Configuration deviation prediction method based on digital twinning space structure

Through the digital twin-based method, the finite element model is updated and the temperature effect is simulated, the accuracy of position deviation prediction in spatial grid structure construction is solved, and the accuracy and safety of construction are improved.

CN119089724APending Publication Date: 2024-12-06TSINGHUA UNIVERSITY +1
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202410956596.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In the construction of spatial grid structures, due to the positional changes caused by the existence of the temperature field, it is difficult for the prior art to accurately predict the positional deviation of the pre-installed structure, which may have adverse effects during construction.

Method used

By obtaining point cloud data of preinstalled structures, updating the finite element model, and building a digital twin model based on this, simulating the temperature effect during the installation cycle, and predicting the positional deviation of the preinstalled structures.

Benefits of technology

It realizes that the positioning shape deviation is more accurately determined through simulation before construction, takes into account the influence of temperature effects, and improves the accuracy of construction and structural safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089724A_ABST
    Figure CN119089724A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of space grid structure construction control, in particular to a configuration deviation prediction method of a space structure based on digital twinning. The method comprises the steps that point cloud data of a pre-installed structure is acquired, a finite element model of a target building is updated based on the point cloud data, a digital twin model is established based on the updated finite element model, the pre-installed structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building; the installation period of the preassembled structure is obtained, estimated temperature information in the installation period is determined, and the installation period comprises time used for combination, hoisting and closure; performing temperature effect simulation in the digital twinborn model based on the estimated temperature information to obtain the configuration deviation of the preassembled structure; and sending the configuration deviation to the target equipment. By adopting the method, the configuration deviation generated by the preassembled structure can be more accurately determined.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of construction control of spatial grid structures, and in particular to a method for predicting configuration deviations of spatial structures based on digital twins. Background Art

[0002] Spatial grid structures are widely used in large urban public buildings such as stadiums, high-speed rail stations, terminals and exhibition halls due to their advantages such as diverse structural forms, strong spanning capacity, high rigidity, light weight and clear force. However, due to the complex geometric information, large component size and irregular shape of such structures, the construction is relatively complicated. At present, considering the scale of structural components and the difficulty and danger of high-altitude operations, in the construction of spatial grid structures, each structure is usually divided into sections, and the components of each section are assembled on the ground to obtain a pre-assembled structure, and then the pre-assembled structure is lifted to the design height and then connected from the air. The construction control method in the relevant technology usually adopts forward calculation based on the design model of the pre-assembled structure, that is, the force analysis of the pre-assembled structure is carried out through methods such as component activation, boundary definition, and load application to obtain the expected position deviation (theoretical value), and then the actual construction is guided according to the expected position deviation.

[0003] However, in actual construction, during the period from ground installation to hoisting construction, the pre-installed structure will undergo shape changes due to the existence of the temperature field. Due to the existence of shape changes caused by the temperature field effect, if the construction continues according to the expected shape deviation, construction shape deviation will occur. The resulting construction shape deviation can only be remedied by enlarging bolt holes, on-site welding, or even forcibly correcting structural deformation, which will obviously have an adverse effect on structural safety.

[0004] Therefore, how to more accurately determine the configuration deviation caused by the pre-installed structure is an urgent problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide a configuration deviation prediction method for spatial structures based on digital twins that can more accurately determine the configuration deviation caused by the pre-installed structure in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for predicting configuration deviation of a spatial structure based on digital twins, comprising:

[0007] Acquire point cloud data of the preinstalled structure, update a finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0008] Obtaining the installation period of the pre-installed structure and determining the estimated temperature information within the installation period, wherein the installation period includes the time taken for assembly, hoisting and closure;

[0009] Based on the estimated temperature information, a temperature effect simulation is performed in the digital twin model to predict the configuration deviation of the pre-installed structure;

[0010] The configuration deviation is sent to a target device.

[0011] In one embodiment, updating the finite element model of the target building based on the point cloud data includes:

[0012] Performing key point recognition on the point cloud data to obtain multiple nodes and determine the coordinates of each node;

[0013] Determining the correspondence between the nodes and the components in the preassembled structure;

[0014] Based on the coordinates of each node and the corresponding relationship between the node and the components in the preassembled structure, the finite element model of the target building is updated.

[0015] In one embodiment, determining the correspondence between the node and the component in the preinstalled structure includes:

[0016] Performing a neighborhood search on each of the nodes in the point cloud data, and deleting points in the neighborhood to obtain simplified point cloud data;

[0017] The simplified point cloud data is clustered and classified to obtain a plurality of clusters, and the corresponding relationship between the nodes and the components in the pre-assembled structure is determined based on the clusters.

[0018] In one of the embodiments, before establishing the digital twin model, it also includes:

[0019] Each component in the updated finite element model is updated to a zero load state.

[0020] In one embodiment, determining the estimated temperature information during the installation period includes:

[0021] Obtaining historical temperature information of the current area, wherein the historical temperature information includes temperature data for N days, and the temperature data includes temperature values ​​at multiple times;

[0022] Using the historical temperature information as training samples to train an initial network model to obtain a trained temperature prediction model;

[0023] The installation period is input into the temperature prediction model to determine estimated temperature information within the installation period.

