Project progress, quality and safety collaborative management and control system and method based on BIM and Internet of Things

Abstract

The invention discloses a project progress, quality and safety collaborative management and control system and method based on BIM and Internet of Things, and belongs to the technical field of constructional engineering informatization management. In order to improve engineering management efficiency and reliability, the system comprises a data acquisition layer, a data processing layer, an application layer and a security module. The data acquisition layer is connected with the data processing layer, the data processing layer is connected with the application layer, and the security module is respectively connected with the data acquisition layer, the data processing layer and the application layer; the data acquisition layer comprises IoT equipment, an external data interface, data middleware and a BIM model, the IoT equipment acquires data through the external data interface, the IoT equipment is connected with the BIM model through the data middleware, and the data processing layer comprises a multi-source data fusion engine and an intelligent algorithm module; the application layer comprises a model management module, a model display module, an early warning management module, a data management module, a three-dimensional visual monitoring platform, an intelligent decision center and a mobile terminal module. The project management efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction engineering information management, and specifically relates to a system and method for collaborative management and control of project progress, quality, and safety based on BIM and the Internet of Things. Background Art

[0002] In the construction industry, especially for large-scale infrastructure projects (such as hydropower stations, bridges, and high-rise buildings), the coordinated management of project progress, quality, and safety has always been a core challenge in the industry. With the development of information technology, BIM (Building Information Modeling) and the Internet of Things are gradually being applied to project management. However, existing technologies still have the following significant problems:

[0003] Information silos are severe, with project progress, quality, and safety management data scattered across different systems (such as progress management software, quality inspection platforms, and safety monitoring systems). Data formats and protocols are inconsistent, making real-time linkage and comprehensive analysis difficult. For example, when construction progress lags, there's no way to automatically link material inventory or equipment status data to adjust plans, leading to delayed decision-making.

[0004] BIM and IoT applications are disconnected. Existing BIM technology is often limited to static model display during the design phase, without deep integration with real-time IoT data during the construction phase (such as machine positioning and environmental monitoring). This leads to a disconnect between the model and the actual construction status. For example, BIM models cannot dynamically reflect real-time issues such as excessive concrete pouring temperatures.

[0005] The level of intelligence is insufficient, with schedule adjustments often based on manual judgment and experience. There is a lack of dynamic optimization algorithms that account for multiple factors (such as weather, supply chain, and manpower), which can easily lead to wasted resources or construction delays. Safety hazard identification lags behind. Traditional safety inspections rely on manual on-site inspections, which fail to cover the entire construction site in real time. The hazard rectification process is cumbersome (such as issuing paper work orders and manual tracking), resulting in inefficient response. Quality control is passive, with quality inspections mostly performed post-event. There is a lack of proactive early warning mechanisms based on real-time data, making it impossible to prevent construction deviations.

[0006] Weak visualization and collaboration capabilities. The existing management system lacks 3D dynamic visualization capabilities, making it difficult to intuitively display project status and inefficient cross-departmental collaboration. For example, safety managers are unable to view progress risk areas through a unified platform, resulting in a disconnect between safety measures and construction plans. Summary of the Invention

[0007] The problem to be solved by the present invention is to improve the efficiency and reliability of engineering management, and propose a system and method for collaborative management of engineering progress, quality and safety based on BIM and the Internet of Things.

[0008] To achieve the above object, the present invention is implemented through the following technical solutions:

[0009] A collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things, including a data acquisition layer, a data processing layer, an application layer, and a security module;

[0010] The data acquisition layer is connected to the data processing layer, the data processing layer is connected to the application layer, and the security module is connected to the data acquisition layer, the data processing layer, and the application layer respectively;

[0011] The data acquisition layer includes IoT devices, external data interfaces, data middleware, and BIM models. IoT devices collect data through external data interfaces, and the IoT devices connect to the BIM model through data middleware.

