Real estate operation engineering construction progress intelligent supervision system based on digital twinning

Abstract

The invention provides a real estate operation engineering construction progress intelligent supervision system based on digital twinning, which belongs to the technical field of engineering construction progress supervision and comprises a data acquisition unit, a data identification unit, a data twinning unit, a progress identification unit, a reason analysis unit, a progress prediction unit and a visual supervision and management unit. According to the invention, the progress risk point can be predicted 3-7 days in advance, the project period deviation is reduced by 37% in actual measurement, the construction cost is reduced by millions of millions, a manager can supervise the progress of the construction process and non-standard behaviors in the construction process in real time, real-time remote supervision is realized, and the manager can make a decision in advance by predicting the progress, so that the construction site construction can be better managed.

Description

Technical Field

[0001] This invention relates to the field of engineering construction progress monitoring technology, and in particular to an intelligent monitoring system for the construction progress of real estate operation projects based on digital twins. Background Technology

[0002] Traditional engineering construction progress relies primarily on manual monitoring, which has the following drawbacks: 1. Information fragmentation and inefficient collaboration: Design drawings, schedules, and site data are scattered across different systems (such as BIM, ERP, and site logs), forming "data silos" and causing delays in the transmission of change information. According to industry statistics, poor information collaboration leads to a change rate as high as 15-25%, with rework costs exceeding 10% of the total budget. 2. Uncontrolled progress and delayed risk management: Traditional Gantt chart progress management relies on manual entry, with actual progress deviations being discovered on average 7-15 days later, resulting in a project delay rate exceeding 20%. Risk response is passive; for example, hidden defects (pipeline misalignment) often surface during the acceptance phase, increasing single rectification costs by 30%. 3. Quality relies on human experience: Inspections depend on the subjective judgment of supervisors, resulting in a missed inspection rate exceeding 40%; key parameters such as concrete strength and steel structure welding lack real-time monitoring. 4. Difficulty in controlling safety risks: High-risk scenarios such as high-altitude operations and deep foundation pits rely on surveillance cameras and manual monitoring, with a safety hazard identification rate of less than 60%, and an accident rate accounting for 3% of the total project cost. Therefore, it is necessary to design an intelligent monitoring system for the construction progress of real estate operation projects based on digital twins to address the above shortcomings. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent monitoring system for the construction progress of real estate operation projects based on digital twins, thereby solving the technical problems mentioned in the background art.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] A digital twin-based intelligent monitoring system for the construction progress of real estate operation projects includes a data acquisition unit, a data identification unit, a data twin unit, a progress identification unit, a cause analysis unit, a progress prediction unit, and a visual supervision and management unit. The data acquisition unit is connected to the data identification unit, the data identification unit is connected to the progress identification unit via the data twin unit, the progress identification unit is connected to both the cause analysis unit and the progress prediction unit, the progress prediction unit is connected to the visual supervision and management unit, and the cause analysis unit is connected to both the data acquisition unit and the visual supervision and management unit.

[0006] The data acquisition unit is used to capture construction site footage via drones, collect real-time video data using cameras, and use sensors to collect real-time data on the working status of cranes. It also identifies material movement in real-time using tags attached to materials. The data recognition unit uses point cloud error analysis to identify overall site changes, analyze concrete pouring volume, identify worker density and movements, and analyze material location and transformation data. The data twin unit constructs a 3D site model, incorporates environmental data, builds a construction lifecycle map, constructs a data management library, and maps and generates data. The progress recognition unit uses a progress recognition neural network to identify and output site progress. If progress is slower than a set value, the cause analysis unit analyzes and identifies the reasons for the slow progress, outputting the reasons to the visualization supervision and management unit and notifying the relevant construction departments through the data acquisition unit. The progress prediction unit predicts the construction progress for a future period, providing managers with advanced decision-making support. The visualization supervision and management unit allows managers to view the construction progress in real-time for timely management and decision-making.

[0007] Furthermore, the data acquisition unit includes a drone horizontal imaging module, a crane sensor group module, a material label recognition module, and a camera module. The drone horizontal imaging module is used to collect video data of the entire construction site from above by using a camera mounted on a drone. The crane sensor group module is used to sense the operating status data of the crane and the data of the materials being lifted in real time. The material label recognition module is installed inside the building materials in the unit and senses the movement route of the building materials in real time to determine whether they have left the construction site. The camera module is an AI camera installed on the construction site to collect video data of the construction process in real time.

