Fabricated building construction monitoring method based on BIM

Abstract

The invention relates to the technical field of building construction, in particular to a BIM-based fabricated building construction monitoring method, and ensures that a construction team can obtain real state visual information of a construction site in a BIM model by integrating real-time data collected by an intelligent sensor with the BIM model. Therefore, constructors can perform construction more accurately, inspection is assisted through the augmented reality technology, deviation is found and corrected in time, and construction precision and engineering quality are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction, and particularly to a BIM-based construction monitoring method for prefabricated buildings. Background Art

[0002] In modern building construction, improving construction efficiency, reducing costs, ensuring safety and quality, and minimizing environmental impact are important challenges faced by the industry. Traditional construction monitoring methods often suffer from insufficient real-time performance, limited data analysis capabilities, and imperfect early warning mechanisms, making it difficult to meet the requirements of modern construction management. Specifically, the following problems exist: In the prior art, construction teams usually cannot obtain visual information on the real state of the construction site, resulting in construction workers being unable to adjust construction details in a timely manner according to the actual situation. Due to the lack of real-time and comprehensive monitoring means, problems during the construction process are often not discovered and solved in a timely manner, leading to an increase in downtime and affecting the construction progress.

[0003] In view of the above problems, the prior art urgently needs to be improved. Summary of the Invention

[0004] The present invention provides a BIM-based construction monitoring method for prefabricated buildings. By integrating the real-time data collected by intelligent sensors with the BIM model, the present invention ensures that the construction team can obtain visual information on the real state of the construction site in the BIM model. This enables construction workers to carry out construction more accurately and, with the assistance of augmented reality (AR) technology for inspection, promptly discover and correct deviations, thereby significantly improving construction accuracy and project quality.

[0005] The technical solution adopted by the present invention to solve the above technical problems is: A BIM-based construction monitoring method for prefabricated buildings, comprising the following steps: Step 1: Deploy intelligent sensors at the construction site; Step 2: Set up edge computing nodes to process sensor data in real time, conduct preliminary analysis, and generate real-time information during the construction process; Step 3: Establish a BIM model, integrate the real-time data collected by intelligent sensors with the BIM model, and ensure that the construction team can obtain visual information on the real state of the construction site in the BIM model; Step 4: Based on the real-time data and historical data, the construction management system constructs a construction progress prediction model through big data analysis, predicts and optimizes the construction progress, and provides construction adjustment suggestions; Step 5: When the intelligent sensors detect an abnormal situation, an early warning is automatically generated through the monitoring and dispatching platform and promptly transmitted to the on-site person in charge, and the dispatching and resource allocation of construction tasks are automatically adjusted; Step 6: Use augmented reality technology to assist in construction inspection, and compare the BIM model with the actual construction situation for inspection.

[0006] Furthermore, the intelligent sensors are deployed in the foundation and subgrade area, the main structure frame area, the concrete pouring area, the construction elevator and scaffolding area, the high-altitude operation area, and the underground pipeline and infrastructure area of the construction site. The intelligent sensors include displacement sensors, stress sensors, temperature sensors, humidity sensors, vibration sensors, and gas sensors.

[0007] Furthermore, in Step 2, an edge computing node is set up to process sensor data in real time, conduct preliminary analysis, and generate real-time information during the construction process, including: Step 2-1: Set up the hardware environment of the edge computing node; Step 2-2: Integrate the intelligent sensors with the edge computing node; Step 2-3: Real-time collect the raw data from each intelligent sensor; Step 2-4: Analyze and process the raw data; Step 2-5: Generate real-time information; Step 2-6: Synchronize and store the real-time data and information that have been analyzed and preprocessed.

[0008] Furthermore, the establishment of the BIM model in Step 3 includes: Step 3-1: Create the basic framework of the BIM model; Step 3-2: Build the data interface and integration architecture; Step 3-3: Integrate and update the real-time data; Step 3-4: Conduct multi-dimensional real-time data display and analysis.

[0009] Furthermore, the integration of the real-time data collected by the intelligent sensors with the BIM model in Step 3 includes: According to the positions of the intelligent sensors, correspond the coordinates of the geometric figures, so that the BIM model is associated with the intelligent sensor data; Combine the intelligent sensor data with the geometric figures of the BIM model to visualize the sensor values in the BIM model.

[0010] Further, the automatic adjustment of construction task scheduling and resource allocation in step 5 includes: the construction management platform receives abnormal alarm information from the edge computing node; according to the abnormal situation, it calls the construction progress prediction model for prediction and analyzes the impact of the abnormality on the construction progress; according to the prediction data, it uses a data-driven scheduling algorithm to optimize the scheduling plan; the resource allocation adjustment includes materials, equipment, and human resources, and according to the prediction data, it automatically adjusts the construction task scheduling and resource allocation; according to the adjusted scheduling plan, it issues instructions to the on-site construction personnel to ensure progress control in case of abnormalities.

[0011] Further, the use of augmented reality technology to assist construction inspection in step 6 includes: identifying the building space through computer vision algorithms to judge the difference between the construction completion degree and the preset value; according to the judgment result, marking the deviation area in real time; comparing the BIM model with the actual construction situation to output specific deviation information; visually associating the deviation information with the BIM model to guide the construction team to make corrections.

[0012] The advantages of the present invention are as follows: By integrating the real-time data collected by intelligent sensors with the BIM model, the present invention ensures that the construction team can obtain visual information on the real state of the construction site in the BIM model. This enables construction personnel to carry out construction more accurately, and through the assistance of augmented reality (AR) technology for inspection, deviations can be detected and corrected in a timely manner, thereby significantly improving construction accuracy and project quality and ensuring effective control of the construction progress. Specific embodiments

[0013] The technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0014] Embodiment 1: The present invention provides a BIM-based prefabricated building construction monitoring method, which is characterized by including the following steps: Step 1: Deploy intelligent sensors at the construction site; specifically, deploying intelligent sensors at the construction site is to ensure the safety, quality of the construction process, and real-time monitoring of the state of the building structure. The sensors can help capture changes in the construction environment and structural responses in real time, discover potential problems in a timely manner, and reduce accidents and potential engineering quality hazards. The following is a detailed description of the common key positions at the construction site and the types and functions of sensors that should be deployed: 1. Foundation and subgrade area Critical locations: Foundation slab and foundation beam: Especially in areas with unstable soil or soft soil foundations, the settlement, displacement, and stress state of the foundation are very important. Pile foundation and bored pile: As a key part of bearing the weight of the building, the stress and displacement of the pile need to be monitored.

