BIM-based Building Steel Structure Deformation Detection Method, System and Storage Medium

Abstract

The present invention relates to the technical field of deformation detection, and discloses a BIM-based building steel structure deformation detection method, system and storage medium, which are used to improve the accuracy of BIM-based building steel structure deformation detection. The method includes: analyzing the component parameters of the steel structure based on the optimized point cloud data to obtain a set of component parameters; based on the set of component parameters, inputting the optimized point cloud data into a region growing algorithm for analyzing the geometric parameters of the connection part to obtain connection part parameters; performing structural deformation analysis on the connection part parameters to obtain structural deformation parameters, evaluating the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree; updating the initial BIM model of the target building with the structural deformation parameters, connection part parameters and set of component parameters to obtain a target BIM model; predicting the deformation trend of the target BIM model to obtain a target deformation trend, and transmitting the target deformation trend to a preset data display terminal.

Description

Technical Field

[0001] The present invention relates to the technical field of deformation detection, and in particular to a method, system and storage medium for detecting the deformation of building steel structures based on BIM. Background Art

[0002] In the construction industry, especially in engineering projects involving high-rise buildings and large-span structures, the safety and stability of steel structures have always been important considerations during the design and maintenance processes. With the development of construction technology, Building Information Modeling (BIM) technology has become an important tool for modern construction project management, which can provide detailed three-dimensional visualization of structures and facilitate information sharing and communication in all project phases. However, although the application of BIM technology in the design and construction phases has been quite mature, there are still many challenges in the operation and maintenance phases of buildings, especially in the application of structural deformation monitoring.

[0003] On the one hand, during the long-term use of steel structures, due to the influence of the external environment and material aging, etc., deformation may occur. If this deformation is not detected and processed in time, it may pose a serious threat to the safety of the building. Currently, traditional steel structure deformation detection methods often rely on manual inspections or simple sensor monitoring. These methods are not only inefficient but also difficult to achieve precise detection of subtle structural deformations. In addition, traditional methods often cannot provide sufficient data to support a comprehensive structural performance assessment of the building, which to a certain extent limits the scientificity and effectiveness of structural maintenance and reinforcement decisions.

[0004] On the other hand, although terrestrial laser scanning technology makes it possible to obtain accurate three-dimensional data of building structures, effectively integrating these data into the BIM model, especially how to use these data for dynamic monitoring and trend prediction of structural deformation, is still a technical challenge. Existing research mainly focuses on how to improve the acquisition and processing efficiency of point cloud data, while less attention is paid to how to combine the analysis results of point cloud data with the update of the BIM model to achieve real-time monitoring and prediction of structural deformation. This technical gap limits the application potential of BIM in the building maintenance and operation phases and also affects the guarantee of the long-term stability and safety of buildings.

[0005] In summary, although BIM technology has made significant progress in the construction industry, there are still a series of technical and application challenges in the detection of building steel structure deformation. How to effectively integrate terrestrial laser scanning technology and BIM model to achieve precise detection and dynamic monitoring of steel structure deformation is an urgent problem to be solved. This not only concerns the long-term use safety of buildings but also is the key to improving the full-cycle value of BIM technology application. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a BIM-based method, system, and storage medium for detecting the deformation of building steel structures, which are used to improve the accuracy of detecting the deformation of building steel structures based on BIM.

[0007] The present invention provides a BIM-based method for detecting the deformation of building steel structures, including: performing ground laser scanning on the steel structure of a target building through a preset point cloud acquisition device to obtain initial point cloud data, and at the same time, performing data optimization on the initial point cloud data to obtain optimized point cloud data; analyzing the component parameters of the steel structure based on the optimized point cloud data to obtain a set of component parameters; based on the set of component parameters, inputting the optimized point cloud data into a preset region growing algorithm based on normal distribution for analyzing the geometric parameters of the connection part to obtain connection part parameters; performing structural deformation analysis on the connection part parameters through a segmented fitting algorithm to obtain structural deformation parameters, and evaluating the degree of deformation of the target building based on the structural deformation parameters to obtain the degree of structural deformation; updating the initial BIM model of the target building with the structural deformation parameters, the connection part parameters, and the set of component parameters to obtain a target BIM model; predicting the deformation trend of the target BIM model based on the degree of structural deformation to obtain a target deformation trend, and transmitting the target deformation trend to a preset data display terminal.

[0008] In the present invention, the step of performing ground laser scanning on the steel structure of a target building through a preset point cloud acquisition device to obtain initial point cloud data, and at the same time, performing data optimization on the initial point cloud data to obtain optimized point cloud data includes: positioning and calibrating the point cloud acquisition device to obtain a calibrated point cloud acquisition device; performing ground laser scanning on the steel structure of the target building through the calibrated point cloud acquisition device to obtain the initial point cloud data; performing spatial filtering on the initial point cloud data to obtain first point cloud data; performing dimensionality reduction on the first point cloud data through a principal component analysis algorithm to obtain second point cloud data; performing color correction on the second point cloud data to obtain third point cloud data; and performing format conversion on the third point cloud data to obtain the optimized point cloud data.

[0009] In the present invention, the step of analyzing the component parameters of the steel structure based on the optimized point cloud data to obtain a set of component parameters includes: fitting the cross-section of the steel structure to the optimized point cloud data through a cross-section fitting algorithm to obtain a plurality of fitted cross-sections; respectively matching the structural components of each of the fitted cross-sections through an edge point extraction algorithm to obtain a plurality of steel structure components, and at the same time, extracting the geometric parameters of each of the steel structure components, and combining the geometric parameters of each of the steel structure components into the set of component parameters.

[0010] In the present invention, the steps of performing steel structure cross-section fitting on the optimized point cloud data through a cross-section fitting algorithm to obtain multiple fitted cross-sections include: calibrating the main axis direction of the steel structure to obtain the main axis direction, and based on the main axis direction, performing hierarchical slicing on the optimized point cloud data to obtain multiple two-dimensional point cloud layers; respectively performing edge recognition on each of the two-dimensional point cloud layers to obtain the outer contour line data of each of the two-dimensional point cloud layers; respectively performing geometric shape analysis on the outer contour line data of each of the two-dimensional point cloud layers to obtain multiple initial cross-sections; based on multiple standard steel structure cross-section shapes, performing matching on the multiple initial cross-sections through the cross-section fitting algorithm to obtain multiple cross-sections to be processed; respectively performing cross-section parameter optimization on each of the cross-sections to be processed to obtain the multiple fitted cross-sections.

