A dome structure static performance analysis method and system

By preprocessing and feature extraction of response data of large-span dome structures, combined with clustering performance analysis model, the accuracy of static performance analysis in the existing technology is solved, and more comprehensive static performance analysis is achieved, and the Accuracy and comprehensiveness of the analysis.

CN118709501BActive Publication Date: 2024-11-26NANCHANG HANGKONG UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411185871.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The prior art is difficult to conduct a comprehensive and accurate analysis of the static properties of large-span dome structures, resulting in low analysis accuracy.

Method used

By obtaining the response data of the dome structure for preprocessing, the displacement, strain, stress and energy dissipation characteristic data are extracted, and the pretrained feature performance analysis model is input for analysis. Finally, cluster analysis is performed through the clustering performance analysis model to obtain the dome Analysis results of static properties of the structure.

Benefits of technology

It improves the comprehensiveness and accuracy of the static performance analysis of the dome structure, and provides more reliable structural design and construction support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118709501B_ABST
    Figure CN118709501B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of structural static performance analysis in civil engineering, and specifically discloses a method and system for static performance analysis of a dome structure, the method comprising: obtaining response data of a dome structure, and performing preprocessing to obtain first response data; performing feature extraction on the first response data to obtain displacement feature data, strain feature data, stress feature data, and energy dissipation feature data; respectively inputting the obtained data into corresponding feature performance analysis models to obtain corresponding static performance analysis results, pre-constructing a clustering performance analysis model, inputting the first static performance analysis result, the second static performance analysis result, the third static performance analysis result, and the fourth static performance analysis result into the clustering performance analysis model for clustering analysis to obtain the static performance analysis result of the dome structure; the implementation of the present invention improves the comprehensiveness and accuracy of the static performance analysis results of the dome structure.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of structural static performance analysis in civil engineering, and in particular to a method and system for static performance analysis of a dome structure. Background Art

[0002] The large-span structure in civil engineering refers to a building structure with a larger span, which has unique design and construction requirements. The large-span structure can create an open column-free space, providing greater flexibility and visual transparency. Common examples include large stadiums and high-speed rail stations. These structures usually have high complexity and load-bearing capacity. However, while the large-span structure has many advantages, its construction has high requirements on the strength and performance of the materials. Due to its large span and complex structural form, the structural stress and deformation will be more significant.

[0003] As an effective way to enclose large-span spaces, dome structures in large-span structures are widely used in the field of architecture. In recent years, with the emergence of new structural forms, such as air-film reinforced concrete dome thin shell structures and chord-supported dome structures, the static performance analysis of dome structures is particularly important. These structural forms not only overcome many shortcomings of traditional structures, but also show many unique technical advantages. However, the current research on the static performance of these new dome structures is still in its infancy, with few comprehensive analyses and low accuracy.

[0004] Therefore, the problem of how to conduct a comprehensive and accurate analysis of the static performance of the dome structure needs to be solved urgently. Summary of the invention

[0005] The purpose of this patent application is to provide a method and system for analyzing the static performance of a dome structure, aiming to comprehensively and accurately analyze the static performance of a dome structure.

[0006] In order to achieve the above-mentioned invention object, the present application discloses a method for analyzing static performance of a dome structure, the method comprising:

[0007] Acquiring response data of the dome structure, and preprocessing the response data to obtain first response data;

[0008] Extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data, and energy dissipation feature data;

[0009] Input the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, input the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, input the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and input the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result;

[0010] A clustering performance analysis model is pre-constructed, and the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result are input into the clustering performance analysis model for clustering analysis to obtain a static performance analysis result of the dome structure.

[0011] Furthermore, before the step of obtaining the response data of the dome structure and preprocessing the response data to obtain the first response data, the following steps are also included:

[0012] Constructing a dome structure model, and determining the position and degree of freedom of each node in the dome structure according to the dome structure model;

[0013] Dividing the dome structure model into finite element units according to the node positions and the node degrees of freedom to obtain a finite element model;

[0014] The finite element model is solved based on the finite element method to obtain response data of the dome structure.

