Bridge steel structure collaborative design method and system based on BIM technology

Abstract

The invention relates to the technical field of building information models and intelligent design, and provides a bridge steel structure collaborative design method and system based on the BIM technology, and the method comprises the steps: obtaining a plurality of bridge steel structure BIM models from a BIM database, and design parameter vectors, structure topological graphs and collaborative design data vectors thereof; constructing a structural feature extraction model by training a BIM structure encoder model, calculating the similarity between the models, and retrieving a similar model; establishing a BIM data fusion model, and training by combining the design parameter vector of the target model and the collaborative design data vector of the similar model to obtain a collaborative design prediction model; and searching a similar model for a to-be-collaborative design model, and generating collaborative design data through a prediction model based on design parameters of the to-be-collaborative design model and collaborative data of the similar model. According to the method, intelligent collaborative optimization of bridge steel structure design can be realized, the design efficiency and accuracy are improved, and manual intervention and repeated work are reduced.

Description

Technical Field

[0001] The present invention relates to the field of building information modeling and intelligent design technology, and more specifically, to a bridge steel structure collaborative design method and system based on BIM technology. Background Art

[0002] In the architecture, engineering, and construction (AEC) industry, the design of steel bridge structures is a complex and multidisciplinary process. Traditional bridge steel structure design relies primarily on two-dimensional drawings and manual coordination, an approach that is not only inefficient but also prone to information inconsistencies and poor communication. With the advent of Building Information Modeling (BIM) technology, designers can integrate the geometric information, spatial relationships, geographic information, and property information of building components of bridge steel structures into a three-dimensional digital model, thereby improving design efficiency and quality. However, current BIM technology still has some limitations in the collaborative design of bridge steel structures. Existing BIM collaborative design methods primarily focus on information sharing and communication between different disciplines. However, they lack effective technical support for the collaborative design of complex structures such as bridge steel structures, especially in terms of parametric collaboration and intelligent model matching during the design phase. Existing collaborative design systems often require designers to manually compare models and adjust parameters, which is not only time-consuming and labor-intensive, but also prone to errors. Furthermore, for projects such as bridge steel structures that require multi-disciplinary collaborative design, existing technologies struggle to rapidly evaluate and optimize different design options, resulting in extended design cycles and increased costs.

[0003] In the process of implementing the embodiments of the present invention, the inventors discovered that there are at least the following problems or defects in the existing technology: First, the existing BIM collaborative design method cannot effectively extract features and calculate similarities for the complex topological structure of bridge steel structures, making it difficult to achieve intelligent model matching and collaborative design. Second, when processing collaborative design data, the existing technology lacks an effective data fusion and prediction mechanism and cannot fully utilize existing design experience and data to generate new collaborative design solutions. Finally, the existing BIM collaborative design system still needs to be improved in terms of user interaction and automation, and cannot meet the requirements of modern bridge steel structure design for efficient collaboration and rapid iteration. Summary of the Invention

[0004] The present invention provides a bridge steel structure collaborative design method and system based on BIM technology.

[0005] In a first aspect of the present invention, a bridge steel structure collaborative design method based on BIM technology is provided, comprising:

[0006] Obtain multiple completed bridge steel structure BIM models from the BIM engineering database, and obtain the BIM design parameter vectors, BIM structural topology diagrams, and collaborative design data vectors for each model;

[0007] Establishing a BIM structure encoder model, and training the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structural feature extraction model;

[0008] Based on the structural feature extraction model, calculating the similarity index between the bridge steel structure BIM models, and obtaining the bridge steel structure BIM models that meet the conditions as similar models;

[0009] Establishing a BIM data fusion model, and training the BIM data fusion model to obtain a collaborative design prediction model;

[0010] Obtain a BIM model of the bridge steel structure to be collaboratively designed. Based on the BIM model to be collaboratively designed, use the similarity model to input the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

[0011] Furthermore, each of the bridge steel structure BIM models includes: a BIM design parameter module, a BIM structural topology module and a collaborative design data module; wherein the BIM design parameter module includes: multiple structural components contained in the model, the BIM parametric attribute value of each component and the BIM annotation information contained in the model.

[0012] Furthermore, obtaining the BIM design parameter vector includes:

[0013] Perform parameter standardization processing on the BIM design parameter module using a BIM data preprocessing tool;

[0014] The standardized design parameters are converted into the BIM design parameter vector using a BIM parameter encoding method.

[0015] Furthermore, obtaining the collaborative design data vector includes:

[0016] Performing data normalization processing on the collaborative design data module using a BIM information cleaning tool;

[0017] Obtaining a BIM collaborative data template for the engineering category to which the bridge steel structure belongs, and using a sequence alignment algorithm to calculate the matching degree between the normalized collaborative data and the template;

[0018] When the matching degree reaches or exceeds a set threshold, redundant parts of the normalized collaborative data and the template are removed;

[0019] The collaborative data after removing the redundant parts is converted into the collaborative design data vector by using the BIM data encoding method.

[0020] Furthermore, the processing of the BIM design parameter module or the collaborative design data module by a BIM data preprocessing tool or a BIM information cleaning tool includes:

[0021] Remove unstructured BIM tags and format control symbols;

[0022] Clear temporary marking information during the design phase;

[0023] Filter statements containing special engineering symbols, unit identifiers, or component codes;

[0024] Unified tolerance annotations and version identifiers in parameters;

[0025] Remove temporary change parameters during the construction deepening phase;

[0026] Clear the component attribute parameters added after the design closed loop;

[0027] Remove redundant labels from component classification.

[0028] Furthermore, generating the BIM structure topology diagram includes:

[0029] Parsing the initial BIM model and the revised BIM model into parametric topological structures respectively;

[0030] The BIM change detection algorithm is used to calculate the topological node mapping relationship between the initial and revised BIM models;

[0031] Based on the mapping relationship, the change operation type of the BIM model is determined, topological feature nodes are generated according to the change type, and the topological feature nodes are combined into a three-dimensional topological graph according to the hierarchical structure of the initial BIM model to form a BIM structure topological graph; wherein the change operation types include geometric adjustment, component removal, component addition, position offset, and topology preservation.

