Fabricated building construction monitoring method based on digital twinborn technology

Abstract

The invention discloses a prefabricated building construction monitoring method based on a digital twinning technology, and the method comprises the following steps: constructing a digital twinning model of a prefabricated building, and setting a virtual cursor of each component; three-dimensional reconstruction is carried out on the actual installation conditions of the components, and actual measurement data of each component is obtained; comparing the measured data with the virtual cursor to obtain attitude deviation data of the component; presetting a tolerance threshold range, and comparing the attitude deviation data with the tolerance threshold range to obtain a deviation component exceeding the range; different marks are made on the deviation component, and the deviation component is adjusted based on the different marks; and uploading the adjusted component attitude data to the digital twin model, and updating the component deviation analysis result in real time until the component installation is qualified. According to the invention, real-time monitoring and rapid adjustment of the mounting precision of the component in the construction process of the fabricated building are realized, the construction efficiency and quality are improved, and effective technical support is provided for precise construction of the fabricated building.

Description

Technical Field

[0001] The present invention belongs to the technical field of prefabricated building construction, and in particular relates to a prefabricated building construction monitoring method based on digital twin technology. Background Art

[0002] During the construction of prefabricated buildings, there are often deviations between the actual installation position and posture of components and the theoretical position in the design model. If these deviations exceed the allowable tolerance range, they will affect the structural safety and functionality of the building. However, traditional manual measurement methods have difficulty in real-time and accurate detection and quantification of the installation deviation of each component, especially in large and complex prefabricated projects. At the same time, even if deviations are found, construction workers lack an intuitive and effective way to quickly locate the problem components and make precise adjustments. This leads to inefficient assembly quality control and increases the risk of rework and quality defects. In addition, due to the lack of real-time monitoring and data accumulation of the component installation process, it is difficult for project managers to fully grasp the construction progress and quality status, and they are unable to discover and solve systemic problems in a timely manner.

[0003] Therefore, how to achieve automated and accurate detection, visual presentation and intelligent correction guidance of component installation deviations during the construction of prefabricated buildings, while realizing digital management of the construction process, has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method for monitoring prefabricated building construction based on digital twin technology to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a method for monitoring the construction of an assembled building based on digital twin technology, comprising the following steps:

[0006] Constructing a digital twin model of the prefabricated building, and setting a virtual cursor of each component in the digital twin model;

[0007] Carry out 3D reconstruction of the actual installation conditions of the components and obtain the measured data of each component;

[0008] Compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component;

[0009] Preset a tolerance threshold range, compare the posture deviation data with the tolerance threshold range, and obtain the deviation component that exceeds the range;

[0010] Marking the deviation component differently and adjusting the deviation component based on the different marks;

[0011] The adjusted component posture data is uploaded to the digital twin model, and the component deviation analysis results are updated in real time until the component is installed qualifiedly.

[0012] Optionally, a digital twin model of a prefabricated building is constructed, and a process of setting a virtual cursor of each component in the digital twin model includes:

[0013] Acquire the construction drawing data and 3D design model data of the prefabricated building, preprocess and convert the construction drawing data and 3D design model data, and use the 3D reconstruction algorithm to build a digital twin model of the prefabricated building based on the preprocessed construction drawing data and 3D design model data; calculate the theoretical installation position and posture parameters of the components in the digital twin model based on the position and posture information of the components in the construction drawings and 3D design models, and add a virtual cursor for each component.

[0014] Optionally, the actual installation conditions of the components are three-dimensionally reconstructed, and the process of obtaining measured data of each component includes:

[0015] The video image data of the construction site is obtained and preprocessed, and the preprocessed video image data is used to identify components. Based on the component identification results, multi-view stereo vision technology is used to perform feature matching on images of the same component at different viewpoints, and the spatial coordinate information of the component is obtained to generate sparse three-dimensional point cloud data of the component. The sparse three-dimensional point cloud data of the component is preprocessed, and a three-dimensional reconstruction algorithm is used based on the preprocessed sparse three-dimensional point cloud data to generate a three-dimensional model of the component, and the measured data of the component is obtained; the measured data of the component includes the actual spatial coordinates and posture data of the component.