[0015] Sensor types and functions: Displacement sensor: Monitor the settlement and horizontal displacement of the foundation and pile foundation. Stress sensor: Monitor the stress condition of the pile foundation or foundation to prevent excessive settlement or structural instability caused by overloading. Temperature and humidity sensor: Monitor the humidity and temperature of the soil to evaluate the soil stability and its possible impact on the foundation. Vibration sensor: During the foundation construction process, monitor the foundation displacement and settlement caused by vibration, especially in urban environments, to prevent the impact on surrounding buildings.

[0016] 2. Structural main frame area Critical locations: Connection points of floor slab, beam, and column: These places bear large loads and are easily affected by the external construction environment or later loads. Core tube area: Such as key locations in elevator shafts and stairwells, which bear important structural functions and need special attention. Large-span beams or high-rise structures in high-rise buildings: Monitoring these structures helps ensure their stability.

[0017] Sensor types and functions: Stress / strain sensor: Used to monitor the stress condition of components (such as beams, columns, and floor slabs) to prevent material overload or structural failure. Displacement sensor: Monitor the deformation or displacement of components to ensure that the components do not undergo excessive displacement or deformation. Vibration sensor: Monitor the impact of construction processes or external loads on the structure to avoid structural fatigue or damage caused by vibration.

[0018] 3. Concrete pouring area Critical locations: Concrete pouring area: Such as walls, floor slabs, columns, and foundations, especially when pouring large-volume concrete, temperature crack problems are likely to occur. Curing area after concrete pouring: These areas need to maintain appropriate humidity and temperature to ensure the curing effect of concrete.

[0019] Sensor types and functions: Temperature sensor: Monitor the temperature change after concrete pouring to avoid cracks caused by large temperature differences, especially during the construction of large-volume concrete.

[0020] Humidity sensor: Monitor the humidity of concrete to ensure that it does not crack during the curing process and that the cement can react fully. Stress / strain sensor: Detect the stress change during the hardening process of concrete to ensure that the concrete structure does not crack due to excessive stress.

[0021] 4. Construction elevator and scaffolding area Critical Locations: Installation Points for Construction Elevators and Suspended Baskets: These devices often carry a large number of construction workers and equipment. Overloading or improper installation may lead to safety accidents. Scaffold Support Points: The scaffold support system is an important safety area during construction. Especially in high-rise building construction, the stability of the scaffold is crucial.

[0022] Sensor Types and Functions: Displacement Sensors: Monitor the vertical displacement and deviation of construction elevators or scaffolds to prevent equipment tilting or collapse. Stress / Load Sensors: Used to monitor the stress conditions of hoisting equipment and scaffolds to ensure no overloading. Vibration Sensors: Detect the vibration of construction elevators or scaffolds to prevent accidents caused by unstable equipment or improper operation.

[0023] 5. High-Altitude Working Areas Critical Locations: Roofs and High-Altitude Working Platforms: High-altitude work often involves high risks. Therefore, it is necessary to monitor the safety of construction workers and the stability of the working platform. High-Rise Building Facade Construction Areas: Such as curtain wall installation and exterior wall painting, it is necessary to ensure stability, no vibration, or other external factor interferences during the construction process.

[0024] Sensor Types and Functions: Displacement Sensors: Used to monitor the vertical or horizontal displacement of roof platforms or high-altitude platforms to ensure the stability of the working area. Meteorological Sensors (wind speed, air pressure, temperature): Monitor external environmental conditions. Especially during high-altitude work, excessive wind speed may pose a threat to safety. Vibration Sensors: Monitor the vibration of high-altitude working platforms to avoid accidents caused by unstable construction equipment or personnel due to platform instability.

[0025] 6. Underground Pipeline and Infrastructure Areas Critical Locations: Underground Pipeline and Infrastructure Areas: Such as the laying and construction process of water, electricity, and gas underground pipelines. Especially when contacting the existing urban underground pipe network, it is necessary to monitor the state of the pipelines and the surrounding soil. Tunnel and Basement Areas: Monitor the soil stability during the excavation of tunnels or basements to prevent landslides or structural cracks.

[0026] Sensor Types and Functions: Stress / Strain Sensors: Monitor the deformation and stress state of underground pipelines and the surrounding soil to prevent pipeline rupture or soil slip. Displacement Sensors: Monitor the displacement of the soil or pipelines to ensure that underground operations do not affect the surrounding structures or other facilities. Vibration Sensors: Monitor the vibration during underground construction to avoid affecting adjacent buildings or underground facilities.

[0027] Sensor Types and Functions: Gas sensors: Monitor the concentrations of harmful gases (such as carbon monoxide and sulfur dioxide) to ensure no toxic gas leakage at the construction site. Noise sensors: Monitor the noise levels at the construction site to prevent exceeding the specified limits. Temperature and humidity sensors: Monitor the temperature and humidity conditions of the construction site environment to ensure suitable working conditions, especially in extreme climates. The key positions at the construction site need to be determined according to the characteristics of the specific project, construction environment, and project scale. The foundation, main structure, concrete pouring, construction elevator, and scaffolding positions are all key areas for deploying intelligent sensors. The deployment of sensors can help monitor the dynamic changes during the construction process, ensure construction safety and quality, and provide data support for later building maintenance and management. Through intelligent sensor technology, the construction site can real-time master various information on-site, improve construction efficiency, reduce safety risks, and ensure project quality.

[0028] Step 2: Set up edge computing nodes to process sensor data in real-time, conduct preliminary analysis, and generate real-time information during the construction process. Specifically, it includes: Step 2-1: Set up the hardware environment of the edge computing node; Step 2-1-1: Determine the required hardware configuration for the edge computing node, including computing units, storage devices, and network interfaces, to ensure the ability to process data streams from multiple sensors.

[0029] Step 2-1-2: Configure the power supply and stable network connection of the edge computing node to ensure that the device can operate 24 / 7 and data transmission is uninterrupted.

[0030] Step 2-1-3: Install the hardware required for the edge computing node, including CPU, memory, and GPU, and ensure that the system can carry high-frequency data processing tasks.

[0031] Step 2-2: Integrate sensors with the edge computing node; Step 2-2-1: Install sensors related to the construction site, including temperature, humidity, pressure, displacement, and vibration sensors, and ensure their correct connection to the edge computing node.

