drawings to be modeled, automatically names and assigns material properties to each building component in the 3D geometric model, and automatically parses the reference specifications in the construction drawings to be modeled, automatically assigning support constraint information and load information to the 3D geometric model, and automatically creating a visualized finite element model based on the construction drawings.

[0008] Furthermore, the automatic modeling method for finite element models based on construction drawings provided by this invention uses an adaptive moment estimation optimization algorithm to optimize and train a deep learning semantic segmentation network model to establish a construction drawing recognition module based on computer vision technology.

[0009] Furthermore, the automatic modeling method for finite element models based on construction drawings provided by the present invention includes a construction drawing recognition module based on computer vision technology, comprising a plan view recognition submodule and a 3D view recognition submodule. The method automatically establishes a 3D geometric model by fusing the dimension information of each building component and the assigned horizontal and vertical axis numbers and 3D coordinate information of the plan view of the construction drawing to be modeled automatically output by the plan view recognition submodule and / or the 3D view of the construction drawing to be modeled automatically output by the 3D view recognition submodule.

[0010] Furthermore, the automatic modeling method for finite element models based on construction drawings provided by the present invention parses the reference specifications of the construction drawings to be modeled by searching and understanding the reference specifications of the construction drawings to be modeled through a large language model.

[0011] Furthermore, the automatic modeling method for finite element models based on construction drawings provided by this invention includes the following method for establishing the grid dimension recognition module:

[0012] The grid layer is converted into quadrant form, and the axis number and coordinates of the intersection points of the horizontal and vertical grids are recorded. The non-decomposable grid layer is parsed into a series of arrays consisting of horizontal and vertical axis numbers and three-dimensional coordinates.

[0013] To address the aforementioned technical problems, this invention also provides an automatic finite element modeling system based on construction drawings, comprising:

[0014] The construction drawing recognition module based on computer vision technology is used to automatically identify unannotated construction drawings to be modeled, automatically extract the names, dimensions and material information of building components, and automatically output them as annotated construction drawings to be modeled.

[0015] The grid dimension recognition module is used to assign horizontal and vertical axis numbers and three-dimensional coordinate information to each building component on the construction drawings that are automatically output by the construction drawing recognition module and are marked for modeling.

[0016] The automatic modeling module based on a large language model automatically identifies the dimensional information of each building component in the construction drawings to be modeled, as well as the assigned horizontal and vertical axis numbers and 3D coordinate information, and integrates them to automatically build a 3D geometric model in 3D drawing software. It also automatically identifies the names and material information of each building component in the construction drawings to be modeled, automatically labels the names of each building component in the 3D geometric model and assigns material properties. Furthermore, it automatically parses the reference specifications of the construction drawings to be modeled, automatically assigns support constraint information and load information to the 3D geometric model, and automatically builds a visualized finite element model based on the construction drawings.

[0017] Furthermore, the automatic modeling system for finite element models based on construction drawings provided by this invention includes an automatic modeling module based on a large language model, comprising a plan and elevation fusion submodule, an attribute assignment submodule, and a visualization submodule.

[0018] The plan and elevation fusion submodule is used to fuse the horizontal and vertical axis numbers and three-dimensional coordinate information of each building component in the plan, elevation and combination of the construction drawings automatically output by the construction drawing recognition module based on computer vision technology, and automatically build a three-dimensional geometric model in the three-dimensional drawing software.

[0019] The attribute assignment submodule is used to automatically identify the names and material information of each building component in the construction drawings to be modeled through the large language model, automatically name and assign material attributes to each building component in the three-dimensional geometric model, and automatically assign support constraint information and load information to the three-dimensional geometric model by automatically parsing the reference specifications of the construction drawings to be modeled through the large language model, and automatically establish a finite element model based on the construction drawings.

[0020] The visualization submodule is used to visualize the established finite element model.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0022] The present invention provides an automatic finite element modeling method and system based on construction drawings. This method utilizes a computer vision-based construction drawing recognition module to automatically identify unannotated construction drawings, extract the names, dimensions, and material information of building components, and automatically output them as annotated construction drawings. A grid dimension recognition module assigns grid dimension information, such as horizontal and vertical axis numbers and three-dimensional coordinates, to each building component on the annotated construction drawings. A large language modeling module automatically builds a visual finite element model from the annotated construction drawings with grid dimension information. Compared to manual modeling by professional modeling engineers, this method offers higher modeling efficiency and quality, eliminates the need for professional modeling engineers, avoids errors and omissions common in manual modeling, and prevents visual fatigue that leads to poor quality and low accuracy in construction drawings. It replaces manual labor and reduces labor costs.