[0032] Furthermore, the establishing of a BIM structure encoder model and training the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structure feature extraction model includes:

[0033] The encoder uses a BIM graph neural network to aggregate the geometric attributes of each node in the structural topology graph from bottom to top to form a coding tensor;

[0034] The decoder uses the BIM model to reconstruct the network and restore the encoded tensor to a three-dimensional topological structure from top to bottom;

[0035] Based on the multiple BIM structure topology graphs, a topology reconstruction training strategy is used to enable the three-dimensional topology structure to completely reproduce the input BIM structure topology graph.

[0036] Furthermore, the calculating of the similarity index between each pair of the bridge steel structure BIM models includes:

[0037] The BIM structure encoder model is used to encode two BIM models to obtain two corresponding feature tensors, structural feature similarities of the two feature tensors are calculated, and similarity indicators of the two BIM models are determined based on the numerical values ​​of the structural feature similarities.

[0038] Furthermore, training the BIM data fusion model includes:

[0039] The parameter encoder adopts a BIM feature encoder to encode the BIM design parameter vector of each BIM model into a first feature vector;

[0040] The collaborative data encoder uses a BIM context encoder to encode the collaborative design data vectors of several similar models corresponding to each BIM model into a second feature vector;

[0041] The second feature vector is weighted according to the corresponding similarity index, and tensor splicing is performed with the first feature vector through the BIM feature fusion layer to form a fused feature vector;

[0042] The prediction decoder adopts the BIM data generation network, combined with the attention mechanism and the gated recurrent unit, to decode the fused feature vector into the collaborative design data of the BIM model to be generated.

[0043] In a second aspect of the present invention, a bridge steel structure collaborative design system based on BIM technology is provided, comprising:

[0044] A BIM data integration module is used to obtain a BIM model of the bridge steel structure from a BIM engineering database, and obtain a BIM design parameter vector, a BIM structure topology diagram, and a collaborative design data vector for each model based on the model;

[0045] A BIM feature comparison module is configured to establish a BIM structure encoder model, train the BIM structure encoder model based on the plurality of BIM structure topology graphs to obtain a structure feature extraction model; calculate similarity indices between two of the bridge steel structure BIM models based on the structure feature extraction model, and obtain a bridge steel structure BIM model that meets the conditions as a similarity model;

[0046] A BIM model training module is used to establish a BIM data fusion model and train the BIM data fusion model to obtain a collaborative design prediction model;

[0047] The BIM collaborative generation module is used to obtain the BIM model of the bridge steel structure to be collaboratively designed, and based on the BIM model to be collaboratively designed, use the similarity model to take the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model as input, input them into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

[0048] According to the above-mentioned embodiments of the present invention, there are at least the following beneficial effects: the method and system for collaborative design of bridge steel structures based on BIM technology of the present invention can improve the efficiency and accuracy of collaborative design of bridge steel structures. By establishing a BIM structure encoder model and training a structural feature extraction model, it is possible to accurately extract features and calculate similarity of the topological structure of the BIM model of the bridge steel structure, thereby quickly retrieving several models with the highest similarity to the model to be designed, providing valuable references for designers, reducing repetitive design work, and shortening the design cycle. At the same time, the construction of the BIM data fusion model and the generation of the collaborative design prediction model can organically combine the design parameters of the model to be collaboratively designed with the collaborative design data of similar models, and use advanced algorithms to generate high-quality collaborative design data, further improving the scientificity and reliability of the design and reducing design risks.

[0049] Furthermore, the present invention can also achieve efficient processing and standardized management of BIM design parameters and collaborative design data. Through BIM data preprocessing tools and BIM information cleaning tools, design parameters and collaborative design data can be standardized and normalized, redundant information and temporary tags can be removed, ensuring data accuracy and consistency, and providing a high-quality data foundation for subsequent model training and collaborative design. Overall, the present invention can provide an intelligent and automated solution for the collaborative design of bridge steel structures, helping to promote technological progress and development in the bridge steel structure design industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0051] Figure 1 A schematic diagram of a flow chart of a bridge steel structure collaborative design method based on BIM technology provided by one embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a bridge steel structure collaborative design system based on BIM technology provided by one embodiment of the present invention;

[0053] Figure 3 The figure schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0055] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0056] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0057] Reference below Figure 1 , Figure 1 The flowchart of the bridge steel structure collaborative design method based on BIM technology provided by one embodiment of the present invention is as follows. Figure 1 As shown in the figure, a collaborative design method for bridge steel structures based on BIM technology includes:

[0058] S1. Obtain multiple BIM models of bridge steel structures that have been designed from the BIM engineering database, and obtain the BIM design parameter vector, BIM structure topology diagram, and collaborative design data vector of each model;

[0059] S2. Establish a BIM structure encoder model, and train the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structure feature extraction model;

[0060] S3. Based on the structural feature extraction model, calculate the similarity index between the two bridge steel structure BIM models, and obtain the bridge steel structure BIM models that meet the conditions as similar models;

[0061] S4. Establish a BIM data fusion model and train the BIM data fusion model to obtain a collaborative design prediction model;

[0062] S5. Obtain a BIM model of the bridge steel structure to be collaboratively designed. Based on the BIM model to be collaboratively designed, use the similarity model to input the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

[0063] It should be noted that the present invention proposes a collaborative design method for bridge steel structures based on BIM technology. BIM, or Building Information Modeling, is a digital technology that integrates information on the entire life cycle of a construction project. It optimizes the design, construction, and operation processes by creating and using three-dimensional models. In the present invention, multiple BIM models of bridge steel structures that have been designed are obtained from the BIM engineering database. The purpose of this step is to collect enough design samples for subsequent model training and similarity analysis. The BIM model contains rich information, such as BIM design parameter vectors, BIM structural topology diagrams, and collaborative design data vectors. The BIM design parameter vector refers to a collection of parameterized attribute values ​​of each structural component in the model. These parameterized attribute values ​​may include the size, material properties, connection methods, etc. of the component; the BIM structural topology diagram describes the geometric structure and spatial relationship of the bridge steel structure, and reflects the connection and layout between the components; the collaborative design data vector records the data generated during the collaborative design process, such as design change records, collaborative operation records, etc. These data are helpful in understanding and optimizing the collaborative design process.

