BIM (Building Information Modeling)-based special-shaped hyperboloid building field model generation method and system

Abstract

The invention relates to the technical field of building simulation, and discloses a BIM-based special-shaped hyperboloid building site model generation method and system, and the method comprises the steps: collecting the multi-source heterogeneous point cloud data of a special-shaped hyperboloid building site to construct a three-dimensional feature tensor model, and recognizing the key curvature mutation point of the tensor model to construct a space reference topology network; based on the digital skeleton model, geometric contour features are analyzed, hyperboloid fitting is carried out, and an initial BIM model is obtained; performing multi-physics field coupling simulation on the initial model to obtain a target BIM model; extracting curvature distribution and structural stress parameters of the target BIM model to obtain basic model parameters, and constructing a building performance prediction model in combination with historical performance reference data; and inquiring a bearing capacity standard and a deformation threshold value, and analyzing the optimal curved surface parameter combination and a prestress applying strategy to obtain optimized simulation parameters, so as to simulate the special-shaped hyperboloid building by utilizing target model simulation. According to the method, the simulation precision of the special-shaped hyperboloid building can be improved.

Description

Technical Field

[0001] The invention relates to a method and a system for generating a site model of a special-shaped hyperbolic building based on BIM, and belongs to the technical field of building simulation. Background Art

[0002] In modern architectural design, special-shaped hyperbolic buildings have gradually become the focus of the architectural field with their unique aesthetic effects and innovation. The complex curved surface modeling of this type of building breaks through the regular form of traditional buildings and adds a different charm to the city skyline. However, its unique geometric shape has brought unprecedented challenges to building construction. Site model generation is crucial for the construction of special-shaped hyperbolic buildings. Accurate site models can help the construction team intuitively understand the architectural design intent, effectively plan the construction process, and accurately guide construction operations, thereby ensuring building quality, reducing construction errors, and controlling construction costs and construction periods. By building a detailed site model, potential problems in design and construction can be discovered in advance, and timely adjustments and optimizations can be achieved.

[0003] At present, there are many methods for generating on-site models of special-shaped hyperbolic buildings. Traditional methods mostly rely on manual measurement and interpretation of two-dimensional drawings. This method is not only inefficient, but also difficult to ensure the accuracy of measurement data when facing complex hyperbolic surfaces, which can easily cause model deviations, leading to rework and waste of resources during construction. Although some methods based on computer-aided design (CAD) have improved modeling efficiency to a certain extent, they are insufficient in data processing and model detail expression for complex hyperbolic surface shapes, and it is difficult to meet the needs of on-site construction for high-precision models. Summary of the invention

[0004] The present invention provides a method and system for generating a site model of a special-shaped hyperbolic building based on BIM, the main purpose of which is to improve the simulation accuracy of the special-shaped hyperbolic building.

[0005] To achieve the above object, the present invention provides a method for generating a site model of a special-shaped hyperbolic building based on BIM, comprising: Collect multi-source heterogeneous point cloud data at the site of the special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building; Based on the spatial reference topological network, a digital skeleton model of the special-shaped hyperbolic building is constructed; using the digital skeleton model, geometric contour features of the special-shaped hyperbolic building are analyzed; based on the geometric contour features, a hyperbolic surface is fitted to the special-shaped hyperbolic building to obtain surface fitting information; based on the surface fitting information, an initial BIM model of the special-shaped hyperbolic building is constructed; Performing multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model, dividing the initial structural model into building information units to obtain building division units, constructing a mechanical relationship model between each unit of the building division unit, and obtaining a target BIM model; The curvature distribution parameters and structural stress parameters of the target BIM model are extracted to obtain basic model parameters, the historical performance benchmark data of the special-shaped hyperbolic building are queried, and a building performance prediction model of the special-shaped hyperbolic building is constructed by using the basic model parameters and the historical performance benchmark data. The bearing capacity standard and deformation threshold of the special-shaped hyperbolic building are queried, and the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building are analyzed by using the building performance prediction model to obtain optimized simulation parameters. Based on the optimized simulation parameters, the special-shaped hyperbolic building is simulated by using the target BIM model.

[0006] Optionally, constructing a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data includes: Querying geometric information, radar echo information and material images in the multi-source heterogeneous point cloud data; Based on the geometric information, calculating geometric features of the multi-source heterogeneous point cloud data; Analyzing material features in the multi-source heterogeneous point cloud data based on the radar echo information; Analyzing defect features in the multi-source heterogeneous point cloud data based on the material image; Based on the geometric features, the material features and the defect features, a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data is constructed.

[0007] Optionally, the identifying a key curvature mutation point of the three-dimensional feature tensor model includes: Performing point cloud mapping on the three-dimensional feature tensor model to obtain a mapping point cloud; Constructing a set of domain points of the mapping point cloud; Calculating the covariance matrix of the domain point set; Performing eigenvalue decomposition on the covariance matrix to obtain decomposition eigenvalues; Based on the decomposed eigenvalues, calculating the principal curvature and principal direction of the mapped point cloud; Based on the principal curvature and the principal direction, a key curvature mutation point of the three-dimensional feature tensor model is determined.

[0008] Optionally, the use of the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building includes: Using the key curvature mutation points, constructing the topological network nodes of the special-shaped hyperbolic building; Identify the spatial position relationship and geometric features of the key curvature mutation points to determine the connection relationship of the topological network nodes; Perform node linking on each node in the topology network based on the connection relationship to obtain an initial reference topology network; After configuring the attributes of the initial reference topology network, a spatial reference topology network is obtained.