[0016] Optionally, the component's attitude deviation data includes: a three-dimensional coordinate deviation value of the component and deviation values ​​of the component at three angles: pitch angle, yaw angle and roll angle.

[0017] Optionally, the deviation component is marked differently, and the process of adjusting the deviation component based on the different marks includes:

[0018] For components that do not exceed the tolerance threshold range, the cursor is set to the default color; for deviation components that exceed the tolerance threshold range, different cursor colors are set based on different degrees of deviation; a clustering algorithm is used to group the deviation components based on their different degrees of deviation, and corresponding installation processes are adopted for adjustment and improvement.

[0019] Optionally, the adjusted component posture data is uploaded to the digital twin model, and the component deviation analysis results are updated in real time until the component is installed properly. The process includes:

[0020] The adjusted component posture data is uploaded to the digital twin model, and the digital twin model regenerates the digital twin model based on the adjusted component posture data. The updated digital twin model and the three-dimensional model of the measured component are analyzed for deviation again. If the deviation value still exceeds the preset tolerance threshold range, the iterative process of adjusting the component and updating the digital twin model is repeated until the component deviation is within the preset tolerance threshold range, and the component is judged to be installed qualifiedly.

[0021] The present invention also provides an assembled building construction monitoring system based on digital twin technology, which is used to implement an assembled building construction monitoring method based on digital twin technology, including: a virtual model building module, a measured data acquisition module, a data comparison module, a deviation data marking module and a deviation data adjustment module;

[0022] The virtual model construction module is used to construct a digital twin model of the prefabricated building, and a virtual cursor is set for each component in the digital twin model;

[0023] The measured data acquisition module is used to perform three-dimensional reconstruction of the actual installation conditions of the components and obtain the measured data of each component;

[0024] The data comparison module is used to compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component;

[0025] The deviation data marking module is used to mark the deviation component differently and adjust the deviation component based on the different marks;

[0026] The deviation data adjustment module is used to upload the adjusted component posture data to the digital twin model and update the component deviation analysis results in real time until the component is installed qualifiedly.

[0027] The present invention also provides an electronic device, comprising: a memory and a processor; the memory is used to store a program; the processor is used to execute the program to implement each step of the prefabricated building construction monitoring method based on digital twin technology.

[0028] The present invention also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various steps of the prefabricated building construction monitoring method based on digital twin technology are implemented.

[0029] Compared with the prior art, the present invention has the following advantages and technical effects:

[0030] The method disclosed in the present invention establishes a digital twin model and sets a virtual cursor for a component, uses computer vision technology to collect the actual installation data of the component in real time, compares and analyzes the measured data with the virtual cursor, and calculates the deviation value of the component in spatial position and posture. Cursors of different colors are set according to the size of the deviation to intuitively display the severity of the deviation. The digital twin model and the deviation cursor information are synchronized to the construction site to guide construction personnel to quickly locate and adjust the deviation components, and the adjusted data is uploaded in real time to update the analysis results. The present invention realizes real-time monitoring and rapid adjustment of the installation accuracy of components during the construction of prefabricated buildings, improves construction efficiency and quality, and provides effective technical support for the precise construction of prefabricated buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0032] Figure 1 A schematic diagram of a process of a method for monitoring construction of an assembled building based on digital twin technology according to an embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of the structure of an assembled building construction monitoring system based on digital twin technology according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0035] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Embodiment 1

[0037] like Figure 1 As shown, in this embodiment, a method for monitoring the construction of an assembled building based on digital twin technology is provided, comprising the following steps:

[0038] Build a digital twin model of the prefabricated building and set a virtual cursor for each component in the digital twin model;

[0039] Carry out 3D reconstruction of the actual installation conditions of the components and obtain the measured data of each component;

[0040] Compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component;

[0041] Preset the tolerance threshold range, compare the posture deviation data with the tolerance threshold range, and obtain the deviation components that exceed the range;

[0042] Different marks are made on the deviation components, and the deviation components are adjusted based on the different marks;

[0043] The adjusted component posture data is uploaded to the digital twin model, and the component deviation analysis results are updated in real time until the component is installed qualifiedly.