[0012] The data processing layer includes a multi-source data fusion engine and an intelligent algorithm module;

[0013] The application layer includes a model management module, a model display module, an early warning management module, a data management module, a three-dimensional visualization monitoring platform, an intelligent decision-making center and a mobile terminal module.

[0014] Furthermore, the model management module is used to bind BIM and IoT data; the model display module is used to achieve three-dimensional visualization; the early warning management module is used to provide early warning data viewing and handle real-time anomalies; the data management module is used for full-process data storage and analysis, and provides progress, quality, and safety data management.

[0015] Furthermore, the safety module is used for closed-loop management of quality and safety.

[0016] A method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things is implemented based on a collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things, and includes the following steps:

[0017] S1. The data collection layer dynamically binds BIM and IoT data to collect real-time progress data, environmental data, and resource data.

[0018] S2. The data processing layer inputs the real-time progress data, environmental data, and resource data collected in step S1 into the multi-source data fusion engine for data fusion. The output fusion vector is then input into the intelligent algorithm module to generate a BIM optimization solution.

[0019] S3. The application layer performs construction deviation detection and warning based on the BIM optimization solution obtained in step S2, compares the real-time progress data collected in step S1, and obtains warning information;

[0020] S4. The safety module performs closed-loop safety and quality management based on the warning information obtained in step S3.

[0021] Furthermore, the specific implementation method of step S1 includes the following steps:

[0022] S1.1. Build a lightweight BIM model with attribute information. In the BIM model, bind a device code to each construction entity. The IoT sends real-time data, including device codes and device monitoring data, to the data collection layer for storage.

[0023] S1.2. Set the attribute code of the model component of the BIM model to the equipment code;

[0024] S1.3. Use the lightweight data middleware Eclipse Ditto to synchronize the real-time data collected in step S1.1 with the model parameters of the BIM model in step S1.2 in real time to achieve dynamic data binding.

[0025] Furthermore, the lightweight data middleware Eclipse Ditto in step S1 supports MQTT and OPC UA protocols.

[0026] Furthermore, the specific implementation method of step S2 includes the following steps:

[0027] S2.1. Build a multi-source data fusion engine, including using a Transformer encoder to process time series data, a graph neural network (GNN) to model equipment-material relationships, and a convolutional neural network (CNN) to analyze construction site images.

[0028] Input real-time progress data, environmental data, and resource data into the multi-source data fusion engine and output the fusion feature vector;

[0029] S2.2. Build intelligent algorithm modules;

[0030] Construct a state space to receive the fused feature vector output by the large model;

[0031] Build an action space to dynamically generate correction strategies, including adding equipment and adjusting processes;

[0032] Building a reward function , the calculation formula is:

[0033]

[0034] in, is the construction period shortening rate coefficient, is the cost saving rate coefficient, is the quality risk value coefficient, 、 、 Dynamically configured by the big model according to the BIM project type;

[0035] Build a training mechanism for intelligent algorithms: Use the Q-learning iterative optimization strategy, and the update rules are:

[0036]

[0037] in, For the target network, is the Q value of the current state-action pair, estimated by a deep neural network, is the learning rate, which controls the model update step size (default value is 0.01), The next state Q value calculated for the target network, synchronizing parameters every 1000 steps, It is the state action, and it is updated when the Q value is updated. In order to provide real-time rewards, the project duration reduction rate, cost saving rate and quality risk are dynamically calculated. is the discount factor, set to 0.99, which is used to balance long-term benefits and short-term rewards;

[0038] S2.3. Input the fused feature vector obtained in step S2.1 into the intelligent algorithm module constructed in step S2.2 and output the BIM optimization solution.

[0039] Furthermore, the specific implementation method of step S3 includes the following steps:

[0040] S3.1. The application layer receives the BIM optimization solution obtained in step S2.

[0041] S3.2. Progress deviation detection and warning: Compare the planned progress of the BIM optimization plan with the actual construction machinery positioning data, and extract the planned progress value from the BIM model , obtain the actual progress value through IoT sensors , according to the formula Calculate the hysteresis percentage L;

[0042] S3.3. Quality Deviation Detection and Early Warning: Real-time monitoring of concrete temperature and humidity data triggers an alert when it exceeds the BIM design threshold. When the BIM model updates design parameters, the threshold is automatically synchronized to the monitoring equipment using the Eclipse Ditto middleware. The threshold is dynamically adjusted based on environmental conditions.