[0009] Optionally, the using the digital skeleton model to analyze the geometric contour features of the special-shaped hyperbolic building includes: Querying curvature feature points in the digital skeleton model; Using a preconfigured spatial alignment matrix to spatially register the curvature feature points to obtain a registration point cloud; Using the registered point cloud as a characteristic reference point of a special-shaped hyperbolic building; Performing surface smoothing processing on the characteristic reference points to obtain regularized characteristic points; A hyperbolic surface parameterized fitting is performed on the regularized feature points, and the geometric contour features of the special-shaped hyperbolic surface building are determined based on the fitting result of the hyperbolic surface parameterized fitting.

[0010] Optionally, performing hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour feature to obtain surface fitting information includes: Constructing a point coordinate tensor of the geometric contour feature; Querying the fitting constraint conditions of the special-shaped hyperbolic building; Based on the point coordinate tensor and the fitting constraint condition, construct a tensor product interpolation matrix of the special-shaped hyperbolic building; Based on the tensor product interpolation matrix, constructing a sparse regularization equation for the special-shaped hyperbolic building; The sparse regularized equation group is solved, and the surface fitting information of the special-shaped hyperbolic building is determined according to the solution set of the sparse regularized equation group.

[0011] Optionally, performing multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model includes: Performing structural mechanics analysis on the initial BIM model to obtain structural mechanics information; Based on the structural mechanics information, construct a structural mechanics response simulation module of the initial BIM model; Performing thermodynamic analysis on the initial BIM model to obtain thermodynamic information; Based on the thermodynamic information, construct a surface temperature change analysis module of the initial BIM model; Performing wind load analysis on the initial BIM model to obtain wind load information; Based on the wind load information, construct a wind load dynamic module of the initial BIM model; Based on the structural mechanics response simulation module, the curved surface temperature change analysis module and the wind load dynamic module, multi-physical field coupling simulation is performed on the initial BIM model to obtain an initial structural model.

[0012] Optionally, constructing a mechanical relationship model between each unit of the building division unit to obtain a target BIM model includes: Querying the connection mode between each unit in the building division unit; Based on the connection mode, determining the unit stress type of the building division unit; Based on the unit stress type, constructing a mechanical equilibrium function of the building division unit; Calculating the stress value of the building division unit based on the mechanical equilibrium function; The stress value is imported into the initial BIM model to obtain a target BIM model.

[0013] Optionally, the use of the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building includes: configuring an initial prediction model of the special-shaped hyperbolic building; utilizing the base model parameters and the historical performance benchmark data; Performing model training on the initial prediction model to obtain a performance prediction matrix; The composite performance deviation value of the performance prediction matrix is ​​calculated using the following formula: ; in, Indicates the composite performance deviation value, represents the actual wind-induced displacement at time t, express The predicted value of Indicates the degree of damage to the material. express The predicted value of Indicates the material deformation error, express The predicted value of represents the wind vibration weight, represents the damage weight, represents the thermal deformation weight, represents the maximum instantaneous displacement deviation, represents the damage distribution divergence, represents the average deformation error; When the composite performance deviation value is not greater than a preset composite performance deviation value, the initial prediction model is used as a building performance prediction model.

[0014] In order to solve the above problems, the present invention also provides a BIM-based site model generation system for special-shaped hyperbolic building, the system comprising: A topological network construction module is used to collect multi-source heterogeneous point cloud data at the site of a special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building; An initial BIM model construction module is used to construct a digital skeleton model of the special-shaped hyperbolic building based on the spatial reference topological network, analyze the geometric contour features of the special-shaped hyperbolic building by using the digital skeleton model, perform hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour features to obtain surface fitting information, and construct an initial BIM model of the special-shaped hyperbolic building based on the surface fitting information; The target BIM model is constructed to perform multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model, divide the initial structural model into building information units to obtain building division units, and construct a mechanical relationship model between each unit of the building division unit to obtain a target BIM model; The building simulation module is used to extract the curvature distribution parameters and structural stress parameters of the target BIM model to obtain basic model parameters, query the historical performance benchmark data of the special-shaped hyperbolic building, use the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building, query the bearing capacity standard and deformation threshold of the special-shaped hyperbolic building, use the building performance prediction model to analyze the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building, obtain optimized simulation parameters, and simulate the special-shaped hyperbolic building based on the optimized simulation parameters using the target BIM model.