[0044] The process of constructing a digital twin model of a prefabricated building and setting a virtual cursor for each component in the digital twin model includes:

[0045] The construction drawings and 3D design model data of the prefabricated building are obtained, and the data is preprocessed and converted to a format to facilitate the subsequent construction of the digital twin model. Based on the preprocessed construction drawings and 3D design model data, a 3D reconstruction algorithm is used to construct a digital twin model of the prefabricated building, which contains various components of the building. For each component in the digital twin model, its theoretical installation position and posture parameters are calculated based on its position and posture information in the construction drawings and 3D design model. In the digital twin model, a virtual cursor is added to each component, and the position and posture of the virtual cursor are set according to the theoretical installation position and posture parameters calculated in the previous step. The constructed digital twin model is rendered using 3D visualization rendering technology to generate a realistic 3D visualization scene, and the virtual cursor is rendered into the scene. Through the human-computer interaction interface, users are allowed to browse the digital twin model in the 3D visualization scene and view the virtual cursor of each component to intuitively understand the theoretical installation position and posture of the component.

[0046] Specifically, obtaining the construction drawings and 3D design model data of prefabricated buildings is the first step in building a digital twin model. These data include the geometric information, component size, material properties, etc. of the building. Preprocessing and format conversion are to unify data in different formats into a format that can be recognized by the digital twin model, so that data can be easily exchanged between different software platforms. Using a 3D reconstruction algorithm, a digital twin model can be built based on the preprocessed data. Commonly used 3D reconstruction algorithms include point cloud-based reconstruction, grid-based reconstruction, etc. For example, a grid-based reconstruction algorithm can be used to represent the various components of a building as a 3D grid model, and these grid models can be combined into a complete building model. The model will include various components such as wall panels, floor slabs, beams, and columns. For each component in the model, such as a prefabricated wall panel, its theoretical installation position and posture parameters need to be calculated based on its information in the construction drawings and 3D design model. For example, the theoretical installation position of the wall panel can be expressed in 3D coordinates, and the posture parameters can be expressed in rotation angles. These parameters describe the position and direction where the wall panel should be installed in an ideal state. In the digital twin model, a virtual cursor can be added to each component. The virtual cursor is a visual mark that indicates the theoretical installation position and posture of the component. For example, an arrow can be used to indicate the installation direction of the wall panel, and the position of the arrow is the theoretical installation center point of the wall panel. The position and posture parameters of the virtual cursor are set according to the theoretical parameters calculated in the previous step. Using 3D visualization rendering technology, the digital twin model can be rendered into a realistic 3D scene. In this way, users can intuitively see the theoretical installation position and posture of each component in the 3D scene. Through the human-computer interaction interface, users can browse the digital twin model in the 3D scene. For example, users can use the mouse to rotate, zoom, and pan the scene to view the model from different angles. Users can also click on a component to view its detailed information, such as the size, material, installation parameters, etc. of the component. By viewing the virtual cursor, users can intuitively understand the theoretical installation position and posture of the component.

[0047] It is feasible to perform three-dimensional reconstruction of the actual installation conditions of the components and obtain the measured data of each component, including:

[0048] By arranging multiple video acquisition devices at the construction site, the actual component installation situation of the construction site is collected in real time, and the video image data of the construction site is obtained. The obtained video image data is preprocessed, including image denoising, image enhancement and other operations, to improve the image quality and provide high-quality image data for subsequent component recognition and three-dimensional reconstruction. The target detection algorithm based on deep learning is used to identify the components of the preprocessed video image data, obtain the category, position and other information of the components in the image, and provide the initial position information of the components for subsequent three-dimensional reconstruction. According to the component recognition results, the multi-view stereo vision technology is used to match the images of the same component at different perspectives, obtain the spatial coordinate information of the component, and generate the sparse three-dimensional point cloud data of the component. The obtained sparse point cloud data of the component is processed by point cloud filtering, point cloud registration and other processing to eliminate the noise and error in the point cloud data and improve the accuracy and stability of the point cloud data. According to the processed point cloud data, a three-dimensional reconstruction algorithm, such as the Poisson reconstruction algorithm, is used to generate a three-dimensional model of the component and obtain the actual spatial coordinates and posture data of the component.

