Artificial intelligence-based building information model intelligent optimization method and system

Abstract

The application provides an artificial intelligence-based building information model intelligent optimization method and system. First, the initial building information model and the corresponding site environment data are obtained; second, the site environment data, geometric attribute information and physical attribute information are coupled and analyzed to obtain first performance data of the building component; then, the structure response data in the preset historical period is obtained; then, based on the first performance data and the structure response data, the target mapping relationship is derived; then, according to the target mapping relationship, the shape parameters and the material parameters are adjusted synchronously; finally, when the adjusted shape parameters and the material parameters meet the preset threshold, the optimized building information model is generated. The technical scheme provided by the application not only realizes the change from relying on artificial experience to intelligent and accurate optimization, but also improves the optimization efficiency and the result reliability.

Description

Technical Field

[0001] This application relates to the field of model optimization technology, and in particular to an intelligent optimization method and system for building information models based on artificial intelligence. Background Technology

[0002] As modern architecture develops towards higher heights, larger spans, and more complex shapes, buildings need to address the complex physical environment effects such as wind and heat in the actual operating environment after completion during the design phase. To ensure the structural safety and performance of buildings throughout their entire life cycle, it is necessary to conduct performance analysis and optimization of building information models during the design phase. This will enable them not only to meet regulatory requirements but also to adapt to the real environmental conditions of specific construction sites, thus achieving a shift from compliant design to performance optimization.

[0003] To address this need, existing technical solutions typically employ an integration of Building Information Modeling (BIM) and Computer-Aided Engineering (CAE) software. This approach first completes the 3D geometric modeling and material property definition of the building within BIM software. Then, the model is imported into specialized CAE analysis software. In CAE, operators manually set standardized environmental load conditions, such as selecting basic wind pressure and temperature boundary conditions according to specifications. Finite element analysis is then used to calculate the internal forces, deformations, and other mechanical responses of the structure under these standard load conditions. Finally, based on the analysis results, the component cross-sectional dimensions or material specifications in the BIM model are iteratively adjusted through trial and error until the calculation results meet the safety standards stipulated in the specifications.

[0004] However, this existing approach has significant drawbacks. First, the environmental loads relied upon for analysis are mostly based on statistically standardized values, failing to deeply couple with the complex wind fields and solar radiation distribution caused by the actual topography of the building site, resulting in discrepancies between the analysis conditions and the actual situation. Moreover, performance analysis and model optimization are two relatively independent steps, with the optimization process heavily reliant on manual intervention by engineers' experience. There is a lack of a mechanism that can automatically and intelligently link the physical environment analysis results with the adjustment of building component parameters, making the optimization inefficient and difficult to find the global optimum. Summary of the Invention

[0005] This application provides an intelligent optimization method and system for building information models based on artificial intelligence, which addresses the problems in existing technologies such as the disconnect between building information model performance optimization and the real site environment, and the insufficient automation and intelligence of the optimization process.

[0006] Firstly, this application provides an intelligent optimization method for building information models based on artificial intelligence, including:

[0007] Acquire an initial building information model and site environment data corresponding to the initial building information model, wherein the initial building information model includes geometric and physical attribute information of building components;

[0008] The site environment data, geometric attribute information, and physical attribute information are coupled and analyzed to obtain the first performance data of the building component;

[0009] Obtain the structural response data of the building component within a preset historical period;

[0010] Based on the correlation analysis between the first performance data and the structural response data, the target mapping relationship of the building components is derived.

[0011] Based on the target mapping relationship, the morphological parameters and material parameters of building components in the initial building information model are adjusted synchronously until the adjusted morphological parameters and material parameters meet the preset threshold, so as to generate an optimized building information model.

[0012] Optionally, an initial building information model and site environment data corresponding to the initial building information model are obtained. The initial building information model includes geometric and physical attribute information of building components, including:

[0013] Obtain the original building model from the pre-set design database, and extract the geometric and physical attribute information of the building components in the original building model;

[0014] The three-dimensional point cloud data of the target building site is obtained through three-dimensional scanning technology, and a real-scene model of the site is constructed based on the three-dimensional point cloud data.

[0015] Obtain meteorological monitoring data for the target building site;

[0016] The original building model is spatially matched and superimposed with the site reality model to locate the building components in the site reality model, thus obtaining the initial building information model.

[0017] Based on the meteorological monitoring data, the site real-scene model, and the geometric and physical properties of the building components, the solar radiation illuminance and wind pressure intensity on the outer surface of the building components are analyzed and calculated as site environmental data.

[0018] Optionally, the site environment data, the geometric attribute information, and the physical attribute information are coupled and analyzed to obtain the first performance data of the building component, including:

[0019] The transient temperature field distribution of each building component under solar radiation irradiance is calculated based on the solar radiation irradiance, the surface orientation and area in the geometric attribute information, and the material thermal conductivity and specific heat capacity in the physical attribute information.

[0020] Based on the wind pressure intensity on the outer surface of the building components and the structural shape and dimensions in the geometric attribute information, calculate the structural internal force distribution of each building component under wind load;

[0021] The thermal stress induced by the transient temperature field distribution is superimposed with the internal force distribution of the structure to determine the comprehensive stress state of each building component;

[0022] Based on the comprehensive stress state and the material strength parameters in the physical property information, the safety margin of each building component is evaluated.

[0023] The safety margin of each building component is compared with a preset safety threshold to identify target building components with a safety margin lower than the safety threshold, and the identification information and corresponding safety margin value of the target building components are recorded.

[0024] Based on the identification information and corresponding safety margin values ​​of all target building components, the first performance data is output.

[0025] Optionally, the thermal stress induced by the transient temperature field distribution is superimposed with the internal force distribution of the structure to determine the comprehensive stress state of each building component, including:

[0026] Based on the transient temperature field distribution, the thermal stress value and direction at each point inside the building component are calculated to form a thermal stress distribution field;

[0027] Based on the internal force distribution of the structure, the structural stress value and direction at each point inside the building component are calculated to form a structural stress distribution field;

[0028] Vector synthesis is performed on the stress components at corresponding positions in the thermal stress distribution field and the structural stress distribution field to obtain the composite stress value and direction at each point inside the building component;

[0029] Based on the combined stress values ​​and directions of all points, determine the maximum stress value in the building component and the location where the maximum stress value occurs in the building component;

[0030] Based on the maximum stress value and the location where the maximum stress value occurs, the overall stress state of the building component is determined.

[0031] Optionally, based on the correlation analysis between the first performance data and the structural response data, the target mapping relationship of the building component is derived, including:

[0032] The identification information and corresponding safety margin value of each target building component in the first performance data are matched with the actual deformation data recorded by the building component with the same identification in the structural response data within the preset historical period.

[0033] For each building component that has been matched, establish a time-based correspondence between the safety margin numerical sequence of the building component and the actual deformation data sequence;

[0034] Based on the correspondence, the regular deformation pattern presented in the actual deformation data when the safety margin value is lower than the preset level is identified.