[0024] In one embodiment, the simulating the temperature effect in the digital twin model based on the estimated temperature information to predict the configuration deviation of the pre-assembled structure includes:

[0025] Construct a solar radiation model based on the location information of the current region;

[0026] constructing a daily temperature model according to the estimated temperature information;

[0027] Constructing a thermal convection model and a long-wave radiation model of the preassembled structure according to parameter information of components corresponding to the preassembled structure;

[0028] Determine the relationship between the temperature distribution of the pre-installed structure and time based on the solar radiation model, the daily temperature model, the thermal convection model and the long-wave radiation model;

[0029] Based on the relationship between the temperature distribution and time, a simulation is performed in the digital twin model to predict the configuration deviation of the preassembled structure.

[0030] In a second aspect, the present application also provides a configuration deviation prediction device for a spatial structure based on digital twins, the device comprising an updating module, an estimated temperature information determination module, an estimated temperature information determination module, and a sending module, wherein:

[0031] An updating module, used to obtain point cloud data of a preinstalled structure, and update a finite element model of a target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0032] An estimated temperature information determination module is used to obtain the installation period of the pre-installed structure and determine the estimated temperature information within the installation period, wherein the installation period includes the time used for assembly, hoisting and closure;

[0033] A simulation module, configured to simulate temperature effects in the digital twin model based on the estimated temperature information, and predict the configuration deviation of the pre-installed structure;

[0034] The sending module sends the configuration deviation to the target device.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquire point cloud data of the preinstalled structure, update a finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0037] Obtaining the installation period of the pre-installed structure and determining the estimated temperature information within the installation period, wherein the installation period includes the time taken for assembly, hoisting and closure;

[0038] Based on the estimated temperature information, a temperature effect simulation is performed in the digital twin model to predict the configuration deviation of the pre-installed structure;

[0039] The configuration deviation is sent to a target device.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0041] Acquire point cloud data of the preinstalled structure, update a finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0042] Obtaining the installation period of the pre-installed structure and determining the estimated temperature information within the installation period, wherein the installation period includes the time taken for assembly, hoisting and closure;

[0043] Based on the estimated temperature information, a temperature effect simulation is performed in the digital twin model to predict the configuration deviation of the pre-installed structure;

[0044] The configuration deviation is sent to a target device.

[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0046] Acquire point cloud data of the preinstalled structure, update a finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0047] Obtaining the installation period of the pre-installed structure and determining the estimated temperature information within the installation period, wherein the installation period includes the time taken for assembly, hoisting and closure;

[0048] Based on the estimated temperature information, a temperature effect simulation is performed in the digital twin model to predict the configuration deviation of the pre-installed structure;

[0049] The configuration deviation is sent to a target device.

[0050] The above-mentioned configuration deviation prediction method, device, equipment, storage medium and program product, after obtaining the point cloud data of the preinstalled structure, updates the finite element model of the target building based on the point cloud data, so that the preinstalled structure in the finite element model is consistent with the actual preinstalled structure, and at the same time establishes a digital twin model based on the updated finite element model, and the digital twin model has a simulation function; at the same time, by pre-obtaining the installation period of the preinstalled structure, the corresponding temperature information of the preinstalled structure during the installation period is obtained; simulation is performed in the digital twin model based on the temperature information, and in the digital twin model, the temperature information will cause the various components in the preinstalled structure to produce different degrees of position and / or shape changes, so that the configuration deviation of the preinstalled structure can be determined; the present application can obtain the configuration deviation of the preinstalled structure by simulation before construction, and considers the impact of the temperature effect on the change of the preinstalled structure, so that the determined construction deviation is more in line with the actual situation and more accurate; the configuration deviation is sent to the target device, and when the on-site workers guide the construction based on the configuration deviation, they can have a more accurate judgment on the unloading position and installation sequence, thereby facilitating the improvement of the structural safety of the building. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A diagram showing an application environment of a configuration deviation prediction method in an embodiment;

[0053] Figure 2 A schematic diagram of a flow chart of a configuration deviation prediction method in one embodiment;

[0054] Figure 3 A schematic flow chart of the steps of updating a finite element model in one embodiment;

[0055] Figure 4 A schematic diagram of a flow chart of a method for determining estimated temperature information in one embodiment;

[0056] Figure 5 A schematic diagram of a simulation process in an embodiment;

[0057] Figure 6 A logical architecture diagram of a configuration deviation prediction method in one embodiment;

[0058] Figure 7 is a structural block diagram of a configuration deviation prediction device in one embodiment;

[0059] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution 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. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] The configuration deviation prediction method of the spatial structure based on digital twin provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the point cloud acquisition device 102 communicates with the computer device 104 through the network. The data storage system can store the data that the computer device 104 needs to process. The data storage system can be integrated on the server, or placed on the cloud or other network servers. The point cloud acquisition device 102 can collect the point cloud data of the pre-installed structure and send it to the computer device 104. The computer device 104 updates the finite element model of the target model based on the received point cloud data, and establishes a digital twin model based on the updated finite element model. The established digital twin model contains all deformation information caused by component blanking errors, installation deviations, etc., and the configuration is consistent with the actual structure, and has a mechanical calculation function. Among them, the computer device 104 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices, portable wearable devices, and servers. Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc.; portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.; servers can be implemented with independent servers or server clusters consisting of multiple servers.