[0043] S3.4. Safety risk detection and warning: This includes on-site AI camera monitoring to identify people without helmets in real time, triggering a location warning upon identification and sending it to the on-site supervisor.

[0044] AI cameras deployed on the slope are used to detect cracks through image recognition algorithms; GNSS positioning modules are used to obtain the coordinates of the crack locations; and through the Eclipse Ditto data middleware, the crack coordinates are bound to the slope components in the BIM model and trigger an early warning.

[0045] Furthermore, the specific implementation method of step S4 includes the following steps:

[0046] S4.1. Based on the warning information identified in step S3, the security module automatically generates work orders using different work order templates. These work orders include location information, problem description information, and rectification deadline information. The rectification deadline is automatically calculated based on the severity level of the hidden danger using the following formula:

[0047]

[0048] in, The highest risk level, In order to dynamically generate formulas to ensure that serious hidden dangers are dealt with first, This is the hidden danger detection time, which is automatically recorded by the system. The current hidden danger level is dynamically determined based on sensor data or AI recognition results;

[0049] S4.2. The security module notifies the on-site supervisor via SMS on the mobile device.

[0050] S4.3. The on-site supervisor uploads photos of the rectification work through the mobile module. The application layer verifies the completion status through an image comparison algorithm, and a closed-loop confirmation is carried out. Once the rectification is completed, the security module removes the corresponding risk marker, modifies the security status attributes, and generates an unalterable log containing a timestamp, responsible person, and digital signature.

[0051] Beneficial effects of the present invention:

[0052] The present invention describes a collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things. This system binds BIM and IoT to each other through device coding and deeply integrates GIS positioning to build an intelligent system for collaborative control of progress, quality, and safety. This system breaks down information silos, dynamically associates BIM models with IoT data, supports three-dimensional visual monitoring, and automatically optimizes progress and identifies quality and safety risks through algorithms, reducing manual intervention, achieving full-process automation of "monitoring-early warning-processing-verification," and improving project management efficiency and reliability.

[0053] The collaborative management and control system for project progress, quality, and safety based on BIM and the Internet of Things described in the present invention overcomes the shortcomings of existing technologies through three major innovations: deep integration of BIM and IoT data, intelligent decision-making driven by reinforcement learning, and closed-loop management of safety and quality, and provides a full-dimensional intelligent solution for complex project management. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a structural diagram of a collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things according to the present invention;

[0055] Figure 2 This is a flow chart of a method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things as described in the present invention. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention and are not intended to limit the present invention. That is, the specific embodiments described herein are only some embodiments of the present invention, not all embodiments. Generally, the components of the specific embodiments of the present invention described and illustrated in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0057] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected specific embodiments of the present invention. All other specific embodiments obtained by those skilled in the art based on the specific embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0058] In order to further understand the content, features and effects of the present invention, the following specific embodiments are given as examples, and the attached Figure 1 and attached Figure 2 The detailed instructions are as follows:

[0059] Example 1:

[0060] A collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things, including a data acquisition layer, a data processing layer, an application layer, and a security module;

[0061] The data acquisition layer is connected to the data processing layer, the data processing layer is connected to the application layer, and the security module is connected to the data acquisition layer, the data processing layer, and the application layer respectively;

[0062] The data acquisition layer includes IoT devices, external data interfaces, data middleware, and BIM models. IoT devices collect data through external data interfaces, and the IoT devices connect to the BIM model through data middleware.

[0063] The data processing layer includes a multi-source data fusion engine and an intelligent algorithm module;

[0064] The application layer includes a model management module, a model display module, an early warning management module, a data management module, a three-dimensional visualization monitoring platform, an intelligent decision-making center and a mobile terminal module.