[0008] Furthermore, the data recognition unit includes a point cloud differential comparison recognition module, a material conversion quantity recognition module, a concrete pouring quantity recognition module, and a worker density and action recognition module. The point cloud differential comparison recognition module is used to identify the overall change data of the construction site through point cloud differential comparison. The material conversion quantity recognition module is used to identify the speed of material use and then compare it with the construction progress to determine whether the construction is being done shoddy. The concrete pouring quantity recognition module is used to identify the concrete pouring quantity in real time and judge the progress of the process based on the construction quantity and overall changes. The worker density and action recognition module is used to identify the number of workers on the construction site and to identify the speed and standard of workers' actions and whether there are any actions with safety hazards based on the action recognition algorithm.

[0009] Furthermore, the data twin unit includes a 3D model construction module, an environmental data input module, a digital masterline module, and a twin library management module. The 3D model construction module is used to construct 3D data of the construction site based on design drawings. The environmental data input module is used to input collected environmental data in real time, with environmental data at each point in time corresponding to construction progress data. The digital masterline module is used to generate a full lifecycle data map of people, equipment, materials, regulations, and environmental protection during the construction process. The twin library management module is used to generate mapping data based on environmental data, 3D data, and lifecycle data maps.

[0010] Furthermore, the progress identification unit includes a progress identification network module and a progress transformation output module. The progress identification network module is used to generate construction progress information based on the data from the data acquisition unit, the data identification unit, and the data twin unit. The progress transformation output module is used to determine whether the construction progress is slower than the set construction progress. If it is slower, the cause analysis unit analyzes the reasons for the slow construction and then feeds back the reasons to the managers and construction department.

[0011] Furthermore, the progress prediction unit includes a meteorological and raw material data input module, a process map construction module, and a time sequence recognition network module. The meteorological and raw material data input module is used to obtain weather forecast data for the next few days. The process map construction module is used to generate a construction sequence map and precautions for the construction site based on the nature of the construction site. The time sequence recognition network module is used to predict the progress data of the construction site for the next few days based on environmental data, material arrival data, and current construction progress data, and generate a 3D model of the construction site for the site manager to view.

[0012] Furthermore, the cause analysis unit includes an equipment operation phase comparison module, a worker action phase video recognition module, and an environment recognition comparison module. The equipment operation phase comparison module compares the operating speed of the equipment by collecting video data or sensor data over a fixed period of time. By comparing the equipment operating speed with the set project progress, it determines whether the cause is equipment operation. The worker action phase video recognition module compares the identified worker actions and sequence with baseline actions to determine whether the cause is worker-related. The environment recognition comparison module identifies whether the cause is weather-related or environmental factors affecting construction.

[0013] The present invention, by adopting the above-described technical solution, has the following beneficial effects:

[0014] This invention can predict progress risk points 3-7 days in advance, and actual tests have shown that it reduces schedule deviations by 37% and reduces rush work costs by millions. Managers can monitor the progress of the construction process and any non-standard behaviors in real time, and conduct remote monitoring in real time. At the same time, by predicting the progress, managers can make decisions in advance and better manage the construction site. Attached Figure Description

[0015] Figure 1 This is a system unit block diagram of the present invention;

[0016] Figure 2 This is a block diagram of the data acquisition unit module of the present invention;

[0017] Figure 3 This is a block diagram of the data recognition unit module of the present invention;

[0018] Figure 4 This is a block diagram of the data twin unit module of the present invention;

[0019] Figure 5 This is a block diagram of the progress recognition unit module of the present invention;

[0020] Figure 6 This is a block diagram of the degree prediction unit module of the present invention;

[0021] Figure 7 This is a block diagram of the cause analysis unit module of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many details listed in the specification are merely to provide the reader with a thorough understanding of one or more aspects of the present invention, and these aspects of the invention can be implemented even without these specific details.

[0023] like Figure 1 As shown, a digital twin-based intelligent monitoring system for the construction progress of real estate operation projects includes a data acquisition unit, a data recognition unit, a data twin unit, a progress recognition unit, a cause analysis unit, a progress prediction unit, and a visual supervision and management unit. The data acquisition unit is connected to the data recognition unit, the data recognition unit is connected to the progress recognition unit via the data twin unit, the progress recognition unit is connected to both the cause analysis unit and the progress prediction unit, the progress prediction unit is connected to the visual supervision and management unit, and the cause analysis unit is connected to both the data acquisition unit and the visual supervision and management unit. A spatiotemporal encoder is developed to uniformly map discrete data streams into 4D spatiotemporal coordinates (x, y, z, t), constructing a three-dimensional model that follows the data changes over time.

[0024] The data acquisition unit is used to capture construction site footage via drones, collect real-time video data using cameras, and use sensors to collect real-time data on the working status of cranes. It also identifies material movement in real-time using tags attached to materials. The data recognition unit uses point cloud error analysis to identify overall site changes, analyze concrete pouring volume, identify worker density and movements, and analyze material location and transformation data. The data twin unit constructs a 3D site model, incorporates environmental data, builds a construction lifecycle map, constructs a data management library, and maps and generates data. The progress recognition unit uses a progress recognition neural network to identify and output site progress. If progress is slower than a set value, the cause analysis unit analyzes and identifies the reasons for the slow progress, outputting the reasons to the visualization supervision and management unit and notifying the relevant construction departments through the data acquisition unit. The progress prediction unit predicts the construction progress for a future period, providing managers with advanced decision-making support. The visualization supervision and management unit allows managers to view the construction progress in real-time for timely management and decision-making.