[0049] Furthermore, a target detection algorithm based on deep learning is used to perform component recognition on the preprocessed image data. The process of obtaining information such as the category and position of the component in the image includes:

[0050] The image data is preprocessed, including image denoising, image enhancement and other operations, to obtain the preprocessed image. According to the preprocessed image, the target detection algorithm based on deep learning is used to identify the components in the image and obtain the category information of the components. In the process of target detection, the position coordinates of the components are determined by the algorithm to obtain the position information of the components in the image. The category information and position information of the components are associated to obtain the category and corresponding position coordinates of each component. According to the category and position information of the components, the spatial topological relationship between the components is established to form the logical association between the components. The category and position information of the components are statistically analyzed to obtain the number and distribution of components of different categories. The results of component recognition are compared with the preset component information to determine the accuracy of the recognition results, and the recognition algorithm is optimized and improved.

[0051] Furthermore, based on the processed point cloud data, a Poisson reconstruction algorithm is used to generate a three-dimensional model of the component, and the process of obtaining the actual spatial coordinates and posture data of the component includes:

[0052] Obtain the preprocessed point cloud data, which contains the spatial coordinate information of the component. According to the obtained point cloud data, the Poisson reconstruction algorithm is used to process the point cloud data to generate a three-dimensional mesh model of the component. On the basis of the generated three-dimensional mesh model, the normal vector information of the component surface is obtained by the triangular patch method. According to the obtained normal vector information of the component surface, the principal component analysis method is used to calculate the posture angle data of the component. The three-dimensional mesh model, spatial coordinate data and posture angle data of the component are fused to obtain the complete three-dimensional model data of the component. The octree algorithm is used to spatially index the three-dimensional model data of the component to improve the efficiency of retrieval and access to the model in subsequent applications. The three-dimensional model data, spatial coordinates and posture data of the component are stored in the three-dimensional model database for subsequent applications, such as three-dimensional visualization, virtual assembly, etc.

[0053] Specifically, in modern engineering projects, the construction and analysis of three-dimensional models is a crucial link. First, by acquiring point cloud data, which is usually derived from laser scanning or photogrammetry technology, the spatial coordinate information of the component can be accurately captured. For example, at a construction site, a laser scanner can quickly collect point cloud data of the entire building, which records the geometric shape of every corner and surface of the building in detail. Next, the point cloud data is processed using the Poisson reconstruction algorithm, which can infer a smooth surface from the disordered point cloud and generate a three-dimensional mesh model of the component. After the three-dimensional mesh model is generated, the normal vector information of the component surface can be calculated by the triangular patch method. This step is very critical for determining the illumination model and performing physical simulation, because the normal vector is the basis for judging the interaction between the surface and the light and simulating the force of the object. Then, the principal component analysis method is used to calculate the posture angle data of the component, which is particularly important for object recognition and manipulation in the robot vision system. In order to improve the efficiency of retrieval and access to model data, the octree algorithm is used to spatially index the three-dimensional model data of the component. Finally, the component's 3D model data, spatial coordinates, and posture data are stored in a 3D model database, which makes the data usable by a variety of applications.

[0054] It is feasible to compare the measured data of the component with the virtual cursor position of the corresponding component in the digital twin model, and calculate the deviation values ​​of the component in the three directions of X, Y, and Z, as well as the deviation values ​​of the pitch angle, yaw angle, and roll angle. The process includes:

