BIM model-based curtain wall construction progress visualization method and system

Abstract

The invention relates to the field of building information management and construction progress visualization, in particular to a curtain wall construction progress visualization method and system based on a BIM model, and the method comprises the steps: obtaining the three-dimensional position information and installation state data of a curtain wall unit plate in real time through a sensor and an image collection device, and comparing the three-dimensional position information and installation state data with BIM integrated data, generating and updating a digital twinborn model; analyzing the construction data by using an artificial intelligence model, detecting a construction deviation and generating a construction adjustment suggestion; an optimal path is calculated through a construction path optimization algorithm, construction data are integrated to generate visual feedback, and the construction progress, the installation state and deviation information are displayed in real time through a visual engine, so that the construction monitoring and management efficiency is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the fields of building information management and construction progress visualization, and in particular to a curtain wall construction progress visualization method and system based on a BIM model. Background Art

[0002] As a key part of the building's external structure, the installation and progress management of curtain walls directly affect the overall delivery of the project. Traditional curtain wall construction monitoring methods rely on manual inspections and scattered data records, which makes it difficult to achieve real-time monitoring and timely adjustments during the construction process. With the popularization of building information models (BIM), three-dimensional models can be integrated with construction progress and on-site data to achieve visual management of the construction process, significantly improving construction efficiency and quality. However, the existing technology (Chinese invention patent, publication number: CN118396540A, name: A curtain wall progress monitoring method and system) has the following main deficiencies or defects: Existing technologies usually use handheld devices for data entry and scanning, which may result in manual operation errors and untimely information updates. Due to the lack of real-time monitoring means of the construction site, it is difficult to capture and feedback the installation progress in real time, affecting the timeliness of decision-making. The construction deviation detection and adjustment suggestion functions of the existing system are relatively simple, and it is difficult to cope with complex construction environments and changing site conditions. Summary of the invention

[0003] In view of the many problems existing in the above-mentioned prior art, the present invention provides a curtain wall construction progress visualization method and system based on the BIM model. The present invention combines sensors, image acquisition equipment, laser scanning and artificial intelligence models to collect construction site data in real time, compare it with the BIM model, and generate and update the digital twin model. The artificial intelligence model analyzes the data, identifies progress deviations in construction, automatically generates construction adjustment suggestions, realizes dynamic monitoring and visual feedback of the curtain wall construction progress, and effectively improves construction efficiency and accuracy.

[0004] A curtain wall construction progress visualization method based on a BIM model comprises the following steps: Constructing a three-dimensional BIM model including geometric parameters of curtain wall unit panels and a construction plan to generate standardized BIM data, and integrating the construction plan with the standardized BIM data to generate BIM integrated data; By using sensors and image acquisition equipment arranged at the construction site, the three-dimensional position information and installation status data of the curtain wall unit panels are collected in real time, and the three-dimensional position information and installation status data are compared with the BIM integrated data to generate and update the digital twin model data in real time; Through the positioning device embedded in the curtain wall unit panel and the image acquisition device based on 3D vision technology, the installation progress and installation status of the curtain wall unit panel are monitored in real time, and the on-site positioning data and installation status data are generated; Analyzing the site positioning data and installation status data based on an artificial intelligence model, detecting deviations in the construction progress, generating construction adjustment suggestions, and dynamically adjusting the construction plan based on the construction adjustment suggestions; The site positioning data, installation status data, construction adjustment suggestions and digital twin model data are integrated to generate visual feedback data, and the construction progress, installation status and deviation information are displayed in real time through the visualization engine.

[0005] Preferably, the step of collecting the three-dimensional position information and installation status data of the curtain wall unit panels by means of sensors and image acquisition equipment arranged at the construction site includes: performing continuous scanning by means of laser scanning equipment and drones to capture the real-time three-dimensional spatial coordinates and contour data of the curtain wall unit panels, and performing noise filtering and precision optimization processing on the data to generate cleaned three-dimensional point cloud data.

[0006] Preferably, the step of comparing the three-dimensional position information and the installation status data of the curtain wall unit panel with the BIM integrated data includes: gradually aligning the cleaned three-dimensional point cloud data with the BIM integrated data through an iterative nearest point matching algorithm to generate matching data, and the matching data is used to update the digital twin model data in real time.

[0007] Preferably, the step of real-time monitoring the installation progress of the curtain wall unit panels by means of a positioning device embedded in the curtain wall unit panels includes: embedding a magnetic positioning tag on the curtain wall unit panels, and acquiring the position information of the curtain wall unit panels in real time through a magnetic field sensor arranged at the construction site, and generating on-site positioning data, wherein the on-site positioning data reflects the real-time position and installation progress of the curtain wall unit panels.

[0008] Preferably, the step of generating approach positioning data by the positioning device includes: calculating the real-time position offset of the curtain wall unit panel according to the change of the magnetic field strength of the magnetic tag, and generating position correction data, wherein the position correction data is used to adjust the installation position of the curtain wall unit panel.

[0009] Preferably, the step of analyzing the on-site positioning data and the installation status data of the curtain wall unit panels based on the artificial intelligence model includes: combining historical construction data, installation time and spatial position changes through a multivariate spatiotemporal analysis model to generate spatiotemporal dynamic status data, and detecting deviations in the construction progress based on the spatiotemporal dynamic status data.

[0010] Preferably, the spatiotemporal dynamic state data is calculated by the following formula:

[0011] in, Indicates time The state deviation at the moment; Indicates Construction nodes in time The speed of entry at the moment; Indicates time Environmental factors at all times.

[0012] Preferably, the step of generating construction path optimization data based on the artificial intelligence model includes: analyzing the dependency relationship of construction nodes, the current construction status and resource allocation, using the construction path optimization algorithm to calculate the optimal construction path, and generating construction path optimization data. , the construction path optimization data The calculation is done by the following formula:

[0013] in, Represents construction path optimization data; For the Time estimate for each construction node; For the The resource demand weight of each construction node; For the The priority of each construction node.

[0014] Preferably, the step of displaying the construction progress, installation status and deviation information of curtain wall unit panels through a visualization engine includes: generating a construction heat map through a three-dimensional visualization engine, wherein the construction heat map is generated based on multi-dimensional data and intuitively displays the real-time progress health status of construction nodes.

[0015] A system for implementing a curtain wall construction progress visualization method based on a BIM model, the system comprising: A BIM model building module is used to build a three-dimensional BIM model including geometric parameters of curtain wall unit panels and a construction plan, generate standardized BIM data, and integrate the construction plan with the standardized BIM data to generate BIM integrated data; The on-site data acquisition module includes sensors and image acquisition equipment arranged at the construction site, which collect the three-dimensional position information and installation status data of the curtain wall unit panels in real time, and compare the three-dimensional position information and installation status data with the BIM integrated data to generate and update the digital twin model data in real time; The progress monitoring module includes a positioning device embedded in the curtain wall unit panel and an image acquisition device based on 3D vision technology, which monitors the installation progress and status of the curtain wall unit panel in real time and generates on-site positioning data and installation status data; An artificial intelligence analysis module, which analyzes the approach positioning data and installation status data based on an artificial intelligence model, detects deviations in the construction progress, and generates construction adjustment suggestions, wherein the artificial intelligence analysis module is used to dynamically adjust the construction plan based on the construction adjustment suggestions; The visualization engine module is used to integrate the on-site positioning data, installation status data, construction adjustment suggestions and digital twin model data, generate visualization feedback data, and display the construction progress, installation status and deviation information in real time through the visualization engine.