[0032] Step 2-2-2: Configure the data interface protocol (such as MQTT, Modbus, CAN bus) between the edge computing node and the sensors to ensure that sensor data can be transmitted to the computing node in real-time.

[0033] Step 2-2-3: Connect the communication mechanism between the sensors and the edge node to ensure the stability and real-time nature of data transmission.

[0034] Step 2-3: Real-time collect the raw data from each intelligent sensor; Step 2-3-1: Start the sensor data acquisition system, collect the raw data from each intelligent sensor in real time, and perform preliminary filtering and denoising.

[0035] Step 2-3-2: Preprocess the collected data, such as removing outliers, standardizing the data, and synchronizing timestamps, to ensure the validity and consistency of the data.

[0036] Step 2-3-3: Format the processed data as needed for subsequent analysis and storage.

[0037] Step 2-4: Analyze and process the raw data; Step 2-4-1: Run preliminary data analysis algorithms on the edge computing node to analyze and process the sensor data, and detect anomalies or potential risks during the construction process (such as excessive vibration, abnormal pressure).

[0038] Step 2-4-2: Evaluate whether the sensor data exceeds the normal range according to the set threshold rules and warning models, and generate warning information.

[0039] Step 2-4-3: Conduct real-time trend analysis on the construction data, evaluate the construction progress and resource usage, and generate a real-time information report during the construction process.

[0040] Step 2-5: Generate real-time information; Step 2-5-1: Generate real-time data information during the construction process on the edge computing node, such as the status of construction equipment, environmental monitoring data, and resource allocation, and update and store it in the system in real time.

[0041] Step 2-5-2: According to the preset warning rules, if the analysis results show abnormal situations (such as equipment failures, non-compliant construction environments), generate warning feedback and mark the abnormal events.

[0042] Step 2-5-3: Push the warning information to relevant personnel (such as on-site supervisors, dispatchers) in real time through the edge computing node to ensure timely response and decision-making.

[0043] Step 2-6: Synchronize and store the real-time data and information that have been analyzed and preprocessed; Step 2-6-1: Synchronize the real-time data and information that have been analyzed and preprocessed to the cloud or central server to ensure the integrity of data storage and subsequent analysis.

[0044] Step 2-6-2: Ensure a data backup mechanism for recovery in case of equipment failures or data loss.

[0045] Step 2-6-3: Send the real-time monitoring and early warning data to the cloud platform for further analysis and cross-regional management decisions.

[0046] Step 2-6-4: Receive feedback from on-site staff (such as repair and adjustment operations), and adjust the data processing and early warning rules through the edge computing node to optimize the early warning accuracy and response speed.

[0047] Step 2-6-5: Dynamically update the early warning threshold and risk prediction model according to the changes and real-time feedback on the construction site.

[0048] This Step 2 first requires setting up the hardware environment of the edge computing node, determining the required hardware configuration, including computing units, storage devices, and network interfaces. Configure the power supply and a stable network connection, and install the required hardware, such as CPUs, memory, and GPUs, to ensure that the system can carry high-frequency data processing tasks. Then, integrate the sensors with the edge computing node. Install sensors related to the construction site, including temperature, humidity, pressure, displacement, and vibration sensors, and ensure their correct connection to the edge computing node. Configure the data interface protocol between the edge computing node and the sensors, such as MQTT, Modbus, or CAN bus, to ensure that the sensor data can be transmitted to the computing node in real time. Next, collect the raw data from each intelligent sensor in real time. Start the sensor data acquisition system, collect the raw data in real time, and perform preliminary filtering and denoising. Preprocess the collected data, such as removing outliers, standardizing, and synchronizing timestamps, to ensure the validity and consistency of the data. Format the processed data as needed for subsequent analysis and storage. Run preliminary data analysis algorithms on the edge computing node to analyze and process the sensor data, detect anomalies or potential risks during the construction process, such as excessive vibration or abnormal pressure. Evaluate whether the sensor data exceeds the normal range according to the set threshold rules and early warning models, and generate early warning information. Conduct real-time trend analysis on the construction data, evaluate the construction progress and resource usage, and generate a real-time information report during the construction process. Generate real-time data information during the construction process on the edge computing node, such as the status of construction equipment, environmental monitoring data, and resource allocation, and update and store it in the system in real time. According to the preset early warning rules, if the analysis results show abnormal situations, such as equipment failures or non-compliant construction environments, generate early warning feedback and mark the abnormal events. Push the early warning information to relevant personnel, such as on-site supervisors or dispatchers, through the edge computing node in real time to ensure timely response and decision-making. Then synchronize the analyzed and preprocessed real-time data and information to the cloud or central server to ensure the integrity of data storage and subsequent analysis. Ensure the data backup mechanism for recovery in case of equipment failures or data loss. Send the real-time monitoring and early warning data to the cloud platform for further analysis and cross-regional management decisions.

[0049] Finally, optimize the processing strategy of the edge computing node according to on-site feedback. Upon receiving feedback from on-site staff, such as repair or adjustment operations, adjust the data processing and warning rules through the edge computing node to optimize the warning accuracy and response speed. Dynamically update the warning threshold and risk prediction model according to the changes and real-time feedback at the construction site.

[0050] By setting up edge computing nodes, the present invention can achieve real-time processing and analysis of sensor data. As the outpost of data processing, the edge computing node can quickly respond to data changes on-site and reduce the latency of data transmission to the cloud. This distributed computing architecture not only improves the efficiency of data processing but also ensures basic data analysis and warning functions in the case of unstable network connections.

[0051] The setting of edge computing nodes can also reduce the computing burden on the central server. By performing preliminary data filtering and analysis at the edge and only transmitting key information to the cloud, the bandwidth requirements and storage pressure of data transmission are greatly reduced. This hierarchical processing method enables the system to better handle the massive data generated by large-scale sensor networks. In addition, the real-time processing ability of edge computing nodes enables the system to more quickly identify and respond to abnormal situations at the construction site. Through preset rules and models, the edge node can detect potential safety hazards or quality problems in the first place and immediately generate warning information. This rapid response mechanism is of great significance for preventing construction accidents and ensuring construction quality.