[0035] Extract the characteristic parameters of the regular deformation pattern, and associate the characteristic parameters with the critical conditions that trigger the safety margin value of the regular deformation pattern;

[0036] Based on the association results of all matched building components, the association rules between the theoretical safety state and the actual deformation behavior of the building components are summarized.

[0037] Based on the association rules, a target mapping relationship is constructed for predicting the structural behavior of building components according to the first performance data.

[0038] Optionally, based on the association rules, a target mapping relationship for predicting the structural behavior of building components according to the first performance data is constructed, including:

[0039] The association rule is converted into multiple judgment rules, each of which defines the range of the safety margin value and the corresponding deformation characteristics;

[0040] The safety margin value is used as the input parameter for the target mapping relationship;

[0041] The deformation features are used as the output parameters of the target mapping relationship;

[0042] A mapping table is established based on the correspondence between safety margin values ​​and deformation characteristics in different ranges;

[0043] The mapping table is validated to ensure that all input parameters have corresponding output parameters.

[0044] Construct the target mapping relationship based on the verified mapping relationship table.

[0045] Optionally, based on the target mapping relationship, the morphological parameters and material parameters of building components in the initial building information model are synchronously adjusted until the adjusted morphological parameters and material parameters meet a preset threshold, in order to generate an optimized building information model, including:

[0046] The set of building components to be adjusted and the order of adjustment are determined based on the target mapping relationship;

[0047] According to the adjustment order, each building component in the set of building components to be adjusted is adjusted in turn. The adjustment direction of the shape parameters and material parameters corresponding to each building component is determined according to the target mapping relationship, and the shape parameters and material parameters are modified synchronously.

[0048] After each modification of the morphological parameters and material parameters, the first performance data is recalculated based on the modified morphological parameters and material parameters, and the predicted deformation data is output through the target mapping relationship.

[0049] When the predicted deformation data meets the preset conditions, the parameter adjustment results of the current building component are saved;

[0050] Once all the building components to be adjusted have completed their parameter adjustments, an optimized building information model is generated based on the parameter adjustment results of all building components.

[0051] Secondly, this application provides an intelligent optimization system for building information modeling based on artificial intelligence, comprising:

[0052] The first acquisition module is used to acquire an initial building information model and site environment data corresponding to the initial building information model. The initial building information model includes geometric and physical attribute information of building components.

[0053] The first analysis module is used to couple and analyze the site environment data, the geometric attribute information, and the physical attribute information to obtain the first performance data of the building component.

[0054] The second acquisition module is used to acquire the structural response data of the building component within a preset historical period;

[0055] The second analysis module is used to perform correlation analysis based on the first performance data and the structural response data to deduce the target mapping relationship of the building components.

[0056] The adjustment module is used to synchronously adjust the shape parameters and material parameters of building components in the initial building information model according to the target mapping relationship, until the adjusted shape parameters and material parameters meet the preset threshold, so as to generate an optimized building information model.

[0057] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the intelligent optimization method for building information model based on artificial intelligence as described in the first aspect above.

[0058] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements an intelligent optimization method for building information modeling based on artificial intelligence as described in the first aspect.

[0059] This application can generate performance data that truly reflects the building's performance under the influence of specific microenvironments by acquiring and coupling environmental data of a specific site with the component attributes of a building information model. This process transforms the basis of optimization analysis from idealized standard conditions to a real physical environment closely related to the actual construction site, effectively solving the problem of the disconnect between optimization analysis and the real site environment in existing technologies.

[0060] Specifically, by establishing a target mapping relationship between historical structural response data and the aforementioned performance data, an intelligent rule capable of predicting actual structural behavior based on design state is constructed, making the subsequent parameter optimization process based on evidence and avoiding excessive reliance on engineer experience in traditional methods.

[0061] Furthermore, during the optimization phase, the shape and material parameters of building components are automatically adjusted synchronously and in an orderly manner based on the target mapping relationship. After each adjustment, the effect is verified by recalculating performance data and predicting deformation behavior, forming a closed-loop iterative optimization process.

[0062] This method ensures that every parameter modification directly improves structural safety until the preset reliability requirements are met, thus systematically solving the shortcomings of insufficient automation and intelligence in the optimization process of existing technologies, and improving the accuracy and efficiency of optimization. Therefore, the solution provided in this application realizes the transformation of building information model performance optimization from relying on human experience to automation, accuracy and reliability.

[0063] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 A flowchart of an intelligent optimization method for building information model based on artificial intelligence provided in this application is shown;

[0066] Figure 2 This application provides a schematic diagram of the structure of an intelligent optimization system for building information modeling based on artificial intelligence.

[0067] Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0068] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0069] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0070] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0071] Figure 1 This application provides a flowchart of an intelligent optimization method for building information modeling based on artificial intelligence, such as... Figure 1 As shown, the method includes:

[0072] Step 101: Obtain an initial building information model and site environment data corresponding to the initial building information model. The initial building information model includes geometric and physical attribute information of building components.

[0073] Optionally, step 101 may specifically include:

[0074] Step 1011: Obtain the original building model from the preset design database, and extract the geometric and physical attribute information of the building components in the original building model.

[0075] Step 1012: Obtain three-dimensional point cloud data of the target building site through three-dimensional scanning technology, and construct a real-scene model of the site based on the three-dimensional point cloud data.

[0076] Step 1013: Obtain meteorological monitoring data of the target building site.

[0077] Step 1014: Spatial matching and overlay of the original building model and the site reality model are performed to locate the building components in the site reality model, thereby obtaining the initial building information model.

[0078] Step 1015: Based on the meteorological monitoring data, the site real-scene model, and the geometric and physical attribute information of the building components, analyze and calculate the solar radiation illuminance and wind pressure intensity on the outer surface of the building components as site environmental data.

[0079] In this step, the initial building information model refers to a digital model that includes the three-dimensional geometry and physical properties of all building components, which serves as the starting point for the optimization process.

[0080] Site environmental data refers to data describing the natural external forces acting on the specific location of a building, used to accurately analyze the building's performance in the actual environment.

[0081] Building components refer to independent structural or enclosing units that make up the whole building, such as beams, columns, walls, and slabs. They are used as the smallest objects for performance analysis and are obtained by analyzing the original building model.

[0082] Geometric attribute information refers to parameters that describe the spatial shape and size of building components, such as length, area, volume, and coordinates. These parameters are used to calculate the load-bearing area and structural characteristics of the components and are extracted from the original building model.

[0083] Physical property information refers to parameters that describe the inherent properties of building component materials, such as thermal conductivity, specific heat capacity, density, and strength. These parameters are used to analyze the physical response of components under environmental influences and are extracted from the original building model.

[0084] A pre-built design database refers to a centralized storage system that stores all digital results from the project design phase, providing the most original design data.

[0085] The original building model refers to a three-dimensional design model obtained directly from the design database without any environmental adaptation optimization. It is used as the basis for building the initial building information model and is obtained by calling from a pre-built design database.