[0064] The role of the encoder model is to encode the information in the BIM structure topology map and extract the encoding tensor that can characterize the structural features. The decoder is responsible for restoring the encoding tensor to a three-dimensional topological structure to achieve complete reproduction of the input BIM structure topology map. When training the BIM structure encoder model, a topological reconstruction training strategy is adopted, and training is performed through a large number of BIM structure topology map samples, so that the model can learn the feature representations of different structure topologies. The similarity index between the two BIM models of the bridge steel structure is calculated by encoding the two BIM models using the BIM structure encoder model to obtain the corresponding two feature tensors, and then calculating the structural feature similarity of the two feature tensors. The numerical value of the similarity index can reflect the degree of similarity between the two BIM models in terms of structural features. The higher the numerical value, the more similar the two models are. In the present invention, by setting a threshold, several similar models whose similarity to the BIM model to be collaboratively designed meets the set threshold can be screened out. These models will be used as reference models for subsequent collaborative design predictions.

[0065] To construct the BIM data fusion model, the parameter encoder uses a BIM feature encoder, which encodes the BIM design parameter vector of each bridge steel structure BIM model into a first feature vector. The collaborative data encoder uses a BIM context encoder, which encodes the collaborative design data vectors of several similar models corresponding to the model into a second feature vector. When fusing these two feature vectors, the second feature vector is weighted according to the corresponding similarity index and then tensor-concatenated with the first feature vector through the BIM feature fusion layer to form a fused feature vector. The predictive decoder uses a BIM data generation network, combined with an attention mechanism and a gated recurrent unit, to decode the fused feature vector into the collaborative design data for the BIM model to be generated. In practical applications, the input parameters of the BIM data fusion model can include the specific values ​​of the BIM design parameter vector, such as component dimensions and material properties, as well as information such as design change records in the collaborative design data vector. This model construction and data processing approach can effectively generate high-quality collaborative design data, supporting the collaborative design of bridge steel structures.

[0066] The collaborative design prediction model analyzes and processes the input BIM design parameter vector and collaborative design data vector, and ultimately outputs collaborative design data suitable for the BIM model to be collaboratively designed. First, the aforementioned structural feature extraction model is used to extract features and calculate similarity for the BIM model to be collaboratively designed. By comparing with historical BIM models in the database, several similar models whose similarity to the model to be collaboratively designed meets the set threshold are retrieved. These similar models have a high similarity with the model to be designed in terms of structural features and can provide valuable reference for the current design. The similarity threshold is a pre-set parameter used to measure the degree of similarity between the model to be collaboratively designed and the historical model. Only historical models whose similarity reaches or exceeds this threshold will be selected as similar models for subsequent collaborative design data generation.

[0067] Next, the BIM design parameter vector of the BIM model to be collaboratively designed is used as part of the input. This vector represents the parametric attributes of each structural component in the current model, such as size, material type, and connection method. It is a digital expression of the model's design intent and structural characteristics. Simultaneously, the collaborative design data vectors of several retrieved similar models are used as another part of the input. The collaborative design data vectors record information such as the collaborative strategies used in the design of similar structures, design change records, and details of the multi-disciplinary collaboration.

[0068] The collaborative design prediction model processes these two input data components. It can include multiple processing layers, such as a parameter encoder, collaborative data encoder, feature fusion layer, and prediction decoder. The parameter encoder extracts features from the BIM design parameter vector, while the collaborative data encoder extracts features from the collaborative design data vectors of similar models. The feature fusion layer integrates the extracted features to form a fused feature vector. Finally, the prediction decoder decodes the fused feature vector to generate collaborative design data for the BIM model to be collaboratively designed.

[0069] In some embodiments, each of the bridge steel structure BIM models includes: a BIM design parameter module, a BIM structural topology module and a collaborative design data module; wherein the BIM design parameter module includes: multiple structural components contained in the model, the BIM parametric attribute value of each component and the BIM annotation information contained in the model.

[0070] It should be noted that each bridge steel structure BIM model mentioned in the present invention includes a BIM design parameter module, a BIM structural topology module and a collaborative design data module. The BIM design parameter module is one of the core parts of the model, which contains detailed information about each structural component in the model. This information not only includes the geometric dimensions of the components, such as length, width, height, etc., but also covers the BIM parameterized attribute values ​​of each component, such as material type, bearing capacity, connection method, etc. In addition, the model also contains BIM annotation information, which is used to record design intent, construction requirements or other important design instructions, providing additional reference for designers and construction personnel. The BIM structural topology module mainly describes the geometric structure and spatial relationship of the bridge steel structure. It shows the connection method and overall layout between components in the form of a topological diagram. The collaborative design data module records various data generated during the collaborative design process. These data are of great significance for understanding design changes, optimizing design processes and improving design efficiency.

[0071] Specifically, the BIM parametric attribute values ​​in the BIM design parameter module are key information for component design. These attributes can include component material properties, such as steel strength grade and yield strength; geometric properties, such as component cross-sectional shape and dimensions; and connection properties, such as welding methods and bolt connection specifications. These parametric attribute values ​​are stored in the BIM model in a standardized format, making them easy for designers to query and modify. The BIM structural topology module visualizes the geometric structure and spatial relationships of the bridge steel structure in the form of a topological graph. Nodes in the topological graph represent components, and edges represent the connections between components. This graph structure clearly displays the layout and connection methods of the entire bridge steel structure. The collaborative design data module records various data from the collaborative design process, such as design change records and collaborative operation records. This data is stored in a time series format, allowing designers to trace every step and change in the design process.