[0016] Compared with the prior art, the advantages and beneficial effects of the present invention are: The present invention realizes the automatic progress collection and monitoring of curtain wall unit panels through embedded positioning devices and three-dimensional visual technology, greatly reducing the error rate of manual operation; The present invention collects on-site data through laser scanning and drones, realizes real-time three-dimensional visualization of the construction process, and effectively improves the accuracy of construction monitoring and progress feedback; The present invention analyzes the on-site positioning data and installation status data through an artificial intelligence model to generate construction adjustment suggestions, so that the deviation of the construction progress can be dynamically adjusted, further improving the construction efficiency; The present invention calculates the optimal construction path through a construction path optimization algorithm, and optimizes resource allocation and construction scheduling based on resource allocation and construction node priority. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 A schematic diagram of the improvement process of detecting deviations and generating adjustment suggestions for the AI ​​model in the present invention; Figure 3 A schematic diagram showing an improved process of the visualization engine in the present invention; Figure 4 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0018] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0019] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0020] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0021] like Figure 1 As shown, a curtain wall construction progress visualization method based on a BIM model includes the following steps: Constructing a three-dimensional BIM model including geometric parameters of curtain wall unit panels and a construction plan to generate standardized BIM data, and integrating the construction plan with the standardized BIM data to generate BIM integrated data; The geometric parameters of the curtain wall unit panel include the shape, size, installation angle, connection method and material properties of the unit panel. The geometric parameters are generated by design software (such as Revit, etc.) and processed using a standardized data format to ensure consistency and compatibility between different platforms and software systems. These geometric parameters provide the basis for the entire BIM model, enabling each curtain wall unit panel to be accurately positioned in three-dimensional space. This precise positioning is crucial for subsequent construction progress tracking and dynamic adjustment of the construction plan.

[0022] The integration of the construction plan is the key to the dynamic nature of the entire BIM model. The construction plan not only includes the installation sequence of the curtain wall unit panels, but also involves information such as construction period, resource allocation, and equipment scheduling. By integrating the construction plan with the geometric data, the generated BIM integrated data can dynamically display the status of each construction stage in the model. In this process, the construction plan is decomposed into multiple nodes, each of which corresponds to a specific curtain wall unit panel, so that the installation process of each unit panel can be presented in the form of a timeline in the model. In this way, managers can intuitively understand the installation progress of each unit panel and clarify the construction priority and current completion status.

[0023] The entire construction process is visualized in a panoramic manner through the generated BIM integrated data. The construction team can view the progress of each construction stage in real time and compare it with the predetermined plan. This not only improves the management efficiency of the project, but also allows timely detection of deviations in the construction progress and optimization of the construction process by adjusting resources, equipment or construction period. In addition, the integrated data also provides complete digital information for future maintenance, renovation and expansion, simplifying the subsequent operation management work.

[0024] For example, in the curtain wall construction of a high-rise building, the architects used design software to define the geometric parameters of the curtain wall unit panels in detail, and integrated these geometric data with the specific construction plan in the early stage of construction. In the actual construction process, the project management team can clearly see the installation progress of each curtain wall unit panel through BIM integrated data. When there is a shortage of resources on site, which causes the installation progress of some curtain wall unit panels to be delayed, the system can promptly identify the delay and make adjustment suggestions, helping the construction team to dynamically schedule and optimize resources, avoiding global construction delays caused by local problems.

[0025] The three-dimensional position information and installation status data of the curtain wall unit panels are collected in real time through sensors and image acquisition equipment arranged at the construction site, and the three-dimensional position information and installation status data are compared with the BIM integrated data to generate and update the digital twin model data in real time; Sensor systems and image acquisition devices are used to obtain the actual spatial position and installation status information of curtain wall unit panels. Sensors can include laser scanners, total stations, and embedded positioning devices to provide accurate three-dimensional position information in real time. These devices can capture the precise position of each curtain wall unit panel in three-dimensional space and generate high-precision point cloud data, which reflects the actual installation status of the curtain wall panel relative to the building structure. Image acquisition equipment, usually including high-resolution cameras and three-dimensional camera systems, is responsible for monitoring the installation status of the unit panels, such as inclination, flatness, angle and other parameters to ensure that their installation meets the design specifications.

[0026] The collected 3D position information and installation status data are transmitted to the central data processing system through the sensor network and compared with the BIM integrated data. The BIM integrated data contains the design geometric parameters and the predetermined installation position of the curtain wall unit panels. Therefore, by comparing the actual collected data with the design data, the system can automatically detect deviations in the curtain wall installation process. For example, if the position of a curtain wall unit panel is offset from the design position beyond the allowable error range, the system will automatically issue an alarm and prompt the construction team to make adjustments.

[0027] In order to achieve this comparison process, the data processing system uses an automated comparison algorithm, the most common of which is the Iterative Closest Point (ICP) algorithm. The ICP algorithm matches the actual collected 3D point cloud data with the BIM integrated data point by point, and calculates the error between the actual position information of each curtain wall unit panel on site and the theoretical position information in the BIM model. This process is automated and can be completed in real time to ensure that the construction progress is consistent with the design plan.

[0028] Once the comparison is completed, the system will generate real-time updated digital twin model data. The digital twin model is a bridge between the physical world and the virtual model. It reflects the installation status of the curtain wall in real time. Any deviation, progress or adjustment can be immediately reflected in the digital twin model. This model not only contains the current geometric state, but also contains all relevant data during the installation process, such as the installation order, time, resource usage and other information of the unit panels. Through the digital twin model, construction managers can accurately monitor the progress and quality of the construction site dynamically and respond quickly according to the actual situation on site.

[0029] In applications, the real-time update of the digital twin model provides strong support for monitoring and adjusting the construction process. For example, in the curtain wall construction of a large commercial complex, sensors and image acquisition equipment collect the position information of hundreds of curtain wall unit panels in real time every day. When the system detects that the installation position of some unit panels deviates from the designed position, the management team quickly locates the problem panel through the digital twin model and can immediately arrange personnel to make on-site adjustments. This dynamic response capability greatly reduces the rework caused by position deviation and improves construction efficiency.

[0030] Preferably, the step of collecting the three-dimensional position information and installation status data of the curtain wall unit panels by means of sensors and image acquisition equipment arranged at the construction site includes: performing continuous scanning by means of laser scanning equipment and drones to capture the real-time three-dimensional spatial coordinates and contour data of the curtain wall unit panels, and performing noise filtering and precision optimization processing on the data to generate cleaned three-dimensional point cloud data.

[0031] The combination of laser scanning equipment and drones for data collection can greatly improve the efficiency and accuracy of data collection at the construction site. Laser scanning equipment, especially equipment based on LiDAR (Light Detection and Ranging) technology, can accurately capture the position and geometric outline of each curtain wall unit panel in three-dimensional space by emitting lasers and receiving reflected signals. The advantage of LiDAR scanning equipment lies in its high precision and high resolution, which can generate three-dimensional point cloud data containing millions of points, thereby describing in detail the spatial position of each unit panel, the installation angle, and the relative position of adjacent structures.

[0032] The use of drones has greatly expanded the coverage of scanning equipment. Since curtain wall unit panels are usually distributed at high altitudes or in areas that are difficult to directly access, drones equipped with LiDAR equipment can perform a full-scale scan of the construction site from multiple angles. Drones are flexible and efficient, can quickly fly to the target location, and collect data in real time, which is particularly suitable for large-scale curtain wall construction projects. Drone scanning can reduce the need for traditional scaffolding or manual operation, reducing construction costs and risks.