[0011] In the present invention, the steps of inputting the optimized point cloud data into a preset region growing algorithm based on normal distribution for analyzing the geometric parameters of the connection part to obtain the connection part parameters based on the component parameter set include: based on the component parameter set, inputting the optimized point cloud data into the region growing algorithm based on normal distribution for point cloud splitting to obtain the point cloud subsets of each steel structure component; respectively performing neighborhood analysis on the point cloud subsets of every two steel structure components through the region growing algorithm to obtain the connection regions of every two steel structure components; based on a preset connection region range, performing region screening on the connection regions of every two steel structure components to obtain multiple connection regions to be processed; respectively performing point cloud data matching on each of the connection regions to be processed to obtain multiple connection region point cloud data; respectively performing point cloud density analysis on each of the connection region point cloud data to obtain the point cloud density data of each of the connection region point cloud data; based on the point cloud density data of each of the connection region point cloud data, respectively performing spatial continuity evaluation on each of the connection regions to be processed to obtain the spatial continuity results of each of the connection regions to be processed; based on the spatial continuity results of each of the connection regions to be processed, performing region screening on the multiple connection regions to be processed to obtain multiple connection part regions; respectively performing geometric parameter extraction on each of the connection part regions to obtain the connection part parameters.

[0012] In the present invention, the step of performing structural deformation analysis on the connection part parameters through a piecewise fitting algorithm to obtain structural deformation parameters, and evaluating the deformation degree of the target building based on the structural deformation parameters to obtain the structural deformation degree includes: calibrating the position of the connection part for the connection part parameters to obtain connection part position parameters; based on the connection part position parameters, analyzing the deformation starting point of the steel structure to obtain the deformation starting point position; based on the deformation starting point position, segmenting the optimized point cloud data to obtain multiple starting point local point clouds; respectively performing local deformation fitting on each of the starting point local point clouds to obtain deformation fitting data for each of the starting point local point clouds; respectively extracting features from the deformation fitting data of each of the starting point local point clouds to obtain a deformation feature set for each of the starting point local point clouds, wherein the deformation feature set includes: deformation amplitude and deformation direction; based on the deformation feature set of each of the starting point local point clouds, extracting structural deformation parameters from the connection part parameters to obtain the structural deformation parameters, wherein the structural deformation parameters include: deformation angle and offset distance; analyzing the deformation distribution of the structural deformation parameters to obtain deformation distribution data corresponding to the structural deformation parameters; and evaluating the deformation degree of the target building based on the deformation distribution data to obtain the structural deformation degree.

[0013] In the present invention, the step of predicting the deformation trend of the target BIM model based on the structural deformation degree to obtain the target deformation trend and transmitting the target deformation trend to a preset data display terminal includes: performing time series analysis on the structural deformation parameters based on the structural deformation degree to obtain deformation dynamic characteristics; predicting the deformation trend of the target BIM model based on the deformation dynamic characteristics to obtain the target deformation trend; converting the data format of the target deformation trend to obtain a display data format, and transmitting the target deformation trend to the data display terminal according to the display data format.

[0014] The present invention also provides a BIM-based building steel structure deformation detection system, including:

[0015] A scanning module, configured to perform ground laser scanning on the steel structure of a target building through a preset point cloud acquisition device to obtain initial point cloud data, and at the same time, optimize the initial point cloud data to obtain optimized point cloud data;

[0016] An analysis module, configured to analyze the component parameters of the steel structure according to the optimized point cloud data to obtain a component parameter set;

[0017] An input module for inputting the optimized point cloud data into a preset region growing algorithm based on normal distribution for analyzing the geometric parameters of the connection part according to the component parameter set, so as to obtain connection part parameters;

[0018] An evaluation module for performing structural deformation analysis on the connection part parameters through a segmented fitting algorithm to obtain structural deformation parameters, and evaluating the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree;

[0019] An update module for updating the initial BIM model of the target building to a target BIM model according to the structural deformation parameters, the connection part parameters and the component parameter set;

[0020] A prediction module for predicting the deformation trend of the target BIM model based on the structural deformation degree to obtain a target deformation trend, and transmitting the target deformation trend to a preset data display terminal.

[0021] The present invention provides a BIM-based building steel structure deformation detection device, including: a memory and at least one processor, wherein instructions are stored in the memory; the at least one processor calls the instructions in the memory so that the BIM-based building steel structure deformation detection device executes the above-mentioned BIM-based building steel structure deformation detection method.

[0022] The present invention provides a computer-readable storage medium, in which instructions are stored, and when the instructions run on a computer, the computer is made to execute the above-mentioned BIM-based building steel structure deformation detection method.

[0023] In the technical solution provided by the present invention, by combining the terrestrial laser scanning technology and the BIM model, the real-time monitoring of the building steel structure can be realized, and at the same time, the deformation area of the structure can be accurately located. By using time series analysis and machine learning models to deeply analyze the collected structural deformation data, the future deformation trend of the building steel structure can be predicted. Through the detailed parameter analysis of the steel structure components and the geometric parameter analysis of the connection parts, combined with the structural deformation parameters, a comprehensive evaluation of the overall performance of the building steel structure can be provided. By updating the structural deformation parameters and the deformation trend prediction results to the target BIM model and transmitting them to the data display terminal, an intuitive visual display of the structural deformation can be provided. Through the automated data collection and analysis process, the dependence on manual inspection is reduced, which not only improves the efficiency of maintenance work, but also improves the accuracy of detection and evaluation. The automated process reduces human errors and ensures the accurate evaluation of the state of the building steel structure. Description of the Drawings

[0024] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings required for the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0025] Figure 1 It is a flowchart of a BIM-based building steel structure deformation detection method in an embodiment of the present invention;

[0026] Figure 2 It is a flowchart of analyzing the component parameters of the steel structure based on the optimized point cloud data in an embodiment of the present invention;

[0027] Figure 3 It is a schematic diagram of a BIM-based building steel structure deformation detection system in an embodiment of the present invention;

[0028] Figure 4 It is a schematic diagram of an embodiment of a BIM-based building steel structure deformation detection device in an embodiment of the present invention.