[0052] In specific implementation, industrial-grade edge computing devices can be selected, such as Dell Edge Gateway 5000 series or Cisco IR1101 integrated service routers. These devices have powerful computing capabilities and rich interfaces, and can adapt to the complex environment of the construction site. For example, a Dell Edge Gateway 5100 can be configured, which has an Intel Atom processor, 4GB RAM and 32GB storage space, and can process data streams from more than 100 sensors simultaneously. At the software level, open-source edge computing frameworks such as Eclipse ioFog or Apache EdgeX Foundry can be used. These frameworks provide a flexible microservices architecture and can quickly deploy and update edge computing applications. For example, using Eclipse ioFog, a data preprocessing microservice can be written to perform preliminary filtering and anomaly detection on sensor data, and then transfer the processed data to the early warning analysis microservice. For the data transmission protocol, the lightweight MQTT protocol can be adopted. The publish / subscribe mode of the MQTT protocol is very suitable for the real-time transmission of sensor data. For example, an independent MQTT topic can be set for each type of sensor (such as temperature, humidity, vibration), and the edge computing node subscribes to these topics to receive sensor data in real time. In terms of setting early warning rules, methods based on thresholds and trend analysis can be adopted. For example, for the temperature monitoring of the concrete pouring area, the following rules can be set: if the temperature rises by more than 10°C within 15 minutes, or the temperature exceeds 65°C, a high-temperature early warning is triggered. Such rules can effectively prevent the thermal cracking problem of concrete.

[0053] Through the setting of such edge computing nodes and the real-time data processing method, the present invention can significantly improve the efficiency and accuracy of construction monitoring. Compared with the traditional centralized data processing method, the solution of the present invention can respond more quickly to the changes on the construction site, provide more timely early warning information, thereby effectively reducing construction risks and improving construction quality and efficiency.

[0054] Step 3: Establish a BIM model, integrate the real-time data collected by sensors with the BIM model to ensure that the construction team can obtain visual information on the real state of the construction site in the BIM model. Specifically, it includes: Step 3-1: Create the basic framework of the BIM model, including: creating a prefabricated building structure model using building information modeling tools; converting the BIM model into lightweight geometric graphics, where the lightweight geometric graphics specifically include: exporting two-dimensional and three-dimensional geometric graphic information of building components from the BIM model; mapping the geometric graphics into a three-dimensional model using a common file format. In the pre-construction phase, use BIM software (any one of Revit, Tekla, or Navisworks) to create a detailed digital model of the construction project, which contains information related to building structure, infrastructure, mechanical equipment, MEP (mechanical, electrical, and plumbing), and construction processes. The basic model construction includes all key parts and components of the building, including the foundation, floors, columns, beams, walls, and roof structural elements. Ensure the integrity of the geometric and spatial data of the model to lay a foundation for subsequent sensor data integration. According to the monitoring requirements of the construction site and the types of sensors deployed, identify the key positions in the BIM model, including the foundation, structural framework, and concrete pouring areas, and mark the sensor interfaces at these positions. Plan the data integration scheme for the sensors, including the data collection frequency, data types, and data formats, to ensure that real-time monitoring data can be connected to the BIM model.

[0055] The technical solution proposed by the present invention effectively solves the problems of large BIM model data volume and slow processing speed by converting the BIM model into lightweight geometric graphics. The lightweight geometric graphics retain the key geometric information of building components, while greatly reducing the data volume and improving the efficiency of data processing and visualization. Specifically, the technical solution of the present invention includes the following steps: First, use building information modeling tools to create an assembled building structure model. This step can use common BIM software, such as Revit, ArchiCAD or Tekla Structures, to create a three-dimensional model containing complete building information according to the building design drawings and relevant specifications. Next, convert the BIM model into lightweight geometric graphics. This step is the core of the present invention and specifically includes two sub-steps: First, export the two-dimensional and three-dimensional geometric graphic information of building components from the BIM model. In this process, it is necessary to extract the key geometric features of building components, such as outlines, dimensions and positions. For example, for a wall component, its planar outline and height information can be extracted; for a beam component, its cross-sectional shape and length information can be extracted. These geometric information are sufficient to express the basic form of the component, but the data volume is much smaller than the complete BIM model. Second, use a common file format to map the geometric graphics into a three-dimensional model. This step can use lightweight 3D file formats such as OBJ, FBX or glTF. These formats can effectively express three-dimensional geometric information, while having a small file size and a fast loading speed. By converting the extracted geometric information into these formats, the data volume can be greatly reduced while retaining the necessary spatial information. Through the above steps, the present invention realizes the lightweight processing of the BIM model. This lightweight geometric graphic model retains the basic form and spatial relationship of building components, while greatly reducing the data volume, thereby improving the efficiency of data processing and visualization. In practical applications, this lightweight geometric graphic model can be loaded and rendered more quickly, and is especially suitable for real-time display and interaction on mobile devices or web pages. For example, when using a tablet computer to view a building model at a construction site, the lightweight model can be loaded quickly and operated smoothly, improving the work efficiency of construction workers. In addition, the lightweight geometric graphic model can be more easily integrated with other systems. For example, when conducting construction monitoring, sensor data can be mapped to the lightweight model more quickly to achieve real-time visual monitoring. This integration not only improves the response speed of the system, but also reduces the hardware requirements, enabling the monitoring system to run on more devices.

[0056] As a preferred implementation manner, the present invention can adopt the following specific steps to realize the lightweight of the BIM model: 1. Use Revit software to create a BIM model of an assembled building, including all main components such as walls, beams, columns, and floors.

[0057] 2. Use the API or plug-ins of Revit to extract the key geometric information of each component. For example, for walls, extract their planar contour coordinates and height; for beams, extract their cross-sectional dimensions and axis coordinates.

[0058] 3. Convert the extracted geometric information into the OBJ format. The OBJ format is a simple 3D geometric description format that can effectively express the information of vertices, edges, and faces.

[0059] 4. Use the Three.js WebGL library to load the geometric data in the OBJ format into the Web environment to achieve online rendering and interaction of lightweight models.

[0060] 5. Add unique identifiers to each component in the lightweight model to maintain the association with the component information in the original BIM model.

[0061] In this way, the BIM model that may originally reach several hundred megabytes can be compressed to a few megabytes or even smaller, while retaining sufficient geometric information for visualization and spatial analysis.

[0062] Compared with directly using the complete BIM model, the lightweight method proposed by the present invention has significant advantages. First, the data processing speed is greatly improved, enabling faster model loading and rendering. Especially at the construction site with limited network conditions, this advantage is particularly obvious. Second, the lightweight model reduces the hardware requirements, allowing complex building models to run smoothly on ordinary mobile devices. Finally, the lightweight model is more easily integrated with other systems, such as real-time monitoring systems, thus improving the efficiency and real-time performance of the entire construction monitoring process.