[0033] The original point cloud data generated by the collected three-dimensional spatial coordinates and contour data are usually accompanied by a certain amount of noise, which may be caused by changes in ambient light, equipment vibration or other external interference. Therefore, these point cloud data must be further processed. Common techniques for noise filtering include statistical filtering and noise removal algorithms based on neighborhood density, which can effectively remove discrete points or error data that do not conform to actual geometric features. After noise filtering, the next step is accuracy optimization processing, usually using the ICP (iterative closest point) algorithm or other point cloud registration algorithms to align the processed point cloud data with the geometric data in the BIM model to ensure the spatial consistency of the two.

[0034] The generated cleaned 3D point cloud data can be used as a real-time reflection of the construction site, and can clearly describe the installation status and position of each curtain wall unit panel. This data is not only the basis for subsequent construction progress comparison and analysis, but also can be used as data input for the digital twin model. The digital twin model receives these cleaned and optimized point cloud data in real time and updates the current construction status, allowing managers to monitor the construction progress on site in real time through the digital model. If the position of some curtain wall unit panels deviates from the design plan, the system will automatically issue an alarm and generate adjustment suggestions based on the current deviation.

[0035] This technical means has shown significant advantages in specific applications. For example, in a curtain wall construction project of a large commercial building, drones and LiDAR equipment are used to collect 3D position information of thousands of curtain wall unit panels every day. Through the generated cleaned point cloud data, the management team can update the construction progress in the BIM model every day and compare it with the construction plan. When errors are found in the installation position of certain unit panels, the system promptly prompts the construction personnel to make adjustments to ensure that the project proceeds smoothly according to the planned schedule.

[0036] The effect of this method is mainly reflected in the following aspects: Improved accuracy: LiDAR scanning equipment combined with drones can provide precise 3D spatial data, ensuring that the location of curtain wall unit panels is accurately reflected in the BIM model.

[0037] Real-time monitoring: Through the efficient data collection of drones and the real-time processing of point cloud data, the monitoring of construction progress has been transformed from static detection to dynamic real-time monitoring.

[0038] Automated processing: Through automatic noise filtering and accuracy optimization, human intervention is reduced, data processing efficiency and accuracy are further improved, and a reliable data foundation is provided for construction progress visualization.

[0039] Preferably, the step of comparing the three-dimensional position information and the installation status data of the curtain wall unit panel with the BIM integrated data includes: gradually aligning the cleaned three-dimensional point cloud data with the BIM integrated data through an iterative nearest point matching algorithm to generate matching data, and the matching data is used to update the digital twin model data in real time.

[0040] The comparison of 3D position information and installation status data depends on the alignment of point cloud data and BIM integrated data. The cleaned point cloud data reflects the actual 3D position and installation status of the curtain wall unit panels on site, while the BIM integrated data contains the ideal geometric data generated according to the design. By comparing the two, it is possible to determine whether there is a deviation between the actual installation situation and the design plan, and update the corresponding model in real time.

[0041] The Iterative Closest Point (ICP) algorithm plays an important role in this process. ICP is a common point cloud registration algorithm used to find the best registration between different point cloud data sets. Specifically, it matches the cleaned point cloud data with the geometric model in the BIM integrated data. In each iteration, the algorithm finds the closest point in the two sets of data and minimizes the distance between them, thereby gradually aligning the two sets of data. The core of the ICP algorithm is to match the geometric shapes in the two sets of point cloud data to a minimum error state through multiple iterations, thereby achieving the best registration of the data.

[0042] In actual application, this comparison process can provide real-time feedback on the current installation status of curtain wall unit panels. If the error between the position of a unit panel in the point cloud data and the planned position in the BIM model exceeds the allowable tolerance range, the system will automatically generate an alarm and prompt the relevant construction personnel to make corrections. For example, some unit panels may have been slightly misaligned or tilted during installation. The ICP algorithm can quickly detect this deviation and calculate the precise error value. Through the generated matching data, the system can not only inform the construction team which areas have deviations, but also provide specific adjustment suggestions so that they can quickly make corresponding adjustments.

[0043] The generated matching data will also be updated in real time to the digital twin model. The digital twin model is a virtual model that reflects the physical world in real time. It is dynamically generated based on BIM integrated data and actual data on site. During the construction process, the digital twin model continuously obtains and updates these matching data, allowing managers to view the actual installation status of each curtain wall unit panel at any time and intuitively display the actual deviation in the virtual model.

[0044] The combination of this comparison process and the digital twin model has a significant effect and can significantly improve the visualization of construction progress. For example, in the implementation of a large project, the construction team used a large amount of point cloud data collected daily by sensors and imaging equipment, combined with BIM integrated data for comparison. The system can accurately identify and analyze the deviation of the installation position of the unit board, prompting the construction team to make immediate corrections, thereby greatly reducing the rework rate. The real-time update of the digital twin model not only allows the management team to grasp the on-site situation at any time, but also enables the project team to adjust the subsequent construction plan in real time according to the current progress, so as to keep the overall project on track.

[0045] Through this comparison and real-time update process, the installation status of each curtain wall unit panel at the construction site can be accurately reflected in the BIM model, ensuring that the design plan closely matches the actual construction. Through automated data comparison, the management team can reduce the burden of manual inspection and improve overall construction efficiency and accuracy through analysis of matching data.

[0046] Through the positioning device embedded in the curtain wall unit panel and the image acquisition device based on 3D vision technology, the installation progress and installation status of the curtain wall unit panel are monitored in real time, and the on-site positioning data and installation status data are generated; Positioning devices are usually embedded inside each curtain wall unit panel, using common magnetic positioning technology or RFID technology. These devices can track the exact position of each unit panel in three-dimensional space in real time. In actual construction, each curtain wall unit panel needs to be installed precisely at the position specified by the design. These embedded positioning devices can continuously track the entry process and position changes of the unit panel by interacting with the receiver or sensor network arranged at the construction site. The positioning device is not only used for initial installation positioning, but also can detect whether the unit panel has undergone slight displacement or deviation during the installation process.

[0047] At the same time, image acquisition equipment based on 3D vision technology provides detailed visual data by photographing and analyzing the appearance and installation status of curtain wall unit panels. 3D vision technology uses multi-view images to reconstruct the 3D structural information of the unit panels, and can accurately capture the installation angle, inclination, and whether each unit panel is flush with adjacent unit panels. This image acquisition equipment is usually fixed at different angles on the construction site to ensure continuous photography and monitoring of the unit panels without blind spots. Through the image data collected by these devices, the system can continuously monitor the installation status of each unit panel without affecting the construction progress.

[0048] The collected 3D position information and installation status data are transmitted to the data processing center through the sensor network. The approach positioning data generated by the positioning device includes the real-time coordinates and installation depth of each unit board, while the installation status data generated by the 3D vision device describes the installation angle, inclination, etc. of the unit board in detail. The combination of these data can form a complete construction progress and installation status feedback to ensure that the entire construction process is carried out in accordance with the design requirements.

[0049] In the application, the on-site positioning data and installation status data are the basis for visualization of construction progress. Through real-time analysis of these data, the system can clearly understand the current construction progress and installation accuracy. If the on-site position of some curtain wall unit panels deviates from the predetermined position, the system will promptly issue an alarm to prompt the construction team to make adjustments. At the same time, the installation status data generated by the 3D vision equipment can provide real-time feedback on the installation quality, helping managers evaluate whether recalibration or fine-tuning is needed during the construction process.