[0029] Reference numerals:

[0030] 301, scanning module; 302, analysis module; 303, input module; 304, evaluation module; 305, update module. Specific embodiments

[0031] The following will clearly and completely describe the technical solutions of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0032] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0033] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0034] For ease of understanding, the specific process of the embodiments of the present invention will be described below. Please refer to Figure 1 , Figure 1 which is a flowchart of a method for detecting the deformation of a building steel structure based on BIM according to an embodiment of the present invention. As Figure 1 shown, it includes the following steps:

[0035] S101. Perform ground laser scanning on the steel structure of the target building through a pre-set point cloud acquisition device to obtain initial point cloud data. At the same time, perform data optimization on the initial point cloud data to obtain optimized point cloud data;

[0036] Specifically, perform positioning and calibration processing on the point cloud acquisition device to ensure the accuracy and reliability of subsequent data. Through the calibrated point cloud acquisition device, perform ground laser scanning on the steel structure of the target building to collect initial point cloud data. Perform spatial filtering processing on the initial point cloud data to eliminate noise and unnecessary data, and obtain more accurate first point cloud data. In order to further improve the processing efficiency and quality of the data, use the principal component analysis algorithm to perform dimensionality reduction processing on the first point cloud data, retain the most important data features, and greatly reduce the complexity of data processing, and obtain more refined second point cloud data. Perform color correction processing on the second point cloud data to ensure the visual accuracy of the point cloud data, so that the color matches the color of the actual building steel structure more, and obtain third point cloud data. In order to adapt to the needs of subsequent analysis and processing, perform format conversion on the third point cloud data to ensure that these data can be effectively recognized and processed by subsequent software and algorithms, and obtain optimized point cloud data.

[0037] S102. Analyze the component parameters of the steel structure according to the optimized point cloud data to obtain a set of component parameters;

[0038] Specifically, the specific cross-sectional shape of the steel structure in the optimized point cloud data is identified and fitted through a cross-sectional fitting algorithm to obtain multiple fitted cross-sections. In order to identify the specific steel structure components from these fitted cross-sections, an edge point extraction algorithm is used to analyze each fitted cross-section. This algorithm identifies and extracts the edge points of the steel structure cross-section, and accurately matches the corresponding steel structure components through the edge points. By comparing and matching the predefined steel structure component library, it is ensured that each fitted cross-section can accurately correspond to a specific steel structure component. The geometric parameters of each steel structure component are extracted. The key geometric features such as the size, shape, and position of each component are measured and recorded. The geometric parameters of each component include the basic dimension information of the component, and may also include important information such as the relative position relationship and connection method between components. The geometric parameters of the extracted steel structure components are merged to form a comprehensive component parameter set. This component parameter set includes the detailed geometric parameters of each component, and integrates the mutual relationship between all components and the overall structure layout information.

[0039] Furthermore, the principal axis direction of the steel structure is calibrated to provide a clear reference direction for subsequent data processing. Based on the principal axis direction, the optimized point cloud data is subjected to layer slicing processing to convert the complex three-dimensional point cloud data into multiple two-dimensional point cloud layers that are easier to process. Each two-dimensional point cloud layer is equivalent to the cross-sectional view of the steel structure at a specific height. Edge recognition is performed on each two-dimensional point cloud layer to obtain the outer contour line data of each two-dimensional point cloud layer. This outer contour line data directly reflects the physical contour of the steel structure at different heights. Geometric shape analysis is performed on the outer contour line data of each two-dimensional point cloud layer, and the initial cross-sectional shape that can represent a specific part of the steel structure is extracted from the outer contour line data. Based on the standard steel structure cross-sectional shape, a cross-sectional fitting algorithm is used to accurately match the initial cross-section to obtain multiple cross-sections to be processed. The matching process needs to comprehensively consider the distribution characteristics of the point cloud data and the similarity between the predefined standard cross-sectional shapes to ensure that the most suitable standard cross-sectional shape can be found for each initial cross-section. Finally, the cross-section parameter optimization is performed on each cross-section to be processed, and the fitted cross-section is refined and adjusted to make the fitted cross-section more accurately reflect the actual situation of the steel structure, ensuring that the best consistency is achieved between the geometric shape, size, and the actual state of the steel structure for each fitted cross-section, and multiple accurately fitted cross-sections are obtained.

[0040] S103. Based on the component parameter set, the optimized point cloud data is input into a preset region growing algorithm based on normal distribution for analyzing the geometric parameters of the connection part to obtain the connection part parameters;

[0041] Specifically, based on the set of component parameters, the optimized point cloud data is input into the region growing algorithm based on the normal distribution for point cloud splitting. According to the geometric and spatial characteristics of the components, the point cloud data is effectively split into point cloud subsets for each steel structure component, ensuring the pertinence and efficiency of data processing. Through the algorithm, neighborhood analysis is performed on the point cloud subsets of every two steel structure components to identify the connection regions between these components. The connection regions are the key parts in the analysis of the stability and structural integrity of the steel structure. To further optimize the analysis results, the identified connection regions are screened through the preset connection region range to obtain multiple connection regions to be processed. The screening process ensures that the focus of subsequent processing is concentrated on the most critical connection parts, improving the accuracy and efficiency of the analysis. Point cloud data matching is performed for each target connection region to be processed, and a point cloud set corresponding to a specific connection region is extracted from a large amount of point cloud data. Point cloud density analysis is performed on each obtained connection region point cloud data set to help understand the point cloud distribution inside the connection region and provide data support for evaluating the spatial continuity of the connection part. The point cloud density data reflects the geometric complexity and structural details of the connection region. Based on the point cloud density data of the point cloud data for each connection region, spatial continuity evaluation is performed on each connection region to be processed. Pay attention to the distribution continuity of the point cloud inside the connection region, and the evaluation result directly affects the understanding of the stability and integrity of the connection part. According to the spatial continuity results of each connection region to be processed, region screening is performed again to screen out the final connection part region. For each finally determined connection part region, geometric parameters are extracted, and these parameters describe the specific geometric characteristics of the connection part, such as shape, size, and their spatial position relationship.

[0042] S104. Perform structural deformation analysis on the connection part parameters through the segmented fitting algorithm to obtain structural deformation parameters, and evaluate the deformation degree of the target building based on the structural deformation parameters to obtain the structural deformation degree.