[0062] In an exemplary embodiment, Figure 2 As shown in the figure, a method for predicting the configuration deviation of a spatial structure based on digital twin is provided. Figure 1 The computer device 104 in the embodiment is used as an example to illustrate the method, including steps 10 to 40, wherein:

[0063] Step 10: Obtain the point cloud data of the preinstalled structure, update the finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model. The preinstalled structure is a partial structure of the target building, and the finite element model is the mechanical model corresponding to the target building.

[0064] For the embodiment of the present application, at least one component is spliced ​​and combined on the ground to form a preinstalled structure; the preinstalled structure needs to be lifted to a high place for installation and splicing with other structures to form a target structure, and the target structure is a spatial grid structure. Among them, the collection of point cloud data is carried out when the preinstalled structure is formed on the ground, that is, the point cloud data is collected before the preinstalled structure is installed at a high place. Furthermore, the point cloud data is obtained using three-dimensional laser scanning technology. The three-dimensional laser scanning technology can quickly obtain the three-dimensional coordinates of each sampling point on the surface of the preinstalled structure in a non-contact measurement manner, and has the characteristics of large range, high precision, and high resolution. Based on the principle of laser ranging, further reverse processing can be performed according to information such as angle and distance to output the three-dimensional point cloud data of the preinstalled structure.

[0065] Usually, a mechanical model will be designed in advance before the construction of a building to verify the feasibility of the entire building. Usually, the mechanical model is established based on the finite element model. The finite element model is a model established when using the finite element analysis method. It is a combination of units that are connected only at nodes, transmit forces only at nodes, and are constrained only at nodes. It is the result of the discretization of the mechanical model and is a digital model for numerical calculations.

[0066] The digital twin model of the target building is established based on the finite element model of the target building. In the digital twin model of the target building, the established digital twin model includes the geometric shape of each component, construction steps, materials, dimensions, connection relationships and constraint boundary conditions of each component and each part, etc., to achieve simulation prediction. Among them, the finite element model of the target building is established during the design stage of the target building and before the actual construction stage of the target, and is used to guide the actual construction; however, since the actual structure or parameters may be adjusted to a certain extent during the actual construction process, therefore, the point cloud data of the pre-installed structure during the actual construction is collected to update the finite element model, so that the part of the pre-installed structure in the finite element model can be consistent with the actual structure; since the pre-installed structure is a partial structure of the target building, the parameter information of the pre-installed structure can be directly selected from the finite element model. Considering that the parameter information of the pre-installed structure may also be adjusted during the actual construction, in another possible implementation method, the parameter information of the pre-installed structure can also be input by the user.

[0067] Step 20: Obtain the installation period of the pre-installed structure and determine the estimated temperature information during the installation period. The installation period includes the time used for assembly, hoisting and closure.

[0068] For the embodiment of the present application, the installation period can be determined based on the lifting height of the pre-installed structure, the number of components, and the number of installation steps; for example, a mapping relationship between the installation time and the number of components, the lifting height, and the number of installation steps is pre-set, and then based on the determined pre-installed structure, the required installation time can be determined. However, in practice, the installation period of the pre-installed structure also depends on the equipment status on site, the experience of the personnel, and the scheduling situation. Therefore, the installation period can be further input by the user.

[0069] Step 30: Simulate the temperature effect in the digital twin model based on the estimated temperature information to obtain the configuration deviation of the pre-installed structure;

[0070] Step 40: Send the configuration deviation to the target device.

[0071] Pre-installed structures are generally placed in an open-air environment during construction. Under sunlight, the temperature difference between the exposed structure and the surrounding environment is large, so the impact of temperature effects on pre-installed structures should be fully considered. In addition, under sunlight, the temperature field of the components is not uniform, and the position of the components and parameters such as material and color all have an impact on the temperature field distribution. For the embodiment of the present application, by obtaining the estimated temperature information of the components during the installation period waiting between installations, the temperature environment is configured in the digital twin space based on the estimated temperature information, and then the actual position and shape of each component in the pre-installed structure due to temperature can be simulated. The shape deviation of the pre-installed structure can be determined by the expected position and expected shape of each component in the pre-installed structure in the design model, combined with the actual position and shape of each component in the pre-installed structure due to temperature. The shape deviation specifically includes the position change information and shape change information of each component.