[0015] Further, feature extraction is performed on the first response data to obtain displacement feature data, strain feature data, stress feature data and energy dissipation feature data, which specifically includes the following steps:

[0016] Extracting the displacement of each node of the dome structure according to the first response data, wherein the displacement includes horizontal displacement and vertical displacement;

[0017] The displacement amplitude at each node is calculated based on the displacement amount to obtain displacement characteristic data, strain characteristic data, stress characteristic data and energy dissipation characteristic data.

[0018] Furthermore, feature extraction is performed on the first response data to obtain strain feature data, which specifically includes the following steps:

[0019] Extracting strain quantities of each node of the dome structure according to the first response data, wherein the strain quantities include tension, compression and shear;

[0020] The strain amplitude at each node is calculated based on the strain amount to obtain strain characteristic data.

[0021] Furthermore, feature extraction is performed on the first response data to obtain stress feature data, which specifically includes the following steps:

[0022] Extracting stress amounts of each node of the dome structure according to the first response data, wherein the stress amounts include normal stress and shear stress;

[0023] The stress amplitude at each node is calculated based on the strain amount to obtain stress characteristic data.

[0024] Further, feature extraction is performed on the first response data to obtain energy dissipation feature data, which specifically includes the following steps:

[0025] Extracting elastic deformation data and velocity of each node of the dome structure according to the first response data;

[0026] Calculating the elastic potential energy of each node of the dome structure according to the elastic deformation data to obtain the strain energy dissipation;

[0027] Calculate the kinetic energy of each node of the dome structure according to the speed to obtain the kinetic energy dissipation;

[0028] Energy dissipation characteristic data is obtained according to the strain energy dissipation amount and the kinetic energy dissipation amount.

[0029] Furthermore, the pre-built clustering performance analysis model is implemented using the following formula:

[0030] E=( x 1 - m 1 ) 2 +( x 2 - m 2 ) 2 +( x 3 - m 3 ) 2 +( x 4 - m 4 ) 2 ;

[0031] in, x 1 , x 2 , x3 , x 4 They are the first static performance analysis result, the second static performance analysis result, the third static performance analysis result, and the fourth static performance analysis result. m 1、 m 2、 m 3、 m 4 Respectively represent x 1 , x 2 , x 3 , x 4 The initial cluster center E is based on x 1 , x 2 , x 3 , x 4 Clustering performance analysis results for clustering performance analysis model testing.

[0032] Furthermore, the present invention also discloses a dome structure static performance analysis system, the system comprising:

[0033] A first response data module, used to obtain response data of the dome structure, and pre-process the response data to obtain first response data;

[0034] A feature extraction module, used for extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data and energy dissipation feature data;

[0035] A static performance analysis result submodule, used for inputting the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, inputting the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, inputting the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and inputting the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result;

[0036] The static performance analysis result module is used to pre-build a cluster performance analysis model, input the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result into the cluster performance analysis model for cluster analysis, and obtain the static performance analysis result of the dome structure.

[0037] The beneficial effects of the present invention are:

[0038] The present invention obtains response data of the dome structure, pre-processes the response data and constructs it in a characteristic performance analysis model, so as to obtain multiple static performance analysis results. Then, by pre-constructing a clustering performance analysis model and performing clustering analysis, the static performance analysis results of the dome structure can be finally obtained. The implementation of the above-mentioned technology of the present invention can improve the comprehensiveness and accuracy of the static performance analysis results of the dome structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of an embodiment of a dome structure static performance analysis method of the present application;

[0040] Figure 2 This is a schematic diagram of the structure of an embodiment of a dome structure static performance analysis system of the present application;

[0041] Figure 3 The figure is a schematic diagram of the structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0043] Example 1, reference Figure 1 This embodiment provides a method for analyzing the static performance of a dome structure, which specifically includes steps S10 to S40. The detailed description of each of the above steps is as follows:

[0044] S10, acquiring response data of the dome structure, and preprocessing the response data to obtain first response data.