[0043] Specifically, calibrate the position of the connection part for the connection part parameters to obtain the connection part position parameters, providing an accurate spatial reference for deformation analysis. Based on the connection part position parameters, conduct deformation starting point analysis to identify the starting position of the deformation. Based on the deformation starting point position, segment the optimized point cloud data to obtain multiple starting point local point clouds. Decompose the point cloud data into multiple local point clouds corresponding to the deformation starting points, and each local point cloud represents the specific structural state near the starting point. Conduct local deformation fitting on each starting point local point cloud, and through the segmented fitting algorithm, capture the deformation conditions within each local area. The deformation fitting data of each starting point local point cloud obtained provides a detailed description of the deformation conditions of each local area, including key information such as the amplitude and direction of the deformation. Extract features from the deformation fitting data of each starting point local point cloud, and extract a representative set of deformation features from the deformation data, including the amplitude of the deformation and the deformation direction. Extract structural deformation parameters based on the deformation feature set of each starting point local point cloud, and integrate the local deformation features into the deformation parameters of the overall structure, including the deformation angle and the offset distance. Conduct deformation distribution analysis on the structural deformation parameters to understand the distribution of structural deformation in the entire building. Based on the deformation distribution data, evaluate the deformation degree of the target building. The evaluation is based on the deformation distribution of the entire structure, providing comprehensive data support for the evaluation results, and finally obtaining the structural deformation degree.

[0044] S105. Update the initial BIM model of the target building according to the structural deformation parameters, connection part parameters, and component parameter set to obtain the target BIM model;

[0045] Specifically, update the initial BIM model of the target building according to the structural deformation parameters, connection part parameters, and component parameter set. Through BIM software and tools, integrate the parameters into the model, which includes adjusting the dimensions, shapes, and positions of the corresponding components in the model, as well as updating the details of the connection parts to reflect the actual structural deformation conditions. During the update process, it is necessary to pay attention to maintaining the consistency and accuracy of the model data. Any parameter update needs to be carefully considered for its impact on the overall model to ensure that the modification does not introduce errors or inconsistencies. At the same time, in order to achieve a high degree of authenticity of the model, through the functions of BIM software, such as dynamic simulation and visualization technology, intuitively display the impact of structural deformation on the entire building and its various components. Finally, update the initial BIM model to the target BIM model reflecting the current physical state of the building.

[0046] S106. Based on the structural deformation degree, predict the deformation trend of the target BIM model to obtain the target deformation trend, and transmit the target deformation trend to the preset data display terminal.

[0047] It should be noted that for time series analysis based on the degree of structural deformation, dynamic characteristics of deformation are extracted from historical deformation data, such as deformation speed, acceleration, and other factors that may affect future deformation trends. Based on the dynamic characteristics of deformation, through prediction models and algorithms, the deformation trend of the target BIM model is predicted. Based on the current deformation state and historical deformation characteristics, the possible deformation trend of the structure in the future is predicted. This includes the direction, speed of deformation, and the possible ultimate state that may be reached, ensuring the comprehensiveness and accuracy of the prediction results. The obtained target deformation trend is a prediction of the future state of the building, providing forward-looking information for building maintenance, reinforcement, or design improvement. To ensure that these prediction results can be effectively transmitted to the data display terminal and used by the end user, the data format of the target deformation trend is converted. The predicted deformation trend is converted into a data format suitable for display, including the structured processing of data and the selection of visual expression methods, such as charts, animations, or other graphical display methods. The target deformation trend in the converted display data format is transmitted to the data display terminal through a preset communication protocol and interface. The data display terminal may include a large screen in the monitoring center, an engineer's computer system, or a mobile device connected through the Internet.

[0048] By performing the above steps, through the combination of terrestrial laser scanning technology and BIM model, real-time monitoring of building steel structures can be achieved, and at the same time, the deformed area of the structure can be accurately located. By using time series analysis and machine learning models to deeply analyze the collected structural deformation data, the future deformation trend of building steel structures can be predicted. Through the detailed parameter analysis of steel structure components and the geometric parameter analysis of connection parts, combined with structural deformation parameters, a comprehensive assessment of the overall performance of building steel structures can be provided. By updating the structural deformation parameters and deformation trend prediction results to the target BIM model and transmitting them to the data display terminal, an intuitive visual display of structural deformation can be provided. Through the automated data collection and analysis process, the dependence on manual inspection is reduced, not only improving the efficiency of maintenance work, but also improving the accuracy of detection and assessment. The automated process reduces human errors and ensures an accurate assessment of the state of building steel structures.

[0049] In a specific embodiment, the process of performing step S101 may specifically include the following steps:

[0050] (1) Position and calibrate the point cloud acquisition device to obtain a calibrated point cloud acquisition device;

[0051] (2) Perform terrestrial laser scanning on the steel structure of the target building through the calibrated point cloud acquisition device to obtain initial point cloud data;

[0052] (3) Perform spatial filtering processing on the initial point cloud data to obtain the first point cloud data;

[0053] (4) Perform dimensionality reduction processing on the first point cloud data through the principal component analysis algorithm to obtain the second point cloud data;

[0054] (5) Perform color correction processing on the second point cloud data to obtain the third point cloud data;

[0055] (6) Perform format conversion on the third point cloud data to obtain the optimized point cloud data.

[0056] Specifically, perform positioning and calibration processing on the point cloud acquisition device. Positioning mainly determines the specific position and orientation of the device in space, while calibration involves adjusting and setting device parameters to ensure the accuracy of the scanned data. By comparing known standard objects or marker points, adjust the device until the data it acquires matches the accurate dimensions and shape of the actual object, obtaining a calibrated point cloud acquisition device. Use the calibrated point cloud acquisition device to perform ground laser scanning on the steel structure of the target building to obtain the initial point cloud data. Perform spatial filtering processing on the initial point cloud data. Spatial filtering uses various algorithms, such as Gaussian filtering, median filtering, etc., to remove noise points and isolated points, and retain the point cloud data representing the main body of the steel structure, obtaining the first point cloud data. The first point cloud data undergoes dimensionality reduction processing through the principal component analysis (PCA) algorithm. PCA is a statistical method that transforms data into a new coordinate system through linear transformation, such that the largest variance of any projection of the data lies on the first coordinate (referred to as the first principal component), the second largest variance lies on the second coordinate, and so on. Extract the most important features and structural information from the complex point cloud data to obtain a more concise second point cloud data that contains the main structural information. Perform color correction processing on the second point cloud data. Color correction refers to adjusting the color information in the point cloud data according to factors such as environmental lighting conditions and device characteristics to make it closer to the color of the real object, obtaining the third point cloud data. Perform format conversion on the third point cloud data to convert it into a data format that can be recognized and processed by a specific software or system, obtaining the optimized point cloud data.