[0072] Preferably, parametric modeling tools can be used to better construct and manage BIM design parameter modules. These tools allow designers to quickly generate and modify component models by inputting parametric property values. For example, designers can automatically generate corresponding component models by inputting parameters such as component length, width, and material type, and can easily adjust these parameters to meet different design requirements. In the construction of the BIM structural topology module, professional BIM modeling software such as Revit or ArchiCAD can be used. These software provide powerful topology modeling capabilities, can automatically generate topology diagrams based on design parameters, and support editing and modification of topological structures. In the management of the collaborative design data module, BIM collaborative platforms such as BIM360 can be utilized. These platforms can record various operations and changes during the design process in real time and provide version control functions to ensure the integrity and consistency of design data. Through these specific technical means, the construction efficiency and quality of the bridge steel structure BIM model can be effectively improved, providing a solid foundation for subsequent collaborative design.

[0073] In some embodiments, obtaining the BIM design parameter vector includes:

[0074] Perform parameter standardization processing on the BIM design parameter module using a BIM data preprocessing tool;

[0075] The standardized design parameters are converted into the BIM design parameter vector using a BIM parameter encoding method.

[0076] It should be noted that the process of obtaining BIM design parameter vectors mentioned in the present invention is to standardize and encode the information in the BIM design parameter module for subsequent model training and collaborative design. The BIM data preprocessing tool is a software tool specifically used to process BIM data. It can clean and standardize the data in the BIM design parameter module. The BIM parameter encoding method converts the standardized design parameters into a vector form suitable for model processing. The purpose of this process is to ensure that the data format input into the model is unified and accurate, thereby improving the model training effect and the reliability of collaborative design.

[0077] Specifically, the data in the BIM design parameter module usually contains multiple types of parameters, such as the geometric parameters of components: length, width, height, etc., material parameters: strength, elastic modulus, etc., and connection parameters: connection type, connection size, etc. The role of the BIM data preprocessing tool is to standardize these parameters, for example, converting dimensional parameters of different units into the same unit, such as millimeters, and unifying the description of material parameters into standard material property codes. The BIM parameter encoding method is to convert these standardized parameters into numerical vectors through specific encoding rules. For example, one-hot encoding or embedding encoding can be used to convert discrete parameter values ​​into continuous numerical vectors. These vectors can be used as input to machine learning models or deep learning models for subsequent feature extraction and collaborative design prediction.

[0078] Preferably, BIM data preprocessing tools can be integrated into BIM modeling software, such as adding a preprocessing plug-in to Revit or ArchiCAD, so that designers can directly standardize parameters during the design process. During the parameter encoding process, appropriate encoding methods can be selected for different parameter types. For example, for continuous geometric parameters, normalization can be used directly; for discrete material type parameters, embedded encoding can be used to map each material type to a low-dimensional vector space. In addition, in order to improve the efficiency and accuracy of encoding, pre-trained encoder models can be used. These models have been trained on a large amount of BIM data and can automatically learn the optimal encoding method for parameters. Through these specific technical means, the generation process of BIM design parameter vectors can be ensured to be efficient and accurate, providing high-quality data support for subsequent collaborative design.

[0079] In some embodiments, obtaining the collaborative design data vector includes:

[0080] Performing data normalization processing on the collaborative design data module using a BIM information cleaning tool;

[0081] Obtaining a BIM collaborative data template for the engineering category to which the bridge steel structure belongs, and using a sequence alignment algorithm to calculate the matching degree between the normalized collaborative data and the template;

[0082] When the matching degree reaches or exceeds a set threshold, redundant parts of the normalized collaborative data and the template are removed;

[0083] The collaborative data after removing the redundant parts is converted into the collaborative design data vector by using the BIM data encoding method.

[0084] It should be noted that the process of obtaining collaborative design data vectors mentioned in the present invention is to normalize and encode the information in the collaborative design data module for subsequent model training and collaborative design. The core of this process is to ensure the consistency and accuracy of the collaborative design data, while removing redundant information and improving the availability of the data. The BIM information cleaning tool is a software tool specifically used to process BIM data, which can clean and normalize the data in the collaborative design data module. The sequence alignment algorithm is an algorithm for calculating the matching degree between the normalized collaborative data and the template. In this way, the redundant parts in the data can be identified and removed. The BIM data encoding method is to convert the processed collaborative data into a vector form suitable for model processing for subsequent collaborative design predictions.

[0085] Specifically, the data in the collaborative design data module usually contains information such as design change records, collaborative operation records, and design review opinions. These data may have problems such as inconsistent formats and redundant information during the generation process, and need to be processed by BIM information cleaning tools. The main functions of the cleaning tool include deleting unstructured BIM tags, clearing temporary marking information in the design phase, filtering statements containing special engineering symbols, etc., to ensure the accuracy and consistency of the data. The sequence alignment algorithm is used to compare the normalized collaborative data with the predefined BIM collaborative data template and calculate the matching degree between the two. When the matching degree reaches or exceeds the set threshold, it means that the data is highly consistent with the template. At this time, the redundant part of the data that matches the template can be removed. The BIM data encoding method is to convert the processed collaborative data into a numerical vector. For example, embedded coding or one-hot encoding can be used to convert discrete data values ​​into continuous numerical vectors so that they can be used as input to the model.

[0086] Preferably, BIM information cleaning tools can be integrated into the BIM collaborative design platform, such as adding a cleaning plug-in to platforms such as BIM360 or Navisworks, so that designers can directly clean and normalize the data during the collaborative design process. In the application of the sequence alignment algorithm, a specific matching threshold can be set, such as 80% or higher, to ensure the accuracy and consistency of the data. For the BIM data encoding method, a suitable encoding method can be selected according to the characteristics of the collaborative design data. For example, for text data in design change records, text embedding encoding can be used to convert the text into a low-dimensional vector representation; for time series data in collaborative operation records, time series encoding can be used to combine time information and operation type information for encoding. Through these specific technical means, the generation process of collaborative design data vectors can be ensured to be efficient and accurate, providing high-quality data support for subsequent collaborative design.