[0086] 3D scanning technology refers to a measurement technology that uses the principle of laser ranging to obtain the three-dimensional coordinates of a large number of points on the surface of an object in a non-contact manner. It is used to quickly obtain the real three-dimensional geometric information of a target site by operating a 3D laser scanner to scan the site.

[0087] The target building site refers to the specific geographical area where the planned or existing building is located. It is used to define the spatial scope for data collection and environmental analysis and is determined through project planning documents.

[0088] Three-dimensional point cloud data refers to a dense set of three-dimensional spatial coordinate points that characterize the surface morphology of an object, obtained through three-dimensional scanning technology. It is used to reconstruct the true three-dimensional morphology of a site with high precision and is obtained by performing preliminary noise reduction processing on the original measurement data obtained from the scan.

[0089] A site reality model refers to a three-dimensional digital model constructed based on three-dimensional point cloud data that realistically reflects the topography, landforms, and surrounding features of the target building site. It is used to provide an accurate geometric background for environmental analysis and is generated by surface reconstruction algorithms using point cloud data processing software.

[0090] Meteorological monitoring data refers to continuous natural environmental parameters recorded by meteorological observation equipment deployed near the site. It is used to define environmental loads such as wind and heat acting on buildings and is obtained by reading historical or real-time monitoring records from meteorological stations.

[0091] Solar irradiance refers to the amount of solar radiation energy that is vertically irradiated onto the surface of a unit building component per unit time. It is used to calculate the temperature change and thermal stress of building components caused by solar irradiation. It is calculated by combining solar radiation intensity from meteorological data, shading information from the site model, and geometric properties of the component surface.

[0092] Wind pressure intensity refers to the pressure exerted on a unit area of ​​a building's surface when wind blows towards it. It is used to calculate the wind load on building components and is calculated by combining wind speed and direction data from meteorological data, the influence of terrain from the site model, and the geometric properties of the component's shape.

[0093] In this step, the system first accesses a pre-set design database via network connection to retrieve the electronic file of the original building model. Then, a model parsing program is used to read the electronic file, separating and extracting the geometric and physical attribute information of each individual building component. Next, a 3D laser scanner is used to perform a comprehensive scan and measurement of the target building site. The instrument emits lasers and receives reflected signals to obtain a large number of accurate 3D coordinate points. After initial filtering of obvious noise, these 3D coordinate points form 3D point cloud data. Subsequently, this 3D point cloud data is imported into professional reverse engineering software. The reverse engineering software uses a surface fitting algorithm to connect these discrete points into continuous triangular patches, ultimately generating a site reality model.

[0094] At the same time, meteorological monitoring data recorded by meteorological sensors set up near the site is automatically obtained through the network interface. Then, the spatial alignment function of the 3D modeling software is used to move and rotate the original building model to the correct position with certain fixed ground features in the site real scene model as reference benchmarks. After the position registration is completed, an initial building information model that accurately reflects the spatial relationship of the building in the real environment is obtained.

[0095] Finally, based on the obtained meteorological monitoring data, the solar radiation intensity at a specific moment is considered, taking into account the possible shading effects of the surrounding terrain and buildings in the site reality model. At the same time, combined with the specific orientation, tilt angle, and material absorption capacity of each building component surface obtained from the initial building information model, the solar radiation illuminance at each point on the surface of each component is calculated using the radiative heat transfer calculation formula. Similarly, based on wind speed and direction data, and considering the influence of the site reality model on airflow and the shape and orientation of the building components themselves, the wind pressure intensity generated by the wind on the surface of the components is calculated using aerodynamic principles. These calculated solar radiation illuminance and wind pressure intensity values ​​are combined to obtain the site environmental data.

[0096] For example, in the optimization of an office building project located in region A, the original building model file was first downloaded from the company's internal BIM collaboration platform, i.e., the pre-built design database. Then, the original building model file was opened using model browsing software, and its data extraction function was used to obtain geometric attribute information such as the area and volume of all building components such as exterior walls and roofs, as well as physical attribute information such as the type of wall insulation material and the concrete strength grade. Next, Company B was hired to survey the entire target building site using a mobile 3D laser scanning vehicle, obtaining detailed 3D point cloud data. Company B used point cloud processing software to clean and model this 3D point cloud data, generating a high-precision site reality model including surrounding roads, green spaces, and adjacent buildings. Simultaneously, hourly meteorological monitoring data for the most recent year was purchased from the meteorological bureau of region A.

[0097] Then, in professional BIM software, the original building model is imported into the existing site reality model. By selecting several control points on the site reality model and matching them with corresponding points on the model, the BIM software automatically completes coordinate transformation and alignment, resulting in an accurately positioned initial building information model. Based on this, the BIM software's built-in analysis module reads solar parameters from meteorological data and considers the shading of the target building site's low-lying area by a tall building on the south side of the site reality model. Combining the orientation and glass type of the building's glass curtain wall, it calculates the specific solar radiation illuminance values ​​received by each facade at different times. At the same time, the analysis module also calculates the wind pressure intensity of each area on the building surface based on wind speed and direction data and considering the building's streamlined shape. These calculated illuminance and pressure values ​​are stored as a site environmental data file for the target building site.

[0098] Step 102: Couple the analysis of the site environment data, the geometric attribute information, and the physical attribute information to obtain the first performance data of the building component.

[0099] Optionally, step 102 may specifically include:

[0100] Step 1021: Calculate the transient temperature field distribution of each building component under solar radiation irradiance based on solar radiation irradiance, surface orientation and area in the geometric attribute information, and material thermal conductivity and specific heat capacity in the physical attribute information.

[0101] Step 1022: Calculate the structural internal force distribution of each building component under wind load based on the wind pressure intensity on the outer surface of the building component and the structural shape and dimensions in the geometric attribute information.

[0102] Step 1023: Superimpose the thermal stress caused by the transient temperature field distribution with the internal force distribution of the structure to determine the comprehensive stress state of each building component.

[0103] Optionally, step 1023 may specifically include: calculating the thermal stress value and direction at each point inside the building component based on the transient temperature field distribution, forming a thermal stress distribution field; calculating the structural stress value and direction at each point inside the building component based on the structural internal force distribution, forming a structural stress distribution field; performing vector synthesis on the stress components at corresponding positions in the thermal stress distribution field and the structural stress distribution field to obtain the combined stress value and direction at each point inside the building component; determining the maximum stress value and the location where the maximum stress value occurs in the building component based on the combined stress value and the combined stress direction at all points; and determining the comprehensive stress state of the building component based on the maximum stress value and the location where the maximum stress value occurs.

[0104] Step 1024: Based on the comprehensive stress state and the material strength parameters in the physical property information, evaluate the safety margin of each of the building components.

[0105] Step 1025: Compare the safety margin of each building component with a preset safety threshold, identify target building components with a safety margin lower than the safety threshold, and record the identification information and corresponding safety margin value of the target building components.