[0050] For example, in a curtain wall construction project of a large commercial building, the construction team embedded RFID positioning devices in each unit panel and deployed multiple 3D visual devices on site. Through the collaborative work of these devices, the project management team can view the installation progress and status of each curtain wall unit panel in real time every day. When the installation position of some unit panels deviates from the design position beyond the predetermined error range, the system automatically prompts and provides adjustment suggestions through the BIM model, thus avoiding large-scale rework problems in the later stage.

[0051] This monitoring method based on positioning and visual technology not only greatly improves the accuracy and visualization level of construction progress, but also can timely detect and correct potential problems in construction, ensuring that the project is carried out according to the predetermined plan and standards. The real-time generated on-site positioning data and installation status data provide construction managers with dynamic and accurate construction information, and through integration with the BIM model, it realizes the visualization and dynamic adjustment capabilities of the construction progress.

[0052] By combining these two technologies, the construction team can monitor the entire process and avoid the impact of human factors on the construction progress and quality. This monitoring method not only improves the overall construction efficiency, but also provides basic data for the subsequent analysis and optimization of the construction progress. For example, the on-site positioning data can be used to analyze the bottleneck of the construction progress, while the installation status data can help determine whether there are equipment or material problems in the construction and propose corresponding optimization plans.

[0053] Preferably, the step of real-time monitoring the installation progress of the curtain wall unit panels by means of a positioning device embedded in the curtain wall unit panels includes: embedding a magnetic positioning tag on the curtain wall unit panels, and acquiring the position information of the curtain wall unit panels in real time through a magnetic field sensor arranged at the construction site, and generating on-site positioning data, wherein the on-site positioning data reflects the real-time position and installation progress of the curtain wall unit panels.

[0054] The magnetic positioning tag embedded in each curtain wall unit panel uses the change of magnetic field to locate the real-time position of each unit panel. The magnetic positioning tag is a non-contact sensing device, usually installed on the back or inside of the curtain wall unit panel, which can emit a stable magnetic field signal. The signal is captured by a network of magnetic field sensors distributed on the construction site. The magnetic field sensors are arranged in key areas of the building facade to form an induction network covering the curtain wall installation area. These sensors can detect the position of the magnetic tag in real time and transmit the data to the central control system.

[0055] This magnetic field-based positioning method has high positioning accuracy and stability. The magnetic positioning tag does not require power drive, and its signal strength is not affected by light, weather and other conditions in the on-site environment, which can ensure continuous monitoring of the construction progress. The sensor obtains the three-dimensional coordinates of each unit board in real time and generates on-site positioning data. This data includes the specific location of each unit board, such as x, y, and z coordinates, as well as its installation angle relative to the building facade.

[0056] By acquiring this location information, the system can track the arrival and installation progress of each curtain wall unit panel. The arrival positioning data reflects in real time the movement path of the unit panel at the construction site, the final installation position, and whether it matches the predetermined design position in the BIM model. Each movement or installation of the unit panel generates corresponding positioning data through the sensor network and compares it with the geometric parameters in the BIM model.

[0057] When the installation position of a unit board deviates from the designed position, the system can detect the deviation and send out an early warning signal by comparing the on-site positioning data with the BIM integrated data, prompting the construction personnel to adjust the installation process. This automated monitoring method greatly reduces the need for manual inspection and rework, and improves the accuracy and efficiency of the construction process.

[0058] The on-site positioning data is not only used for deviation detection, but also for dynamically updating the BIM model. During the installation process, the construction team can check the installation progress of each unit panel at any time through the real-time positioning data, and dynamically adjust the construction plan according to the actual installation situation. For example, if the installation progress of unit panels in certain areas is ahead of schedule or behind schedule, the construction manager can reschedule the allocation of other resources based on the positioning data to optimize the construction process.

[0059] The effect of this technology in application is very significant. For example, in a curtain wall construction project of a large commercial building, the combination of magnetic positioning tags and sensor networks helps the project management team to view the installation progress of hundreds of curtain wall unit panels in real time every day. When a unit panel is installed in a position that deviates due to equipment failure, the system can immediately detect the problem and prompt the construction staff to make corrections, thus avoiding large-scale rework and waste of resources. In the end, the project was completed ahead of schedule and the construction quality was significantly improved.

[0060] The positioning method based on magnetic field sensing technology also has the following important effects: Real-time precise positioning: Magnetic positioning tags provide high-precision location information to ensure that curtain wall unit panels can be accurately installed according to design requirements.

[0061] Efficient deviation detection and correction: By comparing the installation position with the designed position in real time through the sensor network, the construction team can get feedback and make adjustments as soon as the problem occurs, thus reducing the number of reworks.

[0062] Dynamic construction progress management: Based on real-time site positioning data, managers can dynamically adjust construction plans to improve resource utilization efficiency and construction speed.

[0063] Preferably, the step of generating approach positioning data by the positioning device includes: calculating the real-time position offset of the curtain wall unit panel according to the change of the magnetic field strength of the magnetic tag, and generating position correction data, wherein the position correction data is used to adjust the installation position of the curtain wall unit panel.

[0064] The magnetic tags embedded in each curtain wall unit panel can be captured in real time in the magnetic field sensor network arranged at the construction site by generating stable magnetic field signals. When the unit panel is displaced or tilted during the construction process, the magnetic field strength of the magnetic tag will change accordingly. The magnetic field sensor can detect this change and calculate the three-dimensional coordinate position of the unit panel based on the difference in magnetic field strength. Since there is a clear correlation between the signal strength and position of the magnetic tag, the system can calculate the offset between the actual position and the designed position of the unit panel by processing the changes in these signals.

[0065] The calculated real-time position offset data reflects the current position status of the unit panel. These offset data can not only identify the offset of the unit panel in three-dimensional space, but also detect its rotation, tilt and other state changes. For complex curtain wall systems, position offset involves not only translation, but also rotation and other geometric changes. Therefore, in real-time monitoring, the system will calculate the specific offset direction and amplitude according to the changes in magnetic field strength in different directions to ensure monitoring accuracy.

[0066] The generation of position correction data depends on the calculation results of position offset. The system compares the preset installation position in the BIM integrated data with the actual detected offset data, and automatically calculates the amplitude and direction of the adjustment. This correction data is directly used to guide the construction team to fine-tune the installation position to ensure that the curtain wall unit panels can be accurately installed at the designed position. For slight deviations, the system can prompt the construction staff to make manual adjustments; for larger deviations, the system may generate detailed correction suggestions and even adjust the construction sequence to ensure that the overall construction progress is not affected.

[0067] For example, in a high-rise building curtain wall project, when the construction team found that some unit panels were slightly tilted after installation, the system quickly detected the offset through the signal change of the magnetic tag and generated position correction data. The construction staff manually fine-tuned the data to ensure that the final installation position of the unit panel met the design requirements. Through this automated offset detection and correction mechanism, the project reduced the risk of large-scale rework and significantly improved construction efficiency.

[0068] This real-time position monitoring and correction method based on changes in magnetic field strength has the following advantages: High precision: The magnetic tags and sensor network can provide millimeter-level positioning accuracy, ensuring that the curtain wall unit panels are always in the correct position during installation.

[0069] Strong real-time performance: The system can capture position changes in real time and generate correction data immediately, so the construction team can make adjustments at the first time, reducing waiting time.

[0070] Automated correction: By generating position correction data, the system can automatically detect and feedback offset information, reducing manual inspection and error accumulation, and improving the level of automation in construction.

[0071] In addition, position correction data can also be used for long-term construction process optimization. For example, by analyzing the offset patterns of multiple unit panels during installation, the system can predict which areas are more likely to deviate, thereby adjusting the construction plan and resource allocation to further optimize the construction process.