[0065] Furthermore, the model management module is used to bind BIM and IoT data; the model display module is used to achieve three-dimensional visualization; the early warning management module is used to provide early warning data viewing and handle real-time anomalies; the data management module is used for full-process data storage and analysis, and provides progress, quality, and safety data management.

[0066] Furthermore, the safety module is used for closed-loop management of quality and safety.

[0067] Example 2:

[0068] A method for collaboratively controlling project progress, quality, and safety based on BIM and the Internet of Things is implemented based on the collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things described in Example 1, and includes the following steps:

[0069] S1. The data collection layer dynamically binds BIM and IoT data to collect real-time progress data, environmental data, and resource data.

[0070] Furthermore, the specific implementation method of step S1 includes the following steps:

[0071] S1.1. Build a lightweight BIM model with attribute information. In the BIM model, bind a device code to each construction entity. The IoT sends real-time data, including device codes and device monitoring data, to the data collection layer for storage.

[0072] Furthermore, each construction entity includes a dam, powerhouse, and diversion tunnel;

[0073] S1.2. Set the attribute code of the model component of the BIM model to the equipment code;

[0074] S1.3. Use the lightweight data middleware Eclipse Ditto to synchronize the real-time data collected in step S1.1 with the model parameters of the BIM model in step S1.2 in real time, achieving dynamic data binding.

[0075] Furthermore, the lightweight data middleware Eclipse Ditto in step S1 supports MQTT and OPC UA protocols;

[0076] S2. The data processing layer inputs the real-time progress data, environmental data, and resource data collected in step S1 into the multi-source data fusion engine for data fusion. The output fusion vector is then input into the intelligent algorithm module to generate a BIM optimization solution.

[0077] Furthermore, the specific implementation method of step S2 includes the following steps:

[0078] S2.1. Build a multi-source data fusion engine, including using a Transformer encoder to process time series data, a graph neural network (GNN) to model equipment-material relationships, and a convolutional neural network (CNN) to analyze construction site images.

[0079] Input real-time progress data, environmental data, and resource data into the multi-source data fusion engine and output the fusion feature vector;

[0080] S2.2. Build intelligent algorithm modules;

[0081] Construct a state space to receive the fused feature vector output by the large model;

[0082] Build an action space to dynamically generate correction strategies, including adding equipment and adjusting processes;

[0083] Building a reward function , the calculation formula is:

[0084]

[0085] in, is the construction period shortening rate coefficient, is the cost saving rate coefficient, is the quality risk value coefficient, 、 、 Dynamically configured by the big model according to the BIM project type;

[0086] Build a training mechanism for intelligent algorithms: Use the Q-learning iterative optimization strategy, and the update rules are:

[0087]

[0088] in, For the target network, is the Q value of the current state-action pair, estimated by a deep neural network, is the learning rate, which controls the model update step size (default value is 0.01), The next state Q value calculated for the target network, synchronizing parameters every 1000 steps, It is the state action, and it is updated when the Q value is updated. In order to provide real-time rewards, the project duration reduction rate, cost saving rate and quality risk are dynamically calculated. is the discount factor, set to 0.99, which is used to balance long-term benefits and short-term rewards;

[0089] S2.3. Input the fused feature vector obtained in step S2.1 into the intelligent algorithm module constructed in step S2.2 and output the BIM optimization solution.

[0090] S3. The application layer performs construction deviation detection and warning based on the BIM optimization solution obtained in step S2, compares the real-time progress data collected in step S1, and obtains warning information;

[0091] Furthermore, the specific implementation method of step S3 includes the following steps:

[0092] S3.1. The application layer receives the BIM optimization solution obtained in step S2.