[0106] Step 1026: Based on the identification information and corresponding safety margin values ​​of all target building components, output the first performance data.

[0107] In this step, the first performance data refers to the structural safety assessment results that identify potential weaknesses and their safety levels in the initial model, which are used to guide subsequent targeted optimizations.

[0108] Surface orientation refers to the orientation and tilt angle of the outer surface of a building component in space. It is used to determine the amount of solar radiation received by the surface and is obtained by analyzing the spatial coordinates and normal vectors in the geometric attribute information.

[0109] Area refers to the actual size of the outer surface of a building component, used to calculate the total amount of environmental impact it receives, and is calculated through geometric attribute information.

[0110] The thermal conductivity of a material is a physical parameter that measures a material's ability to conduct heat and is used to calculate the rate of temperature transfer within a component.

[0111] Specific heat capacity is a physical parameter that measures a material’s ability to store heat and is used to calculate how quickly a component’s temperature changes.

[0112] Transient temperature field distribution refers to the temperature values ​​and spatial variations of various points inside a building component at a specific moment. It is used to analyze the thermal stress caused by uneven temperature in the component and is obtained by solving the heat conduction equation that takes into account solar radiation illuminance, component geometry, and material properties.

[0113] Structural shape and dimensions refer to the specific three-dimensional shape and measurement of building components, used to calculate their mechanical response under wind pressure.

[0114] Structural internal force distribution refers to the collection of forces and moments generated at various points inside a building component under wind pressure. It is used to evaluate the structural strength of the component and is obtained through mechanical analysis of the component using the finite element method.

[0115] Thermal stress refers to the internal force generated when the thermal expansion and contraction of a building component are constrained due to uneven internal temperature. It is calculated by substituting the transient temperature field distribution into the material constitutive relation.

[0116] The direction of thermal stress refers to the direction in which thermal stress acts at a specific point inside a component, and is determined by analyzing the direction of the temperature gradient at that specific point.

[0117] The comprehensive stress state refers to the most dangerous stress level and location inside a building component after considering the combined effects of thermal stress and structural internal forces. It is used to comprehensively assess the safety of the component and is obtained by vector superposition of thermal stress and structural internal forces.

[0118] A thermal stress distribution diagram is a map depicting the magnitude and direction of thermal stress at various points inside a building component. It is obtained by calculating and visualizing the thermal stress values ​​at all points inside the component.

[0119] Structural internal force values ​​refer to the magnitude of the force caused by wind load at a certain point inside a building component, which is obtained through structural analysis calculations.

[0120] The direction of internal forces refers to the direction of action of internal forces at a specific point inside a structural member, which is determined through structural analysis.

[0121] A structural stress distribution diagram is a map depicting the magnitude and direction of stress caused by internal forces at various points within a building component. It is obtained by converting structural internal force distribution data.

[0122] The combined stress value refers to the total stress after combining the thermal stress and structural stress at a certain point inside a building component, which is calculated by vector addition.

[0123] The direction of the combined stress refers to the direction of the combined stress at a specific point inside the component, which is determined by vector addition.

[0124] The maximum stress value refers to the maximum value of the combined stress value among all points inside a building component. It is used to determine the most dangerous state and is obtained by traversing and comparing the combined stress values ​​of all points.

[0125] The location of the maximum stress value refers to the specific location where the maximum stress value occurs on the building component. It is used to locate potential failure points and is obtained by recording the spatial coordinates corresponding to the maximum stress value.

[0126] Safety margin refers to the margin between the strength of a building component material and the maximum stress it can withstand. It is used to quantify the safety level of a component and is calculated by dividing the material strength parameter by the maximum stress value.

[0127] The preset safety threshold refers to the minimum acceptable safety margin value set according to specifications or experience. It is used to determine whether a component is safe and is preset by the designer.

[0128] Identification information refers to the number or name that can uniquely identify a specific building component, used for tracking and locating the component, and is extracted from the original building model.

[0129] In this step, the numerical calculation library is first used to solve the three-dimensional unsteady heat conduction partial differential equation for each building component, taking the solar radiation irradiance received on its surface as the heat source, and determining the heat source intensity based on the surface orientation and area in its geometric property information. At the same time, the thermal properties of the material are determined based on the thermal conductivity and specific heat capacity in its physical property information. The transient temperature field distribution of the temperature at each point inside the component changes with time during solar irradiation is calculated.

[0130] Secondly, using finite element analysis software, the building components are discretized into a large number of tiny elements based on their structural shape and size in their geometric attribute information. Then, a load defined by wind pressure intensity data is applied to the outer surface of the components, and the boundary conditions of the components are fixed. Finally, by solving the static equilibrium equations, the distribution of internal forces at various points inside the components under wind load is obtained.

[0131] Next, based on the calculated transient temperature field distribution, the thermal stress values ​​and directions generated at various points inside the component due to the resistance to material expansion or contraction caused by temperature changes are calculated using thermoelastic mechanics formulas, thus forming a thermal stress distribution map; at the same time, based on the calculated internal force distribution of the structure, the internal forces are converted into stresses using stress formulas, thus obtaining the internal force values ​​and directions at various points inside the component, thus forming a structural stress distribution map.

[0132] Then, the thermal stress distribution map and the structural stress distribution map are matched one-to-one. For each point at the same location, its thermal stress value and structural stress value are regarded as vectors, and vector addition is performed according to their respective directions to obtain the combined stress value and the direction of the combined stress at the same location.

[0133] After completing the vector superposition of all points at the same location, the entire component is traversed to find the maximum stress value among all the combined stress values, and the location of the point where the maximum stress value occurs is recorded. The combined stress state of the building component is determined by combining the maximum stress value and its location.

[0134] Then, the material strength parameter in the physical property information is read and divided by the determined maximum stress value to calculate the safety margin of the building component. This safety margin value indicates how many times the material strength is compared to the actual maximum stress. Next, the calculated safety margin of each building component is compared with a pre-set value representing the minimum acceptable safety level, i.e., a preset safety threshold. Building components with safety margin values ​​lower than the preset safety threshold are selected and marked as target building components. Their unique identification information and specific safety margin values ​​are recorded. Finally, the identification information of all marked target building components and their corresponding safety margin values ​​are compiled into a structured data list as the first performance data output, clearly indicating which components in the initial model have safety hazards under given environmental loads and the degree of unsafety.