[0057] In a specific embodiment, as Figure 2 shown, the process of executing step S102 may specifically include the following steps:

[0058] S201. Perform steel structure cross-section fitting on the optimized point cloud data through the cross-section fitting algorithm to obtain multiple fitted cross-sections;

[0059] S202. Perform structural component matching on each fitted cross-section through the edge point extraction algorithm to obtain multiple steel structure components. At the same time, extract the geometric parameters of each steel structure component, and merge the geometric parameters of each steel structure component into a component parameter set.

[0060] It should be noted that the optimized point cloud data is subjected to steel structure cross-section fitting by the cross-section fitting algorithm. The cross-section fitting algorithm identifies the main axis direction of the steel structure in space by analyzing the overall layout and directionality of the point cloud data. The algorithm slices the point cloud data along the main axis direction, and each slice is equivalent to the cross-section of the steel structure at a specific position. By analyzing and processing the point cloud within these slices, the algorithm can identify and reconstruct the accurate shape of each cross-section, obtaining multiple fitted cross-sections. The edge point extraction algorithm is used to perform structural component matching on each fitted cross-section respectively, to identify and match specific structural components. The geometric features at the edge of the cross-section are identified, and these features reflect the shape, size, and connection method of the steel structure components. By analyzing the point cloud distribution of each fitted cross-section through the edge point extraction algorithm, and calculating indicators such as local density change and curvature change of the point cloud, the edge points are identified. By connecting these edge points, the outer contour of each cross-section is reconstructed. Through further analysis of the outer contour, it is decomposed into several parts representing different steel structure components, and each part corresponds to a specific structural component. For the identified steel structure components, the algorithm extracts their geometric parameters, including length, width, thickness, curvature, etc., and these parameters are key indicators for evaluating the component status and performance. The geometric parameters of each steel structure component are combined into a component parameter set, providing a comprehensive geometric description of the entire steel structure. For example, for a specific steel beam, the algorithm determines the shape of its cross-section (such as I-shaped, T-shaped, or other shapes), and measures parameters such as the height, width of the cross-section, and the thickness of the web and flange. By summarizing this data, a comprehensive evaluation of the entire steel structure is carried out, including identifying potential structural problem areas, evaluating the load-bearing capacity of the structure, and planning necessary repair and reinforcement work.

[0061] In a specific embodiment, the process of executing step S201 may specifically include the following steps:

[0062] (1) Calibrate the main axis direction of the steel structure to obtain the main axis direction, and based on the main axis direction, perform hierarchical slicing on the optimized point cloud data to obtain multiple two-dimensional point cloud layers;

[0063] (2) Perform edge recognition on each two-dimensional point cloud layer respectively to obtain the outer contour line data of each two-dimensional point cloud layer;

[0064] (3) Perform geometric shape analysis on the outer contour line data of each two-dimensional point cloud layer respectively to obtain multiple initial cross-sections;

[0065] (4) Based on multiple standard steel structure cross-section shapes, perform matching on the multiple initial cross-sections through the cross-section fitting algorithm to obtain multiple cross-sections to be processed;

[0066] (5) Optimize the cross-section parameters for each cross-section to be processed respectively to obtain multiple fitted cross-sections.

[0067] Specifically, calibrate the main axis direction of the steel structure. By analyzing the distribution of the overall point cloud data, determine the main axis direction of the steel structure. For example, calculate the principal component analysis (PCA) of the point cloud data to determine the main direction of the data distribution. Based on the main axis direction, perform hierarchical slicing on the optimized point cloud data, and divide the point cloud data into a series of parallel slices along the main axis direction. Each slice is equivalent to a two-dimensional cross-section of the steel structure at a specific height, and multiple two-dimensional point cloud layers are obtained. Use an edge detection algorithm to identify the edges of each two-dimensional point cloud layer, and identify the point clouds that form the edges of the steel structure in each point cloud layer to obtain the outer contour line data of each two-dimensional point cloud layer. The outer contour line data depicts the cross-sectional shape of the steel structure at different heights. Analyze the geometric shape of the outer contour line data of each two-dimensional point cloud layer, extract the geometric shape representing the cross-section of the steel structure from the outer contour line data to obtain multiple initial cross-sections. These initial cross-sections are intuitive geometric representations of the steel structure at different positions. Based on multiple predefined standard steel structure cross-section shapes, match the initial cross-sections through a cross-section fitting algorithm to identify the closest standard cross-section shape. Through geometric matching and optimization algorithms, ensure that the matched cross-section shape can be as close as possible to the actual cross-section of the steel structure. Optimize the cross-section parameters for each cross-section to be processed obtained by matching. By adjusting the cross-section shape and size, make it more accurately conform to the geometric characteristics of the actual steel structure to obtain the final fitted cross-section.

[0068] In a specific embodiment, the process of performing step S103 may specifically include the following steps:

[0069] (1) Based on the component parameter set, input the optimized point cloud data into a region growing algorithm based on normal distribution for point cloud splitting to obtain the point cloud subsets of each steel structure component;

[0070] (2) Perform neighborhood analysis on the point cloud subsets of every two steel structure components respectively through the region growing algorithm to obtain the connection regions of every two steel structure components;

[0071] (3) Based on the preset connection region range, perform region screening on the connection regions of every two steel structure components to obtain multiple connection regions to be processed;

[0072] (4) Perform point cloud data matching on each connection region to be processed respectively to obtain multiple connection region point cloud data;

[0073] (5) Perform point cloud density analysis on each connection region point cloud data respectively to obtain the point cloud density data of each connection region point cloud data;

[0074] (6)Evaluate the spatial continuity of each connection area to be processed respectively based on the point cloud density data of each connection area point cloud data, and obtain the spatial continuity result of each connection area to be processed;

[0075] (7)Based on the spatial continuity results of each connection area to be processed, screen multiple connection areas to be processed to obtain multiple connection part areas;

[0076] (8)Extract geometric parameters for each connection part area respectively to obtain connection part parameters.