[0063] Step 3-2: Build a data interface and integration architecture; Step 3-2-1: Select a data transmission protocol and standard: Determine the data transmission protocol required for the integration of sensor data and the BIM model. Specifically, the transmission protocol uses Modbus to ensure that sensors can transmit data to the BIM platform in real time. Select the CSV format to transmit sensor data to the integration platform of the BIM model for subsequent processing and visualization.

[0064] Step 3-2-2: Configure real-time data streams and integration interfaces: Configure an API interface between the BIM software and the sensor network so that the real-time data collected by the sensors can flow seamlessly into the BIM platform. Configure a real-time data synchronization interface between the BIM model and the data processing system (such as edge computing nodes, cloud analysis platforms) to ensure the real-time transmission and processing of sensor data.

[0065] Step 3-2-3: Data matching and mapping: Map the data of intelligent sensors to the corresponding positions in the BIM model. For example, create virtual nodes for each sensor in the BIM model, mark their actual positions, and ensure that the data is consistent with the actual building positions. Determine the relationship between sensor data and building component attributes to ensure that the BIM model can reflect the real-time changes in the building structure and environment through the data.

[0066] Step 3-3: Integrate and update the real-time data; Step 3-3-1: Data collection and preprocessing: During the construction process, continuously collect data through the deployed intelligent sensors, and preliminarily process and clean the data (denoise, remove anomalies) through the edge computing nodes. Transmit the preprocessed data to the BIM integration platform in real time to ensure data accuracy and timeliness.

[0067] Step 3-3-2: Dynamically update the BIM model: After real-time access to the intelligent sensor data, the BIM model will be dynamically updated to reflect the actual state of the construction site. By integrating the sensor data, the BIM model can display the real-time temperature, humidity, displacement, and stress information of each part during the construction process. For example, the settlement of the foundation, the stress of structural components, and the temperature information of concrete can be displayed in real time in the BIM model, enabling the construction team to quickly understand the changes in these key indicators.

[0068] Step 3-3-3: Display data visualization and dynamic feedback: Design a real-time monitoring interface on the BIM platform to display the distribution of different sensor data in the model in a graphical way, intuitively reflecting the state of the construction site. The real-time data of displacement sensors can be used to prompt construction personnel by means of color changes in the model (e.g., red indicates exceeding the warning value, and green indicates normal). The data of stress sensors can be displayed through the effect of 3D structural deformation (such as the stress concentration area of building components) to help the team discover structural problems. Compare the differences between the actual measurements and the preset standards, and display the warning information through the BIM model to ensure that construction personnel can take timely measures.

[0069] Step 3-4: Conduct multi-dimensional real-time data display and analysis; Step 3-4-1: Multi-dimensional Integration and Visualization: Combine sensor data with the BIM model to provide multi-dimensional displays: Spatial dimension: Display the geometric structure of the construction site through the BIM model, enabling a clear understanding of the sensor locations and the overall building layout. Temporal dimension: Correlate sensor data with the construction progress and view the changing trends of real-time data during the construction process through a dynamic timeline. Environmental and quality dimension: Combine sensor data with the construction environment (such as temperature, humidity) and structural health status (such as stress, displacement), and display the status of different construction stages in real time through the BIM model.

[0070] Step 3-4-2: Real-time Data Analysis and Anomaly Warning: Integrate the real-time data analysis function, and the system can automatically analyze construction risks and generate warnings based on the real-time monitoring data obtained by intelligent sensors and the BIM model. For example: When it is detected that the vibration in the construction area exceeds the standard, the BIM model will remind by color marking and prompt the surrounding buildings or structural components that may be affected. When the foundation settlement data exceeds the set threshold, the corresponding foundation part in the model will display a warning and prompt the construction personnel to conduct inspections.

[0071] Step 3-4-3: User Interaction and Operation: Provide an interactive interface for the on-site construction team, enabling the staff to view real-time data, adjust monitoring parameters, obtain warning prompts, and view the construction progress through the BIM platform. Support through virtual reality (VR) or augmented reality (AR) technology. Construction personnel can wear AR devices to directly view the construction status on-site and overlay the data and information in the BIM model in real time to help with better understanding and decision-making.

[0072] Through the BIM platform, multi-party collaborative work is achieved. The construction team, design team, and project management team can share construction data and progress information in real time, ensuring that all parties of the project can obtain the dynamic changes at the construction site in a timely manner. Ensure the seamless flow and sharing of data among teams, reduce information silos, and improve project management efficiency. All real-time monitoring data will be automatically synchronized to the cloud to ensure long-term data storage and retrospective analysis. If problems occur during the construction process, the team can view the data of a certain period at any time to analyze the root cause of the problem. The real-time sensor data integrated based on the BIM model forms a complete construction process archive. After the construction is completed, the full-life cycle management team of the project can use this data for later maintenance and optimization to ensure the long-term use safety of the building.

[0073] Specifically, when creating the basic framework of the BIM model, Revit, Tekla or Navisworks BIM software is used to create a detailed digital model of the construction project. This model contains information related to building structures, infrastructure, mechanical equipment, piping (MEP), and construction processes. The construction of the basic model includes all key components and elements of the building, such as foundations, floors, columns, beams, walls, and roof structural elements. Ensure the integrity of the geometric and spatial data of the model to lay the foundation for subsequent sensor data integration.

[0074] When building the data interface and integration architecture, select data transmission protocols and standards, such as Modbus, to ensure that sensors can transmit data to the BIM platform in real time. Select the CSV format to transmit sensor data to the integration platform of the BIM model for subsequent processing and visualization. Configure the real-time data stream and integration interface, and configure an API interface between the BIM software and the sensor network so that the real-time data collected by the sensors can flow seamlessly into the BIM platform. Perform data matching and mapping to map the data of intelligent sensors to the corresponding positions in the BIM model. When integrating and updating real-time data, continuously collect data through the deployed intelligent sensors, and preliminarily process and clean the data through edge computing nodes. Transmit the preprocessed data to the BIM integration platform in real time to ensure data accuracy and timeliness. Dynamically update the BIM model. After real-time access to the intelligent sensor data, the BIM model will be dynamically updated to reflect the actual status of the construction site. When performing multi-dimensional real-time data display and analysis, combine the sensor data with the BIM model to provide multi-dimensional display, including spatial dimension, time dimension, environment and quality dimension. Integrate the real-time data analysis function, and the system can automatically analyze construction risks and generate early warnings based on the real-time monitoring data obtained by intelligent sensors and the BIM model. Provide an interactive interface for the on-site construction team, enabling staff to view real-time data, adjust monitoring parameters, obtain early warning prompts, and view the construction progress through the BIM platform.