[0135] For example, following the specific implementation of the previous step, in an office building in area A, the analysis software first reads and calculates the site environment data of solar radiation illuminance on each exterior wall and roof surface; secondly, for the south-facing glass curtain wall unit, the analysis software, combined with its south-facing orientation, vertical orientation, area (e.g., 200 square meters), and its physical properties such as the thermal conductivity and specific heat capacity of the glass and profiles, uses the finite difference method to solve the transient temperature field distribution of the curtain wall unit under solar irradiation throughout the day. The results show that the temperature of its outer surface glass is significantly higher than that of the interior side in the afternoon; simultaneously, based on the structural shape and size of the curtain wall unit, and the wind pressure intensity acting on it, the analysis software uses the finite element analysis module to calculate the distribution of structural internal forces generated in the curtain wall keel and panels under maximum wind pressure; then, the software imports the calculated transient temperature field distribution into the thermal stress calculation module to obtain a thermal stress distribution diagram caused by the temperature difference between the glass and aluminum frame and its own uneven temperature;

[0136] Furthermore, this thermal stress distribution map is superimposed on the previously calculated structural stress distribution map caused by wind pressure. For example, at a corner of the curtain wall, the thermal stress level is X MPa, directed inwards, and the structural stress is Y MPa, directed to the left. After vector synthesis, the combined stress value at that point is obtained as Z MPa. The software traverses the entire curtain wall unit, finds the point with the largest combined stress value, i.e., the maximum stress value, and records its location. Subsequently, the software reads the material strength parameters of the glass and aluminum of the curtain wall unit, divides the strength by the maximum stress value, and obtains its safety margin, assumed to be 2.5. The software then compares this safety margin with a preset... The safety threshold was compared with the standard requirement of 1.8, and it was found that 2.5 was greater than 1.8. Therefore, this curtain wall unit was not marked as a target building component. However, for a large decorative concrete sunshade on the west side, after repeating the above process, the calculated safety margin was only 1.5, which was lower than the preset safety threshold of 1.8. Therefore, the software recorded the sunshade as a target building component, saved its component ID as FACADE-W-01 and safety margin of 1.5. Finally, all similar component IDs with insufficient safety margins and their safety margin values ​​were summarized to form the first performance data list of the office building project.

[0137] Finally, this step combines real environmental loads, precise component geometry, and material properties to conduct a series of coherent physical simulation calculations, from temperature field to internal force field, stress superposition, and safety assessment. The result is a structural performance assessment report that clearly quantifies the components in the initial building information model that have safety hazards under specific environmental conditions and the degree of their safety risks. This shifts the optimization objective from vaguely improving performance to specifically strengthening weak links, providing a clear and quantitative direction and basis for subsequent intelligent optimization.

[0138] Step 103: Obtain the structural response data of the building component within a preset historical period.

[0139] In this step, the preset historical period refers to a past time period set in advance for analysis. It is used to define the time range of data that is of interest and needs to be collected. It is determined in advance based on factors such as the building's age, seasonal changes, or the impact of specific events.

[0140] Structural response data refers to the measurable physical response records of building components under real environmental loads. It is used to verify theoretical calculation models and establish their relationship with actual behavior. It is obtained through long-term monitoring and recording by sensors deployed on the components.

[0141] In this step, physical sensors, such as strain gauges, used to measure deformation are first pre-embedded on the surface or inside the building components to be monitored and connected to the data acquisition instrument in a certain network layout.

[0142] Next, the data acquisition system is started, so that it automatically and continuously reads the measurement values ​​of each sensor at set time intervals, such as every minute, within a preset historical period, and records these raw readings together with timestamps to form the original time-series monitoring dataset.

[0143] Then, these raw time-series monitoring data are transmitted wirelessly from the data acquisition device on site to the central data server or monitoring platform for storage. Finally, the data processing module of the monitoring platform performs necessary verification on the massive amount of raw time-series monitoring data received, such as removing obvious abnormal values ​​caused by instantaneous sensor failures, and classifying and archiving the data according to the identification information of building components, ultimately generating a complete and orderly record of structural response data for each building component within a preset historical period.

[0144] For example, following the specific implementation of the previous step, in an office building in area A, in order to obtain the required data, the property management department commissioned monitoring company C to attach strain gauges to key components of the building, such as the large concrete sunshade on the west side, and install acceleration sensors on its surface; at the same time, a complete year was set as a preset historical period to observe the structure's response under different seasonal climates; within this preset historical period, the data acquisition box of brand B installed on site automatically collects the readings of all sensors once per minute, continuously recording the minute amplitude vibrations of the sunshade and the minute deformation changes of the steel bars;

[0145] These raw data are uploaded to the D-structure health monitoring platform in the cloud every night via an IoT gateway. The platform automatically performs quality checks on the received data, excluding abnormal data such as instantaneous signal spikes caused by lightning strikes. Then, it is classified and stored according to the component ID FACADE-W-01 and the sensor type. Finally, for component FACADE-W-01, the platform generates detailed structural response data records covering spring, summer, autumn, and winter, including its vibration and deformation history.

[0146] Step 104: Based on the correlation analysis between the first performance data and the structural response data, deduce the target mapping relationship of the building components.

[0147] Optionally, step 104 may specifically include:

[0148] Step 1041: Match the identification information and corresponding safety margin value of each target building component in the first performance data with the actual deformation data recorded by the building component with the same identification in the structural response data within the preset historical period.

[0149] Step 1042: For each building component that has been matched, establish the temporal correspondence between the safety margin numerical sequence of the building component and the actual deformation data sequence.

[0150] Step 1043: Based on the correspondence, identify the regular deformation pattern presented in the actual deformation data when the safety margin value is lower than the preset level.

[0151] Step 1044: Extract the feature parameters of the regular deformation pattern, and associate the feature parameters with the critical conditions that trigger the safety margin value of the regular deformation pattern.

[0152] Step 1045: Based on the association results of all matched building components, summarize the association rules between the theoretical safety state and the actual deformation behavior of the building components.

[0153] Step 1046: Based on the association rules, construct a target mapping relationship for predicting the structural behavior of building components according to the first performance data.

[0154] Optionally, step 1046 may specifically include: converting the association rule into multiple judgment rules, each judgment rule defining a range of safety margin values ​​and corresponding deformation features; using the safety margin values ​​as input parameters of the target mapping relationship; using the deformation features as output parameters of the target mapping relationship; establishing a mapping relationship table based on the correspondence between safety margin values ​​and deformation features in different ranges; validating the mapping relationship table to ensure that all input parameters have corresponding output parameters; and constructing the target mapping relationship based on the validated mapping relationship table.

[0155] In this step, the target mapping relationship refers to the mapping relationship between the performance change law of the building and the structural behavior, which is used to guide the model optimization.

[0156] Actual deformation data refers to the amount of physical shape change of a building component under environmental load, which is directly measured by sensors. It is used to reflect the actual behavior of the component and is obtained by processing monitoring signals from sensors such as strain gauges.

[0157] Each matching building component refers to a structural unit that exists in both the first performance data list and has corresponding historical monitoring records. This is used for effective correlation analysis by comparing the identification information of the two data lists.

[0158] The temporal correspondence refers to pairing the safety margin value calculated at the same moment with the measured actual deformation data to analyze the synergy between the two over time. This is achieved by aligning the data using a unified timestamp.