[0087] In some embodiments, processing the BIM design parameter module or the collaborative design data module using a BIM data preprocessing tool or a BIM information cleaning tool includes:

[0088] Remove unstructured BIM tags and format control symbols;

[0089] Clear temporary marking information during the design phase;

[0090] Filter statements containing special engineering symbols, unit identifiers, or component codes;

[0091] Unified tolerance annotations and version identifiers in parameters;

[0092] Remove temporary change parameters during the construction deepening phase;

[0093] Clear the component attribute parameters added after the design closed loop;

[0094] Remove redundant labels from component classification.

[0095] It should be noted that the process of processing BIM design parameter modules or collaborative design data mentioned in this invention is intended to ensure data accuracy and consistency, thereby improving the efficiency and quality of subsequent collaborative design. BIM data preprocessing tools or BIM information cleaning tools can be used to perform a series of cleaning and normalization operations on the data, removing redundant information and unnecessary tags, making the data more suitable for model training and collaborative design. The application of these tools and methods can effectively reduce noise in the data, improve data usability, and provide a solid foundation for subsequent model construction and prediction.

[0096] Specifically, the functions of the BIM data preprocessing tool and BIM information cleaning tool include deleting unstructured BIM tags and format control symbols, which may be used for temporary marking or format adjustments during the design process but have no practical significance in the final collaborative design. Clearing temporary marking information during the design phase, which is usually used for annotations and reminders during the design process but does not need to be retained in the final model. Filtering statements containing special engineering symbols, unit identifiers, or component codes, which may be used for specific engineering annotations during the design process but may cause confusion in collaborative design. Unifying tolerance annotations and version identifiers in parameters to ensure that all parameters are labeled consistently for ease of subsequent processing and comparison. Removing temporary change parameters during the construction deepening phase, which may be added during the construction phase but are not required during the design phase. Clearing component attribute parameters added after the design loop is closed, which may be added after the design is completed but may not be required in collaborative design. Removing redundant component classification labels to ensure that the classification label of each component is unique and accurate to avoid duplication and confusion.

[0097] Preferably, BIM data preprocessing tools can be integrated into BIM modeling software, such as adding a preprocessing plug-in to Revit or ArchiCAD, so that designers can directly standardize parameters during the design process. In specific operations, the parameters of the tool can be set, such as specifying the type of unstructured tags to be deleted, setting a unified format for tolerance annotations, etc. As for BIM information cleaning tools, they can be integrated into the BIM collaborative design platform, such as adding a cleaning plug-in to BIM360 or Navisworks, so as to clean data in real time during the collaborative design process. During the data processing process, specific cleaning rules can be set, such as filtering specific engineering symbols, clearing specific temporary marks, etc. Through these specific technical means, the data processing process can be ensured to be efficient and accurate, providing high-quality data support for subsequent collaborative design.

[0098] In some embodiments, generating the BIM structure topology diagram includes:

[0099] Parsing the initial BIM model and the revised BIM model into parametric topological structures respectively;

[0100] The BIM change detection algorithm is used to calculate the topological node mapping relationship between the initial and revised BIM models;

[0101] Based on the mapping relationship, the change operation type of the BIM model is determined, topological feature nodes are generated according to the change type, and the topological feature nodes are combined into a three-dimensional topological graph according to the hierarchical structure of the initial BIM model to form a BIM structure topological graph; wherein the change operation types include geometric adjustment, component removal, component addition, position offset, and topology preservation.

[0102] It should be noted that the process of generating a BIM structural topology diagram mentioned in the present invention is to present the geometric structure and spatial relationship of the bridge steel structure in a clear and operable form. This process involves parsing the initial BIM model and the revised BIM model into parameterized topological structures respectively, and calculating the topological node mapping relationship between them through the BIM change detection algorithm. The determination of the topological node mapping relationship is based on the type of change operation, including geometric adjustment, component removal, component addition, position offset, topology maintenance, etc. These change operation types reflect the modification and optimization of the BIM model during the design process. Through these steps, a three-dimensional topological diagram can be generated, which can fully reflect the structural characteristics and change history of the BIM model, providing an important reference for subsequent collaborative design.

[0103] Specifically, the initial BIM model refers to the model created at the beginning of the design, while the revised BIM model refers to the model that has been modified during the design process. Parsing these two models into parametric topological structures means extracting the geometric parameters and spatial relationships of each component in the model and expressing them in a parametric form to facilitate subsequent processing and analysis. The BIM change detection algorithm is an algorithm used to compare the differences between two BIM models. It determines which parts of the model have changed by calculating the topological node mapping relationship between the initial model and the revised model. The change operation type is a specific description of the model change. For example, geometric adjustment refers to a change in the shape or size of a component; component removal refers to the deletion of a component from the model; component addition refers to the addition of a new component to the model; position offset refers to the movement of the component's position; and topology preservation means that the topological structure of the model has not changed. These change operation types provide designers with a clear way to understand and record the change history of the model.

[0104] Preferably, the process of generating a BIM structural topology diagram can be further refined into the following steps: First, using BIM modeling software such as Revit or ArchiCAD, the initial BIM model and the revised BIM model are exported into an intermediate format of parametric topology structures, such as IFC format. Then, a specialized BIM change detection tool, such as Solibri Model Checker, is used to calculate the topological node mapping relationship between the two models. During the calculation process, algorithm parameters can be set, such as defining a geometric adjustment threshold, determining that when a component's shape or size changes exceeding this threshold, it is considered a geometric adjustment operation. For each change operation type, detailed change information can be recorded, such as the identifier and removal time of the removed component for component removal operations. Finally, based on these change operation types and mapping relationships, a BIM visualization tool, such as Navisworks, is used to combine the modified topology into a 3D topology diagram. This topology diagram is then combined with the hierarchical structure of the initial BIM model to form a complete BIM structural topology diagram. Through these specific technical means, the generation process of the BIM structural topology diagram can be ensured to be efficient and accurate, providing clear and detailed structural information for subsequent collaborative design.