[0072] In an embodiment of the present application, after obtaining the point cloud data of the preinstalled structure, the finite element model of the target building is updated based on the point cloud data, so that the preinstalled structure in the finite element model is consistent with the actual preinstalled structure, and a digital twin model is established based on the updated finite element model, and the digital twin model has a simulation function; at the same time, by obtaining the installation period of the preinstalled structure in advance, the temperature information corresponding to the preinstalled structure during the installation period is obtained; simulation is performed in the digital twin model based on the temperature information, and in the digital twin model, the temperature information will cause the various components in the preinstalled structure to produce different degrees of position and / or shape changes, so that the shape deviation of the preinstalled structure can be determined; the present application can obtain the shape deviation of the preinstalled structure by simulation before construction, and considers the impact of the temperature effect on the change of the preinstalled structure, so that the determined construction deviation is more in line with the actual situation and more accurate; the shape deviation is sent to the target device, and when the on-site workers guide the construction based on the shape deviation, they can have a more accurate judgment of the unloading position and installation sequence, thereby facilitating the improvement of the structural safety of the building.

[0073] In one embodiment, referring to Figure 3 In step 10, the finite element model of the target building is updated based on the point cloud data, which may specifically include steps 11 to 13, wherein:

[0074] Step 11: Identify key points of the point cloud data, obtain multiple nodes and determine the coordinates of each node.

[0075] Specifically, key points are identified on point cloud data. Key points refer to points on the surface of an object with significant changes (such as curvature, normal direction, etc.). Key points appear as points with significant geometric features in three-dimensional point cloud data. Each group of adjacent key points constitutes a node, where the node corresponds to the endpoint of each component, or the connection point of two or more components.

[0076] In one possible implementation, the key point identification method can identify key points by analyzing local features, that is, analyzing the geometric properties of each point in the point cloud data and its neighborhood (such as curvature, normal direction, etc.) to identify key points, including calculating local feature descriptors (such as FPFH, SHOT, etc.) and performing key point detection based on these descriptors.

[0077] In another possible implementation, key points can also be identified by a model fitting method, that is, a geometric model (such as a plane, a sphere, a cylinder, etc.) is used to fit a local area in the point cloud data, and key points are identified based on the fitting result. For geometric bodies with obvious geometric features, the key points identified by the model fitting method are more accurate.

[0078] Furthermore, a trained key point recognition network model may be used to recognize key points. The present application does not specifically limit the above-mentioned method for recognizing key points on point cloud data.

[0079] Step 12: Determine the corresponding relationship between the nodes and the components in the pre-installed structure.

[0080] In one possible implementation, the connection relationship between nodes can be selected and input by the user, such as the user establishing an undirected edge between two or more nodes, indicating that the part between the two nodes belongs to the same component.

[0081] In another possible implementation, determining the correspondence between nodes and components in the pre-installed structure may also include: performing a neighborhood search for each node in the point cloud data, and deleting points in the neighborhood to obtain simplified point cloud data; clustering and classifying the simplified point cloud data to obtain multiple clusters, and determining the correspondence between nodes and components in the pre-installed structure based on the clusters.

[0082] Specifically, the neighborhood search may be a spherical neighborhood search, and the spherical radius may be a preset value or may be input by the user. Further, the spherical radius may also be determined based on the distribution density of the nodes. By presetting the mapping relationship between the spherical radius and the distribution density of the nodes, after identifying multiple nodes, the distribution density of the nodes is determined based on the coordinates of each node, and then the spherical radius is determined according to the mapping relationship. The specific value of the spherical radius is not limited in the embodiment of the present application. Further, for the simplified point cloud data, the simplified point cloud data is classified by Euclidean clustering, and a series of point groups with similar characteristics can be obtained. The point groups are clusters, which are separated from each other in space. The distances between the points in each cluster are relatively close, while the distances between the points in different clusters are relatively far. The points in the same cluster are closely adjacent in space and have similar coordinate and position characteristics; and since the point clouds in the simplified point cloud data correspond to the positions of the surface of the pre-installed structure, the entity object corresponding to each cluster is a component or a part of a component in the pre-installed structure, and each cluster can reflect the shape and position of its corresponding entity object.

[0083] Furthermore, after performing Euclidean clustering to obtain clusters, the correspondence between each cluster and the components in the pre-installed structure is determined based on the shape and position of the clusters, that is, based on matching the nodes in each cluster with the endpoints of the corresponding components in the pre-installed structure, the correspondence between the nodes and the components in the pre-installed structure can be determined.

[0084] Step 13: Based on the coordinates of each node and the corresponding relationship between the components in the node pre-installed structure, the finite element model of the target building is updated.

[0085] Specifically, based on the correspondence between the nodes and the components in the pre-installed structure, the coordinates of the nodes are updated in the finite element model of the target building; at the same time, since the material, color or size of the components may be adjusted based on the actual situation during the actual construction, the parameter information of the pre-installed structure can be directly obtained from the finite element model or input by the user. Before the digital twin model is established based on the updated finite element model, the self-weight compensation of each component of the pre-installed structure in the updated finite element model is further performed so that each component is configured to be in a zero-load state.

[0086] Further, refer to Figure 4 In step 20, the estimated temperature information within the installation period is determined, which may specifically include steps 21 to 23, wherein:

[0087] Step 21: Obtain historical temperature information of the current area. The historical temperature information includes temperature data for N days, and the temperature data includes temperature values ​​at multiple times.

[0088] Specifically, the geographical location of the current area is known, and the historical temperature information of the current area is obtained based on the geographical location of the current area. The historical temperature information is the temperature data of each day within a certain period of history.