[0159] Regular deformation patterns refer to specific changes that repeatedly occur in actual deformation data when the theoretical safety level drops to a certain level. These patterns are used to reveal potential risk characteristics and are obtained through statistical analysis of common features in time series data.

[0160] Feature parameters refer to key indicators used to quantitatively describe regular deformation patterns. They are used to accurately define a deformation pattern and are obtained by extracting statistical quantities such as amplitude and frequency from deformation data sequences.

[0161] Critical conditions refer to the theoretical safety margin range corresponding to triggering a specific regular deformation pattern. They are used to define risk thresholds and are obtained by observing the distribution of safety margin values ​​when the deformation pattern occurs.

[0162] The association result refers to the correspondence between the characteristic parameters and critical conditions established for a single building component, and is the basic unit for constructing the overall rules.

[0163] The theoretical safety state refers to the safety level represented by the safety margin value of building components obtained through simulation calculation. It is used to characterize the conclusions of theoretical analysis and is reflected through primary performance data.

[0164] Association rules refer to the general correspondence patterns between theoretical safety status and actual deformation behavior summarized from the analysis of multiple components. They are used to form a basis for prediction and are obtained by summarizing all association results.

[0165] Multiple judgment rules refer to a series of specific if...then... conditional statements in the target mapping relationship, which are used to achieve automatic prediction. They are obtained by converting association rules into logical judgment statements.

[0166] The corresponding deformation features refer to the deformation patterns predicted to occur when specific conditions are met. These are used as prediction outputs and determined through association rules.

[0167] Input parameters refer to the data items that the target mapping relationship needs to receive, which are used to start the prediction process and are set as safety margin values ​​according to the variables on which the association rule depends.

[0168] The output parameters refer to the prediction results returned by the target mapping relationship, which are used to describe the prediction conclusion. The output content is set as the deformation type and degree according to the association rules.

[0169] A mapping table is a data structure that stores the correspondence between input parameters and output parameters in tabular form, enabling fast lookups.

[0170] In this step, the unique identifier of each target building component is used as the query key through a database query operation. The database storing structural response data searches for the actual deformation data record corresponding to the building component with the exact same identifier. This pairs the theoretical calculation results with the measured data one by one, ensuring that the subsequent analysis is based on different dimensions of the same physical object.

[0171] Secondly, for each successfully matched building component, the safety margin value sequence arranged in chronological order within the preset historical period, and the actual deformation data sequence recorded at the same time interval within the same time period are aligned to establish a corresponding data chain on the time axis in which each sampling point simultaneously contains a safety margin value and an actual deformation value.

[0172] Next, using pattern recognition algorithms in data mining techniques, we scan and analyze the established corresponding data chain, focusing on whether the actual deformation data corresponding to the time period when the safety margin value drops below a certain preset level shows a non-random, repeatable waveform or trend, such as increased vibration at a specific frequency or continuous creep growth, and define this repeatable change pattern as a regular deformation pattern.

[0173] Then, signal processing techniques are applied to quantify and extract characteristic parameters that represent the core features of the identified regular deformation patterns. For example, for vibration patterns, the main frequency and amplitude are extracted, and for trend patterns, the rate of change is extracted. At the same time, the range of values ​​in which the safety margin value mainly falls when this deformation pattern occurs is statistically summarized, and this range is determined as the critical condition that triggers the regular deformation pattern. Finally, a clear correlation record is established between the characteristic parameters of this deformation pattern and its critical condition.

[0174] Then, by synthesizing all the matched building components in the obtained association records, inductive reasoning was used to identify the common general patterns among these association records. These general patterns were then refined and expressed as clear association rules. Finally, each of the inductive association rules was translated into computer-executable logical judgment statements, i.e., multiple judgment rules. Each judgment rule explicitly states that if the input safety margin value is within a certain range, then a certain deformation feature will be predicted and output. The safety margin value is explicitly specified as the input parameter of the target mapping relationship, and the deformation type and degree are specified as the output parameters. All judgment rules are systematically organized into a two-column mapping relationship table. The first column is the range of the input safety margin value, and the second column is the description of the corresponding deformation feature. A verification program is written to traverse all possible safety margin value inputs to ensure that the mapping relationship table can give the corresponding output and avoid undefined cases. Finally, this verified and complete mapping relationship table is encapsulated into the target mapping relationship functional module.

[0175] For example, following the specific implementation of the previous step, the first performance data list obtained is analyzed, which includes a safety margin of 1.5 for component FACADE-W-01; then, in the obtained structural response database, the record with component ID FACADE-W-01 is searched, and its actual deformation data for the past year is successfully matched; the sequence of safety margin values ​​calculated each day is aligned with the sequence of deformation data monitored on the same day on the time axis; by analyzing this time chain, it is found that on summer days with strong afternoon sun, when the calculated safety margin value drops below 1.8, a small-amplitude, periodic pattern will continuously appear in the deformation data. The back-and-forth oscillation pattern was identified, and its characteristic parameters, including oscillation amplitude and main period, were extracted. The critical safety margin condition for triggering this oscillation was determined to be a value less than 1.8. The oscillation amplitude (X mm) and period (Y seconds) were then correlated with the critical safety margin condition of <1.8. Furthermore, it was found that for a certain steel frame of the roof, a slow downward bending trend occurred when the safety margin was below 2.0. Combining the correlation results of FACADE-W-01 and multiple components such as the steel frame, a correlation rule was summarized: when the safety margin of a building component is lower than a certain threshold related to the material and environment, a specific deformation pattern related to the component type is likely to occur.

[0176] Based on this, the association rules are converted into judgment rules. If the input safety margin S < 1.8, the output deformation feature is: low-frequency oscillation. The input parameter is set as S, and the output parameter is the deformation description. These rules are filled into the mapping table. Verification ensures that there are corresponding outputs for S from 1.0 to 3.0. Finally, a target mapping relationship that can be used for prediction is formed.

[0177] Finally, this step systematically matches, aligns, identifies patterns, and summarizes the actual structural behavior under long-term monitoring with theoretically calculated safety performance indicators. This successfully constructs an intelligent prediction model, namely the target mapping relationship, that can predict the future structural behavior in the real environment based on the theoretical analysis results of the current design state. This advances optimization decision-making from relying on static calculations to dynamic intelligent judgment based on historical empirical predictions, greatly enhancing the foresight and accuracy of optimization strategies.

[0178] Step 105: Based on the target mapping relationship, the morphological parameters and material parameters of the building components in the initial building information model are adjusted synchronously until the adjusted morphological parameters and material parameters meet the preset threshold, so as to generate an optimized building information model.

[0179] Optionally, step 105 may specifically include:

[0180] Step 1051: Determine the set of building components to be adjusted and the adjustment order based on the target mapping relationship.

[0181] Step 1052: According to the adjustment order, each building component in the set of building components to be adjusted is adjusted in turn. The adjustment direction of the shape parameters and material parameters corresponding to each building component is determined according to the target mapping relationship, and the shape parameters and material parameters are modified synchronously.