[0075] The technical solution of the present invention integrates the real-time data collected by sensors with the BIM model, realizing the visualization of the real state of the construction site. This integration method enables the construction team to intuitively understand the construction progress, quality, and safety status, thereby better conducting construction management and decision-making. For example, in a prefabricated building project, the construction team can view the installation status of each component in real time through the BIM model. When a precast component is installed, the relevant sensor data (such as position and stress condition) will be immediately reflected in the BIM model. If installation deviation or stress anomaly is detected, the system will immediately generate an early warning, and the construction personnel can take corrective measures in a timely manner. In addition, the technical solution of the present invention also supports virtual reality (VR) or augmented reality (AR) technology, enabling construction personnel to wear AR devices to directly view the construction status on site and overlay the data and information in the BIM model in real time, helping to better understand and make decisions. For example, when installing precast wall panels, construction personnel can see virtual installation guiding lines through AR devices to ensure installation accuracy. In this way, the technical solution of the present invention not only improves construction efficiency but also significantly reduces the possibility of construction errors and rework. At the same time, due to the ability to monitor various parameters during the construction process in real time, the construction quality and safety are also greatly improved. For example, during the concrete pouring process, by monitoring the temperature and humidity data in real time, the curing measures can be adjusted in a timely manner to ensure that the concrete reaches the best strength. Compared with traditional construction monitoring methods, the technical solution of the present invention has obvious advantages. Traditional methods often rely on manual inspections and regular reports, making it difficult to achieve real-time monitoring and rapid response. However, the present invention integrates sensor data with the BIM model, realizing all-round and real-time construction monitoring, greatly improving the efficiency and accuracy of construction management. In addition, the technical solution of the present invention also provides a valuable data foundation for subsequent building operation and maintenance. All real-time monitoring data will be automatically synchronized to the cloud to form a complete construction process archive. These data can not only be used for the analysis and optimization of the construction process but also provide important references for the whole life cycle management of the building.

[0076] Step 4: Based on real-time data and historical data, the construction management system constructs a construction progress prediction model through big data analysis to predict and optimize the construction progress and provide construction adjustment suggestions. Specifically, it includes: Constructing the construction progress prediction model to obtain real-time construction data from intelligent sensors and edge computing nodes, including but not limited to multi-dimensional data such as progress, quality, and safety. At the same time, collect historical project data, such as past construction progress, resource usage, weather conditions, etc. Then extract and transform the key features in the data, such as the reasons for construction delays, changes in work efficiency at different time periods, etc., to better train the prediction model; Select appropriate machine learning or statistical models (such as linear regression, time series analysis, random forest, neural network, etc.) according to the data characteristics and requirements; Use historical data as the training set to train the selected prediction model and adjust the model parameters to optimize its performance. Evaluate the accuracy of the model through cross-validation or other methods and make necessary adjustments to ensure that the model can effectively predict future construction progress.

[0077] Construction progress prediction and optimization: Short-term prediction: Based on the real-time data of the last three days or one week, predict the construction progress in the short term (such as within one week) in the future to help the team make daily or weekly work arrangements. Long-term prediction: Utilize more extensive historical data, combined with specific factors of the current project, to predict the expected completion time of the entire project, provide support for long-term planning, analyze which links may cause schedule delays, and take measures in advance to avoid problems. According to the prediction results, optimize the allocation of materials, equipment, and human resources to ensure that sufficient resources are available at the right time and place. When potential risks are detected, automatically adjust the scheduling plan of construction tasks, rearrange the priorities to reduce the possibility of delays. Set a series of predefined rules to automatically generate corresponding adjustment suggestions according to different warning levels, such as increasing the number of workers and changing the work order.

[0078] Step 5: When the intelligent sensor detects an abnormal situation, an early warning is automatically generated through the monitoring and dispatching platform and transmitted to the on-site person in charge in a timely manner, and the dispatching and resource allocation of the construction tasks are automatically adjusted. Specifically, it includes: the construction management platform receives the abnormal alarm information from the edge computing node; according to the abnormal situation, calls the construction progress prediction model for prediction and analyzes the impact of the abnormality on the construction progress; according to the prediction data, uses a data-driven scheduling algorithm to optimize the scheduling plan and allocate resources to ensure that the construction progress is not affected; the resource allocation adjustment includes materials, equipment and human resources, and according to the prediction data, automatically adjusts the dispatching and resource allocation of the construction tasks; according to the adjusted scheduling plan, issues instructions to the on-site construction personnel to ensure progress control under abnormal circumstances. Through the precise correspondence and visualization of the sensor data with the geometric figures of the BIM model, the present invention realizes more precise and real-time data integration. Thus, the construction team can intuitively obtain the real state information of the construction site in the BIM model, thereby better monitoring and managing the construction process.

[0079] When specifically implemented, it is first necessary to determine the specific positions of the sensors at the construction site. This can be achieved through GPS positioning or pre-planned installation positions. Then, convert this position information into the coordinate system in the BIM model. For example, if a three-dimensional Cartesian coordinate system is used, the actual positions of the sensors need to be converted into (x, y, z) coordinates.

[0080] Furthermore, the geometric figures in the BIM model contain the shape, size and position information of the building components. By matching the coordinates of the sensors with the coordinates of these geometric figures, the specific building components or areas corresponding to each sensor can be determined. This matching can be achieved through a spatial indexing algorithm, such as data structures like octree or R-tree, to improve the search efficiency. After completing the coordinate matching, the next step is to combine the data collected by the sensors with the geometric figures in the BIM model. This can be achieved by adding attribute fields to the geometric figures, and these attribute fields are used to store and update the sensor data. For example, for a temperature sensor, a "temperature" attribute can be added to the corresponding geometric figure and its value can be updated in real time. To visualize the sensor values in the BIM model, methods such as color coding or numerical annotation can be adopted. For example, according to the high and low temperature values, the building components can be rendered in different colors, such as blue for low temperature and red for high temperature. For a displacement sensor, the displacement situation can be visually displayed by changing the position or shape of the geometric figure.

