Modularized super high-rise building steel structure design method

Abstract

The invention provides a modular super high-rise building steel structure design method, and belongs to the technical field of building design. According to the method, firstly, format normalization processing is carried out on an existing geometric parameter data set, a data set is constructed, and on the basis, the strength of each connection node is calculated; meanwhile, performing parameterization on each geometric configuration by utilizing a trained condition model, and then performing multiple characterization; and constructing a geometric configuration-design parameter corresponding relation by using the multi-representation data and the structural strength data. And training the constructed classification diffusion model according to the corresponding relation, inputting given construction data to obtain primary design data, and correcting by using specified data to obtain a final design scheme. According to the method, a machine learning scheme is introduced, model parameters are adjusted through data to optimize prediction performance, and then a parameterized design scheme is represented and optimized. By applying the method, the design precision and the design efficiency can be remarkably improved, and the correction frequency and the error rate are reduced.

Description

Technical Field

[0001] This invention relates to the field of architectural design technology, specifically a modular steel structure design method for super high-rise buildings. Background Technology

[0002] Steel structures, using steel as the primary material and employing welding, bolting, and other connection methods, form various spatial structural systems. They are widely used in high-rise buildings, bridges, stadiums, industrial plants, and many other large-scale projects. Especially in earthquake-prone areas, steel structure engineering, due to its excellent seismic performance, has become a crucial means of protecting people's lives and property. With continuous technological advancements, steel structure engineering is also constantly developing and innovating. The application of new steel materials, high-strength bolts, and intelligent welding technologies has significantly improved the safety, economy, and environmental friendliness of steel structure engineering.

[0003] The core components of a steel structure include steel beams, steel columns, steel trusses, and steel space frames. These components form a stable spatial frame through connection nodes, capable of withstanding vertical pressure and horizontal thrust. Different structural combinations meet the design requirements of various buildings. The design scheme is the blueprint for the entire steel structure project, detailing the dimensions, shapes, materials, and connection methods of each component, and has a crucial impact on ensuring construction safety and quality. Safety is the primary prerequisite for steel structure design. Loads, such as self-weight, wind loads, and seismic loads, must be fully considered during the design process to ensure the structure remains stable under extreme conditions. A reasonable structural layout and node design help distribute stress and avoid local overload. While steel structures can be constructed quickly, the rationality of construction techniques and connection methods must also be considered. For example, the processing accuracy of prefabricated components, ease of transportation, and efficiency of on-site assembly are all multifaceted considerations during the design phase. Furthermore, the rational selection of steel types and optimization of structural layout to reduce material waste are key to cost control. Modular design can also improve construction efficiency and shorten the construction period.

[0004] The challenges of modular steel structure design include the complexity of node design, the diversity of connection methods, and the complexity of stress analysis. Nodes, as the "joints" of the structure, require diversification to ensure safety and reliability while facilitating construction. The application of modern computational technology has greatly enhanced the capabilities of stress analysis and optimization design. Furthermore, modular steel structures employ a variety of steel components, such as steel roof trusses, steel frame structures, and steel space frames, each performing different functions. The rational design and selection of these components is crucial for ensuring building safety. These structures play a vital role in the building and are essential for assessing the overall structural stability and load-bearing capacity. For super high-rise buildings (total height greater than 100 meters, number of floors greater than 40), the steel structure system plays an even more critical role, requiring consideration of more factors and having a lower tolerance for error, thus making the design of such steel structures even more challenging. Existing technologies often employ inefficient and inaccurate conventional design schemes, necessitating repeated revisions. Therefore, improving design efficiency and accuracy remains a technical challenge in this field. Summary of the Invention

[0005] The technical problem to be solved by this invention is: how to improve the efficiency and accuracy of modular steel structure design for super high-rise buildings.