[0023] The automatic modeling method and system for finite element models based on construction drawings provided by this invention can automatically output unannotated construction drawings in paper and electronic versions into construction drawings with annotated building component names, dimensions and material information through a construction drawing recognition module based on computer vision technology. It has the advantage of wide applicability. Attached Figure Description

[0024] Figure 1 This is a flowchart of an automatic finite element modeling method based on construction drawings;

[0025] Figure 2 This is a structural schematic diagram of an automatic finite element modeling system based on construction drawings;

[0026] Figure 3 This is a structural diagram of the drawing recognition module;

[0027] Figure 4 This is a structural diagram of the automatic modeling module;

[0028] As shown in the figure:

[0029] 100. Automatic modeling system for finite element models based on construction drawings; 110. Drawing recognition module; 111. Plan view recognition submodule; 112. 3D view recognition submodule; 120. Grid dimension recognition module; 130. Automatic modeling module based on large language model; 131. Plan and elevation fusion submodule; 132. Attribute assignment submodule; 133. Visualization submodule. Detailed Implementation

[0030] The present invention will now be described in detail with reference to the accompanying drawings. The advantages and features of the present invention will become clearer from the following description. It should be noted that the drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0031] Please refer to Figures 1 to 3 This invention provides an automatic finite element modeling method based on construction drawings, which may include the following steps:

[0032] Step S1: Label the names, dimensions, and material information of the building components on the construction drawings; construct a deep learning semantic segmentation network model, using the unlabeled construction drawings as input data and the labeled construction drawings as output data as model training data to establish a construction drawing recognition module 110 based on computer vision technology; the construction drawing recognition module 110 automatically identifies unlabeled construction drawings to be modeled, automatically extracts the names, dimensions, and material information of building components, and automatically outputs labeled construction drawings to be modeled. That is, the labeled construction drawings to be modeled are labeled with the names, dimensions, and material information of each building component. These building components include, but are not limited to, pile foundations, beams, columns, walls, and slabs, and the material information includes, but is not limited to, material grades, column concrete grades, and rebar grades. Based on the extracted material grade information, the system finds matching material information in a self-built database, including standard values ​​of tensile strength, Poisson's ratio, Young's modulus, etc., and assigns it to the corresponding building component.

[0033] In step S1, in order to establish a construction drawing recognition module 110 based on computer vision technology, an adaptive moment estimation optimization algorithm can be used to optimize and train a deep learning semantic segmentation network model to establish the construction drawing recognition module 110 based on computer vision technology.

[0034] In step S1, in order to realize the recognition and annotation of plan view, 3D view and their combination with construction drawings, the construction drawing recognition module 110 based on computer vision technology includes a plan view recognition submodule 111 and a 3D view recognition submodule 112. The module automatically recognizes the size information of each building component of the 3D view of the construction drawing to be modeled by the plan view automatically output by the plan view recognition submodule 111 and / or the 3D view of the construction drawing to be modeled by the 3D view automatically output by the 3D view recognition submodule 112 through the large language model, and fuses the assigned horizontal and vertical axis numbers and three-dimensional coordinate information to automatically build a three-dimensional geometric model.

[0035] Step S2 involves assigning horizontal and vertical axis numbers and 3D coordinate information to each building component of the construction drawings to be modeled, which are automatically output by the construction drawing recognition module 110 and labeled with axis grid dimensions. The method for establishing the axis grid dimensions recognition module 120 includes: converting the axis grid layer into a quadrant format; recording the axis numbers and coordinates of the intersection points of the horizontal and vertical axis grids; and parsing the indivisible axis grid layer into a series of arrays composed of horizontal and vertical axis numbers and 3D coordinates. By assigning axis grid dimensions such as horizontal and vertical axis numbers and 3D coordinates to each building component of the labeled construction drawings, the axis grid dimensions in the construction drawings are identified. This ensures that the geometric information is included in the subsequently identified plan and elevation drawings, guaranteeing smooth integration of plan and elevation drawings during the creation of the 3D geometric model and improving the accuracy and consistency of the 3D geometric model creation.

[0036] Step S3 involves using the large language model as an automatic modeling module. This module automatically identifies the dimensions, assigned axes, and 3D coordinates of each building component in the annotated construction drawings, fusing them into a 3D geometric model within the 3D drawing software. It also automatically identifies the names and material information of each building component in the annotated construction drawings, assigning names and material properties to each component in the 3D geometric model. Furthermore, it automatically parses the reference specifications from the construction drawings, assigning support constraints and load information to the 3D geometric model, and automatically creating a visualized finite element model based on the construction drawings. The established finite element model clearly displays the material information used in each building component, the information of each building node, and the load information attached to the building components.