[0015] Compared with the problems described in the background technology, the embodiment of the present invention first collects multi-source heterogeneous point cloud data to obtain comprehensive and rich building site information, and then constructs a three-dimensional feature tensor model to better capture the spatial characteristics, geometric relationships and intrinsic connections between different data sources of the data, and performs a series of operations such as point cloud mapping on the three-dimensional feature tensor model to identify key curvature mutation points, which help users understand the spatial form and structural characteristics of the building, and lay the foundation for building the spatial topological structure of the building; further, the present invention uses digital technology based on the spatial reference topological network to extract the key geometric features and topological relationships of the special-shaped hyperbolic building, and then analyzes the geometric contour features of the building, extracts information such as boundaries, curvature changes and concave-convex features, and ensures that the fitted hyperbolic surface is highly consistent with the actual building's shape, and then analyzes the surface fitting information of the building, and represents the complex building shape with a mathematical model, which is convenient for various calculations and analyses, and based on the surface fitting information, uses parametric modeling tools to import geometric data into the BIM platform to build an initial BIM Model, obtain an integrated digital model, integrate the geometric and non-geometric information of the building, and provide a unified information platform for the full life cycle management of the construction project; further, the present invention analyzes the initial BIM model in terms of structural mechanics, thermodynamics, wind load, etc. to consider the influence of various physical phenomena and their interactions faced by the building in actual use, and then divides the obtained initial structural model into building information units to refine the functions and effects of different parts of the analysis model; further, the present invention extracts basic model parameters such as curvature distribution parameters and structural stress parameters from the target BIM model to clearly grasp the morphological changes on the surface of the building and the stress conditions of the structure, and provides a quantitative basis for analyzing the performance of the building, and by querying the historical performance benchmark data of the special-shaped hyperbolic building, and comparing and analyzing with the currently extracted basic model parameters, the current performance status of the building is evaluated, and then a performance prediction model is trained to help users understand the behavior of the building under different conditions in advance, predict possible problems and formulate preventive measures, and use the performance prediction model to find out the surface parameter combination and prestressing strategy that makes the building performance optimal, so as to simulate the special-shaped hyperbolic building, so as to achieve the purpose of improving the simulation accuracy of the special-shaped hyperbolic building. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a method for generating a site model of a special-shaped hyperbolic building based on BIM provided by one embodiment of the present invention; Figure 2 A schematic diagram of a module for implementing a method for generating a site model of a special-shaped hyperbolic building based on BIM provided in one embodiment of the present invention.

[0017] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The embodiment of the present application provides a method for generating a site model of a special-shaped hyperbolic building based on BIM. The execution subject of the method for generating a site model of a special-shaped hyperbolic building based on BIM includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for generating a site model of a special-shaped hyperbolic building based on BIM can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. Example 1

[0020] Reference Figure 1 FIG. 1 is a flow chart of a method for generating a site model of a special-shaped hyperbolic building based on BIM according to an embodiment of the present invention. In this embodiment, the method for generating a site model of a special-shaped hyperbolic building based on BIM includes: S1. Collect multi-source heterogeneous point cloud data at the site of the special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topology network of the special-shaped hyperbolic building.

[0021] The embodiment of the present invention can obtain comprehensive and rich building site information by collecting multi-source heterogeneous point cloud data at the site of the special-shaped hyperbolic building. At the same time, the multi-source heterogeneous data can complement each other to ensure that key information is not missed, laying a solid foundation for building a high-precision and complete model.

[0022] Among them, the irregular hyperbolic building refers to a building with unique geometric features in architectural form. "Irregular" means that the shape is irregular, breaking through the simple geometric shapes commonly seen in traditional buildings (such as rectangles, cylinders, etc.), and has a complex and changeable appearance; "hyperbolic" means that the surface of the building is composed of a mathematical surface called a hyperbolic surface.

[0023] Optionally, the multi-source heterogeneous point cloud data can be acquired by scanning the special-shaped hyperbolic building on-site through a mobile scanning system that integrates millimeter-wave radar and inertial navigation.

[0024] The embodiment of the present invention can better capture the spatial characteristics, geometric relationships and intrinsic connections between different data sources of the data by constructing the three-dimensional feature tensor model of the multi-source heterogeneous point cloud data.

[0025] As an embodiment of the present invention, the construction of a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data includes: querying the geometric information, radar echo information and material images in the multi-source heterogeneous point cloud data, calculating the geometric features of the multi-source heterogeneous point cloud data based on the geometric information, analyzing the material features in the multi-source heterogeneous point cloud data based on the radar echo information, analyzing the defect features in the multi-source heterogeneous point cloud data based on the material image, and constructing a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data based on the geometric features, the material features and the defect features.

[0026] Among them, the geometric information refers to information related to the shape, size, position and spatial relationship of the object, and the radar echo information refers to the various information contained in the signal received by the radar after the millimeter wave radar emits a millimeter wave signal and the signal is reflected back after encountering an object.

[0027] Optionally, the geometric information can be obtained by querying the architectural geometric data of the corresponding special-shaped hyperbolic building in the multi-source heterogeneous point cloud data; the radar echo information can be obtained by querying the data collected by the millimeter wave radar setting in the field data of the special-shaped hyperbolic building; the material image can be obtained by collecting the image information of the special-shaped hyperbolic building by a high-definition camera. The calculation of the geometric features of the multi-source heterogeneous point cloud data based on the geometric information can be obtained by calculating the coordinates, normal vectors and curvature of the building points in the special-shaped hyperbolic building. The material features can be obtained by analyzing the intensity and frequency of the reflected signal of the radar echo information. The defect features can be identified by analyzing the image features of the material image using a convolution model. The three-dimensional feature tensor model can determine the three dimensions of the multi-source heterogeneous point cloud data using the geometric features, the material features and the defect features, and then fill the point cloud data features in the multi-source heterogeneous point cloud data into the corresponding dimensions.

[0028] Furthermore, the embodiment of the present invention can help users understand the spatial form and structural characteristics of a building by identifying the key curvature mutation points of the three-dimensional feature tensor model, thereby facilitating the construction of the spatial topological structure of the building.

[0029] The key curvature mutation point refers to a point in three-dimensional space where the curvature of an object surface (such as the surface of a special-shaped hyperbolic building) changes significantly and suddenly.