[0045] During the implementation of this step, it is necessary to install sensors at key locations of the dome structure, such as accelerometers, strain gauges, displacement sensors, etc. These sensors measure the response data of the key location structure under different loading conditions in real time, and conduct control experiments or loading tests to measure and record the response of the structure under experimental loading, such as using loading tests or model tests, and then using computer simulation software for numerical simulation to predict and record the response data of the key location structure under theoretical loading conditions; this step preprocesses the acquired dome structure response data in order to ensure data quality and accuracy, and to prepare for subsequent analysis.

[0046] Specifically, the preprocessing steps include: data cleaning, data alignment and synchronization, data interpolation, unit conversion, data formatting, calibration and calibration; after the above preprocessing steps, the first response data is obtained, that is, the dome structure response data set after cleaning, alignment, interpolation and formatting. These data are used for subsequent feature extraction, machine learning model training or other forms of static performance analysis.

[0047] S20, extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data, and energy dissipation feature data, specifically comprising the following steps:

[0048] The displacement of each node of the dome structure is extracted according to the first response data, wherein the displacement includes horizontal displacement and vertical displacement; the displacement amplitude at each node is calculated based on the displacement to obtain displacement characteristic data.

[0049] The first response data is subjected to feature extraction to obtain strain feature data, comprising the following steps: extracting the strain amount of each node of the dome structure according to the first response data, wherein the strain amount includes tension, compression and shear; and calculating the strain amplitude at each node based on the strain amount to obtain strain feature data.

[0050] The first response data is subjected to feature extraction to obtain stress characteristic data, which specifically includes the following steps: extracting the stress amount of each node of the dome structure according to the first response data, wherein the stress amount includes normal stress and shear stress; and calculating the stress amplitude at each node based on the strain amount to obtain stress characteristic data.

[0051] The first response data is subjected to feature extraction to obtain energy dissipation feature data, which specifically includes the following steps: extracting elastic deformation data and velocity of each node of the dome structure according to the first response data; calculating the elastic potential energy of each node of the dome structure according to the elastic deformation data to obtain strain energy dissipation; calculating the kinetic energy of each node of the dome structure according to the velocity to obtain kinetic energy dissipation; and obtaining energy dissipation feature data according to the strain energy dissipation and the kinetic energy dissipation.

[0052] S30, input the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, input the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, input the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and input the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result.

[0053] In this embodiment, displacement, strain, stress and energy dissipation characteristic data are extracted from the response data of the dome structure. The displacement characteristic data include the amplitude, change rate, pattern recognition, etc. of the displacement. The strain characteristic data involves the distribution, change rate, concentrated area recognition, etc. of the strain. The stress characteristic data includes the distribution, peak value, concentrated area analysis, etc. of the stress. The above-mentioned energy dissipation characteristic data reflects the energy loss of the structure during the loading process, such as damping characteristics, energy consumption pattern, etc. These features are extracted from the data and then used as input to different pre-trained characteristic performance analysis models. The pre-trained performance analysis model is trained on a large amount of data through machine learning or deep learning technology, and is used to predict or analyze the performance indicators of the structure from the characteristic data.

[0054] Secondly, the first characteristic performance analysis model receives displacement characteristic data as input and outputs a first static performance analysis result. The second characteristic performance analysis model receives strain characteristic data as input and outputs a second static performance analysis result to help evaluate the strain concentration area, deformation characteristics, etc. of the structure. The third characteristic performance analysis model receives stress characteristic data as input and outputs a third static performance analysis result, including evaluating the strength, stress concentration point, etc. of the structure. The fourth characteristic performance analysis model receives energy dissipation characteristic data as input and outputs a fourth static performance analysis result.

[0055] From the above, we can see that each characteristic performance analysis model will generate corresponding static performance analysis results based on its input characteristic data. These results are quantitative values, such as maximum displacement, maximum strain, stress distribution, etc., or descriptions of structural characteristics, such as vibration mode, stress distribution, etc.

[0056] S40, pre-constructing a clustering performance analysis model, inputting the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result into the clustering performance analysis model for clustering analysis, and obtaining a static performance analysis result of the dome structure.