[0072] like Figure 2 As shown, the approach positioning data and installation status data are analyzed based on the artificial intelligence model, deviations in the construction progress are detected, construction adjustment suggestions are generated, and the construction plan is dynamically adjusted based on the construction adjustment suggestions; Artificial intelligence (AI) models are used to analyze the on-site positioning data and installation status data obtained from sensors and image acquisition devices in real time. The on-site positioning data reflects the actual position, three-dimensional coordinates and installation progress of the curtain wall unit panels; the installation status data provides more detailed information, such as the inclination and installation angle of the curtain wall unit panels. Through these data, the AI ​​model can not only determine the gap between the current construction progress and the design goals, but also analyze the root causes that may lead to progress deviations.

[0073] The selection of AI models mainly depends on the complexity of different tasks, data structure and required output type. In the present invention, the AI ​​model types that can be selected include the following categories: Deep Neural Network (DNN): DNN is a model suitable for complex pattern recognition tasks and can process large amounts of unstructured data (such as images and sensor data). During curtain wall construction, DNN can be used to analyze on-site positioning data and installation status data, especially when complex spatial and temporal associations are involved. DNN is good at capturing these features. For example, time series data can be processed through multi-layer neural networks to predict future construction progress.

[0074] Convolutional Neural Network (CNN): CNN is particularly suitable for processing image data. Therefore, when three-dimensionally monitoring the installation status of curtain wall unit panels, CNN can process and extract features from images transmitted by image acquisition equipment, and identify installation deviations, angle changes, and other problems. CNN is mainly used for image processing and three-dimensional reconstruction in the present invention.

[0075] Long Short-Term Memory (LSTM): LSTM is a variant of recurrent neural network (RNN) and is particularly suitable for processing time series data. In terms of construction progress prediction, LSTM can learn and predict the time change trend of construction nodes based on historical construction data and current status data, so as to timely discover potential construction delays or anomalies.

[0076] Reinforcement Learning (RL): In the process of construction path optimization, RL can learn through feedback loops to optimize the order of construction nodes and resource allocation strategies. Reinforcement learning gradually improves the construction path through interaction with the environment, especially under complex dependencies and resource constraints.

[0077] Support Vector Machine (SVM) and Decision Tree: For some simpler classification tasks, such as determining the health status of a construction node or whether resources need to be adjusted, classic machine learning algorithms such as SVM and decision tree can also be applied to data classification and decision making.

[0078] In order to ensure that the AI ​​model can effectively perform tasks, sufficient model training must be carried out. The training process of the AI ​​model can be divided into the following main steps: The AI ​​model of the present invention relies on rich construction data for training, and the data sources include site positioning data, installation status data, construction history data, equipment and resource allocation data, etc. In order to improve the accuracy and generalization ability of the model, these data need to be preprocessed, mainly including: Data cleaning: Remove noise and incomplete data, such as through outlier detection and missing value filling, to ensure the quality of data used for model training.

[0079] Data standardization / normalization: Different types of input data (such as location, time, angle, etc.) may have different dimensions. In order for the AI ​​model to better process this data, it needs to be standardized or normalized.

[0080] Data augmentation: Especially in image processing tasks, data augmentation (such as rotation, scaling, and translation) can expand the training dataset and avoid model overfitting.

[0081] When training an AI model, it is usually divided into a training set and a validation set. The model is learned through the training set, and the performance of the model is evaluated through the validation set. The specific training process includes: Supervised learning: Most AI models are trained using supervised learning methods. The models are trained using labeled historical construction data to learn the characteristics of tasks such as construction progress, resource allocation, and deviation information.

[0082] In the construction path optimization task, the AI ​​model needs to learn the dependencies, time constraints and resource allocation of construction nodes, and form the optimal path selection through the accumulation of a large amount of historical data.

[0083] In deviation detection, the AI ​​model learns how to identify deviations and their severity through data samples of known construction deviations and normal installation status.

[0084] Unsupervised learning: In some cases, the data is not labeled, and the model can identify underlying structures or patterns through unsupervised learning. For example, clustering algorithms can be used to analyze abnormal patterns in construction data and identify potential problems in the construction process.

[0085] Reinforcement learning training: If a reinforcement learning model is used for construction path optimization, the training process is carried out through interaction with the construction environment. After each path selection, the model will receive rewards or penalties based on feedback (such as completion time, resource consumption, etc.), and continuously adjust the strategy until the optimal construction path is found.

[0086] During the training process, model hyperparameter tuning is crucial. The main tuning steps include: Choose a suitable optimizer and learning rate: such as Adam, SGD and other optimization algorithms.

[0087] Avoid overfitting: Cross-validation and regularization (L2 regularization, Dropout, etc.) can be used to prevent the model from overfitting on the training data and ensure the model's generalization ability on new data.

[0088] After training, the performance of the model needs to be verified through evaluation indicators. For example: Accuracy: The accuracy of the model in identifying construction deviations or detecting progress.

[0089] Mean Square Error (MSE): used to evaluate the prediction accuracy of approach positioning data and installation status data.

[0090] Reward value: In reinforcement learning tasks, the optimization effect of the model is evaluated by the accumulated reward value.

[0091] Once the AI ​​model is trained and verified, it can be integrated into the entire construction progress visualization system to provide real-time analysis and feedback. The real-time inference capability of the model is crucial, especially in complex construction projects, where the AI ​​model needs to make timely decisions based on real-time data from on-site sensors and data acquisition equipment. Therefore, when deployed, cloud computing or edge computing architecture can be used to ensure the model's reasoning speed and processing capabilities to meet the real-time needs of large-scale construction sites.

[0092] In the specific implementation, the AI ​​model establishes a set of prediction models by learning and modeling historical construction data, current site data and related environmental variables (such as weather, equipment conditions, etc.). This model can quickly identify differences from design goals based on real-time data and determine which unit panels may have installation problems. For example, the AI ​​model can detect that a batch of curtain wall unit panels is slow to enter the site, or that there is a systematic deviation in the installation angle of a certain area. By detecting these deviations, the AI ​​system generates real-time deviation information and provides specific adjustment suggestions.

[0093] When generating construction adjustment suggestions, the AI ​​model makes targeted suggestions through intelligent analysis of data, such as how to adjust resource allocation, optimize construction paths, or schedule equipment. For example, when the AI ​​model detects that the installation progress of unit panels in a certain area is slower than expected, the system can suggest increasing the number of construction personnel in that area or reallocating equipment resources to improve progress. In addition, AI can also suggest that the construction team adjust the overall construction plan based on the current deviation, such as modifying the installation order of subsequent unit panels, or adjusting the time of certain key steps to reduce possible bottlenecks during the construction process.

[0094] Construction adjustment suggestions are not just local adjustments, but can also involve global construction plan adjustments. The power of the AI ​​model lies in its ability to consider the overall situation of the entire project while analyzing local deviations. Based on these analyses, the AI ​​model can recommend dynamic adjustments to the construction plan. Based on these suggestions, the construction team can reasonably optimize subsequent construction resources, schedules, etc. to ensure that the entire project is completed on time. For example, the AI ​​model can predict possible future delays in certain areas based on the current construction progress deviation, and recommend adjusting the construction plans of other areas in advance to avoid delays in the overall construction period.

[0095] This dynamic adjustment not only improves the flexibility of construction, but also significantly reduces the risks in construction. For example, in a high-rise building project, the AI ​​model detected that the installation angle deviation of some curtain wall unit panels was large, and if no adjustment was made, it might lead to greater errors in subsequent installation. The AI ​​system promptly made optimization suggestions, suggesting that the equipment be recalibrated and the order of processes be adjusted, so that the construction team could respond quickly and make adjustments, avoiding the subsequent rework problem on a larger scale.