[0030] As an embodiment of the present invention, the identifying of the key curvature mutation points of the three-dimensional feature tensor model includes: performing point cloud mapping on the three-dimensional feature tensor model to obtain a mapping point cloud, constructing a domain point set of the mapping point cloud, calculating the covariance matrix of the domain point set, performing eigenvalue decomposition on the covariance matrix to obtain decomposed eigenvalues, calculating the principal curvature and principal direction of the mapping point cloud based on the decomposed eigenvalues, and determining the key curvature mutation points of the three-dimensional feature tensor model based on the principal curvature and the principal direction.

[0031] Optionally, the mapping point cloud can be obtained by filtering the three-dimensional feature tensor model and then normalizing it. The domain point set can be obtained by determining the neighborhood range of the point cloud data point through the k-nearest neighbor algorithm, and then collecting all the points within the range. The covariance matrix can be obtained by first calculating the mean of the coordinates of each point in the neighborhood point set, and then using the covariance calculation formula to calculate the covariance between the coordinates of each point in the neighborhood point set, and then constructing a matrix. The decomposed eigenvalues ​​can be obtained by decomposing the covariance matrix using a linear algebra algorithm, such as the QR algorithm. The principal curvature and principal direction can be calculated using a differential geometry algorithm. The key curvature mutation point can be obtained by comparing the calculated principal curvature and principal direction values ​​with a preset threshold, and the preset threshold needs to be set in combination with the actual application data.

[0032] Furthermore, the embodiment of the present invention utilizes the key curvature mutation points to construct the spatial reference topological network of the special-shaped hyperbolic building, which can clarify the relationship between the key structural points in the building, facilitate the analysis of the spatial contour of the building, and facilitate better construction of the building model.

[0033] The spatial reference topological network refers to a network model constructed based on spatial position relationship and topological structure and used to describe the relationship between specific spatial objects.

[0034] As an embodiment of the present invention, the method of constructing a spatial reference topological network of the special-shaped hyperbolic building by using the key curvature mutation points includes: constructing the topological network nodes of the special-shaped hyperbolic building by using the key curvature mutation points, identifying the spatial position relationship and geometric features of the key curvature mutation points to determine the connection relationship of the topological network nodes, linking each node in the topological network nodes based on the connection relationship to obtain an initial reference topological network, and obtaining a spatial reference topological network after configuring the attributes of the initial reference topological network.

[0035] Optionally, the topological network nodes can be constructed using three-dimensional space coordinates. The geometric features can be obtained by calculating geometric parameters such as distances and angles between key curvature mutation points, and the spatial position relationship can be obtained by calculating the distances between points using, for example, the Euclidean distance formula. The attribute configuration of the initial reference topological network can be achieved by assigning geometric attributes to the nodes and edges of the topological network, such as the coordinates and curvature values ​​of the nodes, the length and direction of the edges, and assigning physical attributes to the nodes and edges of the topological network according to the structure and material properties of the building, such as the bearing capacity of the nodes and the stiffness of the edges.

[0036] S2. Based on the spatial reference topological network, a digital skeleton model of the special-shaped hyperbolic building is constructed; using the digital skeleton model, geometric contour features of the special-shaped hyperbolic building are analyzed; based on the geometric contour features, a hyperbolic surface is fitted to the special-shaped hyperbolic building to obtain surface fitting information; based on the surface fitting information, an initial BIM model of the special-shaped hyperbolic building is constructed.

[0037] The embodiment of the present invention constructs the digital skeleton model of the special-shaped hyperbolic building based on the spatial reference topological network, and can extract key lines and nodes that can represent the structure and form of the special-shaped hyperbolic building.

[0038] The digital skeleton model refers to a simplified geometric representation of a building or structure constructed through digital technology, which is usually used to describe its core form, topological relationship and key features.

[0039] Optionally, the digital skeleton model can be constructed based on a spatial reference topological network by extracting key geometric features and topological relationships of special-shaped hyperbolic buildings through digital technology.

[0040] Furthermore, the embodiment of the present invention can analyze the geometric contour features of the irregular hyperbolic building by utilizing the digital skeleton model to extract geometric contour information such as the building's boundary, curvature changes, and concave-convex features, which is accurate and ensures that the fitted hyperbolic surface is highly consistent with the actual building's appearance.

[0041] As an embodiment of the present invention, the use of the digital skeleton model to analyze the geometric contour features of the irregular hyperbolic building includes: querying the curvature feature points in the digital skeleton model, spatially registering the curvature feature points using a preconfigured spatial alignment matrix to obtain a registered point cloud, using the registered point cloud as feature reference points of the irregular hyperbolic building, performing surface smoothing on the feature reference points to obtain regularized feature points, performing hyperbolic parameterized fitting on the regularized feature points, and determining the geometric contour features of the irregular hyperbolic building based on the fitting results of the hyperbolic parameterized fitting.

[0042] Optionally, the curvature feature points can be obtained by traversing the digital skeleton model data and marking the points with abnormal or significant changes in curvature values ​​according to the curvature calculation algorithm. The registration point cloud can be obtained by using spatial alignment matrix geometry linear algebra matrix operations to perform transformation parameters such as translation, rotation and scaling on the rate feature points. The regularized feature points can be obtained by adjusting the feature reference points using algorithms such as least squares or Gaussian filtering to remove local noise and mutations. The hyperbolic parameterized fitting of the regularized feature points can be achieved by selecting a suitable hyperbolic model (such as NURBS hyperbolic surface), adjusting the hyperbolic parameters based on the regularized feature points through optimization algorithms such as least squares method, so that the hyperbolic best approximation feature point distribution is achieved.