[0025] In embodiments of the present invention, such as Figure 2 As shown, the data acquisition unit includes a drone horizontal imaging module, a crane sensor group module, a material label recognition module, and a camera module. The drone horizontal imaging module is used to collect video data of the entire construction site from above by using a camera mounted on a drone. The crane sensor group module is used to sense the operating status data of the crane and the data of the materials being lifted in real time. The material label recognition module is installed inside the building materials in the unit and senses the movement route of the building materials in real time to determine whether they have left the construction site. The camera module is an AI camera installed on the construction site to collect video data of the construction process in real time.

[0026] In embodiments of the present invention, such as Figure 3 As shown, the data recognition unit includes a point cloud differential comparison recognition module, a material conversion quantity recognition module, a concrete pouring quantity recognition module, and a worker density and action recognition module. The point cloud differential comparison recognition module is used to identify the overall change data of the construction site through point cloud differential comparison. The material conversion quantity recognition module is used to identify the speed of material usage and then compare it with the construction progress to determine whether the construction is being done shoddy. The concrete pouring quantity recognition module is used to identify the concrete pouring quantity in real time and judge the progress of the process based on the construction quantity and overall changes. The worker density and action recognition module is used to identify the number of workers on the construction site and to identify the speed and standard of workers' actions based on the action recognition algorithm, and whether there are any actions with safety hazards.

[0027] In embodiments of the present invention, such as Figure 4As shown, the data twin unit includes a 3D model building module, an environmental data input module, a digital master module, and a twin library management module. The 3D model building module is used to build 3D data of the construction site according to the design drawings. The environmental data input module is used to input the collected environmental data in real time, and the environmental data at each time point corresponds to the construction progress data. The digital master module is used to generate a full life cycle data map of people, equipment, materials, regulations, and environmental protection in the construction process. The twin library management module is used to generate mapping data based on environmental data, 3D data, and life cycle data map.

[0028] In embodiments of the present invention, such as Figure 5 As shown, the progress identification unit includes a progress identification network module and a progress transformation output module. The progress identification network module generates construction progress information based on data from the data acquisition unit, data identification unit, and data twin unit. The progress transformation output module determines whether the construction progress is slower than the set construction progress. If it is, the cause analysis unit analyzes the reasons for the slow construction, and then the reasons are fed back to the managers and construction department. The YOLOv7 improved model identifies the main construction elements (such as the amount of rebar binding and the progress of formwork erection). Based on the reinforcement learning algorithm, a construction strength coefficient and an environmental adaptability coefficient are constructed to dynamically evaluate the efficiency of resource input and environmental interference factors, and predict the progress deviation for the next 7 days.

[0029] In embodiments of the present invention, such as Figure 6 As shown, the progress prediction unit includes a meteorological and raw material data input module, a process map construction module, and a time-series recognition network module. The meteorological and raw material data input module is used to obtain weather forecast data for the next few days. The process map construction module is used to generate a construction sequence map and precautions based on the nature of the construction site. The time-series recognition network module is used to predict the progress data of the construction site for the next few days based on environmental data, material arrival data, and current construction progress data, and generate a 3D model of the construction site for the site manager to view. It automatically generates digital medical records for facilities (such as the location of hidden engineering sensor embedding points) and reverse-optimizes construction standards (e.g., frequent repairs to a shop → tracing defects in the wall masonry process).

[0030] In embodiments of the present invention, such as Figure 7 As shown, the cause analysis unit includes an equipment operation phase comparison module, a worker action phase video recognition module, and an environment recognition comparison module. The equipment operation phase comparison module compares the operating speed of the equipment by collecting video data or sensor data over a fixed period of time. By comparing the equipment operating speed with the set project progress, it determines whether the cause is equipment operation. The worker action phase video recognition module compares the identified worker actions and sequence with the baseline actions to determine whether the cause is worker-related. The environment recognition comparison module identifies whether the cause is weather-related or environmental factors affecting construction.

[0031] Application examples:

[0032] In a commercial complex project, the installation sequence of the curtain wall was rearranged by algorithm, which shortened the construction period by 37 days, provided an early warning of steel structure welding quality risks 14 days in advance, avoided rework losses of 12 million yuan, improved progress supervision efficiency by 40%, and reduced equipment maintenance costs by 28% (by utilizing the sensor network buried during the construction period).