[0093] S3.2. Progress deviation detection and warning: Compare the planned progress of the BIM optimization plan with the actual construction machinery positioning data, and extract the planned progress value from the BIM model , obtain the actual progress value through IoT sensors , according to the formula Calculate the hysteresis percentage L;

[0094] For example, if the planned pouring volume for a dam section is 1,000 m³ / day, but the actual sensor feedback shows only 800 m³ has been completed, the system will determine that the progress is 20% behind schedule;

[0095] S3.3. Quality Deviation Detection and Early Warning: Real-time monitoring of concrete temperature and humidity data triggers an alert when it exceeds the BIM design threshold. When the BIM model updates design parameters, the threshold is automatically synchronized to the monitoring equipment using the Eclipse Ditto middleware. The threshold is dynamically adjusted based on environmental conditions.

[0096] Furthermore, environmental conditions include temperature and rainfall;

[0097] S3.4. Safety risk detection and warning: This includes on-site AI camera monitoring to identify people without helmets in real time, triggering a location warning upon identification and sending it to the on-site supervisor.

[0098] AI cameras deployed on the slope are used to detect cracks through image recognition algorithms; GNSS positioning modules are used to obtain the coordinates of the crack locations; and through the Eclipse Ditto data middleware, the crack coordinates are bound to the slope components in the BIM model and trigger an early warning.

[0099] S4. The safety module performs closed-loop safety and quality management based on the warning information obtained in step S3.

[0100] Furthermore, the specific implementation method of step S4 includes the following steps:

[0101] S4.1. Based on the warning information identified in step S3, the security module automatically generates work orders using different work order templates. These work orders include location information, problem description information, and rectification deadline information. The rectification deadline is automatically calculated based on the severity level of the hidden danger using the following formula:

[0102]

[0103] in, The highest risk level, In order to dynamically generate formulas to ensure that serious hidden dangers are dealt with first, This is the hidden danger detection time, which is automatically recorded by the system. The current hidden danger level is dynamically determined based on sensor data or AI recognition results;

[0104] S4.2. The security module notifies the on-site supervisor via SMS on the mobile device.

[0105] S4.3. The on-site supervisor uploads photos of the rectification work through the mobile module. The application layer verifies the completion status through an image comparison algorithm, and a closed-loop confirmation is carried out. Once the rectification is completed, the security module removes the corresponding risk marker, modifies the security status attributes, and generates an unalterable log containing a timestamp, responsible person, and digital signature.

[0106] The application of this embodiment in the coordinated control of concrete pouring progress and quality is shown below:

[0107] Data Binding: The model management module implements BIM-IoT binding through device coding. Mark the concrete pouring area of a dam section in the BIM model and associate it with the temperature and humidity sensor (device ID: S-0023) and the vibrating equipment positioning data (device ID: M-0045).

[0108] Deviation detection: When the sensor shows that the temperature exceeds the limit (32℃> design threshold 28℃), the system automatically highlights the warning in the BIM model, and the model display module (see Figure 1Application layer: Achieve 3D dynamic visualization. Automatically trigger SMS notifications to the responsible person's mobile phone and automatically generate work orders in data management. Work orders are divided into multiple types, and the system automatically selects the type of warning. The system fills in the work order information form based on the data sent by the sensor and sends it to the tablet computer of the specific on-site person in charge.

[0109] Progress Correction: First, construction progress data is imported into the progress management section of the data management system. The AI big model is then trained, fed with data, and trained through reinforcement learning. The BIM model is now linked to the progress data in real time. Delays in progress are displayed in the BIM model using different colors: gray for unfinished projects, yellow for under construction, green for completed projects, and red for overdue projects. When the system receives model data indicating red, the big model considers the current delay, such as a 15% overall delay in a particular construction area, the remaining construction volume (2,000 m³), and available resources (two spare vibrators). Upon identifying the delay, the big model automatically generates a plan to increase night shifts and deploy spare equipment, shortening the project by three days. This significantly improves construction efficiency and progress control. The AI big model intelligently generates reports that shorten the construction cycle. The big model identifies the current project as a "critical flood season project" (a BIM attribute) and automatically sets the reward function weights α=0.7, β=0.2, and γ=0.1. The reinforcement learning model then prioritizes strategies to shorten the construction period.