[0043] Furthermore, the embodiment of the present invention can express the complex shape of the special-shaped hyperbolic building with a mathematical model by performing hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour features to obtain surface fitting information, which is convenient for various calculations and analyses and provides accurate surface data for building a BIM model.

[0044] As an embodiment of the present invention, the method of performing hyperbolic surface fitting on the irregular hyperbolic building based on the geometric contour features to obtain surface fitting information includes: constructing a point coordinate tensor of the geometric contour features, querying fitting constraints of the irregular hyperbolic building, constructing a tensor product interpolation matrix of the irregular hyperbolic building based on the point coordinate tensor and the fitting constraints, constructing a sparse regularized equation of the irregular hyperbolic building based on the tensor product interpolation matrix, solving the sparse regularized equation group, and determining the surface fitting information of the irregular hyperbolic building according to the solution set of the sparse regularized equation group.

[0045] The fitting constraint condition refers to the condition or rule used to limit and guide the generation of the surface during the hyperbolic surface fitting process, so as to ensure that the fitting result meets the design requirements or actual physical conditions.

[0046] Optionally, the point coordinate tensor can be obtained by arranging the three-dimensional coordinates of each point in the geometric contour feature in a specific order, such as arranging the three-dimensional coordinates of each point in the geometric contour feature in a specific order to form a tensor structure. For example, taking [x, y, z] as a group, the coordinates of all points are sequentially combined into a three-dimensional tensor. The fitting constraints can be obtained by extracting the conditions that need to be met when fitting the hyperbolic surface from architectural design documents, mechanical requirements and other materials, such as the curvature range and boundary conditions of a specific part. The tensor product interpolation matrix can be obtained by determining the interpolation nodes according to the point coordinate tensor, combining the fitting constraints, and constructing a matrix using the tensor product operation rules. The sparse regularization equation is formed by introducing a regularization term on the basis of the tensor product interpolation matrix. The solution of the sparse regularization equation group can be solved by using, for example, the gradient descent method and the conjugate gradient method.

[0047] The embodiment of the present invention can obtain an integrated digital model by constructing the initial BIM model of the special-shaped hyperbolic building based on the surface fitting information. The model integrates the geometric information and non-geometric information of the building, and provides a unified information platform for the full life cycle management of the construction project.

[0048] The initial BIM model refers to a digital building model created based on preliminary design data and geometric information in the early stage of the Building Information Modeling (BIM) process.

[0049] Optionally, the initial BIM model can be generated based on the surface fitting information by importing the geometric data of the special-shaped hyperboloid into the BIM platform using a parametric modeling tool.

[0050] S3. Perform multi-physical field coupling simulation on the initial BIM model to obtain an initial structural model, divide the initial structural model into building information units to obtain building division units, construct a mechanical relationship model between each unit of the building division unit, and obtain a target BIM model.

[0051] The embodiment of the present invention performs multi-physical field coupling simulation on the initial BIM model to obtain an initial structural model that can take into account various physical phenomena faced by buildings in actual use, such as mechanics, thermals, acoustics, etc., and then applies the effects of the interaction between these different physical fields to the initial BIM model for simulation.

[0052] As an embodiment of the present invention, the multi-physics field coupling simulation of the initial BIM model to obtain the initial structural model includes: performing structural mechanics analysis on the initial BIM model to obtain structural mechanics information, constructing a structural mechanics response simulation module of the initial BIM model based on the structural mechanics information, performing thermodynamics analysis on the initial BIM model to obtain thermodynamics information, constructing a surface temperature change analysis module of the initial BIM model based on the thermodynamic information, performing wind load analysis on the initial BIM model to obtain wind load information, constructing a wind load dynamic module of the initial BIM model based on the wind load information, and performing multi-physics field coupling simulation on the initial BIM model based on the structural mechanics response simulation module, the surface temperature change analysis module and the wind load dynamic module to obtain the initial structural model.

[0053] Optionally, the structural mechanics analysis of the initial BIM model can be performed using finite element analysis software to discretize the structural components in the BIM model, apply various loads (such as dead loads and live loads), and calculate the stress, strain, displacement and other information of each component. The structural mechanics response simulation module can organize the information obtained from the structural mechanics analysis into a data module, and combine the simulation algorithm to set the module input (such as different working conditions) and output (structural response results) interface. The thermodynamic analysis of the initial BIM model can establish a heat conduction model of the BIM model, consider the thermal physical parameters of the building materials, and analyze the temperature distribution and heat flow transfer under different boundary conditions (such as indoor and outdoor temperature differences). The wind load analysis of the initial BIM model can be based on the wind climate data of the building location, using the computational fluid dynamics (CFD) method to simulate the effect of wind on the building, and obtain information such as wind load size, distribution and wind pressure coefficient.

[0054] Furthermore, the embodiment of the present invention divides the initial structural model into building information units to obtain building division units, which can help users to finely analyze the functions and effects of different parts of the model.

[0055] Optionally, the initial structural model is divided into building information units, and the obtained building division units can be implemented by using tools such as Revit, according to the functional layout, structural characteristics and design requirements of the building, to determine whether the division is implemented by floors, rooms, structural components, etc.

[0056] Furthermore, the embodiment of the present invention obtains the target BIM model by constructing the mechanical relationship model between the various units of the building division units, which can clarify the force transmission mode and interaction mechanism between the various building division units, thereby helping users to deeply understand the mechanical behavior of the building structure and clearly grasp the transmission and distribution rules of the force in the structure.