[0089] Furthermore, the temperature data may also include a continuously changing temperature curve, which can be obtained by actually measuring with a high-precision temperature curve tester. It is usually necessary to set up a temperature curve tester at the construction site of the target building in advance, and then obtain N days of temperature data as the corresponding historical temperature information for the subsequent installation of the pre-installed structure. The temperature data may also be the temperature values ​​at different times of the day, which may be measured by a temperature measurement device pre-installed at the construction site of the target building; the temperature data may also be obtained through relevant statistical websites or databases.

[0090] Step 22: Use the historical temperature information as training samples to train the initial network model to obtain a trained temperature prediction model;

[0091] Step 23: Input the installation period into the temperature prediction model to determine the estimated temperature information within the installation period.

[0092] Specifically, the temperature prediction model is pre-trained. In order to make the trained temperature prediction model have a higher accuracy, the historical temperature information should have a larger capacity, for example, N is equal to 3650. Multiple training samples are constructed based on the historical temperature information; wherein each training sample is the temperature data of a natural day. Specifically, the initial network model is an LSTM (Long Short-Term Memory) network; based on the constructed multiple training samples, the initial network model is trained to obtain a trained temperature prediction model.

[0093] In actual use, the installation period of the pre-installed structure is input into the temperature prediction model to obtain the estimated temperature information within the installation period.

[0094] In another embodiment, determining the estimated temperature information within the installation period may further specifically include: performing fitting based on historical temperature information to estimate the temperature curve of the day of the installation period; and determining the estimated temperature information within the installation period based on the temperature curve.

[0095] Specifically, the historical temperature information is fitted, and a linear regression model can be used to fit multiple temperature curves; wherein the linear regression model can be one of a linear regression model, a polynomial regression model, and a time series analysis model. The specific type of the linear regression model is not specifically limited in the embodiments of the present application. By fitting multiple temperature curves, a temperature curve that best conforms to the temperature variation pattern of the current area in the last N days can be obtained, and this curve is the temperature curve of the day of the installation period. The temperature curve characterizes the relationship between temperature changes over time. Based on the installation period, the estimated temperature information corresponding to the installation period can be determined.

[0096] By fitting the historical temperature information, we can better find the temperature change pattern in the current area, and then accurately infer the estimated temperature information of the pre-installed structure during the installation period, so as to simulate more accurate estimated data for the temperature effect.

[0097] Furthermore, there are three main forms of heat transfer, namely heat conduction, heat radiation and heat convection. Specifically, the factors affecting the transient temperature field of the structure include the heat transfer between the connected components of the structure, the solar radiation absorbed by the components, the daily temperature change, the convective heat exchange between the components and the air, and the heat radiation exchange between the components and the environment. With the continuous advancement of the construction process of the large-span spatial grid structure, the internal force and displacement changes caused by the uneven temperature field may not be released due to the assembly and patching of the structure, and will continue to accumulate, and the final accumulation amount is related to the construction method and the time nodes of each construction step; for large-span spatial steel structures with large scale, complex shape and high importance, in order to accurately simulate the deviations that may occur during the construction process, it is necessary to determine the temperature value of any position of the structure at any time through its transient temperature field, so as to more accurately determine the shape and position changes of each component during the construction process.

[0098] In one embodiment, referring to Figure 5 In step 30, based on the estimated temperature information, the temperature effect is simulated in the digital twin model to obtain the configuration deviation of the pre-installed structure, which may specifically include steps 31-35, wherein steps 31-33 are steps of establishing a solar radiation model, a daily temperature model, a thermal convection model, and a long-wave radiation model, respectively, and steps 34 and 35 are simulation steps; the model established based on steps 31-33 is used as a temperature field constraint condition in the digital twin model, thereby simulating each component of the pre-installed structure in the digital twin model, wherein the time rate in the simulation environment is greater than the time rate in the real environment. The following content specifically introduces the implementation method of each step from step 31 to step 35.

[0099] Step 31: construct a solar radiation model based on the location information of the current area;

[0100] Step 32: construct a daily temperature model based on the estimated temperature information;

[0101] Step 33: construct a thermal convection model and a long-wave radiation model of the pre-installed structure according to the parameter information of the components corresponding to the pre-installed structure.

[0102] The process of establishing the solar radiation model: The solar radiation model is related to the geographical location of the target model construction, so the current location needs to be determined. Secondly, the revolution and rotation of the earth and the longitude and latitude of the observation point will affect the position of the sun. Among them, the revolution of the earth affects the solar declination angle δ, and the rotation affects the solar hour angle ω. The calculation methods of the two are as shown in formulas (1) and (2), where:

[0103]

[0104] ω=(hour s -12)×15° formula (2); where N is the day number in a year, ranging from 1 to 365; hours is the solar time at the observation point, that is, the local time after error correction, ranging from 0h to 24h. Furthermore, the relative position relationship between the sun's rays and any surface on the ground can be expressed by the relationship between the solar altitude angle, the solar azimuth angle and the surface incident angle using formulas (3) and (4):

[0105] sinα s =cosφcosδcosω+sinφsinδ formula (3);