[0081] As a preferred embodiment, the frequency of data update can be set, such as updating sensor data every 5 seconds. At the same time, a data buffering mechanism can be established to handle situations such as network latency or sensor failures, ensuring that the data displayed in the BIM model is always up-to-date and reliable. In addition, to improve the efficiency of data processing and visualization, a lightweight BIM model can be adopted. This can be achieved by simplifying geometric details, using LOD (Level of Detail) technology, or adopting a specialized lightweight format (such as glTF). The lightweight model can greatly improve the rendering speed and interactive performance while retaining the necessary information. In this way, the construction team can view various sensor data in real time in the BIM model, such as temperature, humidity, stress, displacement, etc. For example, during the concrete pouring process, the temperature distribution in different areas can be visually observed, and temperature differences that may cause cracks can be detected in a timely manner. For structural safety monitoring, the stress and displacement conditions of key nodes can be observed in real time, and measures can be taken immediately when the values exceed the preset thresholds. Compared with the prior art, the technical solution of the present invention has the following advantages: First, through precise coordinate matching, seamless integration of sensor data and the BIM model is achieved, improving the accuracy and reliability of the data. Second, through visualization technology, complex sensor data becomes intuitive and easy to understand, facilitating quick decision-making and problem identification. Third, lightweight processing ensures the real-time performance and interactivity of the construction management system, and good performance can be maintained even in large-scale projects. Finally, this integration method provides a solid foundation for subsequent data analysis and intelligent decision-making, which is conducive to further improving the intelligent level of construction management.

[0082] Step 6: Use augmented reality technology to assist in construction inspection, and compare the BIM model with the actual construction situation. Specifically, it includes: identifying the building space through computer vision algorithms, and judging the difference between the construction completion degree and the preset value; according to the judgment result, marking the deviation area in real time; according to the comparison between the BIM model and the actual construction situation, outputting specific deviation information; visually associating the deviation information with the BIM model to guide the construction team to make corrections. The solution of the present invention using augmented reality technology to assist in construction inspection first identifies the building space through computer vision algorithms. This step can be achieved in various ways. For example, deep learning models such as convolutional neural networks (CNNs) or region-based convolutional neural networks (R-CNNs) can be used to identify the various elements of the building space. Another method can also use structured light scanning technology, by projecting a specific pattern of light and analyzing its reflection to reconstruct the 3D space. After the identification is completed, the construction management system will judge the difference between the construction completion degree and the preset value. This step can be achieved by comparing the actual construction status with the preset status in the BIM model. Specifically, image registration technology can be used to align the actual construction image with the BIM model, and then the difference can be identified through pixel-level comparison. Another method is to use feature matching algorithms such as SIFT or SURF to identify key points and compare their positions and features.

[0083] According to the judgment result, the construction management system will mark the deviation area in real time. This can be achieved through augmented reality technology. For example, AR development frameworks such as ARKit or ARCore can be used to overlay virtual marks on the actual construction scene. The marks can use different colors or shapes to represent different degrees of deviation. For example, green indicates compliance with the standard, yellow indicates a slight deviation, and red indicates a serious deviation. The construction management system will output specific deviation information according to the comparison between the BIM model and the actual construction situation. This step can be achieved through data analysis algorithms. For example, statistical methods can be used to calculate indicators such as the mean and standard deviation of the deviation, or machine learning algorithms such as support vector machines (SVMs) can be used to classify different types of deviations.

[0084] Finally, the construction management system visually associates the deviation information with the BIM model to guide the construction team to make corrections. This can be achieved through 3D visualization technology, such as using graphics engines like WebGL or Unity to display the deviation information on the BIM model in the form of graphics, colors, or animations. The construction management system can also generate a detailed correction suggestion report, including specific correction steps and required resources. By adopting augmented reality technology to assist construction inspection, the present invention can significantly improve the efficiency and accuracy of construction inspection. The construction team can visually see the construction deviations in real time, quickly locate the problem areas, and make corrections in a timely manner. This not only reduces the time and errors of manual inspection but also ensures that the construction quality meets the design requirements. In addition, by combining with the BIM model, the present invention can also provide a more comprehensive and accurate construction progress and quality assessment, helping the project management team make more informed decisions.

[0085] As a specific embodiment, the present invention can be applied to a 10-story prefabricated building project. The construction team is equipped with intelligent helmets or tablet devices with AR functions. These devices are equipped with high-definition cameras and depth sensors, capable of capturing real-time images and 3D information of the construction site. The system uses the YOLOv5 algorithm for real-time object detection, with an identification rate of over 95%. For the judgment of the construction completion degree, the system adopts a deep learning model based on ResNet50, trained with a large amount of labeled data, and the judgment accuracy can reach 90%.

[0086] In practical applications, when construction workers wear AR devices and enter the construction site, the BIM model of the area will be automatically loaded. For example, when inspecting the installation of wall panels on the 5th floor, the AR device will display the virtual model of this floor superimposed on the actual scene. The system analyzes the images captured by the camera in real time. If it is found that the position deviation of the wall panel exceeds the set threshold (such as 10 mm), it will be marked with a red contour in the AR view. At the same time, the system will calculate the specific deviation value, such as "15 mm northward deviation", and display it in the AR interface. All inspection results will be synchronized to the BIM model of the project in real time. The project manager can view the overall construction quality status through the central console, and the system will automatically generate a quality report, including information such as problem type statistics and severity distribution. These data can be superimposed on the BIM model in the form of a heat map to visually display the quality status of the entire building.

[0087] In this way, the construction team can timely detect and correct deviations during the construction process, greatly reducing the possibility of rework. At the same time, this real-time and visual inspection method also enhances the quality awareness of construction workers and promotes the improvement of the overall construction quality. The present invention realizes automated, precise and visual construction inspection by combining computer vision, augmented reality and BIM technology. This not only greatly improves the inspection efficiency, reduces human errors, but also provides detailed deviation information in real time to help the construction team make quick adjustments. In addition, the data acquisition and analysis capabilities of the present invention also provide valuable data support for subsequent quality management and optimization, contributing to the continuous improvement of construction techniques and management processes.