[0105] In some embodiments, establishing a BIM structure encoder model and training the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structure feature extraction model includes:

[0106] The encoder uses a BIM graph neural network to aggregate the geometric attributes of each node in the structural topology graph from bottom to top to form a coding tensor;

[0107] The decoder uses the BIM model to reconstruct the network and restore the encoded tensor to a three-dimensional topological structure from top to bottom;

[0108] Based on the multiple BIM structure topology graphs, a topology reconstruction training strategy is used to enable the three-dimensional topology structure to completely reproduce the input BIM structure topology graph.

[0109] It should be noted that the process of establishing a BIM structure encoder model and training a structural feature extraction model mentioned in the present invention is to extract effective information that can characterize the characteristics of the bridge steel structure from the BIM structure topology map. The encoder model aggregates the geometric properties of the nodes in the topology map to form a coding tensor, and the decoder restores the coding tensor to a three-dimensional topological structure. The core of this process is to enable the model to fully reproduce the input BIM structure topology map through a topology reconstruction training strategy, thereby providing accurate feature representation for subsequent similarity calculation and collaborative design. The BIM graph neural network is a neural network specifically used to process graph structure data. It can effectively capture the relationship and geometric properties between nodes, and the BIM model reconstruction network is used to restore the extracted features to the original three-dimensional structure to ensure the accuracy and completeness of feature extraction.

[0110] Specifically, the BIM structure encoder model consists of an encoder and a decoder. The encoder uses a BIM graph neural network, whose function is to perform bottom-up feature aggregation on the geometric properties of each node in the BIM structure topology graph. The geometric properties here include information such as the position, shape, and size of the node, which are integrated into a coding tensor through the aggregation operation of the graph neural network. The decoder uses a BIM model reconstruction network, whose task is to restore the coding tensor from top to bottom to a three-dimensional topological structure. The topology reconstruction training strategy refers to training the model through a large number of BIM structure topology graph samples, so that the decoder can accurately restore the coding tensor to the same topology as the input. Figure 1 This training process involves optimizing the model parameters to minimize the difference between the input topology and the reconstructed topology.

[0111] Preferably, the process of constructing the BIM structure encoder model can be further refined into the following steps: First, a large number of BIM structure topology map samples are collected. These samples should cover different types of bridge steel structures to ensure the generalization ability of the model. Then, the topology map of each sample is encoded using the BIM graph neural network. During the encoding process, the number of layers of the network and the number of nodes per layer can be set. For example, a multi-layer graph convolutional network is used, and the number of nodes per layer can be adjusted according to the complexity of the topology map. Next, the encoded tensor is decoded through the BIM model reconstruction network to reconstruct the three-dimensional topology structure. During the training process, the mean square error (MSE) can be used as the loss function, and the model parameters can be optimized through the back propagation algorithm to minimize the difference between the input topology map and the reconstructed topology map.

[0112] Furthermore, to improve model training efficiency, techniques such as batch normalization and early stopping can be used. These specific technical measures can ensure that the BIM structural encoder model can effectively extract structural features and provide high-quality feature representation for subsequent similarity calculation and collaborative design.

[0113] In some embodiments, calculating the similarity index between each pair of the bridge steel structure BIM models includes:

[0114] The BIM structure encoder model is used to encode two BIM models to obtain two corresponding feature tensors, structural feature similarities of the two feature tensors are calculated, and similarity indicators of the two BIM models are determined based on the numerical values ​​of the structural feature similarities.

[0115] It should be noted that the process of calculating the similarity index between two BIM models of bridge steel structures mentioned in the present invention is to quantify the structural similarity between different BIM models. This process encodes two BIM models using the BIM structure encoder model to obtain two corresponding feature tensors, and then calculates the structural feature similarity of the two feature tensors. The numerical value of the similarity index can reflect the degree of similarity between the two BIM models in structural features. The higher the value, the more similar the two models are. This similarity calculation method provides an important basis for subsequent model retrieval and collaborative design, and can help designers quickly find reference models similar to the model to be designed, thereby improving design efficiency and quality.

[0116] Specifically, the BIM structural encoder model encodes the BIM structural topology diagram, converting complex geometric structures and spatial relationships into feature tensors. A feature tensor is a multidimensional array that compactly represents the structural features of a model. Structural feature similarity is calculated by comparing two feature tensors. This calculation process can employ a variety of similarity metrics, such as cosine similarity and Euclidean distance. Cosine similarity measures the similarity of two vectors by calculating the cosine of the angle between them; values ​​closer to 1 indicate higher similarity. Euclidean distance measures the difference between two vectors by calculating the straight-line distance between them; smaller distances indicate higher similarity. In practical applications, the appropriate similarity metric can be selected based on specific design requirements.

[0117] The process of calculating the similarity index can further include the following steps: First, each BIM model is encoded using a trained BIM structure encoder model to obtain a feature tensor for each model. During the encoding process, the model's topological structure data, such as node coordinates and edge connectivity, can be input. Then, an appropriate similarity metric is selected, such as cosine similarity. When calculating the cosine similarity of two feature tensors, the dot product of the two tensors can be calculated, the norm of each tensor can be calculated separately, and finally the dot product can be divided by the product of the two norms. In this way, a similarity value between 0 and 1 can be obtained. To improve computational efficiency, matrix operations can be used to simultaneously calculate the similarity between multiple models. In addition, a similarity threshold can be set according to actual needs, such as 0.8, to screen out reference models with a similarity to the model to be designed that exceeds this threshold. Through these specific technical means, the similarity calculation process can be ensured to be efficient and accurate, providing a reliable reference basis for subsequent collaborative design.