[0077] Specifically, based on the component parameter set, the optimized point cloud data is input into the region growing algorithm based on normal distribution for point cloud splitting. The algorithm divides the entire point cloud data set into multiple subsets according to the characteristics of the point cloud data, such as density, color, geometric shape, etc., and each subset represents a steel structure component. In this way, the algorithm identifies and separates the point cloud data of each component that makes up the steel structure. The region growing algorithm performs neighborhood analysis on the point cloud subsets of every two steel structure components. Identify the connection areas located between different components. The algorithm identifies potential connection areas between adjacent components by analyzing the spatial proximity of the point cloud. These connection areas are the focus of subsequent analysis because they are often the key areas of structural deformation or damage. Screen the identified connection areas based on the preset connection area range, excluding those areas that do not meet specific geometric or spatial characteristics, to obtain multiple connection areas to be processed. Perform point cloud data matching on each connection area to be processed to obtain connection area point cloud data. Perform point cloud density analysis on each connection area point cloud data to calculate the density distribution of the point cloud within each area. The point cloud density data provides important information about the geometric characteristics and spatial distribution characteristics of the connection area, providing information for evaluating the spatial continuity of the connection area. Evaluate the spatial continuity of each connection area to be processed based on the point cloud density data of each connection area point cloud data. By analyzing the continuity of the point cloud, identify possible defects or deformations in the structure, and obtain the spatial continuity result of each connection area to be processed. Based on the spatial continuity results of each connection area to be processed, screen the connection areas to be processed, identify the most critical connection part areas, and the screening process ensures that the focus of the analysis is concentrated on the areas most likely to have problems. Extract geometric parameters for each identified connection part area, including key geometric characteristics such as the size, shape, and orientation of the connection part.

[0078] In a specific embodiment, the process of performing step S104 may specifically include the following steps:

[0079] (1)Calibrate the position of the connection part for the connection part parameters to obtain the connection part position parameters;

[0080] (2) Analyze the starting point of deformation of the steel structure based on the position parameters of the connection part to obtain the starting point position of deformation;

[0081] (3) Segment the optimized point cloud data based on the starting point position of deformation to obtain multiple starting point local point clouds;

[0082] (4) Perform local deformation fitting on each starting point local point cloud respectively to obtain the deformation fitting data of each starting point local point cloud;

[0083] (5) Extract features from the deformation fitting data of each starting point local point cloud respectively to obtain the deformation feature set of each starting point local point cloud, where the deformation feature set includes: deformation amplitude and deformation direction;

[0084] (6) Extract the structural deformation parameters from the connection part parameters based on the deformation feature set of each starting point local point cloud to obtain the structural deformation parameters, where the structural deformation parameters include: deformation angle and offset distance;

[0085] (7) Analyze the deformation distribution of the structural deformation parameters to obtain the deformation distribution data corresponding to the structural deformation parameters;

[0086] (8) Evaluate the deformation degree of the target building based on the deformation distribution data to obtain the structural deformation degree.

[0087] Specifically, calibrate the position of the connection part parameters to obtain the position parameters of the connection part, providing a necessary spatial reference for subsequent analysis of the deformation starting point. Match the geometric features in the point cloud data with a pre-defined model to determine the exact position of the connection part in three-dimensional space, thereby obtaining the position parameters of the connection part. Based on the position parameters of the connection part, analyze the deformation starting point of the steel structure. By analyzing the changes in the point cloud data around the connection part, identify the position where the deformation initially begins. The deformation starting point represents the initial driving factor of the deformation and potential structural weak points. Based on the position of the deformation starting point, segment the optimized point cloud data to more precisely capture the local characteristics of the deformation. Divide the point cloud data into multiple local regions around the deformation starting point, and generate a starting point local point cloud for each region. These local point clouds contain detailed information about the local deformation of the structure. Perform local deformation fitting on each starting point local point cloud to obtain the deformation fitting data for each region. Use three-dimensional modeling techniques and fitting algorithms, such as the least squares method, to reconstruct the deformed structure shape in three-dimensional space and describe the geometric characteristics of the deformation in each local region. Extract the features of the deformation fitting data for each starting point local point cloud to identify the key features of the deformation, such as the deformation amplitude and deformation direction. Based on the deformation feature set, extract the structural deformation parameters from the connection part parameters. Synthesize the local deformation features into the deformation parameters of the overall structure, such as the deformation angle and offset distance. These parameters can comprehensively reflect the deformation state of the entire structure. Analyze the deformation distribution of the structural deformation parameters to understand the distribution of the deformation in the entire structure, identify the high-risk areas and deformation patterns of the deformation, and obtain the deformation distribution data corresponding to the structural deformation parameters. Evaluate the deformation degree of the target building based on the deformation distribution data, comprehensively considering the overall deformation characteristics and distribution of the structure, as well as the impact of the deformation on the building function and safety, to obtain the deformation degree of the entire structure.

[0088] In a specific embodiment, the process of performing step S106 may specifically include the following steps:

[0089] (1) Based on the structural deformation degree, perform a time series analysis on the structural deformation parameters to obtain the deformation dynamic characteristics;

[0090] (2) Based on the deformation dynamic characteristics, predict the deformation trend of the target BIM model to obtain the target deformation trend;

[0091] (3) Convert the data format of the target deformation trend to obtain the display data format, and transmit the target deformation trend to the data display terminal according to the display data format.

[0092] It should be noted that time series analysis is performed on the structural deformation parameters based on the degree of structural deformation. The deformation data collected at different time points of the structure is analyzed to identify the dynamic characteristics of the deformation, such as deformation speed, acceleration, and periodic changes. Through various methods in statistics and data science, such as time series analysis and autoregressive models, features that can reflect the dynamic behavior of structural deformation are extracted from the historical deformation data. Through the dynamic characteristics, the essence and driving factors of structural deformation are obtained. Based on the dynamic characteristics of deformation, the deformation trend of the target BIM model is predicted. The prediction model is a physics-based model or a data-driven machine learning model. Based on the current deformation characteristics and historical change trends, the possible deformation state of the structure within a future period of time is estimated. This prediction includes information such as the magnitude of deformation, the direction of deformation, and the rate, providing a comprehensive perspective to observe and evaluate the future health state of the structure. The target deformation trend is converted into a data format for easy display and transmission, ensuring that the predicted deformation trend can be effectively displayed on different platforms and devices. Data format conversion usually involves converting the data into charts, curves, animations, or other visual forms that can intuitively display the trend and pattern of structural deformation. At the same time, considering the data transmission format, ensure that the data can be efficiently and accurately transmitted to the data display terminal through the network or other communication methods. The target deformation trend is transmitted to the data display terminal according to the display data format. The data display terminal can be a large screen in the monitoring center, an application on a mobile device, or professional software used by engineers, etc.