[0057] In the above steps, after the static performance analysis of the dome structure, multiple performance indicators or parameter results are obtained, such as maximum stress, maximum displacement, stress distribution, etc. These results can be regarded as data points in a multidimensional space, and each static performance analysis result is represented as a multidimensional vector. Assuming that there are four different static performance analysis results, they are represented as a four-dimensional vector (x 1, x 2, x 3, x 4 ), where each component corresponds to the numerical result of a static performance index. K The mean algorithm constructs a clustering model; this algorithm requires specifying the number of clusters k and the initial cluster centers. Here k It is determined according to the characteristics and needs of the dome structure, and the initial cluster centers are usually selected randomly or by some heuristic method; at the beginning of the algorithm, the initial cluster centers are assigned to the points in the data space, and then the distance from each data point to each cluster center is calculated, and each data point is assigned to the category represented by the nearest cluster center.

[0058] Then, the position of each cluster center is adjusted iteratively to minimize the distance from each data point to its cluster center. This process ends when the stopping condition is met, usually when the cluster center no longer changes significantly or the maximum number of iterations is reached.

[0059] Ultimately, each data point will be assigned to a category represented by a cluster center. These categories reflect the similarities of the static performance analysis results in different characteristics or indicators. By analyzing the characteristics of each cluster, the different characteristics or problems of the dome structure in static performance, such as structural stability and load-bearing capacity, are revealed.

[0060] In this embodiment, before the step of obtaining the response data of the dome structure and preprocessing the response data to obtain the first response data, the method further includes: constructing a dome structure model, and determining the positions of each node and the node degrees of freedom in the dome structure according to the dome structure model; dividing the dome structure model into finite element units according to the node positions and the node degrees of freedom to obtain a finite element model; and solving the finite element model based on the finite element method to obtain the response data of the dome structure.

[0061] More specifically, in one embodiment, constructing a mathematical model of the dome structure is the basis for analyzing its static performance. This process includes the following steps:

[0062] According to the design drawings or CAD models of the actual structure, a geometric model of the dome structure is established, including determining the shape, size, cross-sectional shape, etc. of the structure; node determination is to determine the node position of the structure in the geometric model, wherein the node is the basic calculation unit in finite element analysis, which is used to describe the connection points and force transmission points in the structure. Node degree of freedom determination is to assign degrees of freedom to each node, and the degrees of freedom usually include the displacement and rotational degrees of freedom of the structure, such as three displacement components and three rotation components in three-dimensional space. The finite element method is a commonly used numerical method for solving structural mechanics problems. It requires the structure to be divided into finite element units. The division step includes dividing the volume or surface in the structural model into multiple small finite element units, which can be geometric units of different shapes such as triangles, quadrilaterals, tetrahedrons or hexahedrons.

[0063] Then define material properties, geometric properties and boundary conditions for each finite element. Once the structural model and finite element mesh are established, finite element analysis is performed to solve the response data of the structure. This process includes: assembling the stiffness matrix of the entire structure based on the properties and connection relationships of the finite element units. The stiffness matrix describes the response of the structure under given displacements and forces; defining the boundary conditions of the structure, including support and loading conditions, which will affect the response and stability of the structure. Apply the matrix solution technology of the finite element method to solve the equilibrium equations of the structure and obtain the displacement field of the structure under loading conditions.

[0064] Finally, the first response data of the structure, such as displacement, strain, and stress, are obtained from the solved finite element model. These data are the basis for subsequent static performance analysis and are used to further analyze the vibration characteristics, strength distribution, and stability of the structure. Through the above steps, the mathematical model of the dome structure can be systematically constructed, the finite element mesh can be divided, and the response data of the structure can be obtained based on the finite element method, providing reliable numerical support for subsequent engineering analysis and design.

[0065] In this embodiment, feature extraction is performed on the first response data to obtain displacement feature data, which specifically includes the following steps:

[0066] The displacement of each node of the dome structure is extracted according to the first response data, wherein the displacement includes horizontal displacement and vertical displacement; the displacement amplitude at each node is calculated based on the displacement to obtain displacement characteristic data.