[0106] Where φ is the latitude of the observation point, ranging from -90° to 90°, and positive in the northern hemisphere. For any inclined surface, the incident angle θ of the sun's rays is expressed by formula (5): cosθ = sinβcosα s cos(γ s -γ)-cosβsinα s Formula (5); where β is the inclination angle of the surface, ranging from 0° to 180°, and above 90° means the surface is facing downward; γ is the direction of the surface, and its range is the same as γs. In fact, after the radiation emitted by the sun reaches the earth's atmosphere, most of it can directly reach the ground, which is called direct radiation; a small part of the energy reaches the ground after being scattered and absorbed by various molecules in the atmosphere, which is called incident radiation. At the same time, part of the solar radiation reaching the ground will be reflected by the ground. The solar radiation received by any surface structure on the earth's surface is composed of these three.

[0107] The solar radiation intensity outside the atmosphere is expressed by formula (6):

[0108] Among them, Gsc is the solar constant, which is 1367W / ㎡.

[0109] The direct radiation intensity Gb and the scattered radiation intensity Gd on the horizontal plane are expressed by formulas (7) and (8):

[0110] G d =(0.271-0.294t b )G on sinα s Formula (8); where T L is the Linke turbidity coefficient, which represents the effect of aerosol and water vapor on scattering, and its value range is 2 to 8; m is the atmospheric optical quality corrected by atmospheric pressure, which represents the effect of atmospheric molecules on scattering, and can be expressed by formula (9):

[0111] Where z is the altitude of the observation point; h is the Rayleigh atmospheric height, which is 8434.5m.

[0112] For any inclined surface on the ground, the actual intensity of direct radiation needs to be reduced by the incident angle; the actual intensity of scattered radiation and ground reflected radiation needs to be determined by the radiation angle coefficient. The final solar radiation intensity of the inclined surface under a clear sky is expressed by formula (10):

[0113] Among them, ρ r is the ground reflectivity, which is generally taken as 0.2. When cosθ is negative, the sunlight cannot reach the front of the surface and the contribution of direct radiation is not included.

[0114] A solar radiation model is established based on the above formulas (1)-(10).

[0115] Further, the daily temperature model is established based on the estimated temperature information within the installation period determined in step 20 .

[0116] Furthermore, the process of establishing the thermal convection model is as follows: Since the air is constantly flowing, the surface of the object is constantly exchanging heat with the surrounding air through convection. The basic form follows Newton's cooling law and is expressed by formula (11):

[0117] in, is the convective heat transfer coefficient of the object surface, q is the heat lost per unit area per unit time, T a -T bIt is the temperature difference between the surface of an object and its surroundings.

[0118] in, Different calculation methods are required for different objects, which are related to the surface size of the object. Since circular cross-section steel is often used as a component in a large-span space grid structure, the circular cross-section steel pipe is used as the object in the embodiment of this application. The calculation method is expressed by formula (12), where:

[0119] Among them, d is the outer diameter of the tube; k is the thermal conductivity of air; u is the air velocity; ν is the kinematic viscosity coefficient; the coefficients c and n are segmented according to the Reynolds number. Then, the thermal convection model is established according to the above formulas (11) and (12).

[0120] Furthermore, the establishment process of the long-wave radiation exchange model is as follows: the object and the environment continuously exchange heat radiation, also known as long-wave radiation exchange; the heat flux density of the long-wave radiation exchange between the object and the environment can be expressed by formula (13):

[0121] ε is the radiation emissivity of the surface of the object, which is affected by the surface material and color; σ is the Stefan-Boltzmann constant; T is the absolute temperature of the object; T s is the absolute temperature of the environment.

[0122] The long-wave radiation model is established based on formula (13).

[0123] The above is the process of establishing each model in step 31 to step 33.

[0124] Step 34: determine the relationship between the temperature distribution and time of the pre-installed structure based on the solar radiation model, the daily temperature model, the thermal convection model and the long-wave radiation model;

[0125] Step 35: Simulate in the digital twin model based on the relationship between temperature distribution and time to obtain the configuration deviation of the pre-installed structure.

[0126] Specifically, the solar radiation model, daily temperature model, thermal convection model and long-wave radiation model established in steps 31 to 33 can more accurately characterize the actual environment faced by the components of the pre-installed structure during the installation period; by configuring constraints and boundary conditions in the simulation environment established in the digital twin model based on the solar radiation model, daily temperature model, thermal convection model and long-wave radiation model, the relationship between temperature distribution and time can be obtained, that is, the temperature distribution of any component in the pre-installed structure at any time can be determined based on this relationship.

[0127] Furthermore, based on the relationship between temperature distribution and time, the time-varying non-uniform temperature field of the pre-installed structure is predicted and the temperature effect is simulated in the digital twin model. The temperature of each component of the pre-installed structure in the digital twin model is simulated in a programming platform such as MATLAB (Matrix Laboratory), and then the mechanical calculation of the pre-installed structure is performed based on the temperature values ​​of each component of the pre-installed structure in the finite element calculation software to simulate the position deviation of the pre-installed structure.