[0093] An embodiment of the present invention further provides a BIM-based building steel structure deformation detection system, as Figure 3 shown. The BIM-based building steel structure deformation detection system specifically includes:

[0094] A scanning module 301, configured to perform ground laser scanning on the steel structure of the target building through a preset point cloud acquisition device to obtain initial point cloud data. At the same time, the initial point cloud data is optimized to obtain optimized point cloud data;

[0095] An analysis module 302, configured to perform component parameter analysis on the steel structure according to the optimized point cloud data to obtain a set of component parameters;

[0096] An input module 303, configured to input the optimized point cloud data into a preset region growing algorithm based on normal distribution for connection part geometric parameter analysis based on the set of component parameters to obtain connection part parameters;

[0097] An evaluation module 304, configured to perform structural deformation analysis on the connection part parameters through a piecewise fitting algorithm to obtain structural deformation parameters, and evaluate the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree;

[0098] An update module 305, configured to update the initial BIM model of the target building according to the structural deformation parameters, the connection part parameters, and the component parameter set to obtain a target BIM model;

[0099] A prediction module 306, configured to predict the deformation trend of the target BIM model based on the structural deformation degree to obtain a target deformation trend, and transmit the target deformation trend to a preset data display terminal.

[0100] Through the collaborative work of the above-mentioned various modules, by combining the terrestrial laser scanning technology and the BIM model, the real-time monitoring of the building steel structure can be realized, and at the same time, the deformed area of the structure can be accurately located. By using time series analysis and machine learning models to deeply analyze the collected structural deformation data, the future deformation trend of the building steel structure can be predicted. Through the detailed parameter analysis of the steel structure components and the geometric parameter analysis of the connection parts, combined with the structural deformation parameters, a comprehensive evaluation of the overall performance of the building steel structure can be provided. By updating the structural deformation parameters and the deformation trend prediction results to the target BIM model and transmitting them to the data display terminal, an intuitive visual display of the structural deformation can be provided. Through the automated data collection and analysis process, the dependence on manual inspection is reduced, which not only improves the efficiency of maintenance work, but also improves the accuracy of detection and evaluation. The automated process reduces human errors and ensures the accurate assessment of the state of the building steel structure.

[0101] Figure 4 FIG. 12 is a schematic structural diagram of a BIM-based building steel structure deformation detection device provided by an embodiment of the present invention. The BIM-based building steel structure deformation detection device 400 may vary greatly due to configuration or performance differences, and may include one or more processors (central processing units, CPU) 410 (for example, one or more processors) and a memory 420, and one or more storage media 430 (for example, one or more mass storage devices) for storing application programs 433 or data 432. Among them, the memory 420 and the storage media 430 may be transient storage or persistent storage. The program stored in the storage media 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the BIM-based building steel structure deformation detection device 400. Further, the processor 410 may be configured to communicate with the storage media 430 and execute a series of instruction operations in the storage media 430 on the BIM-based building steel structure deformation detection device 400.

[0102] The BIM-based building steel structure deformation detection device 400 may further include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input / output interfaces 460, and / or one or more operating systems 431, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, and so on. Those skilled in the art can understand that Figure 4 The shown structure of the BIM-based building steel structure deformation detection device does not limit the BIM-based building steel structure deformation detection device, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0103] The present invention also provides a BIM-based building steel structure deformation detection device, which includes a memory and a processor. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor is caused to execute the steps of the BIM-based building steel structure deformation detection method in the above-mentioned various embodiments.

[0104] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are run on a computer, the computer is caused to execute the steps of the BIM-based building steel structure deformation detection method.

[0105] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0107] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A BIM-based method for detecting the deformation of building steel structures, characterized in that, Including: Performing ground laser scanning on the steel structure of the target building through a pre-set point cloud acquisition device to obtain initial point cloud data. Meanwhile, performing data optimization on the initial point cloud data to obtain optimized point cloud data; Performing component parameter analysis on the steel structure according to the optimized point cloud data to obtain a component parameter set, specifically including: performing cross-section fitting of the steel structure on the optimized point cloud data through a cross-section fitting algorithm to obtain a plurality of fitted cross-sections; respectively performing structural component matching on each of the fitted cross-sections through an edge point extraction algorithm to obtain a plurality of steel structure components. Meanwhile, extracting the geometric parameters of each steel structure component and combining the geometric parameters of each steel structure component into the component parameter set; Based on the component parameter set, inputting the optimized point cloud data into a pre-set region growing algorithm based on normal distribution for analyzing the geometric parameters of the connection part to obtain connection part parameters, specifically including: based on the component parameter set, inputting the optimized point cloud data into the region growing algorithm based on normal distribution for point cloud splitting to obtain a point cloud subset of each steel structure component; respectively performing neighborhood analysis on the point cloud subsets of every two steel structure components through the region growing algorithm to obtain the connection region of every two steel structure components; based on a pre-set connection region range, performing region screening on the connection regions of every two steel structure components to obtain a plurality of connection regions to be processed; respectively performing point cloud data matching on each connection region to be processed to obtain a plurality of connection region point cloud data; respectively performing point cloud density analysis on each connection region point cloud data to obtain the point cloud density data of each connection region point cloud data; based on the point cloud density data of each connection region point cloud data, respectively performing spatial continuity evaluation on each connection region to be processed to obtain the spatial continuity result of each connection region to be processed; based on the spatial continuity result of each connection region to be processed, performing region screening on a plurality of connection regions to be processed to obtain a plurality of connection part regions; respectively performing geometric parameter extraction on each connection part region to obtain the connection part parameters; Performing structural deformation analysis on the connection part parameters through a segmented fitting algorithm to obtain structural deformation parameters, and evaluating the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree; Updating the initial BIM model of the target building to the target BIM model according to the structural deformation parameters, the connection part parameters and the component parameter set; Based on the structural deformation degree, predicting the deformation trend of the target BIM model to obtain the target deformation trend, and transmitting the target deformation trend to a pre-set data display terminal.