[0057] As an embodiment of the present invention, constructing a mechanical relationship model between each unit of the building division unit to obtain a target BIM model includes: querying the connection mode between each unit in the building division unit, determining the unit stress type of the building division unit based on the connection mode, constructing a mechanical balance function of the building division unit based on the unit stress type, calculating the stress value of the building division unit based on the mechanical balance function, and importing the stress value into the initial BIM model to obtain the target BIM model.

[0058] Optionally, the connection method can be obtained by traversing each building division unit in the building information model, checking and recording the connection form between adjacent units, such as welding, bolt connection and mortise and tenon connection, or rigid connection, hinge connection and other connection methods between structural units. The unit stress type is obtained by judging the stress type borne by each building division unit, such as tension, pressure, shear force and bending moment, based on different connection methods and combined with mechanical principles. The mechanical balance function can establish a corresponding mechanical balance equation according to the stress type of each building division unit and the balance condition of Newtonian mechanics (balance of force and balance of moment). The stress value of the building division unit calculated based on the mechanical balance function can substitute the known parameters into the mechanical balance function, and the stress value of each building division unit can be obtained by solving the equation, which can be solved by numerical calculation method or analytical method, such as matrix operation, iterative algorithm, etc. The stress value is imported into the initial BIM model by associating the stress value data with the unit attributes in the model through the data import function of the BIM software.

[0059] S4. Extract the curvature distribution parameters and structural stress parameters of the target BIM model to obtain basic model parameters, query the historical performance benchmark data of the special-shaped hyperbolic building, construct a building performance prediction model for the special-shaped hyperbolic building using the basic model parameters and the historical performance benchmark data, query the bearing capacity standard and deformation threshold of the special-shaped hyperbolic building, and use the building performance prediction model to analyze the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building to obtain optimized simulation parameters, and based on the optimized simulation parameters, use the target BIM model to simulate the special-shaped hyperbolic building.

[0060] The embodiment of the present invention obtains basic model parameters by extracting the curvature distribution parameters and structural stress parameters of the target BIM model, which can clearly grasp the morphological changes on the surface of the building and the stress conditions of the structure, provide a quantitative basis for further analyzing the performance of the building, and help discover potential design or structural problems.

[0061] Optionally, the curvature distribution parameters and structural stress parameters may be obtained by querying a data storage terminal in the target BIM model.

[0062] In the embodiment of the present invention, the historical performance benchmark data of the special-shaped hyperbolic building can be queried and compared with the currently extracted basic model parameters to evaluate the current performance status of the building.

[0063] The historical performance benchmark data refers to representative and authoritative performance data of the historical records of the special-shaped hyperbolic building.

[0064] The embodiment of the present invention utilizes the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building, which can help users and designers understand the behavior of the building under different conditions in advance and predict possible performance degradation or structural damage, so as to formulate corresponding preventive measures and optimization plans to improve the reliability and durability of the building.

[0065] The building performance prediction model refers to a tool for predicting the performance of special-shaped hyperbolic buildings under different conditions.

[0066] As an embodiment of the present invention, the use of the basic model parameters and the historical performance benchmark data to construct the building performance prediction model of the special-shaped hyperbolic building includes: configuring an initial prediction model of the special-shaped hyperbolic building, using the basic model parameters and the historical performance benchmark data to perform model training on the initial prediction model to obtain a performance prediction matrix, and calculating the composite performance deviation value of the performance prediction matrix using the following formula: ; in, Indicates the composite performance deviation value, represents the actual wind-induced displacement at time t, express The predicted value of Indicates the degree of damage to the material. express The predicted value of Indicates the material deformation error, express The predicted value of represents the wind vibration weight, represents the damage weight, represents the thermal deformation weight, represents the maximum instantaneous displacement deviation, represents the damage distribution divergence, represents the average deformation error; When the composite performance deviation value is not greater than a preset composite performance deviation value, the initial prediction model is used as a building performance prediction model.

[0067] Optionally, the initial prediction model selects a suitable model architecture, such as a neural network, a regression model, etc., according to the characteristics of the special-shaped hyperbolic building and the performance prediction requirements. The initial prediction model is trained by using the basic model parameters and the historical performance benchmark data. The basic model parameters (such as curvature distribution parameters, structural stress parameters, etc.) and the historical performance benchmark data (such as past wind-induced displacement, material damage, deformation data, etc.) can be organized into a format acceptable to the model, and input into the initial prediction model as training data, and then the model is trained using a machine learning training algorithm, such as stochastic gradient descent, Adam optimization algorithm, etc.

[0068] Optionally, when the composite performance deviation value is not greater than a preset composite performance deviation value, the initial prediction model is used as the building performance prediction model to compare the calculated composite performance deviation value with the preset composite performance deviation value. If the calculated value is less than or equal to the preset value, it means that the prediction performance of the model has reached an acceptable level, and the initial prediction model at this time is determined as the final building performance prediction model; otherwise, return to the model training step, continue to adjust the model parameters for training, and the preset threshold of the composite performance deviation value can be set to 0.2, which needs to be set in combination with the actual application.

[0069] Furthermore, the embodiment of the present invention queries the bearing capacity standard and deformation threshold of the special-shaped hyperbolic building, and uses the building performance prediction model to analyze the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building, and obtains the optimized simulation parameters. It is possible to simulate and analyze different surface parameter combinations and prestressing strategies to find out the surface parameter combination and prestressing strategy that can achieve the best building performance.