[0037] In step S3, the reference specifications of the construction drawings to be modeled can be parsed by searching and understanding the reference specifications of the construction drawings to be modeled through a large language model.

[0038] Please refer to Figures 2 to 4 This invention also provides an automatic finite element modeling system based on construction drawings. Based on the above method, it includes a construction drawing recognition module 110 based on computer vision technology, a grid dimension recognition module 120, and an automatic modeling module 130 based on a large language model, wherein:

[0039] The construction drawing recognition module 110 based on computer vision technology is used to automatically identify unannotated construction drawings to be modeled, automatically extract the names, dimensions and material information of building components, and automatically output them as annotated construction drawings to be modeled.

[0040] The grid dimension recognition module 120 is used to assign horizontal and vertical axis numbers and three-dimensional coordinate information to each building component of the construction drawing to be modeled, which is automatically output by the construction drawing recognition module 110 and has been annotated.

[0041] The automatic modeling module 130 based on the large language model automatically identifies the dimensional information of each building component in the construction drawings to be modeled, as well as the assigned horizontal and vertical axis numbers and three-dimensional coordinate information, and integrates them to automatically build a three-dimensional geometric model in the three-dimensional drawing software. The automatic modeling module 130 also automatically identifies the names and material information of each building component in the construction drawings to be modeled, and automatically names and assigns material properties to each building component in the three-dimensional geometric model. Finally, the automatic modeling module 130 automatically parses the reference specifications of the construction drawings to be modeled, and automatically assigns support constraint information and load information to the three-dimensional geometric model to automatically build a visualized finite element model based on the construction drawings.

[0042] Please refer to Figure 4 The automatic modeling system for finite element models based on construction drawings provided in this embodiment of the invention includes an automatic modeling module 130 based on a large language model, comprising a plan and elevation fusion submodule 131, an attribute assignment submodule 132, and a visualization submodule 133.

[0043] The plan and elevation fusion submodule 131 is used to fuse the horizontal and vertical axis numbers and three-dimensional coordinate information of each building component in the plan, elevation and combination of the construction drawings automatically output by the construction drawing recognition module 110 based on computer vision technology, which are labeled and to be modeled, and to automatically build a three-dimensional geometric model in the three-dimensional drawing software.

[0044] The attribute assignment submodule 132 is used to automatically identify the names and material information of each building component in the construction drawings to be modeled through the large language model, automatically name and assign material attributes to each building component in the three-dimensional geometric model, and automatically assign support constraint information and load information to the three-dimensional geometric model by automatically parsing the reference specifications of the construction drawings to be modeled through the large language model, and automatically establish a finite element model based on the construction drawings.

[0045] The visualization submodule 133 is used to visualize the established finite element model.

[0046] The automatic finite element modeling method and system based on construction drawings provided in this invention automatically identifies unannotated construction drawings to be modeled by a construction drawing recognition module 110 based on computer vision technology, automatically extracts the names, dimensions, and material information of building components, and automatically outputs them as annotated construction drawings to be modeled. A grid dimension recognition module 120 assigns grid dimension information, such as horizontal and vertical axis numbers and three-dimensional coordinates, to each building component on the annotated construction drawings. A large language model is used as the automatic modeling module to automatically build a visual finite element model from the annotated construction drawings with grid dimension information. Compared to manual modeling by professional modeling engineers, this method offers high modeling efficiency and quality, and can achieve finite element model drawing without the intervention of professional modeling engineers. It avoids the problems of errors and omissions that are prone to occur during manual modeling by professional modeling engineers, and does not cause poor quality and low accuracy in construction drawings due to human visual fatigue. It replaces manual labor and reduces labor costs.

[0047] The automatic modeling method and system for finite element models based on construction drawings provided in this invention can automatically output unannotated construction drawings in paper or electronic versions as construction drawings with annotated building component names, dimensions, and material information through the construction drawing recognition module 110 based on computer vision technology. It has the advantage of wide applicability.

[0048] This invention is not limited to the specific embodiments described above. Obviously, the embodiments described above are only a part of the embodiments of this invention, not all of them. All other embodiments obtained by those skilled in the art based on the described embodiments of this invention are within the scope of protection of this invention. Those skilled in the art can make other modifications and variations to this invention. Therefore, if these modifications and variations of this invention fall within the scope of the claims of this invention, then this invention also intends to include these modifications and variations.