2. The method for detecting the deformation of building steel structures based on BIM according to claim 1, wherein, The step of performing ground laser scanning on the steel structure of the target building through a pre-set point cloud acquisition device to obtain initial point cloud data. Meanwhile, performing data optimization on the initial point cloud data to obtain optimized point cloud data includes: Performing positioning and calibration processing on the point cloud acquisition device to obtain a calibrated point cloud acquisition device; The steel structure of the target building is scanned by a calibrated point cloud acquisition device using ground laser scanning to obtain the initial point cloud data; The initial point cloud data is processed by spatial filtering to obtain the first point cloud data; The first point cloud data is processed by principal component analysis algorithm for dimensionality reduction to obtain the second point cloud data; The second point cloud data is processed by color correction to obtain the third point cloud data; The third point cloud data is subjected to format conversion to obtain the optimized point cloud data.

3. The BIM-based building steel structure deformation detection method according to claim 1, wherein The step of fitting the cross-section of the steel structure to the optimized point cloud data by the cross-section fitting algorithm to obtain a plurality of fitted cross-sections includes: Calibrating the main axis direction of the steel structure to obtain the main axis direction, and based on the main axis direction, performing hierarchical slicing on the optimized point cloud data to obtain a plurality of two-dimensional point cloud layers; Performing edge recognition on each of the two-dimensional point cloud layers to obtain the outer contour line data of each of the two-dimensional point cloud layers; Performing geometric shape analysis on the outer contour line data of each of the two-dimensional point cloud layers to obtain a plurality of initial cross-sections; Based on a plurality of standard steel structure cross-section shapes, matching the plurality of initial cross-sections by the cross-section fitting algorithm to obtain a plurality of cross-sections to be processed; Optimizing the cross-section parameters of each of the cross-sections to be processed to obtain the plurality of fitted cross-sections.

4. The method for detecting the deformation of building steel structures based on BIM according to claim 1, characterized in that The step of analyzing the structural deformation of the connection part parameters by the segmented fitting algorithm to obtain the structural deformation parameters, and evaluating the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree includes: Calibrating the position of the connection part of the connection part parameters to obtain the connection part position parameters; Based on the connection part position parameters, analyzing the deformation starting point of the steel structure to obtain the deformation starting point position; Based on the deformation starting point position, segmenting the optimized point cloud data to obtain a plurality of starting point local point clouds; Performing local deformation fitting on each of the starting point local point clouds to obtain the deformation fitting data of each of the starting point local point clouds; Performing feature extraction on the deformation fitting data of each of the starting point local point clouds to obtain the deformation feature set of each of the starting point local point clouds, wherein the deformation feature set includes: deformation amplitude and deformation direction; Based on the deformation feature set of each of the starting point local point clouds, extracting the structural deformation parameters from the connection part parameters to obtain the structural deformation parameters, wherein the structural deformation parameters include: deformation angle and offset distance; Performing deformation distribution analysis on the structural deformation parameters to obtain the deformation distribution data corresponding to the structural deformation parameters; Evaluating the deformation degree of the target building based on the deformation distribution data to obtain the structural deformation degree.

5. The BIM-based building steel structure deformation detection method according to claim 4, wherein, The step of predicting the deformation trend of the target BIM model based on the structural deformation degree to obtain the target deformation trend and transmitting the target deformation trend to a preset data display terminal includes: Based on the structural deformation degree, performing time series analysis on the structural deformation parameters to obtain the deformation dynamic characteristics; Based on the deformation dynamic characteristics, predict the deformation trend of the target BIM model to obtain the target deformation trend; Convert the data format of the target deformation trend to obtain a display data format, and transmit the target deformation trend to the data display terminal according to the display data format.

6. A BIM-based building steel structure deformation detection system for performing the BIM-based building steel structure deformation detection method according to any one of claims 1 to 5, characterized in that, Including: A scanning module, configured to perform ground laser scanning on the steel structure of a target building through a preset point cloud acquisition device to obtain initial point cloud data, and at the same time, optimize the initial point cloud data to obtain optimized point cloud data; An analysis module, configured to perform component parameter analysis on the steel structure according to the optimized point cloud data to obtain a set of component parameters. Specifically, it includes: performing fitting of the cross-section of the steel structure on the optimized point cloud data through a cross-section fitting algorithm to obtain a plurality of fitted cross-sections; respectively performing structural component matching on each of the fitted cross-sections through an edge point extraction algorithm to obtain a plurality of steel structure components, and at the same time, extracting the geometric parameters of each steel structure component, and combining the geometric parameters of each steel structure component into the set of component parameters; An input module, configured to input the optimized point cloud data into a preset region growing algorithm based on normal distribution for analysis of geometric parameters of connection parts based on the set of component parameters to obtain connection part parameters. Specifically, it includes: based on the set of component parameters, inputting the optimized point cloud data into the region growing algorithm based on normal distribution for point cloud splitting to obtain a point cloud subset of each steel structure component; respectively performing neighborhood analysis on the point cloud subsets of every two steel structure components through the region growing algorithm to obtain the connection regions of every two steel structure components; based on a preset connection region range, performing region screening on the connection regions of every two steel structure components to obtain a plurality of connection regions to be processed; respectively performing point cloud data matching on each connection region to be processed to obtain a plurality of connection region point cloud data; respectively performing point cloud density analysis on each of the connection region point cloud data to obtain the point cloud density data of each connection region point cloud data; based on the point cloud density data of each connection region point cloud data, respectively performing spatial continuity evaluation on each connection region to be processed to obtain the spatial continuity result of each connection region to be processed; based on the spatial continuity results of each connection region to be processed, performing region screening on a plurality of connection regions to be processed to obtain a plurality of connection part regions; respectively performing geometric parameter extraction on each of the connection part regions to obtain the connection part parameters; An evaluation module, configured to perform structural deformation analysis on the connection part parameters through a segmented fitting algorithm to obtain structural deformation parameters, and evaluate the deformation degree of the target building according to the structural deformation parameters to obtain the structural deformation degree; An update module, configured to update the initial BIM model of the target building to obtain a target BIM model according to the structural deformation parameters, the connection part parameters, and the set of component parameters; A prediction module, configured to predict a deformation trend of the target BIM model based on the degree of structural deformation, obtain a target deformation trend, and transmit the target deformation trend to a preset data display terminal.

7. A BIM-based building steel structure deformation detection device, characterized in that The BIM-based building steel structure deformation detection device includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory, so that the BIM-based building steel structure deformation detection device executes the BIM-based building steel structure deformation detection method according to any one of claims 1-5.

8. A computer-readable storage medium having instructions stored thereon, characterized in that, When the instructions are executed by the processor, the BIM-based building steel structure deformation detection method according to any one of claims 1-5 is implemented.

Images