[0070] Optionally, the optimization simulation parameters can input different surface parameter combinations (such as curvature parameters and shape parameters of hyperbolic surfaces) into a constructed building performance prediction model, allowing the model to simulate the performance of the building under these parameter combinations, evaluate the pros and cons of each parameter combination according to the bearing capacity standard and deformation threshold, and screen out parameter combinations that meet the requirements.

[0071] Furthermore, the embodiment of the present invention can provide specific guidance for the design, construction and operation of the building by simulating the special-shaped hyperbolic building based on the optimized simulation parameters and using the target BIM model, thereby helping engineers and designers make more scientific decisions and improving the reliability of building simulation.

[0072] Optionally, based on the optimized simulation parameters, the simulation of the special-shaped hyperbolic building using the target BIM model can organize the optimized simulation parameters (such as preferred surface parameters, prestressing parameters, etc.) in a format recognizable by the target BIM model to obtain preprocessed data, and then set reasonable boundary conditions in the target BIM model according to the actual situation and simulation requirements of the special-shaped hyperbolic building, such as fixed constraints, sliding constraints, etc. At the same time, according to the design requirements and actual working conditions, the model is applied with corresponding loads, such as dead loads, live loads, wind loads, and seismic loads. Finally, the simulation is performed in combination with the preprocessed data and boundary conditions.

[0073] Embodiment 2: like Figure 2 The figure shows a functional module diagram of a BIM-based on-site model generation system for special-shaped hyperbolic building according to the present invention.

[0074] The BIM-based field model generation system 200 of a special-shaped hyperbolic building of the present invention can be installed in an electronic device. According to the functions to be implemented, the BIM-based field model generation system of a special-shaped hyperbolic building can include a topology network construction module 201, an initial BIM model construction module 202, a target BIM model construction 203 and a building simulation module 204. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0075] In the embodiment of the present invention, the functions of each module / unit are as follows: The topological network construction module 201 is used to collect multi-source heterogeneous point cloud data at the site of the special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building; The initial BIM model construction module 202 is used to construct a digital skeleton model of the special-shaped hyperbolic building based on the spatial reference topological network, analyze the geometric contour features of the special-shaped hyperbolic building by using the digital skeleton model, perform hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour features to obtain surface fitting information, and construct the initial BIM model of the special-shaped hyperbolic building based on the surface fitting information; The target BIM model construction 203 is used to perform multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model, divide the initial structural model into building information units to obtain building division units, and construct a mechanical relationship model between each unit of the building division unit to obtain a target BIM model; The building simulation module 204 is used to extract the curvature distribution parameters and structural stress parameters of the target BIM model to obtain basic model parameters, query the historical performance benchmark data of the special-shaped hyperbolic building, use the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building, query the bearing capacity standard and deformation threshold of the special-shaped hyperbolic building, use the building performance prediction model to analyze the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building, obtain optimized simulation parameters, and simulate the special-shaped hyperbolic building based on the optimized simulation parameters using the target BIM model.

[0076] In detail, the modules in the BIM-based special-shaped hyperbolic building site model generation system 200 in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means are used as the method for generating a site model of a special-shaped hyperbolic building based on BIM described in the text, and can produce the same technical effects, so I will not go into details here.

[0077] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for generating a site model of a special-shaped hyperbolic building based on BIM, characterized in that: The method comprises: Collect multi-source heterogeneous point cloud data at the site of the special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building; Based on the spatial reference topological network, a digital skeleton model of the special-shaped hyperbolic building is constructed; using the digital skeleton model, geometric contour features of the special-shaped hyperbolic building are analyzed; based on the geometric contour features, a hyperbolic surface is fitted to the special-shaped hyperbolic building to obtain surface fitting information; based on the surface fitting information, an initial BIM model of the special-shaped hyperbolic building is constructed; Performing multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model, dividing the initial structural model into building information units to obtain building division units, constructing a mechanical relationship model between each unit of the building division unit, and obtaining a target BIM model; The curvature distribution parameters and structural stress parameters of the target BIM model are extracted to obtain basic model parameters, the historical performance benchmark data of the special-shaped hyperbolic building are queried, and a building performance prediction model of the special-shaped hyperbolic building is constructed by using the basic model parameters and the historical performance benchmark data. The bearing capacity standard and deformation threshold of the special-shaped hyperbolic building are queried, and the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building are analyzed by using the building performance prediction model to obtain optimized simulation parameters. Based on the optimized simulation parameters, the special-shaped hyperbolic building is simulated by using the target BIM model.

2. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The constructing of the three-dimensional feature tensor model of the multi-source heterogeneous point cloud data includes: Querying geometric information, radar echo information and material images in the multi-source heterogeneous point cloud data; Based on the geometric information, calculating geometric features of the multi-source heterogeneous point cloud data; Analyzing material features in the multi-source heterogeneous point cloud data based on the radar echo information; Analyzing defect features in the multi-source heterogeneous point cloud data based on the material image; Based on the geometric features, the material features and the defect features, a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data is constructed.

3. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The identifying of the key curvature mutation point of the three-dimensional feature tensor model comprises: Performing point cloud mapping on the three-dimensional feature tensor model to obtain a mapping point cloud; Constructing a set of domain points of the mapping point cloud; Calculating the covariance matrix of the domain point set; Performing eigenvalue decomposition on the covariance matrix to obtain decomposition eigenvalues; Based on the decomposed eigenvalues, calculating the principal curvature and principal direction of the mapped point cloud; Based on the principal curvature and the principal direction, a key curvature mutation point of the three-dimensional feature tensor model is determined.

4. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The method of using the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building includes: Using the key curvature mutation points, constructing the topological network nodes of the special-shaped hyperbolic building; Identify the spatial position relationship and geometric features of the key curvature mutation points to determine the connection relationship of the topological network nodes; Perform node linking on each node in the topology network based on the connection relationship to obtain an initial reference topology network; After configuring the attributes of the initial reference topology network, a spatial reference topology network is obtained.

5. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The method of analyzing the geometrical contour features of the special-shaped hyperbolic building by using the digital skeleton model includes: Querying curvature feature points in the digital skeleton model; Using a preconfigured spatial alignment matrix to spatially register the curvature feature points to obtain a registration point cloud; Using the registered point cloud as a characteristic reference point of a special-shaped hyperbolic building; Performing surface smoothing processing on the characteristic reference points to obtain regularized characteristic points; A hyperbolic surface parameterized fitting is performed on the regularized feature points, and the geometric contour features of the special-shaped hyperbolic surface building are determined based on the fitting result of the hyperbolic surface parameterized fitting.

6. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The step of performing hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour feature to obtain surface fitting information includes: Constructing a point coordinate tensor of the geometric contour feature; Querying the fitting constraint conditions of the special-shaped hyperbolic building; Based on the point coordinate tensor and the fitting constraint condition, construct a tensor product interpolation matrix of the special-shaped hyperbolic building; Based on the tensor product interpolation matrix, constructing a sparse regularization equation for the special-shaped hyperbolic building; The sparse regularized equation group is solved, and the surface fitting information of the special-shaped hyperbolic building is determined according to the solution set of the sparse regularized equation group.

7. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The performing multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model includes: Performing structural mechanics analysis on the initial BIM model to obtain structural mechanics information; Based on the structural mechanics information, construct a structural mechanics response simulation module of the initial BIM model; Performing thermodynamic analysis on the initial BIM model to obtain thermodynamic information; Based on the thermodynamic information, construct a surface temperature change analysis module of the initial BIM model; Performing wind load analysis on the initial BIM model to obtain wind load information; Based on the wind load information, construct a wind load dynamic module of the initial BIM model; Based on the structural mechanics response simulation module, the curved surface temperature change analysis module and the wind load dynamic module, multi-physical field coupling simulation is performed on the initial BIM model to obtain an initial structural model.

8. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The step of constructing a mechanical relationship model between the units of the building division unit to obtain a target BIM model includes: Querying the connection mode between each unit in the building division unit; Based on the connection mode, determining the unit stress type of the building division unit; Based on the unit stress type, constructing a mechanical equilibrium function of the building division unit; Calculating the stress value of the building division unit based on the mechanical equilibrium function; The stress value is imported into the initial BIM model to obtain a target BIM model.

9. A method for generating a site model of a special-shaped hyperbolic building based on BIM as claimed in claim 1, characterized in that: The method of using the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building includes: configuring an initial prediction model of the special-shaped hyperbolic building; utilizing the base model parameters and the historical performance benchmark data; Performing model training on the initial prediction model to obtain a performance prediction matrix; The composite performance deviation value of the performance prediction matrix is ​​calculated using the following formula: ； in, Indicates the composite performance deviation value, represents the actual wind-induced displacement at time t, express The predicted value of Indicates the degree of damage to the material. express The predicted value of Indicates the material deformation error, express The predicted value of represents the wind vibration weight, represents the damage weight, represents the thermal deformation weight, represents the maximum instantaneous displacement deviation, represents the damage distribution divergence, represents the average deformation error; When the composite performance deviation value is not greater than a preset composite performance deviation value, the initial prediction model is used as a building performance prediction model.

10. A BIM-based site model generation system for special-shaped hyperbolic buildings, characterized in that: The system comprises: A topological network construction module is used to collect multi-source heterogeneous point cloud data at the site of a special-shaped hyperbolic building, construct a three-dimensional feature tensor model of the multi-source heterogeneous point cloud data, identify key curvature mutation points of the three-dimensional feature tensor model, and use the key curvature mutation points to construct a spatial reference topological network of the special-shaped hyperbolic building; An initial BIM model construction module is used to construct a digital skeleton model of the special-shaped hyperbolic building based on the spatial reference topological network, analyze the geometric contour features of the special-shaped hyperbolic building by using the digital skeleton model, perform hyperbolic surface fitting on the special-shaped hyperbolic building based on the geometric contour features to obtain surface fitting information, and construct an initial BIM model of the special-shaped hyperbolic building based on the surface fitting information; The target BIM model is constructed to perform multi-physics field coupling simulation on the initial BIM model to obtain an initial structural model, divide the initial structural model into building information units to obtain building division units, and construct a mechanical relationship model between each unit of the building division unit to obtain a target BIM model; The building simulation module is used to extract the curvature distribution parameters and structural stress parameters of the target BIM model to obtain basic model parameters, query the historical performance benchmark data of the special-shaped hyperbolic building, use the basic model parameters and the historical performance benchmark data to construct a building performance prediction model for the special-shaped hyperbolic building, query the bearing capacity standard and deformation threshold of the special-shaped hyperbolic building, use the building performance prediction model to analyze the preferred surface parameter combination and prestressing strategy of the special-shaped hyperbolic building, obtain optimized simulation parameters, and simulate the special-shaped hyperbolic building based on the optimized simulation parameters using the target BIM model.

Images