[0182] Step 1053: After each modification of the morphological parameters and material parameters, the first performance data is recalculated based on the modified morphological parameters and material parameters, and the predicted deformation data is output through the target mapping relationship.

[0183] Step 1054: When the predicted deformation data meets the preset conditions, save the parameter adjustment results of the current building component.

[0184] Step 1055: After all the building components to be adjusted have completed their parameter adjustments, an optimized building information model is generated based on the parameter adjustment results of all building components.

[0185] In this step, morphological parameters refer to variable values ​​that describe the geometry and dimensions of building components. They are used to define the spatial form of the components and are obtained by modifying the geometric properties of the components in the initial building information model.

[0186] Material parameters are variable values ​​that describe the material properties of building components. They are used to define the physical properties of the components and are obtained by modifying the material properties of the components in the initial building information model.

[0187] The adjusted morphological and material parameters refer to the final values ​​of the component's shape, size, and material properties determined after the optimization process. These values ​​are used to generate the optimization model and are obtained through iterative adjustment and verification.

[0188] An optimized building information model refers to the final three-dimensional digital model generated after all component parameters have been adjusted and meet performance requirements, which is used to guide construction or operation.

[0189] The set of building components to be adjusted refers to the grouping of building components that need to be optimized. It is used to organize the optimization process in an orderly manner and is determined based on the analysis of the first performance data according to the target mapping relationship.

[0190] The adjustment order refers to the order in which the components in the set of building components to be adjusted are processed. This is used to improve optimization efficiency and is usually obtained by sorting the components from low to high based on their safety margin values.

[0191] The modified morphological and material parameters refer to the component parameter values ​​that are temporarily changed in a single adjustment iteration. They are used to test the optimization effect and are obtained by updating the current parameter values ​​according to the adjustment direction.

[0192] Predicted deformation data refers to the component deformation behavior inferred from the modified performance data and target mapping relationship, and is used to evaluate the effect of a single adjustment.

[0193] The parameter adjustment results refer to the final shape parameters and material parameters of the component that have been confirmed to meet the preset conditions, which are used to generate the final optimized model.

[0194] In this step, firstly, by querying the first performance data list, all building components with safety margins lower than the preset safety threshold are filtered out to form a set of building components to be adjusted. Then, these building components are sorted according to their safety margin values, with the component with the lowest safety margin placed in the first position to be adjusted, thus determining the adjustment order.

[0195] Next, following the determined adjustment order, one building component is taken from the set of building components to be adjusted in turn. Then, the current safety margin value of the building component is input into the target mapping relationship. The target mapping relationship infers, according to its built-in rules, which direction the shape parameters and material parameters of the building component should change in order to improve the predicted deformation data, such as increasing the thickness or replacing it with a higher strength material. Then, in the initial building information model, the specific values ​​of the shape parameters and material parameters of the component are modified synchronously according to this inferred adjustment direction.

[0196] Then, after each modification of the morphological and material parameters, the coupling analysis process is immediately invoked, but at this time the modified morphological and material parameters are used to recalculate the safety margin value of the building component under the new parameters. Then, this newly calculated safety margin value is used as input to invoke the target mapping relationship again. The target mapping relationship queries its rule base according to the new input and immediately outputs a set of predicted deformation data. This set of data predicts the deformation behavior of the component after the parameters are modified.

[0197] Next, the obtained predicted deformation data is compared with a predefined preset condition representing acceptable structural behavior. If the predicted deformation data meets the preset condition, such as the predicted deformation being less than a certain allowable value, the modified morphological parameters and material parameters are saved as the final parameter adjustment result for the building component. If not, the control flow returns to the beginning of the adjustment sequence. For the same component, a new adjustment direction is determined again based on the target mapping relationship, and its morphological parameters and material parameters are further modified. Then, the first performance data and the verification of meeting the preset condition are repeated, forming a loop iterative process until the predicted deformation data meets the preset condition.

[0198] Finally, after all components in the set of building components to be adjusted have undergone adjustment iterations and each has saved its parameter adjustment results, the initial building information model is accessed. Based on the parameter adjustment results saved for each component, the morphological and material parameters of all corresponding components in the initial building information model are updated in batches, thereby generating a new optimized building information model that meets the performance requirements on all adjusted components.

[0199] For example, following the specific implementation of the previous step, firstly, based on the first performance data list, the component with the lowest safety margin, FACADE-W-01, with a safety margin of 1.5, is added to the set of building components to be adjusted and placed first in the adjustment order; secondly, the target mapping relationship is read, and the current safety margin of FACADE-W-01, 1.5, is input. The mapping relationship suggests that the stiffness needs to be enhanced; then, the morphological parameters of the building component are adjusted simultaneously, increasing the thickness of the sunshade support rib from T1 to T2, and the material parameters are adjusted, increasing the concrete grade from C30 to C40; then, using the modified morphological and material parameters, the safety margin of the building component under the same site environment data is recalculated, resulting in a new value of 1.9;

[0200] Meanwhile, the new safety margin of 1.9 is input into the target mapping relationship, and the predicted deformation data is slight vibration with an amplitude within the allowable range. It is then determined that the predicted deformation data meets the preset conditions, and the thickness T2 and concrete grade C40 are saved as the parameter adjustment results of FACADE-W-01. The next component in the set is then processed. After all components in the list have been processed, the parameters of these components are updated in the original BIM model file based on all the saved parameter adjustment results, and finally an optimized building information model is generated to guide the reinforcement and renovation design of the office building.

[0201] Finally, this step intelligently guides the adjustment direction by utilizing the target mapping relationship, and synchronously and iteratively modifies and verifies the morphological and material parameters of each building component that needs optimization. This generates an optimized building information model that meets the predetermined standards in all key performance indicators, thereby realizing closed-loop automation of building structure optimization, significantly improving the efficiency and reliability of the optimization process, and ensuring the actual effectiveness of the optimization results.

[0202] Figure 2 This application provides a structural schematic diagram of an intelligent optimization system for building information modeling based on artificial intelligence, such as... Figure 2 As shown, the system includes:

[0203] The first acquisition module 21 is used to acquire an initial building information model and site environment data corresponding to the initial building information model. The initial building information model includes geometric attribute information and physical attribute information of building components.

[0204] The first analysis module 22 is used to couple and analyze the site environment data, the geometric attribute information and the physical attribute information to obtain the first performance data of the building component.

[0205] The second acquisition module 23 is used to acquire the structural response data of the building component within a preset historical period;

[0206] The second analysis module 24 is used to perform correlation analysis based on the first performance data and the structural response data to deduce the target mapping relationship of the building components.

[0207] The adjustment module 25 is used to synchronously adjust the shape parameters and material parameters of building components in the initial building information model according to the target mapping relationship, until the adjusted shape parameters and material parameters meet the preset threshold, so as to generate an optimized building information model.