[0055] The measured three-dimensional coordinate data and virtual cursor posture data of the component are obtained, wherein the measured data include the coordinate value and three rotation angle values ​​of the component in the three-dimensional space, and the virtual cursor posture data include the three-dimensional coordinate value and three rotation angle values ​​of the corresponding position of the component in the digital twin model; the measured data and the virtual cursor posture data are aligned so that the two sets of data are compared in the same coordinate system; the coordinate deviation value of the component in the three directions of X, Y, and Z is calculated, and the deviation value is equal to the measured coordinate value minus the virtual cursor coordinate value; the deviation value of the component at the three angles of pitch angle, yaw angle, and roll angle is calculated, and the deviation value is equal to the measured angle value minus the virtual cursor angle value; it is determined whether the coordinate deviation value and the angle deviation value exceed the preset threshold value, if so, the component is marked as an abnormal component, and the deviation value is recorded; according to the deviation value of the component, the support vector machine algorithm is used to classify the abnormal components to obtain abnormal components of different degrees; for abnormal components of different degrees, the decision tree algorithm is used to give corresponding processing suggestions, such as fine-tuning, rework, scrapping, etc., and the processing suggestions are associated with the abnormal component information and stored.

[0056] Specifically, obtaining the measured three-dimensional coordinate data and virtual cursor posture data of the component is a key step in achieving accurate comparison and quality management during the construction process. The measured data is usually obtained through high-precision measuring equipment, such as a laser scanner or a total station, to obtain the coordinate values ​​(X, Y, Z) and three rotation angle values ​​(pitch, yaw, and roll) of the component in three-dimensional space. The measured data is aligned with the virtual cursor posture data in order to unify the two sets of data into the same coordinate system for accurate comparison. During the alignment process, coordinate transformation algorithms, such as homogeneous coordinate transformation, are usually used to ensure data consistency. After alignment, the coordinate deviation value and angle deviation value can be calculated.

[0057] It is feasible to compare and analyze the results statistically, determine whether the installation deviation of each component exceeds the preset tolerance threshold range, mark the deviation components differently, and adjust the deviation components based on different marks. The process includes:

[0058] The installation deviation data of each component is obtained, and it is compared with the preset tolerance threshold range to determine whether it exceeds the threshold range; for components that exceed the threshold range, different colors are used to set the cursor according to the deviation size to intuitively indicate the severity of the deviation; for components that do not exceed the threshold range, the cursor is set to the default color, indicating that the installation deviation is within an acceptable range; by comparing and statistically analyzing the results, the number and proportion of components that exceed the threshold range, as well as the distribution of components in each deviation interval, are obtained; based on the statistical analysis results, it is determined whether the overall installation quality meets the requirements. If not, the installation process needs to be optimized and adjusted; a clustering algorithm is used to group components, and components with similar deviation sizes are classified into one category in order to carry out targeted installation process improvements.

[0059] Furthermore, obtaining the installation deviation data of each component is a key step to ensure the quality of the project. These deviation data are compared with the preset tolerance threshold range. For components that exceed the threshold range, different colors are used to set the cursor according to the size of their deviation. By comparing and statistically analyzing the results, the number and proportion of components that exceed the threshold range can be obtained. According to the statistical analysis results, it is judged whether the overall installation quality meets the requirements. If the proportion of components that exceed the threshold range is too high, the installation process needs to be optimized and adjusted. The clustering algorithm is used to group the components and divide them into three categories: the first category has small deviations, the second category has medium deviations, and the third category has large deviations. For the first category of components, only fine-tuning may be required; for the second category of components, partial rework may be required; and for the third category of components, it may be necessary to scrap and remake. After grouping in this way, the installation process can be improved more targeted. By comparing the data before and after, the effect of the installation process optimization is judged until the deviations of all components are within the preset tolerance threshold range. The implementation of this method can not only intuitively display the installation deviation of each component, but also discover the systematic problems in the overall installation through statistical analysis, and improve the installation process through cluster analysis. Finally, through continuous iterative optimization, the overall installation quality is ensured to meet the engineering requirements and the reliability and service life of the equipment are improved. This multi-level optimization strategy not only improves the installation efficiency, but also significantly improves the engineering quality and reduces the subsequent maintenance costs, with significant technical and economic benefits.