[0006] To achieve the above technical objectives, the present invention adopts the following technical solution: A modular steel structure design method for super high-rise buildings includes: 1) Normalize the format of the existing geometric parameter dataset and perform recursive operations to obtain a multi-source geometric parameter dataset; 2) Perform strength calculations on each connection node in the multi-source geometric parameter dataset obtained in step 1), including stress distribution and internal force analysis; 3) For each geometric configuration in the multi-source geometric parameter dataset obtained in step 1), the geometric configuration is parameterized using the trained conditional model, and then the parameterized geometric configuration is interpolated to obtain multiple representations of each geometric configuration. 4) Using the strength calculation results of each connection node in the multi-source geometric parameter dataset obtained in step 2) and the multiple characterization data of each geometric configuration obtained in step 3), establish the correspondence between geometric configuration and design parameters; 5) Construct a classification diffusion model, using the geometric configuration-design parameter correspondence obtained in step 4) as a mapping, and train the classification diffusion model. During the training process, the multiple representations of the geometric configuration and their corresponding calculation coefficients are used as inputs. 6) Given the constructed data, input it into the classification diffusion model trained in step 5) to obtain the design parameters that satisfy the constructed data. Then input the specification data for correction to obtain the final design parameters.

[0007] Preferably, the prescriptive data is obtained by constructing a three-dimensional building foundation model in a BIM platform based on geological survey data of the building site selection; the prescriptive data includes the connection structure and material of the nodes, and the material includes the density and strength data of steel.

[0008] Preferably, the geometric configuration includes the section height of the steel section, the flange width, the web thickness, and the flange thickness.

[0009] Preferably, the calculation coefficients include parameterized section modulus, load performance, and seismic performance.

[0010] Preferably, the parameterized geometric configuration is characterized by the following formula: ; ; ; ; in, For the density of structural steel, Total load; The static pressure component per unit area; For vectorized geometric parameters, its components in the three coordinate directions are: , , ; It is the axial tensile force per unit area.

[0011] Preferably, in the construction data, the vibration equation of the tension member is characterized by the following equation: ; Ms, Cs, and Ks represent the mass matrix, damping matrix, and stiffness matrix of the steel structure, respectively. , , , which are the displacement, velocity, and acceleration vectors of the structure, respectively.

[0012] Preferably, in the construction data, the wind load is characterized by the following formula: ; In the above formula, The wind load is perpendicular to the wind-facing surface of the steel structure. The reference wind pressure standard value, This is the wind pressure non-uniformity coefficient. This is the wind pressure height variation coefficient. This is the drag coefficient. This is the wind load adjustment factor. This represents the area of ​​the windward side of the steel structure. The average width of the steel structure on the windward side. The angle between the wind load and the wind-exposed surface of the steel structure; in: ; The wind speed is based on a reference height of 50 m.

[0013] Preferably, the seismic dynamics equation of the steel structure is characterized by the following equation: ; Where M, C, and K represent the mass matrix, stiffness matrix, and damping matrix, respectively, f( t ) represents the wind load vector. Let x represent the earthquake motion time history, and x be the vibration response vector.

[0014] Preferably, the structural strength model of the steel structure is characterized by the following formula: ; in, M , C , K These are the mass coefficient, damping coefficient, and stiffness coefficient, respectively. These are the force parameters. , This is the stress characteristic coefficient of the steel structure.

[0015] Preferably, the construction data is provided by the following method: calling a preset parametric component library to generate a geometric topology model including steel profiles, connectors, and node strength, and generating a set of structural elements; coupling the set of structural elements with other components, performing nonlinear mechanical analysis, and outputting the construction data and changes of the corresponding nodes.