[0208] Figure 2 The aforementioned intelligent optimization system for building information modeling based on artificial intelligence can execute... Figure 1The implementation principle and technical effects of the AI-based intelligent optimization method for building information models described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit of the AI-based intelligent optimization system for building information models in the above embodiments are described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0209] In one possible design, Figure 2 The illustrated embodiment of an AI-based intelligent optimization system for building information models can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0210] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0211] The processing component 32 is used for the above Figure 1 The embodiment describes an intelligent optimization method for building information modeling based on artificial intelligence.

[0212] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0213] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0214] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0215] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0216] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0217] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0218] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown is an intelligent optimization method for building information model based on artificial intelligence.

[0219] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0220] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0221] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0222] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An intelligent optimization method for building information modeling based on artificial intelligence, characterized in that, include: The process involves acquiring an initial building information model (BIM) and corresponding site environmental data. The initial BIM includes geometric and physical attribute information of building components. This includes: obtaining an original building model from a pre-set design database and extracting the geometric and physical attribute information of the building components from the original model; acquiring 3D point cloud data of the target building site using 3D scanning technology and constructing a site reality model based on the 3D point cloud data; acquiring meteorological monitoring data of the target building site; spatially matching and overlaying the original building model with the site reality model to locate the building components within the site reality model, thus obtaining the initial BIM; and analyzing and calculating the solar radiation illuminance and wind pressure intensity of the outer surface of the building components based on the meteorological monitoring data, the site reality model, and the geometric and physical attribute information of the building components, using this as site environmental data. The analysis of the site environment data, geometric attribute information, and physical attribute information is coupled to obtain the first performance data of the building components. This includes: calculating the transient temperature field distribution of each building component under solar radiation irradiance based on solar radiation irradiance, surface orientation and area in the geometric attribute information, and material thermal conductivity and specific heat capacity in the physical attribute information; calculating the structural internal force distribution of each building component under wind load based on wind pressure intensity on the outer surface of the building component and structural shape and dimensions in the geometric attribute information; superimposing the thermal stress induced by the transient temperature field distribution with the structural internal force distribution to determine the comprehensive stress state of each building component; evaluating the safety margin of each building component based on the comprehensive stress state and material strength parameters in the physical attribute information; comparing the safety margin of each building component with a preset safety threshold, identifying target building components with safety margins lower than the safety threshold, and recording the identification information and corresponding safety margin values ​​of the target building components; and outputting the first performance data based on the identification information and corresponding safety margin values ​​of all target building components. Obtain the structural response data of the building component within a preset historical period; Based on the correlation analysis between the first performance data and the structural response data, the target mapping relationship of the building components is derived, including: matching the identification information and corresponding safety margin value of each target building component in the first performance data with the actual deformation data recorded by the building components with the same identification in the structural response data within the preset historical period; for each building component that has been matched, establishing a temporal correspondence between the safety margin value sequence and the actual deformation data sequence of the building component; based on the correspondence, identifying the regular deformation pattern presented in the actual deformation data when the safety margin value is lower than a preset level; extracting the feature parameters of the regular deformation pattern, and associating the feature parameters with the critical conditions of the safety margin value that trigger the regular deformation pattern; summarizing the association rules between the theoretical safety state and the actual deformation behavior of the building components based on the association results of all matched building components; and constructing a target mapping relationship for predicting the structural behavior of building components based on the first performance data based on the association rules. Based on the target mapping relationship, the morphological and material parameters of building components in the initial building information model are adjusted synchronously until the adjusted morphological and material parameters meet the preset thresholds to generate an optimized building information model, which is used to guide the reinforcement and renovation design of the target building.

2. The method according to claim 1, characterized in that, The thermal stress induced by the transient temperature field distribution is superimposed with the internal force distribution of the structure to determine the comprehensive stress state of each building component, including: Based on the transient temperature field distribution, the thermal stress value and direction at each point inside the building component are calculated to form a thermal stress distribution field; Based on the internal force distribution of the structure, the structural stress value and direction at each point inside the building component are calculated to form a structural stress distribution field; Vector synthesis is performed on the stress components at corresponding positions in the thermal stress distribution field and the structural stress distribution field to obtain the composite stress value and direction at each point inside the building component; Based on the combined stress values ​​and directions of all points, determine the maximum stress value in the building component and the location where the maximum stress value occurs in the building component; Based on the maximum stress value and the location where the maximum stress value occurs, the overall stress state of the building component is determined.

3. The method according to claim 1, characterized in that, Based on the association rules, a target mapping relationship is constructed for predicting the structural behavior of building components according to the first performance data, including: The association rule is converted into multiple judgment rules, each of which defines the range of the safety margin value and the corresponding deformation characteristics; The safety margin value is used as the input parameter for the target mapping relationship; The deformation features are used as the output parameters of the target mapping relationship; A mapping table is established based on the correspondence between safety margin values ​​and deformation characteristics in different ranges; The mapping table is validated to ensure that all input parameters have corresponding output parameters. Construct the target mapping relationship based on the verified mapping relationship table.

4. The method according to claim 1, characterized in that, Based on the target mapping relationship, the morphological and material parameters of building components in the initial building information model are synchronously adjusted until the adjusted morphological and material parameters meet a preset threshold, thereby generating an optimized building information model, including: The set of building components to be adjusted and the order of adjustment are determined based on the target mapping relationship; According to the adjustment order, each building component in the set of building components to be adjusted is adjusted in turn. The adjustment direction of the shape parameters and material parameters corresponding to each building component is determined according to the target mapping relationship, and the shape parameters and material parameters are modified synchronously. After each modification of the morphological parameters and material parameters, the first performance data is recalculated based on the modified morphological parameters and material parameters, and the predicted deformation data is output through the target mapping relationship. When the predicted deformation data meets the preset conditions, the parameter adjustment results of the current building component are saved; Once all the building components to be adjusted have completed their parameter adjustments, an optimized building information model is generated based on the parameter adjustment results of all building components.

5. An intelligent optimization system for building information modeling based on artificial intelligence, applied to the intelligent optimization method for building information modeling based on artificial intelligence according to any one of claims 1-4, characterized in that, include: The first acquisition module is used to acquire an initial building information model and site environment data corresponding to the initial building information model. The initial building information model includes geometric and physical attribute information of building components. The first analysis module is used to couple and analyze the site environment data, the geometric attribute information, and the physical attribute information to obtain the first performance data of the building component. The second acquisition module is used to acquire the structural response data of the building component within a preset historical period; The second analysis module is used to perform correlation analysis based on the first performance data and the structural response data to deduce the target mapping relationship of the building components. The adjustment module is used to synchronously adjust the shape parameters and material parameters of building components in the initial building information model according to the target mapping relationship, until the adjusted shape parameters and material parameters meet the preset threshold, so as to generate an optimized building information model.

6. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the intelligent optimization method for building information model based on artificial intelligence as described in any one of claims 1 to 4.

7. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements an intelligent optimization method for building information modeling based on artificial intelligence as described in any one of claims 1 to 4.

Images