[0033] Matters not covered in this invention are common knowledge.

[0034] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A digital twin-based intelligent monitoring system for the construction progress of real estate operation projects, characterized in that: It includes a data acquisition unit, a data identification unit, a data twin unit, a progress identification unit, a cause analysis unit, a progress prediction unit, and a visual supervision and management unit. The data acquisition unit is connected to the data identification unit. The data identification unit is connected to the progress identification unit via the data twin unit. The progress identification unit is connected to both the cause analysis unit and the progress prediction unit. The progress prediction unit is connected to the visual supervision and management unit. The cause analysis unit is connected to both the data acquisition unit and the visual supervision and management unit. The data acquisition unit is used to capture construction site footage via drones, collect real-time video data using cameras, and use sensors to collect real-time data on the working status of cranes. It also identifies material movement in real-time using tags attached to materials. The data recognition unit uses point cloud error analysis to identify overall site changes, analyze concrete pouring volume, identify worker density and movements, and analyze material location and transformation data. The data twin unit constructs a 3D site model, incorporates environmental data, builds a construction lifecycle map, constructs a data management library, and maps and generates data. The progress recognition unit uses a progress recognition neural network to identify and output site progress. If progress is slower than a set value, the cause analysis unit analyzes and identifies the reasons for the slow progress, outputting the reasons to the visualization supervision and management unit and notifying the relevant construction departments through the data acquisition unit. The progress prediction unit predicts the construction progress for a future period, providing managers with advanced decision-making support. The visualization supervision and management unit allows managers to view the construction progress in real-time for timely management and decision-making.

2. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The data acquisition unit includes a drone horizontal imaging module, a crane sensor group module, a material label recognition module, and a camera module. The drone horizontal imaging module is used to collect video data of the entire construction site from above by using a drone equipped with a camera. The crane sensor group module is used to sense the operating status data of the crane and the data of the materials being lifted in real time. The material label recognition module is installed inside the building materials in the unit and senses the movement route of the building materials in real time to determine whether they have left the construction site. The camera module is an AI camera installed on the construction site to collect video data of the construction process in real time.

3. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The data recognition unit includes a point cloud differential comparison recognition module, a material conversion quantity recognition module, a concrete pouring quantity recognition module, and a worker density and action recognition module. The point cloud differential comparison recognition module is used to identify the overall change data of the construction site through point cloud differential comparison. The material conversion quantity recognition module is used to identify the speed of material usage and then compare it with the construction progress to determine whether the construction is cutting corners. The concrete pouring quantity recognition module is used to identify the concrete pouring quantity in real time and judge the progress of the process based on the construction quantity and overall changes. The worker density and action recognition module is used to identify the number of workers on the construction site and to identify the speed and standard of workers' actions and whether there are any actions with safety hazards based on the action recognition algorithm.

4. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The data twin unit includes a 3D model building module, an environmental data input module, a digital masterline module, and a twin library management module. The 3D model building module is used to build 3D data of the construction site based on design drawings. The environmental data input module is used to input collected environmental data in real time, with environmental data at each point in time corresponding to construction progress data. The digital masterline module is used to generate a full life cycle data map of people, equipment, materials, regulations, and environmental protection during the construction process. The twin library management module is used to generate mapping data based on environmental data, 3D data, and life cycle data maps.

5. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The progress identification unit includes a progress identification network module and a progress transformation output module. The progress identification network module is used to generate construction progress information based on the data from the data acquisition unit, the data identification unit, and the data twin unit. The progress transformation output module is used to determine whether the construction progress is slower than the set construction progress. If it is slower, the cause analysis unit analyzes the reasons for the slow construction and then feeds back the reasons to the managers and construction department.

6. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The progress prediction unit includes a meteorological and raw material data input module, a process map construction module, and a time sequence recognition network module. The meteorological and raw material data input module is used to obtain weather forecast data for the next few days. The process map construction module is used to generate a construction sequence map and precautions for the construction site based on the nature of the construction site. The time sequence recognition network module is used to predict the progress data of the construction site for the next few days based on environmental data, material arrival data, and current construction progress data, and generate a 3D model of the construction site for the construction manager to view.

7. The intelligent monitoring system for construction progress of real estate operation projects based on digital twins according to claim 1, characterized in that: The cause analysis unit includes an equipment operation phase comparison module, a worker action phase video recognition module, and an environment recognition comparison module. The equipment operation phase comparison module compares the operating speed of the equipment by collecting video data or sensor data over a fixed period of time. By comparing the equipment operating speed with the set project progress, it determines whether the cause is equipment operation. The worker action phase video recognition module compares the identified worker actions and sequence with baseline actions to determine whether the cause is worker-related. The environment recognition comparison module identifies whether the cause is weather-related or environmental factors affecting construction.

Images