[0060] As an implementable method, the digital twin model data, including the geometric information, material information and location information of the model, is obtained, converted into a format recognizable by the mobile APP, and stored in the local or cloud database of the mobile device. The actual construction data of the construction site, including the location and size of the installed components, is obtained through sensors or manual input, and compared with the digital twin model to calculate the deviation information. The deviation information is visualized to generate an easy-to-understand graphical representation, such as marking the deviation components with different colors or symbols, and displaying the size and direction of the deviation. An interactive interface is developed in the mobile APP, allowing construction personnel to view the digital twin model and deviation information through gesture operations (such as translation, rotation, zooming, etc.), and to zoom in, zoom out, switch perspectives, etc. as needed. The positioning function is developed to obtain the current location of the construction personnel through GPS, indoor positioning and other technologies, and display it in the digital twin model, and guide the construction personnel to move to the installation location of the target component according to the deviation information. Integrate communication functions in the mobile APP to allow construction personnel to communicate and collaborate with designers, supervisors, etc. in real time. For complex deviation issues, remote guidance and discussion can be carried out through voice, video, etc. Develop data analysis functions to collect and analyze deviation data collected during the construction process, identify frequently occurring deviation types and causes, and provide optimization suggestions to continuously improve construction quality and efficiency.

[0061] It is feasible to upload the adjusted component posture data to the digital twin model and update the component deviation analysis results in real time until the component is installed properly. The process includes:

[0062] The adjusted component posture data is uploaded to the digital twin model, and the model regenerates the digital twin model based on the adjusted component posture data. The updated digital twin model and the measured three-dimensional model are analyzed for deviation again to calculate the accuracy deviation value. If the deviation value still exceeds the allowable range, the iterative process of adjusting the component and updating the virtual model is repeated; if the deviation is within the acceptable range, the component installation is determined to be qualified. The final installation posture data of the component is associated with its ID and stored to form a complete digital twin model for refined management in the subsequent operation and maintenance stage. The advantage of this is that the installation process and final state of the component are fully recorded, which is convenient for traceability and analysis, and is also conducive to controlling the quality of the entire project and providing accurate data support for subsequent operation and maintenance.

[0063] The method disclosed in the present invention establishes a digital twin model and sets a virtual cursor for a component, uses computer vision technology to collect the actual installation data of the component in real time, compares and analyzes the measured data with the virtual cursor, and calculates the deviation value of the component in spatial position and posture. Cursors of different colors are set according to the size of the deviation to intuitively display the severity of the deviation. The digital twin model and the deviation cursor information are synchronized to the construction site to guide construction personnel to quickly locate and adjust the deviation components, and the adjusted data is uploaded in real time to update the analysis results. The present invention realizes real-time monitoring and rapid adjustment of the installation accuracy of components during the construction of prefabricated buildings, improves construction efficiency and quality, and provides effective technical support for the precise construction of prefabricated buildings.

[0064] like Figure 2 As shown, the present invention also provides an assembled building construction monitoring system based on digital twin technology, which is used to implement an assembled building construction monitoring method based on digital twin technology, including: a virtual model building module, a measured data acquisition module, a data comparison module, a deviation data marking module and a deviation data adjustment module;

[0065] The virtual model building module is used to build a digital twin model of the prefabricated building and set a virtual cursor for each component in the digital twin model;

[0066] The measured data acquisition module is used to perform three-dimensional reconstruction of the actual installation conditions of the components and obtain the measured data of each component;

[0067] The data comparison module is used to compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component;

[0068] The deviation data marking module is used to mark the deviation components differently and adjust the deviation components based on the different marks;

[0069] The deviation data adjustment module is used to upload the adjusted component posture data to the digital twin model and update the component deviation analysis results in real time until the component is installed qualifiedly.

[0070] Embodiment 2

[0071] The present invention also provides an electronic device, comprising: a memory and a processor; the memory is used to store programs; the processor is used to execute programs to implement various steps of the prefabricated building construction monitoring method based on digital twin technology.

[0072] Embodiment 3

[0073] The present invention also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various steps of the prefabricated building construction monitoring method based on digital twin technology are implemented.

[0074] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring the construction of assembled buildings based on digital twin technology, characterized in that: The following steps are involved: Constructing a digital twin model of the prefabricated building, and setting a virtual cursor of each component in the digital twin model; Carry out 3D reconstruction of the actual installation conditions of the components and obtain the measured data of each component; Compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component; Preset a tolerance threshold range, compare the posture deviation data with the tolerance threshold range, and obtain the deviation component that exceeds the range; Marking the deviation component differently, and adjusting the deviation component based on the different marks; The adjusted component posture data is uploaded to the digital twin model, and the component deviation analysis results are updated in real time until the component is installed qualifiedly.