[0067] In this embodiment, the displacement of each node is a key output in the results of finite element analysis. Displacement refers to the movement of each node relative to its initial position after the structure is subjected to external forces, which is usually divided into horizontal displacement u and vertical displacement v , horizontal displacement uIndicates the displacement of the node within the structural plane. v Represents the displacement of the node in the vertical direction of the structure. These displacements are usually given in the form of vectors. i , which can be expressed as u i =[ u i , v i ] T , among which u i and v i The nodes are i The horizontal and vertical displacement of the node. u i , the displacement amplitude at the node can be calculated, which helps to evaluate the degree of deformation of the structure. , this displacement amplitude d i Representation Node i The length of the displacement vector at the node is the overall displacement of the node relative to its initial position. Through such analysis and calculation, the deformation of the dome structure under loading conditions can be quantitatively evaluated, providing data support for subsequent structural analysis and design optimization.

[0068] In this embodiment, feature extraction is performed on the first response data to obtain strain feature data, which specifically includes the following steps:

[0069] The strain amount of each node of the dome structure is extracted according to the first response data, wherein the strain amount includes tension, compression and shear; the strain amplitude at each node is calculated based on the strain amount to obtain strain characteristic data.

[0070] In this embodiment, in the finite element analysis, the strain of each node is calculated based on the node displacement. The strain variables generally include the following types: tensile strain : The degree of stretching in the main axis direction of the structure, the compressive strain : The degree of compression in the vertical direction of the structure, shear strain c xy : Shear deformation in the plane of the structure. These strains can be calculated from the displacement data of the nodes. Specifically:

[0071] Tensile strain It can be expressed as the horizontal displacement of the node u The ratio of the difference to the initial position of the node in the horizontal direction, = oh 0 / L ,inu is the current horizontal displacement, u 0 is the initial horizontal position, L is the initial length.

[0072] Compression strain Expressed as the vertical displacement of the node v The ratio of the difference between the initial position of the node in the vertical direction, that is, =vv 0 / H ,in v is the current vertical displacement, v 0 is the initial vertical position, H is the initial height.

[0073] Shear strain c xy Expressed as the horizontal displacement of the node u and vertical displacement v The difference ratio between c xy =2 u- 2 v / L + H ,in L and H are the initial length and height.

[0074] Based on the strain at each node, the strain amplitude at the node is calculated. The strain amplitude is the composite value of all strain components and is used to describe the overall deformation of the node under loading conditions.

[0075] Strain amplitude It is calculated by summing the squares of the strain components and then taking the square root, that is, , this value represents the node i The modulus of the strain vector at reflects the overall deformation degree of the structure after being subjected to force at that location. Through such analysis and calculation, the deformation of the dome structure under different loading conditions is quantitatively evaluated, providing valuable data support for the safety assessment and design optimization of the structure.

[0076] In this embodiment, feature extraction is performed on the first response data to obtain stress feature data, which specifically includes the following steps:

[0077] The stress amount of each node of the dome structure is extracted according to the first response data, wherein the stress amount includes normal stress and shear stress; the stress amplitude at each node is calculated based on the strain amount to obtain stress characteristic data.

[0078] In this embodiment, normal stress refers to the tensile or compressive stress that a node bears in the direction of its principal axis, including the horizontal and vertical directions. These stress amounts are calculated by analyzing the strain at the node, that is, the deformation caused by the structural force, and the elastic properties of the material, that is, the elastic modulus. Shear stress refers to the shear stress that a node is subjected to in the plane of the structure. It is usually determined by the shear strain at the node and the shear modulus of the material. The stress amount can reveal the specific mechanical response of the structure under different loading conditions and help engineers evaluate the strength and stability of the structure.

[0079] Stress amplitude refers to the overall stress level obtained after comprehensively considering all principal stress components at a node, including the contributions of normal stress and shear stress. By calculating the stress amplitude, we can have a more comprehensive understanding of the stress state of a node under actual working conditions. The acquisition and analysis of stress characteristic data is an important step in structural engineering. They provide critical information to help engineers make accurate structural assessments and design decisions.