[0128] Since the digital twin model is updated based on the point cloud data of the pre-installed structure, it can more accurately characterize the current actual shape and position of the pre-installed structure. Combined with the relationship between the temperature distribution and time of any component in the pre-installed structure determined in step 34, the changes in position and temperature of each component in the pre-installed structure caused by the temperature effect, that is, the configuration deviation, can be simulated.

[0129] Furthermore, the position deviation determined in step 35 is sent to the target device to indicate the on-site construction personnel for reference; the determined position deviation can be used for the partition lifting, patching and closing of the spatial grid structure, and the component cutting can be completed in advance by using the deformation prediction method; compared with the deviation obtained by the forward calculation model used in the prior art, the prediction result predicted by the position deviation is more accurate. For the deviation control after the partition lifting, the construction unit can take control measures in advance to avoid excessive deviation.

[0130] Reference Figure 6 As shown, the logic of the prediction of the configuration deviation in the embodiment of the present application is mainly divided into the stage from real to virtual and the stage from virtual to real; the stage from real to virtual is: the pre-installed structure in the spatial grid structure is three-dimensionally scanned to obtain point cloud data, and the node coordinates in the point cloud data are extracted by reverse modeling, and then the finite element model of the target building is updated based on the extracted node coordinates, and the self-weight compensation is considered while the components of the pre-installed structure in the updated finite element model are moved to the position and shape under the zero load state, and then a digital twin model is established based on the updated finite element model. The stage from virtual to real includes: constructing the actual temperature field of the pre-installed structure according to the acquired temperature information (historical monitoring data or environmental data such as thermometer detection), and combining the digital twin model to realize the simulation based on the temperature field and temperature effect, and obtaining the configuration deviation of the pre-installed structure, and then making the construction prediction of the pre-installed structure.

[0131] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0132] Based on the same inventive concept, the embodiment of the present application also provides a configuration deviation prediction device for a spatial structure based on a digital twin for implementing the configuration deviation prediction method for a spatial structure based on a digital twin involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more configuration deviation prediction devices for spatial structures based on digital twins provided below can be referred to the limitations of the configuration deviation prediction method for spatial structures based on digital twins above, and will not be repeated here.

[0133] In an exemplary embodiment, Figure 7 As shown, a configuration deviation prediction device for a spatial structure based on digital twin is provided, comprising an updating module 701, an estimated temperature information determination module 702, a simulation module 703 and a sending module 704, wherein:

[0134] An updating module 701 is used to obtain point cloud data of the preinstalled structure, and update the finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, where the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building;

[0135] The estimated temperature information determination module 702 is used to obtain the installation period of the pre-installed structure and determine the estimated temperature information within the installation period, where the installation period includes the time used for assembly, hoisting and closure;

[0136] A simulation module 703 is used to simulate the temperature effect in the digital twin model based on the estimated temperature information to obtain the configuration deviation of the pre-installed structure;

[0137] The sending module 704 is used to send the configuration deviation to the target device.

[0138] By adopting the above technical solution, after the device obtains the point cloud data of the preinstalled structure, it updates the finite element model of the target building based on the point cloud data, so that the corresponding part of the preinstalled structure in the finite element model is consistent with the real part of the preinstalled structure, and at the same time, a digital twin model is established based on the updated finite element model, and the digital twin model has a simulation function; at the same time, by pre-acquiring the installation period of the preinstalled structure, the corresponding temperature information of the preinstalled structure during the installation period is obtained; simulation is performed in the digital twin model based on the temperature information, and in the digital twin model, the temperature information will cause the various components in the preinstalled structure to produce different degrees of position and / or shape changes, so that the shape deviation of the preinstalled structure can be determined; the present application can obtain the shape deviation of the preinstalled structure by simulation before construction, and considers the impact of the temperature effect on the change of the preinstalled structure, so that the determined construction deviation is more in line with the actual situation and more accurate; the shape deviation is sent to the target device, and when the on-site workers guide the construction based on the shape deviation, they can have a more accurate judgment on the unloading position and installation sequence, thereby facilitating the improvement of the structural safety of the building.

[0139] In one embodiment, the update module 701 is specifically used for:

[0140] Identify key points of point cloud data, obtain multiple nodes and determine the coordinates of each node;

[0141] Determine the correspondence between nodes and components in the pre-assembled structure;

[0142] The finite element model of the target building is updated based on the coordinates of each node, the connection relationship between multiple nodes, and the parameter information of the pre-installed structure.

[0143] In one embodiment, the update module 701 is specifically used for:

[0144] Perform neighborhood search on each node in the point cloud data, and delete the points in the neighborhood to obtain simplified point cloud data;

[0145] The simplified point cloud data is clustered and classified to obtain multiple clusters, and the corresponding relationship between the nodes and the components in the pre-assembled structure is determined based on the clusters.

[0146] In one of the embodiments, the update module is also used to: update each component in the updated finite element model to a zero load state before establishing the digital twin model.

[0147] In one embodiment, the estimated temperature information determination module 702 is specifically configured to:

[0148] Obtaining historical temperature information of the current area, wherein the historical temperature information includes temperature data for N days, and the temperature data includes temperature values ​​at multiple times;

[0149] Using the historical temperature information as training samples to train an initial network model to obtain a trained temperature prediction model;

[0150] The installation period is input into the temperature prediction model to determine estimated temperature information within the installation period.