Claims

1. An automatic finite element modeling method based on construction drawings, characterized in that, include: The names, dimensions, and material information of building components in the construction drawings are labeled; a deep learning semantic segmentation network model is constructed, and the construction drawings before labeling are used as input data and the construction drawings after labeling are used as output data as model training data to establish a construction drawing recognition module based on computer vision technology; through the construction drawing recognition module, the unlabeled construction drawings to be modeled are automatically identified, the names, dimensions, and material information of building components are automatically extracted, and the output is automatically converted into labeled construction drawings to be modeled. By establishing a grid dimension recognition module, horizontal and vertical axis numbers and three-dimensional coordinate information are assigned to each building component in the construction drawings that are automatically output by the construction drawing recognition module and are yet to be modeled. Using a large language model as an automatic modeling module, the system automatically identifies the dimensional information of each building component in the annotated construction drawings to be modeled, along with its assigned horizontal and vertical axis numbers and 3D coordinate information, and integrates them to automatically create a 3D geometric model in 3D drawing software. It also automatically identifies the names and material information of each building component in the annotated construction drawings to be modeled, automatically names and assigns material properties to each building component in the 3D geometric model, and automatically parses the reference specifications in the construction drawings to be modeled, automatically assigning support constraint information and load information to the 3D geometric model, and automatically creating a visualized finite element model based on the construction drawings.

2. The automatic modeling method for finite element models based on construction drawings according to claim 1, characterized in that, An adaptive moment estimation optimization algorithm was used to optimize and train a deep learning semantic segmentation network model to establish a construction drawing recognition module based on computer vision technology.

3. The automatic modeling method for finite element models based on construction drawings according to claim 1, characterized in that, The construction drawing recognition module based on computer vision technology includes a plan view recognition submodule and a 3D view recognition submodule. It automatically recognizes the dimensions of each building component and their assigned horizontal and vertical axis numbers and 3D coordinate information of the plan view of the construction drawing to be modeled automatically output by the plan view recognition submodule and / or the 3D view of the construction drawing to be modeled automatically output by the 3D view recognition submodule, and automatically establishes a 3D geometric model.

4. The automatic modeling method for finite element models based on construction drawings according to claim 1, characterized in that, The reference specifications for the construction drawings to be modeled are searched and understood using a large language model.

5. The automatic modeling method for finite element models based on construction drawings according to claim 1, characterized in that, The method for establishing the grid dimension recognition module includes: The grid layer is converted into quadrant form, and the axis number and coordinates of the intersection points of the horizontal and vertical grids are recorded. The non-decomposable grid layer is parsed into a series of arrays consisting of horizontal and vertical axis numbers and three-dimensional coordinates.

6. An automatic finite element modeling system based on construction drawings, characterized in that, The automatic modeling method for finite element models based on construction drawings, as described in any one of claims 1 to 5, includes: The construction drawing recognition module based on computer vision technology is used to automatically identify unannotated construction drawings to be modeled, automatically extract the names, dimensions and material information of building components, and automatically output them as annotated construction drawings to be modeled. The grid dimension recognition module is used to assign horizontal and vertical axis numbers and three-dimensional coordinate information to each building component on the construction drawings that are automatically output by the construction drawing recognition module and are marked for modeling. The automatic modeling module based on a large language model automatically identifies and integrates the dimensional information of each building component in the annotated construction drawings, along with their assigned horizontal and vertical axis numbers and 3D coordinate information, to automatically create a 3D geometric model in 3D drawing software. It also automatically identifies the names and material information of each building component in the annotated construction drawings, automatically labels the components in the 3D geometric model with names and assigns material properties. Furthermore, it automatically parses the reference specifications in the construction drawings, automatically assigns support constraint information and load information to the 3D geometric model, and automatically creates a visualized finite element model based on the construction drawings.

7. The automatic modeling system for finite element models based on construction drawings according to claim 6, characterized in that, The automatic modeling module based on a large language model includes a plan and elevation fusion submodule, an attribute assignment submodule, and a visualization submodule. The plan and elevation fusion submodule is used to fuse the horizontal and vertical axis numbers and three-dimensional coordinate information of each building component in the plan, elevation and combination of the construction drawings automatically output by the construction drawing recognition module based on computer vision technology, and automatically build a three-dimensional geometric model in the three-dimensional drawing software. The attribute assignment submodule is used to automatically identify the names and material information of each building component in the construction drawings to be modeled through the large language model, automatically name and assign material attributes to each building component in the three-dimensional geometric model, and automatically assign support constraint information and load information to the three-dimensional geometric model by automatically parsing the reference specifications of the construction drawings to be modeled through the large language model, and automatically establish a finite element model based on the construction drawings. The visualization submodule is used to visualize the established finite element model.

Images