[0096] Through the intelligent analysis of AI models and the automatic generation of construction adjustment suggestions, the construction team can quickly discover and respond to on-site problems, reduce the time delay of traditional manual inspections, and improve construction accuracy. The AI ​​model can quickly process a large amount of on-site data and generate adjustment suggestions in real time, greatly improving the efficiency of construction management. At the same time, the dynamic adjustment function ensures that the construction plan can flexibly respond to on-site changes and reduce the risk of construction progress delays.

[0097] Preferably, the step of analyzing the on-site positioning data and the installation status data of the curtain wall unit panels based on the artificial intelligence model includes: combining historical construction data, installation time and spatial position changes through a multivariate spatiotemporal analysis model to generate spatiotemporal dynamic status data, and detecting deviations in the construction progress based on the spatiotemporal dynamic status data.

[0098] The core of the multivariate spatiotemporal analysis model is to conduct a comprehensive analysis of multiple variables in time and space dimensions. The variables here include on-site positioning data, installation status data of curtain wall unit panels, historical construction records, environmental factors, etc. The on-site positioning data provides real-time three-dimensional position information of the unit panels, while the installation status data reflects the angle, inclination and other details of the curtain wall panels during the construction process. By combining these real-time data with historical construction data, the AI ​​model can identify the difference between the current construction status and the design plan, and more importantly, it can predict future construction progress and potential problems by analyzing the spatiotemporal change trends of the data.

[0099] The spatiotemporal dynamic state data is a key product of this step. This data not only reflects the real-time position of the unit panel in three-dimensional space, but also records the time-varying information during the installation process. For example, by tracking the entire process of a curtain wall unit panel from entry to installation completion, the system can construct the spatiotemporal trajectory of the unit panel during the construction process, and combine it with historical construction data to understand whether it meets the predetermined installation schedule and spatial location.

[0100] This spatiotemporal analysis process can be further refined to multiple levels. For a single curtain wall unit panel, the system can determine whether there are deviations by analyzing the time series of its position changes and installation status, such as whether it arrives at the installation site on time, whether the installation is completed within the scheduled time, etc. For multiple unit panels, the system can determine whether there are systemic problems by analyzing the spatiotemporal relationship between different panels, such as whether the construction progress in some areas lags significantly behind other areas, or whether certain resource allocations have led to a decrease in local construction efficiency.

[0101] Through the spatiotemporal dynamic status data, the system can detect deviations in the construction progress in real time. For example, when the unit panel installation progress in a certain area lags significantly behind other areas, the spatiotemporal dynamic status data will show that the construction time in that area is extended, and there is a large spatial deviation between the on-site positioning data and the expected installation path. Based on this information, the system can quickly generate an early warning and prompt construction management personnel to make adjustments.

[0102] In practical applications, the spatiotemporal analysis function of the AI ​​model provides more intelligent construction monitoring. For example, in a large-scale construction project, the AI ​​model analyzed the on-site positioning data of multiple construction areas and found that the speed of unit panels in some areas was significantly slower than that in other areas. Through the spatiotemporal dynamic state data, the system can not only accurately identify these problem areas, but also predict more serious progress delays that may occur in this area in the future. Based on the warnings generated by the system, the management team adjusted the resource allocation and construction sequence and successfully avoided construction delays in this area.

[0103] The effect of this step is reflected in many aspects. First, the spatiotemporal analysis model can accurately capture deviations in the construction progress and provide early warnings of future construction progress by predicting spatiotemporal changes. Second, the generated spatiotemporal dynamic state data provides a global perspective on the construction progress of the entire project, enabling managers to fully understand the construction progress from both time and space dimensions. Finally, the AI ​​model can make intelligent adjustment suggestions based on the analysis results, helping the construction team optimize resource allocation and time scheduling, improve construction efficiency and reduce risks.

[0104] Preferably, the spatiotemporal dynamic state data is calculated by the following formula:

[0105] in, Indicates time The state deviation at the moment; Indicates Construction nodes in time The speed of entry at the moment; Indicates time Environmental factors at all times.

[0106] In the formula Representative time The state deviation at a certain moment reflects the deviation between the actual progress of the construction and the expected progress at a specific point in time. The data is obtained by comprehensively analyzing multiple factors on the construction site, providing a complete view of the current construction status. This real-time monitoring of status deviations allows the system to quickly identify anomalies in construction and adjust resources and plans in a timely manner.

[0107] Approach speed It is one of the core variables that affect state deviation. Indicates Construction nodes in time The speed of entry at each moment. In actual operation, each construction node corresponds to a specific stage of curtain wall construction, such as the installation and alignment of unit panels. The speed of entry determines the work efficiency of the construction node at each moment. For example, if the entry speed of a construction node is much lower than expected, this will directly lead to a lag in the overall progress and cause a state deviation. Therefore, by monitoring ,The system can track the work efficiency of different nodes, find the bottlenecks that affect the ,construction progress, and then propose corresponding optimization solutions.

[0108] Environmental factors is another key variable. Indicates time The impact of environmental factors at all times on construction, such as weather, temperature, humidity, wind speed, etc. These external environmental conditions are often difficult to control in actual construction, but they have a significant impact on the construction progress. For example, bad weather may cause equipment to not work properly or workers to work less efficiently. By introducing environmental factors into the formula, the system can quantify the uncontrollable factors at the construction site and bring them into the scope of progress management. In this way, even if unexpected environmental changes occur during the construction process, the system can analyze and The construction plan should be adjusted accordingly to reflect fluctuations in construction costs.

[0109] By integrating the formula The system accumulates the approach speed and environmental factors at each moment and obtains the overall state deviation of the construction. This cumulative calculation method ensures that the system can dynamically track the progress of construction, not only focusing on the current working status, but also evaluating the cumulative impact of construction history on the current status. For example, if some nodes have large deviations in the early stage, then even if the current entry speed and environmental factors are normal, the status deviation of the node will still be large. This analysis can help the construction team better understand which links have a long-term impact on the overall progress and take corresponding remedial measures.

[0110] In practical applications, this formula enables the system to generate accurate construction progress feedback in real time and help construction managers make timely decisions through dynamically updated state offset data. For example, during the installation of the curtain wall of a large building, the construction team continuously monitored the speed of entry and environmental conditions through this model. When the system detects that some nodes are significantly behind schedule due to weather conditions, the state offset data is automatically updated. As the storm surged, the system immediately sounded an alarm and suggested transferring some construction resources to other less affected areas. Through this dynamic adjustment, the construction team avoided large-scale delays and successfully maintained the overall progress of the project under harsh conditions.

[0111] The main advantage of this formula is that it can dynamically and accurately monitor the construction progress and effectively combine the core factors affecting construction (such as access speed and environmental conditions) through mathematical models. Real-time monitoring ensures the efficiency and transparency of construction nodes, while environmental factors The introduction of helps the team better cope with unforeseen external changes. Through the cumulative calculation of spatiotemporal dynamic state data, the construction team can better understand the overall trend of construction progress and make more reasonable plan adjustments.

[0112] Preferably, the step of generating construction path optimization data based on the artificial intelligence model includes: analyzing the dependency relationship of construction nodes, the current construction status and resource allocation, using the construction path optimization algorithm to calculate the optimal construction path, and generating construction path optimization data. , the construction path optimization data The calculation is done by the following formula:

[0113] in, Represents construction path optimization data; For the Time estimate for each construction node; For the The resource demand weight of each construction node; For the The priority of each construction node.