[0151] In one embodiment, the simulation module 703 is specifically used for:

[0152] Construct a solar radiation model based on the location information of the current region;

[0153] Construct a daily temperature model based on the estimated temperature information;

[0154] According to the parameter information of the components corresponding to the pre-assembled structure, a thermal convection model and a long-wave radiation model of the pre-assembled structure are constructed;

[0155] Determine the relationship between the temperature distribution and time of the pre-installed structure based on the solar radiation model, daily temperature model, thermal convection model and long-wave radiation model;

[0156] Based on the relationship between temperature distribution and time, simulation is carried out in the digital twin model to obtain the configuration deviation of the pre-assembled structure.

[0157] Each module in the above-mentioned configuration deviation prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0158] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting a configuration deviation is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0159] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0160] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the embodiment of the configuration deviation prediction method of the spatial structure based on digital twin are implemented as described above.

[0161] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned embodiment of the method for predicting the configuration deviation of a spatial structure based on digital twins are implemented.

[0162] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-mentioned embodiment of the configuration deviation prediction method of the spatial structure based on digital twin.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0164] 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 completed by instructing the relevant 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. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0165] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0166] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting configuration deviation of a spatial structure based on digital twins, characterized in that: The method comprises: Acquire point cloud data of the preinstalled structure, update a finite element model of the target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building; Obtaining the installation period of the pre-installed structure and determining the estimated temperature information within the installation period, wherein the installation period includes the time taken for assembly, hoisting and closure; Based on the estimated temperature information, a temperature effect simulation is performed in the digital twin model to predict the configuration deviation of the pre-installed structure; The configuration deviation is sent to a target device.

2. The method according to claim 1, characterized in that The updating of the finite element model of the target building based on the point cloud data comprises: Performing key point recognition on the point cloud data to obtain multiple nodes and determine the coordinates of each node; Determining the correspondence between the nodes and the components in the preassembled structure; Based on the coordinates of each node and the corresponding relationship between the node and the components in the preassembled structure, the finite element model of the target building is updated.

3. The method according to claim 2, characterized in that The determining of the correspondence between the node and the component in the preinstalled structure includes: Performing a neighborhood search on each of the nodes in the point cloud data, and deleting points in the neighborhood to obtain simplified point cloud data; The simplified point cloud data is clustered and classified to obtain a plurality of clusters, and the corresponding relationship between the nodes and the components in the pre-assembled structure is determined based on the clusters.

4. The method according to claim 2, characterized in that: Before building a digital twin model, it also includes: Each component in the updated finite element model is updated to a zero load state.

5. The method according to any one of claim 1, characterized in that: The determining of estimated temperature information within the installation period includes: Obtaining historical temperature information of the current area, wherein the historical temperature information includes temperature data for N days, and the temperature data includes temperature values ​​at multiple times; Using the historical temperature information as training samples to train an initial network model to obtain a trained temperature prediction model; The installation period is input into the temperature prediction model to determine estimated temperature information within the installation period.

6. The method according to any one of claims 1 to 5, characterized in that: The performing temperature effect simulation in the digital twin model based on the estimated temperature information to predict the configuration deviation of the pre-assembled structure includes: Construct a solar radiation model based on the location information of the current region; constructing a daily temperature model according to the estimated temperature information; Constructing a thermal convection model and a long-wave radiation model of the preassembled structure according to parameter information of components corresponding to the preassembled structure; Determine the relationship between the temperature distribution of the pre-installed structure and time based on the solar radiation model, the daily temperature model, the thermal convection model and the long-wave radiation model; Based on the relationship between the temperature distribution and time, a simulation is performed in the digital twin model to predict the configuration deviation of the preassembled structure.

7. A configuration deviation prediction device for a spatial structure based on digital twin, characterized in that: The device comprises an updating module, an estimated temperature information determining module, an estimated temperature information determining module and a sending module, wherein: An updating module, used to obtain point cloud data of a preinstalled structure, update a finite element model of a target building based on the point cloud data, and establish a digital twin model based on the updated finite element model, wherein the preinstalled structure is a partial structure of the target building, and the finite element model is a mechanical model corresponding to the target building; An estimated temperature information determination module is used to obtain the installation period of the pre-installed structure and determine the estimated temperature information within the installation period, wherein the installation period includes the time used for assembly, hoisting and closure; A simulation module, configured to simulate temperature effects in the digital twin model based on the estimated temperature information, and predict the configuration deviation of the pre-installed structure; The sending module sends the configuration deviation to the target device.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Carbon nanotube growth prediction and evaluation model based on digital twinning and AI and establishment method thereof

    CN119361049A

  • Intelligent monitoring and early warning method and system based on welding

    CN119703518A

  • Intelligent control method for installation configuration of large-span steel structure

    CN120764124A

  • Medium arch section arch rib reverse assembling and closing precision prediction method based on finite element

    CN121257224A

  • Arch rib reverse assembly and closing precision prediction method based on finite element in hogging section

    CN121257224B