[0080] In this embodiment, feature extraction is performed on the first response data to obtain energy dissipation feature data, which specifically includes the following steps:

[0081] The elastic deformation data and velocity of each node of the dome structure are extracted according to the first response data; the elastic potential energy of each node of the dome structure is calculated according to the elastic deformation data to obtain the strain energy dissipation; the kinetic energy of each node of the dome structure is calculated according to the velocity to obtain the kinetic energy dissipation; and the energy dissipation characteristic data is obtained according to the strain energy dissipation and the kinetic energy dissipation.

[0082] In this embodiment, elastic deformation refers to the reversible deformation of the structure under external loading. By analyzing the first response data, the displacement or deformation data of each node is obtained, which reflects the deformation of the node after the force is applied. The speed represents the movement speed of each node in the structure, which is calculated by the derivative of the time series data, that is, the rate of change of the node displacement over time. The elastic potential energy is the energy stored in the structure under external loading, which is calculated by the elastic deformation data at the node.

[0083] The specific calculation method involves the displacement of the node and the elastic properties of the material, which can be expressed as:

[0084] ;

[0085] Where k is the stiffness coefficient of the node and X is the displacement of the node.

[0086] Kinetic energy is the energy possessed by each node in the structure due to its motion, calculated from the velocity of the node and expressed as:

[0087] ;

[0088] Where m is the mass or equivalent mass of the node, and V is the velocity of the node.

[0089] Energy dissipation is the energy lost by the structure during external loading and movement, which is the loss of elastic potential energy and kinetic energy. It can be calculated by the decay of elastic potential energy and the conversion of kinetic energy into heat, expressed as:

[0090] ;

[0091] Energy dissipation characteristic data provides detailed information about the energy conversion and loss of the structure during operation. By analyzing this data, the energy efficiency, vibration characteristics and response capabilities of the structure are evaluated, providing a basis for optimizing the performance of the structure.

[0092] In this embodiment, the pre-built clustering performance analysis model is implemented using the following formula:

[0093] E=( x 1 - m 1 ) 2 +( x 2 - m 2 ) 2 +( x 3 - m 3 ) 2 +( x 4 - m 4 ) 2 ;

[0094] in, x 1 , x 2 , x 3 , x 4 They are the first static performance analysis result, the second static performance analysis result, the third static performance analysis result, and the fourth static performance analysis result. m 1、 m 2、 m 3、 m 4 Respectively represent x 1 , x 2 , x3 , x 4 The initial cluster center E is based on x 1 , x 2 , x 3 , x 4 Clustering performance analysis results for clustering performance analysis model testing.

[0095] The above E is a measure of error or distance, which is used to measure the difference between the static performance analysis results of the dome structure and the cluster center. The formula calculates the sum of the squares of the deviations between the values ​​of the data points in the four characteristic dimensions and the corresponding cluster centers. This is the square of the Euclidean distance of each data point to its cluster center, which quantifies the proximity of the data point to its cluster center. A small E value indicates that the data point is very close to its cluster center, which means that the data point is relatively consistent with its cluster center and the clustering effect is good. A larger E value indicates that the data point is far from the cluster center, which means that the point is far from its cluster center, or that the current selection of the cluster center is not optimal.

[0096] m 1 , m 2 , m 3 , m 4 are the initial cluster centers, which are randomly selected values ​​at the beginning of the K-means algorithm. Formula E is the distance metric used in the K-means clustering algorithm to calculate each data point to its cluster center. This distance metric helps evaluate the effect of clustering, especially in the static performance analysis of dome structures, and can classify and optimize different static performance results, thereby improving the effectiveness and performance of structural design.