[0088] The working process of the present invention is described as follows: First, deploy an intelligent sensor network at the construction site. The intelligent sensors include displacement sensors, stress sensors, temperature sensors, humidity sensors, vibration sensors and gas sensors. The sensors are installed at key positions on the construction site, such as the foundation and subgrade area, the main structure framework area, and the concrete pouring area. These sensors continuously collect various data on the construction site, such as structural deformation, temperature and humidity changes, and vibration conditions. Then, set up edge computing nodes. These nodes are embedded systems or small servers deployed near the construction site. The edge computing nodes receive the data from the intelligent sensors in real time and perform preliminary processing and analysis. This local data processing greatly reduces data transmission latency. Next, establish a BIM model and integrate it with the real-time data. The BIM model is a building information model created using professional software (such as Revit or Tekla), which contains the geometric information, spatial relationships, geographical information and the attributes of building components of the building. The real-time data processed by the edge computing nodes is transmitted to the BIM platform and associated with the corresponding building components or positions. This integration enables the construction team to intuitively view the real-time status of the construction site in the BIM model. The construction management system constructs a construction progress prediction model based on real-time data and historical data using big data analysis techniques. This model takes into account various factors, such as weather conditions, resource availability, and construction difficulty, and can accurately predict the construction progress and provide optimization suggestions.

[0089] When the construction management system detects abnormal situations, such as excessive structural stress or abnormal environmental parameters, the monitoring and dispatching platform will automatically generate warning messages. These messages are promptly transmitted to the on-site person in charge, and at the same time, the construction management system will automatically adjust the scheduling of construction tasks and resource allocation to cope with the abnormal situations. Augmented reality technology is used to assist construction inspection. Construction workers can overlay the BIM model onto the actual construction scene through AR devices (such as smart glasses or tablets) to intuitively compare the differences between the design and the actual situation, ensuring construction accuracy and quality.

[0090] Finally, the construction management system monitors the noise, vibration, and air quality generated during the construction process in real time. Based on this data, the construction management system can dynamically adjust construction parameters, such as adjusting the operation mode of construction equipment or initiating dust suppression measures, to control environmental impacts. The system regularly summarizes and analyzes all the construction data collected, generating comprehensive reports on construction progress, quality, safety, and the environment. These reports provide the management team with a comprehensive view of the project status, supporting them in audits and decision-making. As a preferred implementation, the present invention can be applied in a large-scale prefabricated housing project. The project includes 10 residential buildings with 18 floors each, and the total construction area is approximately 100,000 square meters. First, approximately 500 intelligent sensors are deployed at the construction site, including 100 displacement sensors, 100 stress sensors, 100 temperature and humidity sensors, 100 vibration sensors, and 100 gas sensors. These sensors are installed at key locations, such as the foundation, main structure, and connections of prefabricated components. 10 edge computing nodes are set up at the construction site, and each node is equipped with a quad-core processor, 8GB of RAM, and 256GB of SSD storage. These nodes are connected to the sensors and the central server through a 5G network and can process the data from 50 sensors in real time. A detailed BIM model is created using Revit software, which includes the geometric information, material properties, and construction sequence of the building. Through a custom API, the real-time integration of sensor data and the BIM model is achieved. The construction management system uses a deep learning model based on LSTM (Long Short-Term Memory Network) for construction progress prediction. This model takes into account historical construction data, weather forecasts, and resource availability factors, and the prediction accuracy reaches over 90%. The system is equipped with 5 AR devices (Microsoft HoloLens 2) for construction inspections. Inspectors can overlay the BIM model onto the actual construction scene through these devices to achieve millimeter-level accuracy comparison.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring construction of prefabricated buildings based on BIM, characterized in that: The following steps are involved: Step 1: Deploy smart sensors at the construction site; Step 2: Set up edge computing nodes to process sensor data in real time, perform preliminary analysis, and generate real-time information during the construction process; Step 3: Establish a BIM model and integrate the real-time data collected by smart sensors with the BIM model to ensure that the construction team can obtain visual information on the real status of the construction site in the BIM model; Step 4: The construction management system builds a construction progress prediction model based on real-time data and historical data through big data analysis, predicts and optimizes the construction progress, and provides construction adjustment suggestions; Step 5: When the intelligent sensor detects an abnormal situation, an early warning is automatically generated through the monitoring and scheduling platform and promptly transmitted to the person in charge of the site, and the scheduling and resource allocation of the construction task are automatically adjusted; Step 6: Use augmented reality technology to assist in construction inspection and compare the BIM model with the actual construction situation.

2. A method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: The smart sensors are deployed in the foundation and subgrade areas, main structure frame areas, concrete pouring areas, construction elevators and scaffolding areas, aerial work areas, underground pipelines and infrastructure areas of the construction site. The smart sensors include displacement sensors, stress sensors, temperature sensors, humidity sensors, vibration sensors and gas sensors.

3. The method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: In step 2, edge computing nodes are set up to process sensor data in real time, perform preliminary analysis, and generate real-time information during the construction process, including: Step 2-1: Set up the edge computing node hardware environment; Step 2-2: Integrate smart sensors with edge computing nodes; Step 2-3: Collect raw data from each smart sensor in real time; Step 2-4: Analyze and process the raw data; Step 2-5: Generate real-time information; Step 2-6: Synchronize and store the analyzed and pre-processed real-time data and information.

4. The method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: The step 3 of establishing the BIM model includes: Step 3-1: Create the basic framework of the BIM model; Step 3-2: Build data interface and integration architecture; Step 3-3: Integrate and update real-time data; Step 3-4: Perform multi-dimensional real-time data display and analysis.

5. The method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: In step 3, the real-time data collected by the smart sensor is integrated with the BIM model, including: according to the position of the smart sensor, the coordinates of the geometric figure correspond to it, so that the BIM model is associated with the smart sensor data; the smart sensor data is combined with the geometric figure of the BIM model, and the sensor value is visualized in the BIM model.

6. The method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: The automatic adjustment of the scheduling and resource allocation of construction tasks in step 5 includes: the construction management platform receives abnormal alarm information from the edge computing node; based on the abnormal situation, calls the construction progress prediction model to make a prediction and analyzes the impact of the abnormality on the construction progress; based on the predicted data, optimizes the scheduling plan using a data-driven scheduling algorithm; resource allocation adjustment includes materials, equipment and human resources, and automatically adjusts the scheduling and resource allocation of construction tasks based on the predicted data; based on the adjusted scheduling plan, issues instructions to on-site construction personnel to ensure progress control under abnormal circumstances.

7. The method for monitoring construction of assembled buildings based on BIM according to claim 1, characterized in that: The use of augmented reality technology to assist construction inspection in step 6 includes: identifying the building space through a computer vision algorithm to determine the difference between the construction completion degree and the preset value; marking the deviation area in real time based on the judgment result; outputting specific deviation information based on the comparison between the BIM model and the actual construction situation; visually associating the deviation information with the BIM model to guide the construction team to make corrections.