[0114] The dependency of construction nodes is an important factor affecting the optimal construction path. During the installation process, each curtain wall unit panel has a mutual dependency relationship with the adjacent panels and supporting structures. For example, some unit panels may have to be installed after a certain node is completed, otherwise it will cause construction interference or space conflicts. Based on these dependencies, the system will build a dependency graph to clearly present the order and association of all construction nodes. By analyzing this dependency, the artificial intelligence model can identify which nodes can be constructed in parallel and which nodes must be completed in a specific order, thereby avoiding resource conflicts and process bottlenecks.

[0115] The current construction status and resource allocation further affect the optimization of the construction path. The current construction status refers to the actual progress and completion of each construction node at a specific point in time. The AI ​​model analyzes real-time data to understand which nodes have been completed, which nodes are under construction, and which nodes are delayed due to insufficient resources or equipment failure. Resource allocation refers to the resource requirements of each node and the currently allocated resources, such as equipment, personnel, materials, etc. In some cases, a node may be delayed due to equipment failure or staff shortage. At this time, the system can dynamically analyze and reallocate resources to prioritize the completion of key nodes.

[0116] By combining these factors, the system uses a construction path optimization algorithm to calculate the optimal construction path. The core purpose of the optimization algorithm is to minimize the total construction time and resource consumption while ensuring construction dependencies. This optimization algorithm can use heuristic algorithms, genetic algorithms and other technologies to generate optimal path suggestions through learning from a large amount of data and historical experience.

[0117] By minimizing the result of the above formula, the system can generate an optimal construction path, optimize the overall progress of the project, maximize the efficiency of resource use, and avoid unnecessary delays and waste. The artificial intelligence model continuously learns and updates the optimization parameters in this process, so that it can adapt to the actual situation of the construction site and maintain the optimal state.

[0118] For example, in a large-scale construction project, the system analyzed the dependencies of curtain wall unit panels and found that some high-rise panels depended on the completion of the underlying structure, which was delayed due to equipment scheduling issues. Through the optimization algorithm, the system identified other regional construction nodes that could be carried out in parallel, and suggested reallocating resources, giving priority to key nodes, and ensuring that the overall construction progress was not affected. In the end, the project completed the scheduled progress target ahead of schedule through the optimized construction path.

[0119] The introduction of the construction path optimization algorithm has greatly improved the efficiency of construction management. First, it can intelligently optimize the construction sequence to avoid delays caused by dependencies or resource conflicts. Second, the system can dynamically adjust resource allocation to ensure that key nodes are completed first and improve the flexibility of the overall schedule. Finally, the construction path optimization algorithm can help managers better predict the bottlenecks and risks of the project, make adjustments in advance, and ensure that the project is completed on time.

[0120] The site positioning data, installation status data, construction adjustment suggestions and digital twin model data are integrated to generate visual feedback data, and the construction progress, installation status and deviation information are displayed in real time through the visualization engine.

[0121] Preferably, Figure 3As shown, the step of displaying the construction progress, installation status and deviation information of curtain wall unit panels through a visualization engine includes: generating a construction heat map through a three-dimensional visualization engine, wherein the construction heat map is generated based on multi-dimensional data and intuitively displays the real-time progress health status of construction nodes.

[0122] The on-site positioning data and installation status data are key data collected in real time during the construction process, reflecting the specific location, installation status, angle, progress and other detailed information of each curtain wall unit panel at the construction site. These data are uploaded to the system in real time through the sensor network and image acquisition equipment, and after processing, they are compared with the design data in the digital twin model. Through this comparison, the system can identify the deviation between the actual construction status and the design target, and generate corresponding deviation information and construction adjustment suggestions.

[0123] Construction adjustment suggestions are based on intelligent analysis of current progress, resource allocation, and deviation information. Through real-time monitoring of site data and installation status, the AI ​​model can analyze whether the progress of certain nodes is in line with expectations, and provide adjustment suggestions based on the analysis results, such as changing the construction sequence, adding or reallocating resources, etc. These adjustment suggestions can help the construction team respond quickly to changes on site and avoid construction delays or quality issues.

[0124] The digital twin model is the core of the entire visualization system. Digital twin technology reflects the current status of the construction site by building a virtual model that is synchronized with the real world. It integrates all real-time data, including positioning, status, adjustment suggestions, etc., and presents it in a virtual space in a three-dimensional way. The dynamic update of the digital twin model ensures real-time visibility of the construction status and provides managers with an accurate virtual reflection, which facilitates construction monitoring and management decision-making.

[0125] Visual feedback data is generated based on the integration of these core data. The system uses a three-dimensional visualization engine to visually present construction progress, installation status and deviation information to users in a graphical manner. The visualization engine can generate a global view of the construction progress through multi-dimensional data (such as time, space, progress, and resources). Users can use this view to view the status of each construction node in real time and quickly identify problem areas or lagging nodes in the construction. This kind of visual feedback is not just a static image or report, but dynamic and real-time, and can be continuously updated as the construction progress changes, ensuring that managers are always aware of the latest construction information.

[0126] To further enhance the visualization, the system also generates a construction heat map. This is a three-dimensional image generated based on multi-dimensional data that can express the real-time progress and health of each construction node through different colors and graphics. The core advantage of the construction heat map is its intuitiveness, which can clearly show which nodes are on track and which nodes have delays or other problems through color changes. Generally speaking, green indicates normal progress, yellow indicates minor delays, and red indicates serious delays or construction problems. Through this heat map, managers can quickly identify nodes that need intervention and take appropriate actions based on the adjustment suggestions provided by the system.

[0127] For example, in a curtain wall construction project for a large commercial building, the construction team monitored the progress of the entire facade installation in real time through the construction heat map generated by the visualization engine. The color of the heat map of some high-rise nodes gradually changed from yellow to red, indicating that the installation progress in this area was seriously lagging behind. After analysis, the system generated construction adjustment suggestions, prompting the team to reallocate equipment and personnel for high-rise construction and give priority to solving construction problems at key nodes. Through this dynamic adjustment, the team successfully avoided delays in the entire project schedule and maintained efficient use of resources.

[0128] First, through the three-dimensional display of the visualization engine, managers can fully understand the project progress without relying on complex text reports or tables. Second, the construction heat map provides managers with an intuitive tool that can quickly identify problem nodes in construction through changes in color and graphics to avoid construction delays or rework. Finally, the dynamically updated digital twin model and real-time generated adjustment suggestions make construction management more flexible and can respond to various problems in real time during project progress.

[0129] like Figure 4 As shown, a system for implementing a curtain wall construction progress visualization method based on a BIM model, the system comprising: The BIM model construction module is used to construct a three-dimensional BIM model containing the geometric parameters of the curtain wall unit panels and the construction plan, generate standardized BIM data, and integrate the construction plan with the standardized BIM data to generate BIM integrated data; the BIM model construction module is responsible for constructing a three-dimensional BIM model containing the geometric parameters of the curtain wall unit panels and the construction plan, and generating standardized BIM data. This model not only contains design drawings, but is also integrated with the construction plan, providing a basic framework for subsequent data comparison and real-time monitoring.

[0130] The field data acquisition module includes sensors and image acquisition equipment arranged at the construction site, which collect the three-dimensional position information and installation status data of the curtain wall unit panels in real time, and compare the three-dimensional position information and installation status data with the BIM integrated data to generate and update the digital twin model data in real time; the field data acquisition module uses sensors and image acquisition equipment arranged at the construction site to collect the three-dimensional position information and installation status data of the curtain wall unit panels in real time. After processing, these data are compared with the BIM integrated data to generate and update the digital twin model in real time. This module verifies the deviation between the design and reality through the actual data continuously collected, so that managers can obtain accurate information on site in a timely manner.