[0016] This invention provides a modular design method for steel structures of super high-rise buildings. The technical solution first normalizes the format of existing geometric parameter datasets to construct a new dataset. Based on this, the strength of each connection node is calculated. Simultaneously, a trained conditional model is used to parameterize each geometric configuration in the multi-source geometric parameter dataset, followed by multiple characterization. A correspondence between geometric configuration and design parameters is constructed using the multiple characterization data and structural strength data. This correspondence is used to train a classification diffusion model. Inputting given construction data yields initial design data, which is then corrected using prescriptive data to obtain the final design scheme. This invention introduces a machine learning approach, adjusting model parameters through data to optimize prediction performance, thereby characterizing and optimizing the parameterized design scheme. Applying this invention can significantly improve design accuracy and efficiency, reduce the number of corrections and error rate, and has a positive impact on improving engineering quality. Attached Figure Description

[0017] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in detail below. To avoid excessive and unnecessary detail, well-known structures or functions will not be described in detail in the following embodiments. The approximate language used in the following embodiments is for quantitative purposes, indicating that a certain degree of variation in quantity is permissible without changing the basic function. Unless otherwise defined, the technical and scientific terms used in the following embodiments have the same meaning as commonly understood by those skilled in the art to which this invention pertains.

[0019] A modular steel structure design method for super high-rise buildings includes: 1) Normalize the format of the existing geometric parameter dataset and perform recursive operations to obtain a multi-source geometric parameter dataset; 2) Perform strength calculations on each connection node in the multi-source geometric parameter dataset obtained in step 1), including stress distribution and internal force analysis; 3) For each geometric configuration in the multi-source geometric parameter dataset obtained in step 1), the geometric configuration is parameterized using the trained conditional model, and then the parameterized geometric configuration is interpolated to obtain multiple representations of each geometric configuration. 4) Using the strength calculation results of each connection node in the multi-source geometric parameter dataset obtained in step 2) and the multiple characterization data of each geometric configuration obtained in step 3), establish the correspondence between geometric configuration and design parameters; 5) Construct a classification diffusion model, using the geometric configuration-design parameter correspondence obtained in step 4) as a mapping, and train the classification diffusion model. During the training process, the multiple representations of the geometric configuration and their corresponding calculation coefficients are used as inputs. 6) Given the constructed data, input it into the classification diffusion model trained in step 5) to obtain the design parameters that satisfy the constructed data. Then input the specification data for correction to obtain the final design parameters.

[0020] The prescriptive data is obtained by the following method: constructing a three-dimensional building foundation model in a BIM platform based on geological survey data of building site selection; the prescriptive data includes the connection structure and material of nodes, and the material includes the density and strength data of steel.

[0021] The geometric configuration includes the section height, flange width, web thickness, and flange thickness of the steel section.

[0022] The calculation coefficients include parameterized section modulus, load performance, and seismic performance.

[0023] The parameterized geometry is characterized by the following equation: ; ; ; ; in, For the density of structural steel, Total load; The static pressure component per unit area; For vectorized geometric parameters, its components in the three coordinate directions are: , , ; It is the axial tensile force per unit area.

[0024] In the aforementioned construction data, the vibration equation of the tension member is characterized by the following formula: ; Ms, Cs, and Ks represent the mass matrix, damping matrix, and stiffness matrix of the steel structure, respectively. , , , which are the displacement, velocity, and acceleration vectors of the structure, respectively.

[0025] In the constructed data, wind load is characterized by the following formula: ; In the above formula, The wind load is perpendicular to the wind-facing surface of the steel structure. The reference wind pressure standard value, This is the wind pressure non-uniformity coefficient. This is the wind pressure height variation coefficient. This is the drag coefficient. This is the wind load adjustment factor. This represents the area of ​​the windward side of the steel structure. The average width of the steel structure on the windward side. The angle between the wind load and the wind-exposed surface of the steel structure; in: ; The wind speed is based on a reference height of 50 m.

[0026] The seismic dynamics equation of the steel structure is characterized by the following equation:

[0027] Where M, C, and K represent the mass matrix, stiffness matrix, and damping matrix, respectively, f( t ) represents the wind load vector. Let x represent the earthquake motion time history, and x be the vibration response vector.

[0028] The structural strength model of the steel structure is characterized by the following formula: ; in, M , C , K These are the mass coefficient, damping coefficient, and stiffness coefficient, respectively. These are the force parameters. , This is the stress characteristic coefficient of the steel structure.