[0118] In some embodiments, the BIM data fusion model includes:

[0119] The parameter encoder adopts a BIM feature encoder to encode the BIM design parameter vector of each BIM model into a first feature vector;

[0120] The collaborative data encoder uses a BIM context encoder to encode the collaborative design data vectors of several similar models corresponding to each BIM model into a second feature vector;

[0121] The second feature vector is weighted according to the corresponding similarity index, and tensor splicing is performed with the first feature vector through the BIM feature fusion layer to form a fused feature vector;

[0122] The prediction decoder adopts the BIM data generation network, combined with the attention mechanism and the gated recurrent unit, to decode the fused feature vector into the collaborative design data of the BIM model to be generated.

[0123] The BIM data fusion model is used to fuse BIM design parameters and collaborative design data. Its purpose is to generate high-quality collaborative design data, thereby providing strong support for the collaborative design of bridge steel structures. This model effectively integrates BIM design parameter vectors and collaborative design data vectors through the collaborative work of multiple modules, including a parameter encoder, collaborative data encoder, feature weighting, feature fusion, and a predictive decoder. It also utilizes techniques such as attention mechanisms and gated recurrent units to improve the accuracy and efficiency of data fusion. This data fusion method can fully leverage existing design experience and data to generate collaborative design solutions whose similarity to the model to be designed meets a set threshold, thereby improving design efficiency and quality.

[0124] Specifically, the parameter encoder in the BIM data fusion model uses a BIM feature encoder, which encodes the BIM design parameter vector of each bridge steel structure BIM model into a first feature vector. This BIM design parameter vector includes information such as the geometric parameters, material properties, and connection methods of each structural component in the model. The collaborative data encoder uses a BIM context encoder, which encodes the collaborative design data vectors of several similar models corresponding to each BIM model into a second feature vector. This collaborative design data vector contains information such as design change records and collaborative operation records. During the feature fusion stage, the second feature vector is weighted according to the corresponding similarity index and then tensor-concatenated with the first feature vector through the BIM feature fusion layer to form a fused feature vector. The similarity index reflects the structural similarity between the reference model and the model to be designed. The predictive decoder uses a BIM data generation network, combined with an attention mechanism and a gated recurrent unit, to decode the fused feature vector into the collaborative design data of the generated BIM model. The attention mechanism is used to highlight important features, while the gated recurrent unit is used to process sequential data, ensuring that the generated collaborative design data has good temporal and spatial consistency.

[0125] The process of building a BIM data fusion model can include the following steps: First, define the structure and parameters of the BIM feature encoder. For example, a multi-layer perceptron (MLP) or a convolutional neural network (CNN) can be used as the feature encoder architecture, with input parameters being specific values ​​in the BIM design parameter vector, such as component length, width, and material strength. For the collaborative data encoder, a recurrent neural network (RNN) or a long short-term memory (LSTM) network can be used to process the sequential information in the collaborative design data vector, with input parameters being the time series data of design change records. During feature weighting, the second feature vector can be weighted based on the value of a similarity metric; for example, higher similarity corresponds to a greater weight. The feature fusion layer can use a simple concatenation operation to merge the weighted second feature vector with the first feature vector into a single fused feature vector. In the predictive decoder, parameters of the attention mechanism, such as the number of attention heads and the hidden layer dimensionality, can be configured to highlight important feature information. Furthermore, parameters of the gated recurrent unit, such as the hidden state dimensionality and the type of gating function, also need to be adjusted based on the specific data characteristics. Through these specific technical means, we can ensure that the BIM data fusion model can effectively generate high-quality collaborative design data, providing efficient and accurate support for the collaborative design of bridge steel structures.

[0126] The aforementioned embodiments of the present invention have the following beneficial effects: The present invention can enhance the intelligent design of steel bridge structures. The BIM structural encoder model automatically extracts structural features from historical models and retrieves and matches the most relevant reference cases based on similarity, enabling designers to quickly access verified optimization solutions. The BIM data fusion model intelligently integrates current design parameters with collaborative data from similar models. Feature weighting and attention mechanisms are used to generate optimal collaborative design solutions, effectively avoiding duplication of design work and improving design quality.

[0127] This approach fully leverages historical project data for knowledge reuse, ensuring comparability across projects through parameter standardization and topological feature extraction. Graph neural network-based 3D topology reconstruction accurately captures structural change characteristics, while sequence alignment algorithms and redundancy removal optimize collaborative data quality. The resulting collaborative design prediction model automatically generates collaborative data that complies with engineering specifications, significantly shortening design cycles and reducing the risk of human error, providing intelligent decision support for bridge steel structure design.

[0128] like Figure 2 As shown, some embodiments provide a bridge steel structure collaborative design system based on BIM technology, the system comprising:

[0129] A BIM data integration module 201 is configured to obtain a BIM model of a bridge steel structure from a BIM engineering database, and obtain a BIM design parameter vector, a BIM structure topology diagram, and a collaborative design data vector for each model based on the model;

[0130] The BIM feature comparison module 202 is configured to establish a BIM structure encoder model, train the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structure feature extraction model; calculate similarity indicators between the bridge steel structure BIM models based on the structure feature extraction model, and obtain a bridge steel structure BIM model that meets the conditions as a similar model;

[0131] A BIM model training module 203 is used to establish a BIM data fusion model and train the BIM data fusion model to obtain a collaborative design prediction model;

[0132] The BIM collaborative generation module 204 is used to obtain the BIM model of the bridge steel structure to be collaboratively designed, and based on the BIM model to be collaboratively designed, use the similarity model to input the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

[0133] It is understandable that the modules and references recorded in the BIM-based bridge steel structure collaborative design system Figure 1 The steps in the BIM-based collaborative design method for bridge steel structures correspond to each other. Therefore, the operations, features, and beneficial effects described above for the BIM-based collaborative design method for bridge steel structures are also applicable to the BIM-based collaborative design system for bridge steel structures and the modules contained therein, and will not be repeated here.