[0110] Closed-loop verification: When construction personnel receive a rectification notice, they go on-site to fix the problem. Once the repair is complete, the sensor data returns to normal (26°C), and the data obtained through the BIM link also displays normal. The system automatically closes the work order and updates the progress status, completing the closed-loop verification process. Verification results are synchronized to the BIM model through the data management module.

[0111] The application of this embodiment to slope safety monitoring and emergency response is shown below:

[0112] Safety monitoring: The installed monitoring equipment automatically monitors the slope and identifies crack expansion trends (length increases from 10cm to 15cm);

[0113] Risk Warning: When crack length exceeds a threshold (12cm), the system automatically demarcates a danger zone (coordinates X:120, Y:350) in the BIM model, prohibiting personnel and equipment from entering. It also automatically triggers a text message notification to the responsible person's mobile phone and sends a message to the material management system.

[0114] Emergency dispatch: When the material management system receives the early warning information, it links with the large model to generate a dispatched protective measures plan. After the on-site person in charge modifies and confirms the plan, it begins to allocate support materials (inventory ID: M-8876) nearby and plans the unmanned vehicle transportation route (the shortest distance is 1.2 km, avoiding construction congestion areas).

[0115] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0116] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and components may be substituted with equivalents without departing from the scope of the present application. In particular, as long as there are no structural conflicts, the various features of the embodiments disclosed herein may be combined with each other in any manner, and the omission of an exhaustive description of these combinations in this specification is solely for the sake of space and resource conservation. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions within the scope of the claims.

Claims

1. A collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things, characterized by: Including data acquisition layer, data processing layer, application layer, and security module; The data acquisition layer is connected to the data processing layer, the data processing layer is connected to the application layer, and the security module is connected to the data acquisition layer, the data processing layer, and the application layer respectively; The data acquisition layer includes IoT devices, external data interfaces, data middleware, and BIM models. IoT devices collect data through external data interfaces, and the IoT devices connect to the BIM model through data middleware. The data processing layer includes a multi-source data fusion engine and an intelligent algorithm module; The application layer includes a model management module, a model display module, an early warning management module, a data management module, a three-dimensional visualization monitoring platform, an intelligent decision-making center and a mobile terminal module.

2. The BIM and IoT-based collaborative control system for project progress, quality, and safety according to claim 1 is characterized by: The model management module is used to bind BIM and IoT data; The model display module is used to achieve three-dimensional visualization; the early warning management module is used to provide early warning data viewing and handle real-time anomalies; the data management module is used for full-process data storage and analysis, and provides progress, quality, and safety data management.

3. The BIM and IoT-based collaborative control system for project progress, quality, and safety according to claim 2 is characterized by: The safety module is used for closed-loop management of quality and safety.

4. A method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things, which is implemented by a collaborative control system for project progress, quality, and safety based on BIM and the Internet of Things according to any one of claims 1 to 3, and is characterized in that: The steps include: S1. The data collection layer dynamically binds BIM and IoT data to collect real-time progress data, environmental data, and resource data. S2. The data processing layer inputs the real-time progress data, environmental data, and resource data collected in step S1 into the multi-source data fusion engine for data fusion. The output fusion vector is then input into the intelligent algorithm module to generate a BIM optimization solution. S3. The application layer performs construction deviation detection and warning based on the BIM optimization solution obtained in step S2, compares the real-time progress data collected in step S1, and obtains warning information; S4. The safety module performs closed-loop safety and quality management based on the warning information obtained in step S3.

5. The method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things according to claim 4 is characterized in that: The specific implementation method of step S1 includes the following steps: S1.

1. Build a lightweight BIM model with attribute information. In the BIM model, bind a device code to each construction entity. The IoT sends real-time data, including device codes and device monitoring data, to the data collection layer for storage. S1.

2. Set the attribute code of the model component of the BIM model to the equipment code; S1.

3. Use the lightweight data middleware Eclipse Ditto to synchronize the real-time data collected in step S1.1 with the model parameters of the BIM model in step S1.2 in real time to achieve dynamic data binding.