2. The method for monitoring the construction of assembled buildings based on digital twin technology according to claim 1 is characterized in that: The process of constructing a digital twin model of a prefabricated building and setting a virtual cursor of each component in the digital twin model includes: Acquire the construction drawing data and 3D design model data of the prefabricated building, preprocess and convert the construction drawing data and 3D design model data, and use the 3D reconstruction algorithm to build a digital twin model of the prefabricated building based on the preprocessed construction drawing data and 3D design model data; calculate the theoretical installation position and posture parameters of the components in the digital twin model based on the position and posture information of the components in the construction drawings and 3D design models, and add a virtual cursor for each component.

3. The method for monitoring construction of assembled buildings based on digital twin technology according to claim 1, characterized in that: The process of 3D reconstruction of the actual installation of components and obtaining the measured data of each component includes: The video image data of the construction site is obtained and preprocessed, and the preprocessed video image data is used to identify components. Based on the component identification results, multi-view stereo vision technology is used to perform feature matching on images of the same component at different viewpoints, and the spatial coordinate information of the component is obtained to generate sparse three-dimensional point cloud data of the component. The sparse three-dimensional point cloud data of the component is preprocessed, and a three-dimensional reconstruction algorithm is used based on the preprocessed sparse three-dimensional point cloud data to generate a three-dimensional model of the component, and the measured data of the component is obtained; the measured data of the component includes the actual spatial coordinates and posture data of the component.

4. The method for monitoring construction of assembled buildings based on digital twin technology according to claim 1, characterized in that: The component's attitude deviation data includes: the component's three-dimensional coordinate deviation value and the component's deviation values ​​at three angles: pitch angle, yaw angle, and roll angle.

5. The method for monitoring construction of assembled buildings based on digital twin technology according to claim 1, characterized in that: The process of marking the deviation component differently and adjusting the deviation component based on the different markings includes: For components that do not exceed the tolerance threshold range, the cursor is set to the default color; for deviation components that exceed the tolerance threshold range, different cursor colors are set based on different degrees of deviation; a clustering algorithm is used to group the deviation components based on their different degrees of deviation, and corresponding installation processes are adopted for adjustment and improvement.

6. The method for monitoring construction of assembled buildings based on digital twin technology according to claim 3 is characterized in that: The process of uploading the adjusted component posture data to the digital twin model and updating the component deviation analysis results in real time until the component is installed properly includes: The adjusted component posture data is uploaded to the digital twin model, and the digital twin model regenerates the digital twin model based on the adjusted component posture data. The updated digital twin model and the three-dimensional model of the measured component are analyzed for deviation again. If the deviation value still exceeds the preset tolerance threshold range, the iterative process of adjusting the component and updating the digital twin model is repeated until the component deviation is within the preset tolerance threshold range, and the component is judged to be installed qualifiedly.

7. An assembled building construction monitoring system based on digital twin technology, characterized in that: The method for monitoring the construction of assembled buildings based on digital twin technology according to any one of claims 1 to 6 comprises: a virtual model building module, a measured data acquisition module, a data comparison module, a deviation data marking module and a deviation data adjustment module; The virtual model construction module is used to construct a digital twin model of the prefabricated building, and a virtual cursor is set for each component in the digital twin model; The measured data acquisition module is used to perform three-dimensional reconstruction of the actual installation conditions of the components and obtain the measured data of each component; The data comparison module is used to compare the measured data of each component with the virtual cursor to obtain the posture deviation data of the component; The deviation data marking module is used to mark the deviation component differently and adjust the deviation component based on the different marks; The deviation data adjustment module is used to upload the adjusted component posture data to the digital twin model and update the component deviation analysis results in real time until the component is installed qualifiedly.

8. An electronic device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the prefabricated building construction monitoring method based on digital twin technology as described in any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, each step of the prefabricated building construction monitoring method based on digital twin technology as described in any one of claims 1 to 6 is implemented.

Images