[0131] The progress monitoring module includes a positioning device embedded in the curtain wall unit panel and an image acquisition device based on 3D vision technology, which monitors the installation progress and status of the curtain wall unit panel in real time and generates on-site positioning data and installation status data; the progress monitoring module relies on the positioning device embedded in the curtain wall unit panel and 3D vision technology to monitor the installation progress and status of the unit panel in real time. The generated on-site positioning data and installation status data can reflect the installation progress of each curtain wall panel to ensure that the installation is in line with the design plan.

[0132] The artificial intelligence analysis module analyzes the approach positioning data and installation status data based on the artificial intelligence model, detects deviations in the construction progress, and generates construction adjustment suggestions. The artificial intelligence analysis module is used to dynamically adjust the construction plan based on the construction adjustment suggestions; at the analysis level, the artificial intelligence analysis module analyzes the approach positioning data and installation status data based on the AI ​​model to detect deviations in the construction progress. The AI ​​model generates construction adjustment suggestions by comparing historical data with real-time information. These suggestions cover construction path optimization, resource reallocation, etc., to ensure that the construction process can be dynamically adjusted to avoid delays or quality issues.

[0133] The visualization engine module is used to integrate the on-site positioning data, installation status data, construction adjustment suggestions and digital twin model data, generate visualization feedback data, and display the construction progress, installation status and deviation information in real time through the visualization engine. The visualization engine module integrates various types of data and generates visualization feedback to display the construction progress, installation status and deviation information. Through the three-dimensional visualization display, users can intuitively view the project progress, quickly locate progress deviations, and make necessary adjustments.

[0134] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.

[0135] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A curtain wall construction progress visualization method based on BIM model, characterized in that: The following steps are involved: Constructing a three-dimensional BIM model including geometric parameters of curtain wall unit panels and a construction plan to generate standardized BIM data, and integrating the construction plan with the standardized BIM data to generate BIM integrated data; By using sensors and image acquisition equipment arranged at the construction site, the three-dimensional position information and installation status data of the curtain wall unit panels are collected in real time, and the three-dimensional position information and installation status data are compared with the BIM integrated data to generate and update the digital twin model data in real time; Through the positioning device embedded in the curtain wall unit panel and the image acquisition device based on 3D vision technology, the installation progress and installation status of the curtain wall unit panel are monitored in real time, and the on-site positioning data and installation status data are generated; Analyzing the site positioning data and installation status data based on an artificial intelligence model, detecting deviations in the construction progress, generating construction adjustment suggestions, and dynamically adjusting the construction plan based on the construction adjustment suggestions; The site positioning data, installation status data, construction adjustment suggestions and digital twin model data are integrated to generate visual feedback data, and the construction progress, installation status and deviation information are displayed in real time through the visualization engine.

2. The method for visualizing curtain wall construction progress based on BIM model according to claim 1, characterized in that: The step of collecting the three-dimensional position information and installation status data of the curtain wall unit panels by means of sensors and image acquisition equipment arranged at the construction site includes: performing continuous scanning by means of laser scanning equipment and drones to capture the real-time three-dimensional spatial coordinates and contour data of the curtain wall unit panels, and performing noise filtering and precision optimization processing on the data to generate cleaned three-dimensional point cloud data.

3. The method for visualizing curtain wall construction progress based on BIM model according to claim 2, characterized in that: The step of comparing the three-dimensional position information and the installation status data of the curtain wall unit panel with the BIM integrated data includes: gradually aligning the cleaned three-dimensional point cloud data with the BIM integrated data through an iterative closest point matching algorithm to generate matching data, and the matching data is used to update the digital twin model data in real time.

4. The method for visualizing curtain wall construction progress based on BIM model according to claim 1, characterized in that: The step of real-time monitoring the installation progress of the curtain wall unit panels by means of a positioning device embedded in the curtain wall unit panels comprises: embedding a magnetic positioning tag on the curtain wall unit panels, and obtaining the position information of the curtain wall unit panels in real time by means of a magnetic field sensor arranged at the construction site, and generating on-site positioning data, wherein the on-site positioning data reflects the real-time position and installation progress of the curtain wall unit panels.

5. The method for visualizing curtain wall construction progress based on BIM model according to claim 4, characterized in that: The step of generating approach positioning data by the positioning device includes: calculating the real-time position offset of the curtain wall unit panel according to the change of the magnetic field strength of the magnetic tag, and generating position correction data, wherein the position correction data is used to adjust the installation position of the curtain wall unit panel.

6. The method for visualizing curtain wall construction progress based on BIM model according to claim 1, characterized in that: The step of analyzing the on-site positioning data and the installation status data of the curtain wall unit panels based on the artificial intelligence model includes: generating spatiotemporal dynamic status data by combining historical construction data, installation time and spatial position changes through a multivariate spatiotemporal analysis model, and detecting deviations in the construction progress based on the spatiotemporal dynamic status data.

7. The method for visualizing curtain wall construction progress based on BIM model according to claim 6, characterized in that: The spatiotemporal dynamic state data is calculated by the following formula: in, Indicates time The state deviation at the moment; Indicates Construction nodes in time The speed of entry at the moment; Indicates time Environmental factors at all times.

8. The method for visualizing curtain wall construction progress based on BIM model according to claim 7, characterized in that: The step of generating construction path optimization data based on the artificial intelligence model includes: analyzing the dependency relationship of construction nodes, the current construction status and resource allocation, using the construction path optimization algorithm to calculate the optimal construction path, and generating construction path optimization data , the construction path optimization data The calculation is done by the following formula: in, Represents construction path optimization data; For the Time estimate for each construction node; For the The resource demand weight of each construction node; For the The priority of each construction node.

9. The method for visualizing curtain wall construction progress based on BIM model according to claim 1, characterized in that: The step of displaying the construction progress, installation status and deviation information of curtain wall unit panels through a visualization engine includes: generating a construction heat map through a three-dimensional visualization engine, wherein the construction heat map is generated based on multi-dimensional data and intuitively displays the real-time progress health status of construction nodes.

10. A system for implementing the curtain wall construction progress visualization method based on the BIM model according to any one of claims 1 to 9, characterized in that: The system comprises: A BIM model building module is used to build a three-dimensional BIM model including geometric parameters of curtain wall unit panels and a construction plan, generate standardized BIM data, and integrate the construction plan with the standardized BIM data to generate BIM integrated data; The on-site data acquisition module includes sensors and image acquisition equipment arranged at the construction site, which collect the three-dimensional position information and installation status data of the curtain wall unit panels in real time, and compare the three-dimensional position information and installation status data with the BIM integrated data to generate and update the digital twin model data in real time; The progress monitoring module includes a positioning device embedded in the curtain wall unit panel and an image acquisition device based on 3D vision technology, which monitors the installation progress and status of the curtain wall unit panel in real time and generates on-site positioning data and installation status data; An artificial intelligence analysis module, which analyzes the approach positioning data and installation status data based on an artificial intelligence model, detects deviations in the construction progress, and generates construction adjustment suggestions, wherein the artificial intelligence analysis module is used to dynamically adjust the construction plan based on the construction adjustment suggestions; The visualization engine module is used to integrate the on-site positioning data, installation status data, construction adjustment suggestions and digital twin model data, generate visualization feedback data, and display the construction progress, installation status and deviation information in real time through the visualization engine.

Images