[0097] The core of the K-means algorithm is to adjust the positions of these cluster centers through continuous iterations so that the distance from the data point to its nearest cluster center is minimized. In practical applications, the K-means algorithm repeatedly calculates the distance from each data point to each cluster center, and then assigns each data point to the cluster center that is closest to it. The value of E reflects the sum of the distances between all data points and their assigned cluster centers. The smaller this value is, the better the clustering effect is, that is, the closer the data points are to the cluster centers to which they belong. Therefore, through this formula, the performance of the K-means algorithm in the static performance analysis of dome structures is quantified to help engineers evaluate and optimize the performance of the structure.

[0098] Example 2, reference Figure 2This embodiment provides a dome structure static performance analysis system, the system applies the method described in Example 1, and the dome structure static performance analysis system provided in this embodiment includes:

[0099] A first response data module 10 is used to obtain response data of the dome structure and pre-process the response data to obtain first response data;

[0100] A feature extraction module 20, used for extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data and energy dissipation feature data;

[0101] The static performance analysis result submodule 30 is used to input the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, input the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, input the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and input the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result;

[0102] The static performance analysis result module 40 is used to pre-build a cluster performance analysis model, input the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result into the cluster performance analysis model for cluster analysis, and obtain the static performance analysis result of the dome structure.

[0103] As described above, it can be understood that the various components of the dome structure static performance analysis system proposed in the present application can realize the functions of any one of the dome structure static performance analysis methods described above.

[0104] In this embodiment, the feature extraction module 20 further includes executing:

[0105] The steps of extracting the strain amount of each node of the dome structure according to the first response data, wherein the strain amount includes tension, compression and shear; and calculating the strain amplitude at each node based on the strain amount to obtain strain characteristic data.

[0106] The feature extraction module 20 further includes executing:

[0107] The steps of extracting stress amounts at each node of the dome structure according to the first response data, wherein the stress amounts include normal stress and shear stress; and calculating stress amplitudes at each node based on the strain amounts to obtain stress characteristic data.

[0108] The feature extraction module 20 further includes executing the following steps:

[0109] Extracting elastic deformation data and velocity of each node of the dome structure according to the first response data;

[0110] Calculating the elastic potential energy of each node of the dome structure according to the elastic deformation data to obtain the strain energy dissipation;

[0111] Calculate the kinetic energy of each node of the dome structure according to the speed to obtain the kinetic energy dissipation;

[0112] Energy dissipation characteristic data is obtained according to the strain energy dissipation amount and the kinetic energy dissipation amount.

[0113] Embodiment 3, a computer device, the internal structure of the computer device can be as follows Figure 3 As shown, a dome structure static performance analysis system described in Example 2 is installed in the computer device.

[0114] The computer device includes a processor, a memory, a network interface, a display device and an input device connected through a system bus.

[0115] The network interface of the computer device is used to communicate with an external terminal through a network connection. The display device of the computer device is used to display an interactive page. The input device of the computer device is used to receive user input. The processor designed for the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium. The non-volatile storage medium stores an operating system, a computer program and a database. The database of the computer device is used to store raw data, and the computer program is used to implement a dome structure static performance analysis method of Example 1 when executed by the processor.

[0116] Embodiment 4, a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by the processor, is used to implement a dome structure static performance analysis method of embodiment 1 and a dome structure static performance analysis system of embodiment 2.