[0029] The construction data is provided by the following method: calling a pre-set parametric component library to generate a geometric topology model including steel profiles, connectors, and node strength, and generating a set of structural elements; coupling the set of structural elements with other components, performing nonlinear mechanical analysis, and outputting the construction data and changes of the corresponding nodes.

[0030] The embodiments of the present invention have been described in detail above, but the content described is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the scope of the present invention should be included within the protection scope of the present invention.

Claims

1. A modular design method for steel structures of super high-rise buildings, characterized in that, include: 1) Normalize the format of the existing geometric parameter dataset and perform recursive operations to obtain a multi-source geometric parameter dataset; 2) Perform strength calculations on each connection node in the multi-source geometric parameter dataset obtained in step 1), including stress distribution and internal force analysis; 3) For each geometric configuration in the multi-source geometric parameter dataset obtained in step 1), the geometric configuration is parameterized using the trained conditional model, and then the parameterized geometric configuration is interpolated to obtain multiple representations of each geometric configuration. 4) Using the strength calculation results of each connection node in the multi-source geometric parameter dataset obtained in step 2) and the multiple characterization data of each geometric configuration obtained in step 3), establish the correspondence between geometric configuration and design parameters; 5) Construct a classification diffusion model, using the geometric configuration-design parameter correspondence obtained in step 4) as a mapping, and train the classification diffusion model. During the training process, the multiple representations of the geometric configuration and their corresponding calculation coefficients are used as inputs. 6) Given the constructed data, input it into the classification diffusion model trained in step 5) to obtain the design parameters that satisfy the constructed data. Then input the specification data for correction to obtain the final design parameters.

2. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The prescriptive data is obtained by constructing a three-dimensional building foundation model in a BIM platform based on geological survey data of the building site selection; the prescriptive data includes the connection structure and material of the nodes, and the material includes the density and strength data of steel.

3. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The geometric configuration includes the section height, flange width, web thickness, and flange thickness of the steel section.

4. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The calculation coefficients include parameterized section modulus, load performance, and seismic performance.

5. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The parameterized geometry is characterized by the following equation: ； ； ； ； in, For the density of structural steel, Total load; The static pressure component per unit area; For vectorized geometric parameters, its components in the three coordinate directions are: , , ; It is the axial tensile force per unit area.

6. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, In the aforementioned construction data, the vibration equation of the tension member is characterized by the following formula: ； Ms, Cs, and Ks represent the mass matrix, damping matrix, and stiffness matrix of the steel structure, respectively. , , , which are the displacement, velocity, and acceleration vectors of the structure, respectively.

7. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, In the constructed data, wind load is characterized by the following formula: ； In the above formula, The wind load is perpendicular to the wind-facing surface of the steel structure. The reference wind pressure standard value, This is the wind pressure non-uniformity coefficient. This is the wind pressure height variation coefficient. This is the drag coefficient. This is the wind load adjustment factor. This represents the area of ​​the windward side of the steel structure. The average width of the steel structure on the windward side. The angle between the wind load and the wind-exposed surface of the steel structure; in: ； The wind speed is based on a reference height of 50 m.

8. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The seismic dynamics equation of the steel structure is characterized by the following equation: ； Where M, C, and K represent the mass matrix, stiffness matrix, and damping matrix, respectively, f( t ) represents the wind load vector. Let x represent the earthquake motion time history, and x be the vibration response vector.

9. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The structural strength model of the steel structure is characterized by the following formula: ； in, M , C , K These are the mass coefficient, damping coefficient, and stiffness coefficient, respectively. These are the force parameters. , This is the stress characteristic coefficient of the steel structure.

10. The modular steel structure design method for super high-rise buildings according to claim 1, characterized in that, The construction data is provided by the following method: calling a pre-set parametric component library to generate a geometric topology model including steel profiles, connectors, and node strength, and generating a set of structural elements; coupling the set of structural elements with other components, performing nonlinear mechanical analysis, and outputting the construction data and changes of the corresponding nodes.

Images