[0134] Reference below Figure 3 , which shows a schematic structural diagram of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0135] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0136] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0137] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0138] The above descriptions are merely some preferred embodiments of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also encompass other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by mutually replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. A bridge steel structure collaborative design method based on BIM technology, characterized in that: include: Obtain multiple completed bridge steel structure BIM models from the BIM engineering database, and obtain the BIM design parameter vectors, BIM structural topology diagrams, and collaborative design data vectors for each model; Establishing a BIM structure encoder model, and training the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structural feature extraction model; Based on the structural feature extraction model, calculating the similarity index between the bridge steel structure BIM models, and obtaining the bridge steel structure BIM models that meet the conditions as similar models; Establishing a BIM data fusion model, and training the BIM data fusion model to obtain a collaborative design prediction model; Obtain a BIM model of the bridge steel structure to be collaboratively designed. Based on the BIM model to be collaboratively designed, use the similarity model to input the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

2. The bridge steel structure collaborative design method according to claim 1, characterized in that: Each of the bridge steel structure BIM models includes: a BIM design parameter module, a BIM structural topology module and a collaborative design data module; wherein the BIM design parameter module includes: multiple structural components contained in the model, the BIM parametric attribute value of each component and the BIM annotation information contained in the model.

3. The bridge steel structure collaborative design method according to claim 2, characterized in that: Obtaining the BIM design parameter vector includes: Perform parameter standardization processing on the BIM design parameter module using a BIM data preprocessing tool; The standardized design parameters are converted into the BIM design parameter vector using a BIM parameter encoding method.

4. The bridge steel structure collaborative design method according to claim 3, characterized in that: Acquiring the collaborative design data vector includes: Performing data normalization processing on the collaborative design data module using a BIM information cleaning tool; Obtaining a BIM collaborative data template for the engineering category to which the bridge steel structure belongs, and using a sequence alignment algorithm to calculate the matching degree between the normalized collaborative data and the template; When the matching degree reaches or exceeds a set threshold, redundant parts of the normalized collaborative data and the template are removed; The collaborative data after removing the redundant parts is converted into the collaborative design data vector by using the BIM data encoding method.

5. The bridge steel structure collaborative design method according to claim 4, characterized in that: The processing of the BIM design parameter module or the collaborative design data module by using a BIM data preprocessing tool or a BIM information cleaning tool includes: Remove unstructured BIM tags and format control symbols; Clear temporary marking information during the design phase; Filter statements containing special engineering symbols, unit identifiers, or component codes; Unified tolerance annotations and version identifiers in parameters; Remove temporary change parameters during the construction deepening phase; Clear the component attribute parameters added after the design closed loop; Remove redundant labels from component classification.

6. The bridge steel structure collaborative design method according to claim 1, characterized in that: Generating the BIM structure topology diagram includes: Parsing the initial BIM model and the revised BIM model into parametric topological structures respectively; The BIM change detection algorithm is used to calculate the topological node mapping relationship between the initial and revised BIM models; Based on the mapping relationship, the change operation type of the BIM model is determined, topological feature nodes are generated according to the change type, and the topological feature nodes are combined into a three-dimensional topological graph according to the hierarchical structure of the initial BIM model to form a BIM structure topological graph; wherein the change operation types include geometric adjustment, component removal, component addition, position offset, and topology preservation.

7. The bridge steel structure collaborative design method according to claim 1, characterized in that: The establishing of a BIM structure encoder model and training the BIM structure encoder model based on the multiple BIM structure topology graphs to obtain a structure feature extraction model includes: The encoder uses a BIM graph neural network to aggregate the geometric attributes of each node in the structural topology graph from bottom to top to form a coding tensor; The decoder uses the BIM model to reconstruct the network and restore the encoded tensor to a three-dimensional topological structure from top to bottom; Based on the multiple BIM structure topology graphs, a topology reconstruction training strategy is used to enable the three-dimensional topology structure to completely reproduce the input BIM structure topology graph.

8. The bridge steel structure collaborative design method according to claim 6, characterized in that: The calculating of the similarity index between each pair of the bridge steel structure BIM models includes: The BIM structure encoder model is used to encode two BIM models to obtain two corresponding feature tensors, structural feature similarities of the two feature tensors are calculated, and similarity indicators of the two BIM models are determined based on the numerical values ​​of the structural feature similarities.

9. The bridge steel structure collaborative design method according to claim 1, characterized in that: Training the BIM data fusion model includes: The parameter encoder adopts a BIM feature encoder to encode the BIM design parameter vector of each bridge steel structure BIM model into a first feature vector; The collaborative data encoder uses a BIM context encoder to encode the collaborative design data vectors of several similar models corresponding to each BIM model into a second feature vector; The second feature vector is weighted according to the corresponding similarity index, and tensor splicing is performed with the first feature vector through the BIM feature fusion layer to form a fused feature vector; The prediction decoder adopts the BIM data generation network, combined with the attention mechanism and the gated recurrent unit, to decode the fused feature vector into the collaborative design data of the BIM model to be generated.

10. A bridge steel structure collaborative design system based on BIM technology, characterized by: include: A BIM data integration module is used to obtain a BIM model of the bridge steel structure from a BIM engineering database, and obtain a BIM design parameter vector, a BIM structure topology diagram, and a collaborative design data vector for each model based on the model; A BIM feature comparison module is configured to establish a BIM structure encoder model, train the BIM structure encoder model based on the plurality of BIM structure topology graphs to obtain a structure feature extraction model; calculate similarity indices between two of the bridge steel structure BIM models based on the structure feature extraction model, and obtain a bridge steel structure BIM model that meets the conditions as a similarity model; A BIM model training module is used to establish a BIM data fusion model and train the BIM data fusion model to obtain a collaborative design prediction model; The BIM collaborative generation module is used to obtain the BIM model of the bridge steel structure to be collaboratively designed, and based on the BIM model to be collaboratively designed, use the similarity model to take the BIM design parameter vector of the BIM model to be collaboratively designed and the collaborative design data vectors of several similar models corresponding to the model as input, input them into the collaborative design prediction model for processing, and output the collaborative design data of the BIM model to be collaboratively designed.

Images