6. The method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things according to claim 5 is characterized in that: In step S1, the lightweight data middleware Eclipse Ditto supports MQTT and OPC UA protocols.

7. The method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things according to claim 6 is characterized in that: The specific implementation method of step S2 includes the following steps: S2.

1. Build a multi-source data fusion engine, including using a Transformer encoder to process time series data, a graph neural network (GNN) to model equipment-material relationships, and a convolutional neural network (CNN) to analyze construction site images. Input real-time progress data, environmental data, and resource data into the multi-source data fusion engine and output the fusion feature vector; S2.

2. Build intelligent algorithm modules; Construct a state space to receive the fused feature vector output by the large model; Build an action space to dynamically generate correction strategies, including adding equipment and adjusting processes; Building a reward function , the calculation formula is: ； in, is the construction period shortening rate coefficient, is the cost saving rate coefficient, is the quality risk value coefficient, 、 、 Dynamically configured by the big model according to the BIM project type; Build a training mechanism for intelligent algorithms: Use the Q-learning iterative optimization strategy, and the update rules are: ； in, For the target network, is the Q value of the current state-action pair, estimated by a deep neural network, is the learning rate, which controls the model update step size (default value is 0.01), The next state Q value calculated for the target network, synchronizing parameters every 1000 steps, It is the state action, and it is updated when the Q value is updated. In order to provide real-time rewards, the project duration reduction rate, cost saving rate and quality risk are dynamically calculated. is the discount factor, set to 0.99, which is used to balance long-term benefits and short-term rewards; S2.

3. Input the fused feature vector obtained in step S2.1 into the intelligent algorithm module constructed in step S2.2 and output the BIM optimization solution.

8. The method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things according to claim 7 is characterized in that: The specific implementation method of step S3 includes the following steps: S3.

1. The application layer receives the BIM optimization solution obtained in step S2. S3.

2. Progress deviation detection and warning: Compare the planned progress of the BIM optimization plan with the actual construction machinery positioning data, and extract the planned progress value from the BIM model , obtain the actual progress value through IoT sensors , according to the formula Calculate the hysteresis percentage L; S3.

3. Quality Deviation Detection and Early Warning: Real-time monitoring of concrete temperature and humidity data triggers an alert when it exceeds the BIM design threshold. When the BIM model updates design parameters, the threshold is automatically synchronized to the monitoring equipment using the Eclipse Ditto middleware. The threshold is dynamically adjusted based on environmental conditions. S3.

4. Safety risk detection and warning: This includes on-site AI camera monitoring to identify people without helmets in real time, triggering a location warning upon identification and sending it to the on-site supervisor. AI cameras deployed on the slope are used to detect cracks through image recognition algorithms; GNSS positioning modules are used to obtain the coordinates of the crack locations; and through the Eclipse Ditto data middleware, the crack coordinates are bound to the slope components in the BIM model and trigger an early warning.

9. The method for collaborative control of project progress, quality, and safety based on BIM and the Internet of Things according to claim 8, characterized in that: The specific implementation method of step S4 includes the following steps: S4.

1. Based on the warning information identified in step S3, the security module automatically generates work orders using different work order templates. These work orders include location information, problem description information, and rectification deadline information. The rectification deadline is automatically calculated based on the severity level of the hidden danger using the following formula: ； in, The highest risk level, In order to dynamically generate formulas to ensure that serious hidden dangers are dealt with first, This is the hidden danger detection time, which is automatically recorded by the system. The current hidden danger level is dynamically determined based on sensor data or AI recognition results; S4.

2. The security module notifies the on-site supervisor via SMS on the mobile device. S4.

3. The on-site supervisor uploads photos of the rectification work through the mobile module. The application layer verifies the completion status through an image comparison algorithm, and a closed-loop confirmation is carried out. Once the rectification is completed, the security module removes the corresponding risk marker, modifies the security status attributes, and generates an unalterable log containing a timestamp, responsible person, and digital signature.

Images