[0117] In summary, the contents described in Examples 1 to 4 above, a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0118] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for analyzing the static performance of a dome structure, characterized in that: The steps include: S00, constructing a geometric model of a dome structure, and determining the positions of each node and the degree of freedom of each node in the dome structure according to the dome structure model; dividing the dome structure model into finite element units according to the node positions and the degree of freedom of each node to obtain a finite element model; The finite element model is solved based on the finite element method to obtain the response data of the dome structure; specifically, the following steps are performed: According to the design drawings or CAD models of the actual structure, a geometric model of the dome structure is established; the node positions of the structure are determined in the geometric model; degrees of freedom are assigned to each node, and the structure is divided into finite element units, wherein the dividing step includes dividing the volume or surface in the structural model into a plurality of small finite element units, wherein the finite element units include but are not limited to geometric unit units of triangles, quadrilaterals, tetrahedrons or hexahedrons; Define material properties, geometric properties and boundary conditions for each finite element unit; assemble the stiffness matrix of the entire structure according to the properties and connection relationships of the finite element units; define the boundary conditions of the structure, which include support and loading conditions; apply the matrix solution technology of the finite element method to solve the equilibrium equation of the structure and obtain the displacement field of the structure under the loading condition; obtain the first response data of the structure from the solved finite element model, which includes displacement, strain and stress; S10, acquiring response data of the dome structure, and preprocessing the response data to obtain first response data; S20, extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data, and energy dissipation feature data; In this step S20, extracting features from the first response data to obtain displacement feature data specifically includes the following steps: (1) extracting the displacement of each node of the dome structure according to the first response data, wherein the displacement includes horizontal displacement and vertical displacement; (2) calculating the displacement amplitude at each node based on the displacement amount to obtain displacement characteristic data; In step S20, feature extraction is performed on the first response data to obtain strain feature data, which specifically includes the following steps: (1) extracting the strain of each node of the dome structure according to the first response data, wherein the strain includes tension, compression and shear; (2) Calculating the strain amplitude at each node based on the strain amount to obtain strain characteristic data; In step S20, feature extraction is performed on the first response data to obtain stress characteristic data, which specifically includes the following steps: (1) extracting stress at each node of the dome structure according to the first response data, wherein the stress includes normal stress and shear stress; (2) calculating the stress amplitude at each node based on the strain amount to obtain stress characteristic data; In this step S20, feature extraction is performed on the first response data to obtain energy dissipation feature data, which specifically includes the following steps: (1) extracting elastic deformation data and velocity of each node of the dome structure according to the first response data; (2) calculating the elastic potential energy of each node of the dome structure according to the elastic deformation data to obtain the strain energy dissipation; (3) calculating the kinetic energy of each node of the dome structure according to the speed to obtain the kinetic energy dissipation; (4) obtaining energy dissipation characteristic data according to the strain energy dissipation and the kinetic energy dissipation; S30, inputting the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, inputting the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, inputting the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and inputting the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result; S40, pre-constructing a clustering performance analysis model, inputting the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result into the clustering performance analysis model for clustering analysis, and obtaining a static performance analysis result of the dome structure; In step S40, the pre-constructed clustering performance analysis model is implemented using the following formula: E=( x 1− μ 1) 2 +( x 2− μ 2) 2 +( x 3− μ 3) 2 +( x 4− μ 4) 2 _ ; in, x 1. x 2. x 3. x 4 are the first static performance analysis results, the second static performance analysis results, the third static performance analysis results, and the fourth static performance analysis results. μ 1、 μ 2、 μ 3、 μ 4 represent x 1. x 2. x 3. x 4 initial cluster centers, E is based on x 1. x 2. x 3. x 4 Clustering performance analysis results of clustering performance analysis model tests.

2. A dome structure static performance analysis system, characterized in that: The system uses a dome structure static performance analysis method as claimed in claim 1; the system comprises: A first response data module, used to obtain response data of the dome structure, and pre-process the response data to obtain first response data; A feature extraction module, used for extracting features from the first response data to obtain displacement feature data, strain feature data, stress feature data and energy dissipation feature data; A static performance analysis result submodule, used for inputting the displacement characteristic data into a pre-trained first characteristic performance analysis model so that the first characteristic performance analysis model outputs a first static performance analysis result, inputting the strain characteristic data into a pre-trained second characteristic performance analysis model so that the second characteristic performance analysis model outputs a second static performance analysis result, inputting the stress characteristic data into a pre-trained third characteristic performance analysis model so that the third characteristic performance analysis model outputs a third static performance analysis result, and inputting the energy dissipation characteristic data into a pre-trained fourth characteristic performance analysis model so that the fourth characteristic performance analysis model outputs a fourth static performance analysis result; The static performance analysis result module is used to pre-build a cluster performance analysis model, input the first static performance analysis result, the second static performance analysis result, the third static performance analysis result and the fourth static performance analysis result into the cluster performance analysis model for cluster analysis, and obtain the static performance analysis result of the dome structure.